|
NOTES: This release includes the 10 gigabit ixgbe FreeBSD Base Driver for Intel Ethernet 10 Gigabit PCI-Express Server Adapters. All 82599, 82598EB and X540-based network connections require the ixgbe driver. All other network connections require the ixgb driver. The ixgb driver can be downloaded at: http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/dev/ixgb/. First identify your adapter. Then follow the appropriate steps for building, installing, and configuring the appropriate driver. |
To verify that your Intel adapter is supported, find the board ID number on the adapter. Look for a label that has a barcode and a number in the format of 123456-001 (six digits hyphen three digits). For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at:
http://support.intel.com/support/go/network/adapter/home.htm
For the latest Intel network drivers for FreeBSD, see:
http://support.intel.com/support/go/network/adapter/home.htm
This driver has been developed for use with all community-supported versions of FreeBSD.
To verify that your Intel adapter is supported, find the board ID number on the adapter. Look for a label that has a barcode and a number in the format of 123456-001 (six digits hyphen three digits). For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at:
http://support.intel.com/support/go/network/adapter/home.htm
For the latest Intel network drivers for FreeBSD, see:
http://downloadcenter.intel.com/scripts-df-external/Support_Intel.aspx
|
|
NOTES:
|
| Supplier | Type | Part Numbers |
| SR Modules | ||
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | AFBR-703SDZ-IN2 |
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | FTLX8571D3BCV-IT |
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | AFBR-703SDDZ-IN1 |
| LR Modules | ||
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | FTLX1471D3BCV-IT |
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | AFCT-701SDZ-IN2 |
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | AFCT-701SDDZ-IN1 |
The following is a list of 3rd party SFP+ modules and direct attach cables that have received some testing. Not all modules are applicable to all devices.
| Supplier | Type | Part Numbers |
| Finisar | SFP+ SR bailed, 10g single rate | FTLX8571D3BCL |
| Avago | SFP+ SR bailed, 10g single rate | AFBR-700SDZ |
| Finisar | SFP+ LR bailed, 10g single rate | FTLX1471D3BCL |
| Finisar | DUAL RATE 1G/10G SFP+ SR (No Bail) | FTLX8571D3QCV-IT |
| Avago | DUAL RATE 1G/10G SFP+ SR (No Bail) | AFBR-703SDZ-IN1 |
| Finisar | DUAL RATE 1G/10G SFP+ LR (No Bail) | FTLX1471D3QCV-IT |
| Avago | DUAL RATE 1G/10G SFP+ LR (No Bail) | AFCT-701SDZ-IN1 |
| Finisar | 1000BASE-T SFP | FCLF8522P2BTL |
| Avago | 1000BASE-T SFP | ABCU-5710RZ |
82599-based adapters support all passive and active limiting direct attach cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
"ifconfig down" turns off the laser for 82599-based SFP+ fiber adapters. "ifconfig up" turns on the later.
|
|
NOTES:
|
The following is a list of SFP+ modules and direct attach cables that have received some testing. Not all modules are applicable to all devices.
| Supplier | Type | Part Numbers |
| Finisar | SFP+ SR bailed, 10g single rate | FTLX8571D3BCL |
| Avago | SFP+ SR bailed, 10g single rate | AFBR-700SDZ |
| Finisar | SFP+ LR bailed, 10g single rate | FTLX1471D3BCL |
82598-based adapters support all passive direct attach cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach cables are not supported.
THIRD PARTY OPTIC MODULES AND CABLES REFERRED TO ABOVE ARE LISTED ONLY FOR THE PURPOSE OF HIGHLIGHTING THIRD PARTY SPECIFICATIONS AND POTENTIAL COMPATIBILITY, AND ARE NOT RECOMMENDATIONS OR ENDORSEMENT OR SPONSORSHIP OF ANY THIRD PARTYS PRODUCT BY INTEL. INTEL IS NOT ENDORSING OR PROMOTING PRODUCTS MADE BY ANY THIRD PARTY AND THE THIRD PARTY REFERENCE IS PROVIDED ONLY TO SHARE INFORMATION REGARDING CERTAIN OPTIC MODULES AND CABLES WITH THE ABOVE SPECIFICATIONS. THERE MAY BE OTHER MANUFACTURERS OR SUPPLIERS, PRODUCING OR SUPPLYING OPTIC MODULES AND CABLES WITH SIMILAR OR MATCHING DESCRIPTIONS. CUSTOMERS MUST USE THEIR OWN DISCRETION AND DILIGENCE TO PURCHASE OPTIC MODULES AND CABLES FROM ANY THIRD PARTY OF THEIR CHOICE. CUSTOMERS ARE SOLELY RESPONSIBLE FOR ASSESSING THE SUITABILITY OF THE PRODUCT AND/OR DEVICES AND FOR THE SELECTION OF THE VENDOR FOR PURCHASING ANY PRODUCT. THE OPTIC MODULES AND CABLES REFERRED TO ABOVE ARE NOT WARRANTED OR SUPPORTED BY INTEL. INTEL ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF SUCH THIRD PARTY PRODUCTS OR SELECTION OF VENDOR BY CUSTOMERS.
|
NOTE: You must have kernel sources installed in order to compile the driver module. |
In the instructions below, x.x.x is the driver version as indicated in the name of the driver tar file.
tar xfz ixgbe-x.x.x.tar.gz
cd
ixgbe-x.x.x
gzip -c ixgbe.4 > /usr/share/man/man4/ixgbee.4.gz
cd ixgbe-x.x.x/src
make load
ifconfig ix<interface_num> <IP_address>
ping <IP_address>
cd ixgbe-x.x.x/src
make
make install
Edit /boot/loader.conf, and add the following line:
ixgbe_load="YES"
OR
compile the driver into the kernel (see item 8).
Edit /etc/rc.conf, and create the appropriate ifconfig_ixgbe<interface_num>
entry:
ifconfig_ix<interface_num>
Example usage:
ifconfig_ix0="inet 192.168.10.1
netmask 255.255.255.0"
NOTE: For assistance, see the ifconfig man page.
The driver supports Transmit/Receive Checksum Offload and Jumbo Frames on all 10GbE adapters.
To enable Jumbo Frames, use the ifconfig utility to increase the MTU beyond 1500 bytes.
|
NOTES: The Jumbo Frames setting on the switch must be
set to at least 22 bytes larger than that of the MTU.
There are known performance issues with this driver when running UDP traffic with Jumbo Frames. |
The Jumbo Frames MTU range for Intel Adapters is 1500 to 16114. The default MTU range is 1500. To modify the setting, enter the following:
ifconfig ix<interface_num> <hostname or IP address> mtu 9000
To confirm an interface's MTU value, use the ifconfig command. To confirm the MTU used between two specific devices, use:
route get <destination_IP_address>
To create a new VLAN interface:
ifconfig <vlan_name> create
To associate the VLAN interface with a physical interface and assign an IP address, netmask, and VLAN ID:
ifconfig <vlan_name> <ip_address> netmask <subnet_mask> vlan <vlan_id> vlandev <physical_interface>
Example:
ifconfig vlan10 10.0.0.1 netmask 255.255.255.0 vlan 10 vlandev ixgb0
In this example, all packets will be marked on egress with 802.1Q VLAN tags, specifying a VLAN ID of 10.
To remove a VLAN interface:
ifconfig <vlan_name> destroy
Checksum offloading supports both TCP and UDP packets and is supported for
both transmit and receive.
Checksum offloading can be enabled or disabled using ifconfig. Both transmit and
receive offloading will be either enabled or disabled together. You cannot
enable/disable one without the other.
To enable checksum offloading:
ifconfig <interface_num> rxcsum
To disable checksum offloading:
ifconfig <interface_num> -rxcsum
To confirm the current setting:
ifconfig <interface_num>
TSO is enabled by default.
To disable:
ifconfig <interface_num> -tso
To re-enable:
ifconfig <interface_num> tso
Large Receive Offload is available in the driver; it is off by default. LRO provides significant RX performance improvement. However it is incompatible with packet-forwarding workloads. The administrator should carefully evaluate the environment and enable when possible.
To enable:
ifconfig <interface_num> lro
It can be disabled by using:
ifconfig <interface_num> -lro
When there is a choice, run on a 64bit OS rather than 32, it makes a
significant difference in improvement.
The interface can generate high number of interrupts. To avoid running into the
limit set by the kernel, adjust hw.intr_storm_threshold setting using sysctl:
sysctl hw.intr_storm_threshold=9000 (the default is 1000)
For this change to take effect on boot, edit /etc/sysctl.conf and add the line:
hw.intr_storm_threshold=9000
If you still see Interrupt Storm detected messages, increase the limit to a
higher number.
Best throughput results are seen with a large MTU; use 9000 if possible.
Under small packets UDP stress test with the 10GbE driver, the FreeBSD system will drop UDP packets, due to socket buffers being full. You may want to change the driver's Flow Control variables to the minimum value for controlling packet reception.
When using the ixgbe driver with RSS
autoconfigured based on the number of cores (the default setting) and that
number is larger than 4, increase the memory resources allocated for the mbuf
pool as follows:
Add to the sysctl.conf file for the system:
kern.ipc.nmbclusters=262144
kern.ipc.nmbjumbop=262144
Some PCI-E x8 slots are actually configured as x4 slots. These
slots have insufficient bandwidth for full 10Gbe line rate with dual port 10GbE
devices. The driver can detect this situation and will write the following
message in the system log: PCI-Express bandwidth available for this card is not
sufficient for optimal performance. For optimal performance a x8 PCI-Express
slot is required.
If this error occurs, moving your adapter to a true x8 slot
will resolve the issue.
For general information and support, go to the support website
If an issue is identified, support is through email only at: freebsd@intel.com
Last modified on 6/23/11 1:50p Revision
Intel support is available on the web or by phone. Support offers the most up-to-date information about Intel products, including installation instructions, troubleshooting tips, and general product information.
Support: http://www.intel.com/support
Corporate Site for Network Products: http://www.intel.com/products/ethernet/overview.htm
Last modified on 5/12/10 3:26p Revision
|
NOTE: This release includes four Linux* Base Drivers for
Intel® Ethernet Network Connection. These drivers are named
igb, e1000,
e1000e and
igbvf.
First identify your adapter. Then follow the appropriate steps for building, installing, and configuring the driver. UPGRADING: If you currently have the e1000 driver installed and need to install e1000e, perform the following:
|
First identify your adapter. Then select the name of the specified base driver: igb, e1000 or e1000e.
For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at:
http://support.intel.com/support/go/network/adapter/idguide.htm
For the latest Intel network drivers for Linux, refer to the following website. Select the link for your adapter.http://support.intel.com/support/go/network/adapter/home.htm
The Linux base drivers support the 2.4.x and 2.6.x kernels. These drivers includes support for Itanium® 2-based systems.
These drivers are only supported as a loadable module. Intel is not supplying patches against the kernel source to allow for static linking of the drivers. For questions related to hardware requirements, refer to the documentation supplied with your Intel Gigabit adapter. All hardware requirements listed apply to use with Linux.
The following features are now available in supported kernels:
Native VLANs
Channel Bonding (teaming)
SNMP
Channel Bonding documentation can be found in the Linux kernel source: /documentation/networking/bonding.txt
The igb driver supports IEEE 1588 time stamping for kernels 2.6.30 and above.
The driver information previously displayed in the /proc file system is not supported in this release. Alternatively, you can use ethtool (version 1.6 or later), lspci, and ifconfig to obtain the same information. Instructions on updating ethtool can be found in the section Additional Configurations later in this document.
To build a binary RPM* package of this driver, run 'rpmbuild -tb igb.tar.gz'.
|
NOTES:
|
Move the base driver tar file to the directory of your
choice. For example, use '/home/username/igb' or '/usr/local/src/igb'.
Untar/unzip the archive, where <x.x.x> is the version number for the driver tar file:
tar zxf igb-<x.x.x>.tar.gz
Change to the driver src directory, where <x.x.x> is the version number for the driver tar:
cd igb-<x.x.x>/src/
Compile the driver module:
# make install
The binary will be installed as:
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/igb/igb.[k]o
The install location listed above is the default location.
This may differ for various Linux distributions.
Load the module using either the insmod or modprobe command:
modprobe igb
insmod igb
Note that for 2.6 kernels the insmod command can be used if the full path to the driver module is specified. For example:
insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/igb/igb.ko
With 2.6 based kernels also make sure that older igb drivers are removed from the kernel, before loading the new module:
rmmod igb; modprobe igb
Assign an IP address to the interface by entering the following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where <IP_address> is the IP address for another machine on the same subnet as the interface that is being tested:
ping <IP_address>
|
|
TROUBLESHOOTING: Some systems have trouble supporting MSI and/or MSI-X interrupts. If you believe your system needs to disable this style of interrupt, the driver can be built and installed with the command:
Normally the driver will generate an interrupt every two seconds, so if you can see that you're no longer getting interrupts in cat /proc/interrupts for the ethX igb device, then this workaround may be necessary. |
To build igb driver with DCA:
If your kernel supports DCA, the driver will build by default with DCA enabled.
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe igb [<option>=<VAL1>,<VAL2>,...]
For example, with two Gigabit PCI adapters, entering:
modprobe igb TxDescriptors=80,128
loads the igb driver with 80 TX descriptors for the first adapter and 128 TX descriptors for the second adapter.
The default value for each parameter is generally the recommended setting, unless otherwise noted.
|
|
NOTES:
|
| Parameter Name | Valid Range/Settings | Default | Description | |
|---|---|---|---|---|
| InterruptThrottleRate | Valid Range: 0,1,3,100-100000 (0=off, 1=dynamic, 3=dynamic conservative) |
3 |
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to
the adapter that is based on the maximum amount of interrupts that the
adapter will generate per second. Setting InterruptThrottleRate to a value greater or equal to 100 will program the adapter to send out a maximum of that many interrupts per second, even if more packets have come in. This reduces interrupt load on the system and can lower CPU utilization under heavy load, but will increase latency as packets are not processed as quickly. The default behaviour of the driver previously assumed a static InterruptThrottleRate value of 8000, providing a good fallback value for all traffic types, but lacking in small packet performance and latency. The hardware can handle many more small packets per second however, and for this reason an adaptive interrupt moderation algorithm was implemented. The driver has two adaptive modes (setting 1 or 3) in which it dynamically adjusts the InterruptThrottleRate value based on the traffic that it receives. After determining the type of incoming traffic in the last timeframe, it will adjust the InterruptThrottleRate to an appropriate value for that traffic. The algorithm classifies the incoming traffic every interval into classes. Once the class is determined, the InterruptThrottleRate value is adjusted to suit that traffic type the best. There are three classes defined: "Bulk traffic", for large amounts of packets of normal size; "Low latency", for small amounts of traffic and/or a significant percentage of small packets; and "Lowest latency", for almost completely small packets or minimal traffic. In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is increased stepwise to 20000. This default mode is suitable for most applications. For situations where low latency is vital such as cluster or grid computing, the algorithm can reduce latency even more when InterruptThrottleRate is set to mode 1. In this mode, which operates the same as mode 3, the InterruptThrottleRate will be increased stepwise to 70000 for traffic in class "Lowest latency". Setting InterruptThrottleRate to 0 turns off any interrupt moderation and may improve small packet latency, but is generally not suitable for bulk throughput traffic
|
|
| LLIPort | 0-65535 |
0 (disabled) |
LLI (Low Latency Interrupts): LLI allows for immediate generation of an
interrupt upon processing receive packets that match certain criteria as set
by the parameters described below. LLI parameters are not enabled when
Legacy interrupts are used. You must be using MSI or MSI-X (see cat
/proc/interrupts) to successfully use LLI. LLI is configured with the LLIPort command-line parameter, which specifies which TCP port should generate Low Latency Interrupts. For example, using LLIPort=80 would cause the board to generate an immediate interrupt upon receipt of any packet sent to TCP port 80 on the local machine.
|
|
| LLIPush | 0-1 |
0 (disabled) |
LLIPush can be set to be enabled or disabled (default). It is most effective
in an environment with many small transactions.
|
|
| LLISize | 0-1500 | 0 (disabled) |
LLISize causes an immediate interrupt if the board receives a packet smaller
than the specified size. |
|
| IntMode |
0-2 (0 = Legacy Int, 1 = MSI and 2 = MSI-X) | 2 | IntMode controls allow load time control over the type of interrupt registered for by the driver. MSI-X is required for multiple queue support, and some kernels and combinations of kernel .config options will force a lower level of interrupt support. 'cat /proc/interrupts' will show different values for each type of interrupt. | |
| RSS | 0-8 | 1 |
0 - Assign up to whichever is less, number of CPUS or number of queues X - Assign X queues where X is less than the maximum number of queues
This parameter is also affected by the VMDq parameter in that it will limit the queues more. VMDQ Model 0 1 2 3+ 82575 4 4 3 1 82576 8 2 2 2 82580 8 1 1 1 |
|
| VMDQ | 0 - 4 on 82575-based adapters; and 0 - 8 for 82576/82580-based adapters. 0 = disabled 1 = sets the netdev as pool 0 2+ = add additional queues but they currently are not used. |
0 |
Supports enabling VMDq pools as this is needed to support SR-IOV. This parameter is forced to 1 or more if the max_vfs module parameter is used. In addition the number of queues available for RSS is limited if this is set to 1 or greater. |
|
| max_vfs | 0-7 If the value is greater than 0 it will also force the VMDq parameter to be 1 or more. |
0 |
This parameter adds support for SR-IOV. It causes the driver to spawn up to max_vfs worth of virtual function. |
|
| QueuePairs | 0-1 | 1 (TX and RX will be paired onto one interrupt vector) |
If set to 0, when MSI-X is enabled, the TX and RX will attempt to occupy
separate vectors. This option can be overridden to 1 if there are not sufficient interrupts available. This can occur if any combination of RSS, VMDQ, and max_vfs results in more than 4 queues being used. |
|
| Node | 0-n 0 - n: where n is the number of the NUMA node that should be used to allocate memory for this adapter port. -1: uses the driver default of allocating memory on whichever processor is running insmod/modprobe. |
-1 (off) | The Node parameter will allow you to pick which NUMA node you want to have the adapter allocate memory from. All driver structures, in-memory queues, and receive buffers will be allocated on the node specified. This parameter is only useful when interrupt affinity is specified, otherwise some portion of the time the interrupt could run on a different core than the memory is allocated on, causing slower memory access and impacting throughput, CPU, or both. | |
| EEE | 0-1 | 1 (enabled) | A link between two EEE-compliant devices will result in periodic bursts of data followed by periods where the link is in an idle state. This Low Power Idle (LPI) state is supported in both 1Gbps and 100Mbps link speeds.
|
|
| DMAC | 0, 250, 500, 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10000. | 0 (disabled) | Enables or disables DMA Coalescing feature. Values are in usecs and increase the internal DMA Coalescing features internal timer. DMA (Direct Memory Access) allows the network device to move packet data directly to the system's memory, reducing CPU utilization. However, the frequency and random intervals at which packets arrive do not allow the system to enter a lower power state. DMA Coalescing allows the adapter to collect packets before it initiates a DMA event. This may increase network latency but also increases the chances that the system will enter a lower power state. Turning on DMA Coalescing may save energy with kernel 2.6.32 and later.
This will impart the greatest chance for your system to consume less power.
DMA Coalescing is effective in helping potentially saving the platform power
only when it is enabled across all active ports. |
|
| MDD (Malicious Driver Detection) | Valid Range: 0, 1; 0 = Disable, 1 = Enable | Default Value: 1 | This parameter is only relevant for I350 devices operating in SR-IOV mode. When this parameter is set, the driver detects malicious VF driver and disables its TX/RX queues until a VF driver reset occurs. |
Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to your distribution documentation. If during this process you are asked for the driver or module name, the name for the Linux Base Driver for the Gigabit family of adapters is e1000.
alias eth0 igb
alias eth1 igb
options igb IntMode=2,1
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU) to a value larger than the default value of 1500. Use the ifconfig command to increase the MTU size. For example:
ifconfig eth<x> mtu 9000 up
This setting is not saved across reboots. The setting change can be made permanent by adding MTU=9000 to the file: /etc/sysconfig/network-scripts/ifcfg-eth<x> (Red Hat distributions). Other distributions may store this setting in a different location.
|
|
NOTES:
|
The driver utilizes the ethtool interface for driver configuration and diagnostics, as well as displaying statistical information. ethtool version 3 or later is required for this functionality, although we strongly recommend downloading the latest version at:
http://ftp.kernel.org/pub/software/network/ethtool/.
Speed and Duplex are configured through the ethtool* utility. ethtool is included with all versions of Red Hat after Red Hat 7.2. For other Linux distributions, download and install ethtool from the following website: http://ftp.kernel.org/pub/software/network/ethtool/.
WoL is configured through the ethtool* utility. ethtool is included with all versions of Red Hat after Red Hat 7.2. For other Linux distributions, download and install ethtool from the following website: http://ftp.kernel.org/pub/software/network/ethtool/.
For instructions on enabling WoL with ethtool, refer to the website listed above.
WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e1000 driver must be loaded prior to shutting down or suspending the system.
|
|
NOTES: Wake On LAN is only supported on port A of
multi-port devices. Wake On LAN is not supported for the Intel® Gigabit VT Quad Port Server Adapter. |
In this mode, a separate MSI-X vector is allocated for each queue and one for
"other" interrupts such as link status change and errors. All interrupts are
throttled via interrupt moderation. Interrupt moderation must be used to avoid
interrupt storms while the driver is processing one interrupt. The moderation
value should be at least as large as the expected time for the driver to process
an interrupt. Multiqueue is off by default.
Requirements: MSI-X support is required for Multiqueue. If MSI-X is not found, the system will
fallback to MSI or to Legacy interrupts. This driver supports multiqueue in kernel versions 2.6.24 and greater. This driver supports receive multiqueue on all kernels that support MSI-X.
|
|
NOTES: Do not use MSI-X with the 2.6.19 or 2.6.20
kernels. On some kernels a reboot is required to switch between a single queue mode and multiqueue modes, or vice-versa. |
Large Receive Offload (LRO) is a technique for increasing inbound throughput of high-bandwidth network connections by reducing CPU overhead. It works by aggregating multiple incoming packets from a single stream into a larger buffer before they are passed higher up the networking stack, thus reducing the number of packets that have to be processed. LRO combines multiple Ethernet frames into a single receive in the stack, thereby potentially decreasing CPU utilization for receives.
|
|
NOTE: LRO requires 2.4.22 or later kernel version. |
IGB_LRO is a compile time flag. The user can enable it at compile time to
add support for LRO from the driver. The flag is used by adding
CFLAGS_EXTRA="-DIGB_LRO" to the make file when it's being compiled.
#
make CFLAGS_EXTRA="-DIGB_LRO" install
You can verify that the driver is using LRO by looking at these counters in
ethtool:
lro_aggregated - count of total packets that were combined
lro_flushed - counts the number of packets flushed out of LRO
lro_recycled - reflects the number of buffers returned to the ring from
recycling
|
|
NOTE: IPv6 and UDP are not supported by LRO. |
When a malicious driver attempts to send a spoofed packet, it is dropped by
the hardware and not transmitted. An interrupt is sent to the PF driver
notifying it of the spoof attempt.
When a spoofed packet is detected the PF driver will send the following message
to the system log (displayed by the "dmesg" command):
Spoof event(s) detected on VF(n)
Where n=the VF that attempted to do the spoofing.
|
|
NOTE: After installing the driver, if your Intel Ethernet Network Connection is not working, verify that you have installed the correct driver. |
Due to limited support for PCI-Express in 2.4 kernels and older 2.6 kernels, the igb driver may run into interrupt related problems on some systems, such as no link or hang when bringing up the device.
We recommend the newer 2.6 based kernels, as these kernels correctly
configure the PCI-Express configuration space of the adapter and all intervening
bridges. If you are required to use a 2.4 kernel, use a 2.4 kernel newer than
2.4.30. For 2.6 kernels we recommend using the 2.6.21 kernel or newer.
Alternatively, on 2.6 kernels you may disable MSI support in the kernel by
booting with the "pci=nomsi" option or permanently disable MSI support in your
kernel by configuring your kernel with CONFIG_PCI_MSI unset.
In some cases ports 3 and 4 don't pass traffic and report 'Detected Tx Unit
Hang' followed by 'NETDEV WATCHDOG: ethX: transmit timed out' errors. Ports 1
and 2 don't show any errors and will pass traffic.
This issue MAY be resolved by updating to the latest kernel and BIOS. The
user is encouraged to run an OS that fully supports MSI interrupts. You can
check your system's BIOS by downloading the Linux Firmware Developer Kit that
can be obtained at http://www.linuxfirmwarekit.org/
When trying to compile the driver by running make install, the following error may occur: "Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree and entering:
# make include/linux/version.h
Degradation in throughput performance may be observed in some Jumbo frames environments. If this is observed, increasing the application's socket buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific application manual and /usr/src/linux*/Documentation/networking/ip-sysctl.txt for more details.
There is a known issue using Jumbo frames when connected to a Foundry BigIron 8000 switch. This is a 3rd party limitation. If you experience loss of packets, lower the MTU size.
Due to the default ARP behavior on Linux, it is not possible to have one system on two IP networks in the same Ethernet broadcast domain (non-partitioned switch) behave as expected. All Ethernet interfaces will respond to IP traffic for any IP address assigned to the system. This results in unbalanced receive traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5)
|
|
NOTE: This setting is not saved across reboots. The
configuration change can be made permanent by adding the line:
|
In order to disable receive flow control using ethtool, you must turn off auto-negotiation on the same command line.
For example:
ethtool -A eth? autoneg off rx off
In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging the network cable while ethtool -p is running will cause the system to become unresponsive to keyboard commands, except for control-alt-delete. Restarting the system appears to be the only remedy.
There is a known hardware compatibility issue on some systems with RHEL3
kernels. Traffic on ports 1 and 2 may be slower than expected and ping times
higher than expected.
This issue MAY be resolved by updating to the latest kernel and BIOS. You can
check your system's BIOS by downloading the Linux Firmware Developer Kit that
can be obtained at http://www.linuxfirmwarekit.org/
Due to a known general compatibilty issue with LRO and routing, do not use LRO when routing packets.
Some systems may experience build issues due to redefinition of irq_handler_t. To resolve this issue build the driver (step 4 above) using the command:
# make CFLAGS_EXTRA=-DAX_RELEASE_CODE=1 install
Kernel panics and instability may be observed on any MSI-X hardware if you use irqbalance with kernels between 2.6.19 and 2.6.21. If such problems are encountered, you may disable the irqbalance daemon or upgrade to a newer kernel.
Page allocation failure. order:0 errors may occur under stress with kernels 2.6.25 and above. This is caused by the way the Linux kernel reports this stressed condition.
Do not remove the igb driver from Dom0 while Virtual Functions (VFs) are
assigned to guests. VFs must first use the xm "pci-detach" command to hot-plug
the VF device out of the VM it is assigned to or else shut down the
VM.
This is a known SLES-10 SP3 issue. After requesting interrupts for MSI-X vectors, system may panic.
Currently the only known workaround is to build the drivers with CFLAGS_EXTRA=-DDISABLE_PCI_MSI if the driver need to be loaded/unloaded. Otherwise the driver can be loaded once and will be safe, but unloading it will lead to the issue.
KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This
includes traditional PCIe devices, as well as SR-IOV-capable devices using Intel
82576-based and 82599-based controllers.
While direct assignment of a PCIe device or an SR-IOV Virtual Function (VF) to a
Linux-based VM running 2.6.32 or later kernel works fine, there is a known issue
with Microsoft Windows Server 2008 VM that results in a "yellow bang" error.
This problem is within the KVM VMM itself, not the Intel driver, or the SR-IOV
logic of the VMM, but rather that KVM emulates an older CPU model for the
guests, and this older CPU model does not support MSI-X interrupts, which is a
requirement for Intel SR-IOV.
If you wish to use the Intel 82576 or 82599-based controllers in SR-IOV mode
with KVM and a Microsoft Windows Server 2008 guest try the following workaround.
The workaround is to tell KVM to emulate a different model of CPU when using
qemu to create the KVM guest:
"-cpu qemu64,model=13"
Using kernel versions earlier than 3.2, do not unload the PF driver with active VFs. Doing this will cause your VFs to stop working until you reload the PF driver and may cause a spontaneous reboot of your system.
Speed and Duplex Configuration
The Linux Base Drivers support the 2.4.x and 2.6.x kernels. These drivers includes support for Itanium® 2-based systems.
These drivers are only supported as a loadable module. Intel is not supplying patches against the kernel source to allow for static linking of the drivers. For questions related to hardware requirements, refer to the documentation supplied with your Intel Gigabit adapter. All hardware requirements listed apply to use with Linux.
The following features are now available in supported kernels:
Native VLANs
Channel Bonding (teaming)
SNMP
Channel Bonding documentation can be found in the Linux kernel source: /documentation/networking/bonding.txt
The driver information previously displayed in the /proc file system is not supported in this release. Alternatively, you can use ethtool (version 1.6 or later), lspci, and ifconfig to obtain the same information. Instructions on updating ethtool can be found in the section Additional Configurations later in this document.
|
NOTE: The Intel® 82562v 10/100 Network Connection only provides 10/100 support. |
To build a binary RPM* package of this driver, run 'rpmbuild -tb e1000.tar.gz'.
|
NOTES:
|
Move the base driver tar file to the directory of your
choice. For example, use '/home/username/e1000' or '/usr/local/src/e1000'.
Untar/unzip the archive, where <x.x.x> is the version number for the driver tar file:
tar zxf e1000-<x.x.x>.tar.gz
Change to the driver src directory, where <x.x.x> is the version number for the driver tar:
cd e1000-<x.x.x>/src/
Compile the driver module:
# make install
The binary will be installed as:
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/e1000/e1000.[k]o
The install location listed above is the default location.
This may differ for various Linux distributions.
Load the module using either the insmod or modprobe command:
modprobe e1000
insmod e1000
Note that for 2.6 kernels the insmod command can be used if the full path to the driver module is specified. For example:
insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/e1000/e1000.ko
With 2.6 based kernels also make sure that older e1000 drivers are removed from the kernel, before loading the new module:
rmmod e1000; modprobe e1000
Assign an IP address to the interface by entering the following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where <IP_address> is the IP address for another machine on the same subnet as the interface that is being tested:
ping <IP_address>
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe e1000 [<option>=<VAL1>,<VAL2>,...]
For example, with two Gigabit PCI adapters, entering:
modprobe e1000 TxDescriptors=80,128
loads the e1000 driver with 80 TX descriptors for the first adapter and 128 TX descriptors for the second adapter.
The default value for each parameter is generally the recommended setting, unless otherwise noted.
|
|
NOTES:
|
| Parameter Name | Valid Range/Settings | Default | Description |
|---|---|---|---|
| AutoNeg | 0x01-0x0F, 0x20-0x2F | 0x2F |
This parameter is a bit mask that specifies which speed and duplex
settings the board advertises. When this parameter is used, the
Speed and Duplex parameters must not be specified.
This parameter is supported only on adapters using copper connections. |
| Duplex | 0-2 (0=auto-negotiate, 1=half, 2=full) | 0 |
Defines the direction in which data is allowed to flow. Can be either
one or two-directional. If both Duplex and the link partner are set to auto-negotiate, the board
auto-detects the correct duplex. If the link partner is forced
(either full or half), Duplex defaults to half-duplex.
This parameter is supported only on adapters using copper connections. |
| FlowControl | 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) | Read flow control settings from the EEPROM | This parameter controls the automatic generation(Tx) and response(Rx) to Ethernet PAUSE frames. |
| InterruptThrottleRate | (not supported on Intel(R) 82542, 82543 or 82544-based adapters) Valid Range: 0,1,3,4, 100-100000 (0=off, 1=dynamic, 3=dynamic conservative, 4=simplified balancing) |
3 |
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to
the adapter that is based on the maximum amount of interrupts that the
adapter will generate per second. Setting InterruptThrottleRate to a value greater or equal to 100 will program the adapter to send out a maximum of that many interrupts per second, even if more packets have come in. This reduces interrupt load on the system and can lower CPU utilization under heavy load, but will increase latency as packets are not processed as quickly. The default behaviour of the driver previously assumed a static InterruptThrottleRate value of 8000, providing a good fallback value for all traffic types, but lacking in small packet performance and latency. The hardware can handle many more small packets per second however, and for this reason an adaptive interrupt moderation algorithm was implemented. Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which it dynamically adjusts the InterruptThrottleRate value based on the traffic that it receives. After determining the type of incoming traffic in the last timeframe, it will adjust the InterruptThrottleRate to an appropriate value for that traffic. The algorithm classifies the incoming traffic every interval into classes. Once the class is determined, the InterruptThrottleRate value is adjusted to suit that traffic type the best. There are three classes defined: "Bulk traffic", for large amounts of packets of normal size; "Low latency", for small amounts of traffic and/or a significant percentage of small packets; and "Lowest latency", for almost completely small packets or minimal traffic. In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is increased stepwise to 20000. This default mode is suitable for most applications. For situations where low latency is vital such as cluster or grid computing, the algorithm can reduce latency even more when InterruptThrottleRate is set to mode 1. In this mode, which operates the same as mode 3, the InterruptThrottleRate will be increased stepwise to 70000 for traffic in class "Lowest latency". In simplified mode the
interrupt rate is based on the ratio of tx and rx traffic. If the bytes
per second rate is approximately equal, the interrupt rate will drop as
low as 2000 interrupts per second. If the traffic is mostly transmit or
mostly receive, the interrupt rate could
modprobe e1000 InterruptThrottleRate=3000,3000,3000 This sets the InterruptThrottleRate to 3000 interrupts/sec for the first, second, and third instances of the driver. The range of 2000 to 3000 interrupts per second works on a majority of systems and is a good starting point, but the optimal value will be platform-specific. If CPU utilization is not a concern, use RX_POLLING (NAPI) and default driver settings. |
| RxDescriptors | 80-4096 | 256 |
This value specifies the number of receive buffer descriptors allocated
by the driver. Increasing this value allows the driver to buffer more
incoming packets, at the expense of increased system memory utilization.
Each descriptor is 16 bytes. A receive buffer is also allocated for each descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending on the MTU setting. The maximum MTU size is 16110.
|
| RxIntDelay | 0-65535 (0=off) | 0 |
This value delays the generation of receive interrupts in units of
1.024 microseconds. Receive interrupt reduction can improve CPU
efficiency if properly tuned for specific network traffic.
Increasing this value adds extra latency to frame reception
and can end up decreasing the throughput of TCP traffic. If the system is
reporting dropped receives, this value may be set too high, causing the
driver to run out of available receive descriptors.
|
| RxAbsIntDelay | 0-65535 (0=off) | 8 | This value, in units of 1.024 microseconds, limits the delay in which a
receive interrupt is generated. Useful only if RxIntDelay is non-zero,
this value ensures that an interrupt is generated after the initial
packet is received within the set amount of time. Proper tuning,
along with RxIntDelay, may improve traffic throughput in specific
network conditions.
This parameter is supported only on 82540, 82545 and later adapters. |
| Speed | 0, 10, 100, 1000 | 0 |
Speed forces the line speed to the specified value in megabits per second (Mbps). If this parameter
is not specified or is set to 0 and the link partner is set to auto-negotiate, the board
will auto-detect the correct speed. Duplex must also be set when Speed is set to either 10 or 100. This parameter is supported only on adapters using copper connections. |
| TxDescriptors | 80-4096 | 256 | This value is the number of transmit descriptors allocated by the driver. Increasing this value allows the driver to queue more transmits. Each descriptor is 16 bytes. |
| TxDescriptorStep |
1 (use every Tx Descriptor) 4 (use every 4th Tx Descriptor) |
1 (use every Tx Descriptor) |
On certain non-Intel architectures, it has been observed that intense TX
traffic bursts of short packets may result in an improper descriptor
writeback. If this occurs, the driver will report a "TX Timeout" and reset
the adapter, after which the transmit flow will restart, though data may
have stalled for as much as 10 seconds before it resumes. The improper writeback does not occur on the first descriptor in a system memory cache-line, which is typically 32 bytes, or 4 descriptors long. Setting TxDescriptorStep to a value of 4 will ensure that all TX descriptors are aligned to the start of a system memory cache line, and so this problem will not occur.
|
| TxIntDelay | 0-65535 (0=off) | 8 | This value delays the generation of transmit interrupts in units of 1.024 microseconds. Transmit interrupt reduction can improve CPU efficiency if properly tuned for specific network traffic. If the system is reporting dropped transmits, this value may be set too high causing the driver to run out of available transmit descriptors. |
| TxAbsIntDelay | 0-65535 (0=off) | 32 |
This value, in units of 1.024 microseconds, limits the delay in which a transmit
interrupt is generated. Useful only if TxIntDelay is non-zero, this value
ensures that an interrupt is generated after the initial packet is sent on
the wire within the set amount of time. Proper tuning, along with TxIntDelay,
may improve traffic throughput in specific network conditions. This parameter is supported only on 82540, 82545 and later adapters. |
| XsumRX | 0-1 | 1 |
A value of '1' indicates that the driver should enable IP checksum
offload for received packets (both UDP and TCP) to the adapter
hardware.
This parameter is not supported on the 82542-based adapter. |
| Copybreak | 0-xxxxxxx (0=off) | 256 |
Usage: insmod e1000.ko copybreak=128 Driver copies all packets below or equaling this size to a fresh rx buffer before handing it up the stack. This parameter is different than other parameters, in that it is a single (not 1,1,1 etc.) parameter applied to all driver instances and it is also available during runtime at /sys/module/e1000/parameters/copybreak |
| SmartPowerDownEnable | 0-1 |
0 (disabled) | Allows Phy to turn off in lower power states. The user can turn off this parameter in supported chipsets. |
| KumeranLockLoss | 0-1 | 1 (enabled) | This workaround skips resetting the Phy at shutdown for the initial silicon releases of ICH8 systems. |
| TxDescPower |
6-12 | 12 | This value represents the size-order of each transmit descriptor. The valid size for descriptors would be 2^6 (64) to 2^12 (4096) bytes each. As this value decreases one may want to consider increasing the TxDescriptors value to maintain the same amount of frame memory. |
Three keywords are used to control the speed and duplex configuration. These keywords are Speed, Duplex, and AutoNeg.
If the board uses a fiber interface, these keywords are ignored, and the fiber interface board only links at 1000 Mbps full-duplex.
For copper-based boards, the keywords interact as follows:
The default operation is auto-negotiate. The board advertises all supported speed and duplex combinations, and it links at the highest common speed and duplex mode IF the link partner is set to auto-negotiate.
If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps is advertised (The 1000BaseT spec requires auto-negotiation.)
If Speed = 10 or 100, then both Speed and Duplex should be set. Auto-negotiation is disabled, and the AutoNeg parameter is ignored. Partner SHOULD also be forced.
The AutoNeg parameter is used when more control is required over the auto-negotiation process. It should be used when you wish to control which speed and duplex combinations are advertised during the auto-negotiation process. The parameter may be specified as either a decimal or hexadecimal value as determined by the bitmap below.
| Bit Position | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 |
| Decimal Value | 128 | 64 | 32 | 16 | 8 | 4 | 2 | 1 |
| Hex Value | 80 | 40 | 20 | 10 | 8 | 4 | 2 | 1 |
| Speed (Mbps): | N/A | N/A | 1000 | N/A | 100 | 100 | 10 | 10 |
| Duplex: | Full | Full | Half | Full | Half |
Some examples of using AutoNeg:
modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
modprobe e1000 AutoNeg=1 (Same as above)
modprobe e1000 AutoNeg=0x02 (Restricts autonegotiation to 10 Full)
modprobe e1000 AutoNeg=0x03 (Restricts autonegotiation to 10 Half or 10 Full)
modprobe e1000 AutoNeg=0x04 (Restricts autonegotiation to 100 Half)
modprobe e1000 AutoNeg=0x05 (Restricts autonegotiation to 10 Half or 100 Half)
modprobe e1000 AutoNeg=0x020 (Restricts autonegotiation to 1000 Full)
modprobe e1000 AutoNeg=32 (Same as above)
Note that when this parameter is used, Speed and Duplex must not be specified.
If the link partner is forced to a specific speed and duplex, then this parameter should not be used. Instead, use the Speed and Duplex parameters previously mentioned to force the adapter to the same speed and duplex.
Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to your distribution documentation. If during this process you are asked for the driver or module name, the name for the Linux Base Driver for the Gigabit family of adapters is e1000.
As an example, if you install the e1000 driver for two Gigabit adapters (eth0 and eth1) and set the speed and duplex to 10full and 100half, add the following to modules.conf or /etc/modprobe.conf:
alias eth0 e1000
alias eth1 e1000
options e1000 Speed=10,100 Duplex=2,1
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU) to a value larger than the default value of 1500. Use the ifconfig command to increase the MTU size. For example:
ifconfig eth<x> mtu 9000 up
This setting is not saved across reboots. The setting change can be made permanent by adding MTU=9000 to the file: /etc/sysconfig/network-scripts/ifcfg-eth<x> (Red Hat distributions). Other distributions may store this setting in a different location.
|
|
NOTES:
|
The driver utilizes the ethtool interface for driver configuration and diagnostics, as well as displaying statistical information. ethtool version 3 or later is required for this functionality, although we strongly recommend downloading the latest version at:
http://ftp.kernel.org/pub/software/network/ethtool/.
WoL is configured through the ethtool* utility. ethtool is included with all versions of Red Hat after Red Hat 7.2. For other Linux distributions, download and install ethtool from the following website: http://ftp.kernel.org/pub/software/network/ethtool/.
For instructions on enabling WoL with ethtool, refer to the website listed above.
WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e1000 driver must be loaded prior to shutting down or suspending the system.
|
|
NOTES: Wake On LAN is only supported on port A for the
following devices:
|
NAPI (Rx polling mode) is supported in the e1000 driver. NAPI is enabled or disabled based on the configuration of the kernel. To override the default, use the following compile-time flags.
To enable NAPI, compile the driver module, passing in a configuration option:
# make CFLAGS_EXTRA=-DE1000_NAPI install
To disable NAPI, compile the driver module, passing in a configuration option:
# make CFLAGS_EXTRA=-DE1000_NO_NAPI install
See ftp://robur.slu.se/pub/Linux/net-development/NAPI/usenix-paper.tgz for more information on NAPI.
|
|
NOTE: After installing the driver, if your Intel Ethernet Network Connection is not working, verify that you have installed the correct driver. |
In some cases ports 3 and 4 don't pass traffic and report 'Detected Tx Unit
Hang' followed by 'NETDEV WATCHDOG: ethX: transmit timed out' errors. Ports 1
and 2 don't show any errors and will pass traffic.
This issue MAY be resolved by updating to the latest kernel and BIOS. The
user is encouraged to run an OS that fully supports MSI interrupts. You can
check your system's BIOS by downloading the Linux Firmware Developer Kit that
can be obtained at http://www.linuxfirmwarekit.org/
Several adapters with the 82573 chipset display "TX unit hang" messages during normal operation with the e1000 driver. The issue appears both with TSO enabled and disabled, and is caused by a power management function that is enabled in the EEPROM. Early releases of the chipsets to vendors had the EEPROM bit that enabled the feature. After the issue was discovered newer adapters were released with the feature disabled in the EEPROM.
If you encounter the problem in an adapter, and the chipset is an 82573-based one, you can verify that your adapter needs the fix by using ethtool:
# ethtool -e eth0
Offset Values
------ ------
0x0000 00 12 34 56 fe dc 30 0d 46 f7 f4 00 ff ff ff ff
0x0010 ff ff ff ff 6b 02 8c 10 d9 15 8c 10 86 80 de 83
^^
The value at offset 0x001e (de) has bit 0 unset. This enables the problematic power saving feature. In this case, the EEPROM needs to read "df" at offset 0x001e.
A one-time EEPROM fix is available as a shell script. This script will verify that the adapter is applicable to the fix and if the fix is needed or not. If the fix is required, it applies the change to the EEPROM and updates the checksum. The user must reboot the system after applying the fix if changes were made to the EEPROM.
Example output of the script:
# bash fixeep-82573-dspd.sh eth0 eth0: is a "82573E Gigabit Ethernet Controller" This fixup is applicable to your hardware executing command: ethtool -E eth0 magic 0x109a8086 offset 0x1e value 0xdf Change made. You *MUST* reboot your machine before changes take effect!
The script can be downloaded at http://e1000.sourceforge.net/files/fixeep-82573-dspd.sh
If you have an Intel PCI Express adapter running at 10mbps or 100mbps, half-duplex, you may observe occasional dropped receive packets. There are no workarounds for this problem in this network configuration. The network must be updated to operate in full-duplex, and/or 1000mbps only.
When trying to compile the driver by running make install, the following error may occur: "Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree and entering:
# make include/linux/version.h
Degradation in throughput performance may be observed in some Jumbo frames environments. If this is observed, increasing the application's socket buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific application manual and /usr/src/linux*/Documentation/networking/ip-sysctl.txt for more details.
There is a known issue using Jumbo frames when connected to a Foundry BigIron 8000 switch. This is a 3rd party limitation. If you experience loss of packets, lower the MTU size.
Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if the available memory is heavily fragmented. This issue may be seen with PCI-X adapters or with packet split disabled. This can be reduced or eliminated by changing the amount of available memory for receive buffer allocation, by increasing /proc/sys/vm/min_free_kbytes.
Due to the default ARP behavior on Linux, it is not possible to have one system on two IP networks in the same Ethernet broadcast domain (non-partitioned switch) behave as expected. All Ethernet interfaces will respond to IP traffic for any IP address assigned to the system. This results in unbalanced receive traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5)
|
|
NOTE: This setting is not saved across reboots. The
configuration change can be made permanent by adding the line:
|
There is a known compatibility issue with 82541/82547 and some low-end switches where the link will not be established, or will be slow to establish. In particular, these switches are known to be incompatible with 82541/82547:
Planex FXG-08TE
I-O Data ETG-SH8
To workaround this issue, the driver can be compiled with an override of the PHY's master/slave setting. Forcing master or forcing slave mode will improve time-to-link.
# make CFLAGS_EXTRA=-DE1000_MASTER_SLAVE=<n>
Where <n> is:
0 = Hardware default
1 = Master mode
2 = Slave mode
3 = Auto master/slave
In order to disable receive flow control using ethtool, you must turn off auto-negotiation on the same command line.
For example:
ethtool -A eth? autoneg off rx off
In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging the
network cable while ethtool -p is running will cause the system to
become unresponsive to keyboard commands, except for control-alt-delete.
Restarting the system appears to be the only remedy.
Speed and Duplex Configuration
The Linux Base Drivers support the 2.4.x and 2.6.x kernels. These drivers includes support for Itanium® 2-based systems.
These drivers are only supported as a loadable module. Intel is not supplying patches against the kernel source to allow for static linking of the drivers. For questions related to hardware requirements, refer to the documentation supplied with your Intel Gigabit adapter. All hardware requirements listed apply to use with Linux.
The following features are now available in supported kernels:
Native VLANs
Channel Bonding (teaming)
SNMP
Channel Bonding documentation can be found in the Linux kernel source: /documentation/networking/bonding.txt
The driver information previously displayed in the /proc file system is not supported in this release. Alternatively, you can use ethtool (version 1.6 or later), lspci, and ifconfig to obtain the same information. Instructions on updating ethtool can be found in the section Additional Configurations later in this document.
|
NOTE: The Intel® 82562v 10/100 Network Connection only provides 10/100 support. |
To build a binary RPM* package of this driver, run 'rpmbuild -tb e1000e.tar.gz'.
|
NOTES:
|
Move the base driver tar file to the directory of your
choice. For example, use '/home/username/e1000e' or '/usr/local/src/e1000e'.
Untar/unzip the archive, where <x.x.x> is the version number for the driver tar file:
tar zxf e1000e-<x.x.x>.tar.gz
Change to the driver src directory, where <x.x.x> is the version number for the driver tar:
cd e1000e-<x.x.x>/src/
Compile the driver module:
# make install
The binary will be installed as:
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/e1000e/e1000e.[k]o
The install location listed above is the default location.
This may differ for various Linux distributions.
Load the module using either the insmod or modprobe command:
modprobe e1000e
insmod e1000e
Note that for 2.6 kernels the insmod command can be used if the full path to the driver module is specified. For example:
insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/e1000e/e1000e.ko
With 2.6 based kernels also make sure that older e1000e drivers are removed from the kernel, before loading the new module:
rmmod e1000e; modprobe e1000e
Assign an IP address to the interface by entering the following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where <IP_address> is the IP address for another machine on the same subnet as the interface that is being tested:
ping <IP_address>
|
|
TROUBLESHOOTING: Some systems have trouble supporting MSI and/or MSI-X interrupts. If you believe your system needs to disable this style of interrupt, the driver can be built and installed with the command:
Normally the driver will generate an interrupt every two seconds, so if you can see that you're no longer getting interrupts in cat /proc/interrupts for the ethX e1000e device, then this workaround may be necessary. |
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe e1000e [<option>=<VAL1>,<VAL2>,...]
The default value for each parameter is generally the recommended setting, unless otherwise noted.
|
|
NOTES:
|
| Parameter Name | Valid Range/Settings | Default | Description |
|---|---|---|---|
| InterruptThrottleRate | 0,1,3,4, 100-100000 (0=off, 1=dynamic, 3=dynamic conservative, 4-simplified balancing) |
3 |
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to
the adapter that is based on the maximum amount of interrupts that the
adapter will generate per second. Setting InterruptThrottleRate to a value greater or equal to 100 will program the adapter to send out a maximum of that many interrupts per second, even if more packets have come in. This reduces interrupt load on the system and can lower CPU utilization under heavy load, but will increase latency as packets are not processed as quickly. The default behavior of the driver previously assumed a static InterruptThrottleRate value of 8000, providing a good fallback value for all traffic types, but lacking in small packet performance and latency. The driver has two adaptive modes (setting 1 or 3) in which it dynamically adjusts the InterruptThrottleRate value based on the traffic that it receives. After determining the type of incoming traffic in the last timeframe, it will adjust the InterruptThrottleRate to an appropriate value for that traffic. The algorithm classifies the incoming traffic every interval into classes. Once the class is determined, the InterruptThrottleRate value is adjusted to suit that traffic type the best. There are three classes defined: "Bulk traffic", for large amounts of packets of normal size; "Low latency", for small amounts of traffic and/or a significant percentage of small packets; and "Lowest latency", for almost completely small packets or minimal traffic. In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is increased stepwise to 20000. This default mode is suitable for most applications. For situations where low latency is vital such as cluster or grid computing, the algorithm can reduce latency even more when InterruptThrottleRate is set to mode 1. In this mode, which operates the same as mode 3, the InterruptThrottleRate will be increased stepwise to 70000 for traffic in class "Lowest latency". In simplified mode the
interrupt rate is based on the ratio of tx and rx traffic. If the bytes
per second rate is approximately equal, the
interrupt rate will drop as low as 2000 interrupts per second. If the
traffic is mostly transmit or mostly receive, the interrupt rate could
be as high as 8000.
modprobe e1000e InterruptThrottleRate=3000,3000,3000 This sets the InterruptThrottleRate to 3000 interrupts/sec for the first, second, and third instances of the driver. The range of 2000 to 3000 interrupts per second works on a majority of systems and is a good starting point, but the optimal value will be platform-specific. If CPU utilization is not a concern, use RX_POLLING (NAPI) and default driver settings. |
| RxIntDelay | 0-65535 (0=off) | 0 |
This value delays the generation of receive interrupts in units of
1.024 microseconds. Receive interrupt reduction can improve CPU
efficiency if properly tuned for specific network traffic.
Increasing this value adds extra latency to frame reception
and can end up decreasing the throughput of TCP traffic. If the system is
reporting dropped receives, this value may be set too high, causing the
driver to run out of available receive descriptors.
|
| RxAbsIntDelay | 0-65535 (0=off) | 8 | This value, in units of 1.024 microseconds, limits the delay in which a receive interrupt is generated. Useful only if RxIntDelay is non-zero, this value ensures that an interrupt is generated after the initial packet is received within the set amount of time. Proper tuning, along with RxIntDelay, may improve traffic throughput in specific network conditions. |
| TxIntDelay | 0-65535 (0=off) | 8 | This value delays the generation of transmit interrupts in units of 1.024 microseconds. Transmit interrupt reduction can improve CPU efficiency if properly tuned for specific network traffic. If the system is reporting dropped transmits, this value may be set too high causing the driver to run out of available transmit descriptors. |
| TxAbsIntDelay | 0-65535 (0=off) | 32 | This value, in units of 1.024 microseconds, limits the delay in which a transmit interrupt is generated. Useful only if TxIntDelay is non-zero, this value ensures that an interrupt is generated after the initial packet is sent on the wire within the set amount of time. Proper tuning, along with TxIntDelay, may improve traffic throughput in specific network conditions. |
| copybreak | 0-xxxxxxx (0=off) | 256 |
Usage: insmod e1000e.ko copybreak=128 Driver copies all packets below or equaling this size to a fresh rx buffer before handing it up the stack. This parameter is different than other parameters, in that it is a single (not 1,1,1 etc.) parameter applied to all driver instances and it is also available during runtime at /sys/module/e1000e/parameters/copybreak |
| SmartPowerDownEnable | 0-1 |
0 (disabled) | Allows Phy to turn off in lower power states. The user can turn off this parameter in supported chipsets. |
| KumeranLockLoss | 0-1 | 1 (enabled) | This workaround skips resetting the Phy at shutdown for the initial silicon releases of ICH8 systems. |
| IntMode | 0-2 (0=legacy, 1=MSI, 2=MSI-X) |
2 (MSI-X)
|
Allows changing the interrupt mode at module load time, without requiring a recompile. If the driver load fails to enable a specific interrupt mode, the driver will try other interrupt modes, from least to most compatible. The interrupt order is MSI-X, MSI, Legacy. If specifying MSI (IntMode=1) interrupts, only MSI and Legacy will be attempted. |
| CrcStripping | 0-1 | 1 (enabled) | Strip the CRC from received packets before sending up the network stack. If you have a machine with a BMC enabled but cannot receive IPMI traffic after loading or enabling the driver, try disabling this feature. |
| EEE | 0-1 | 1 (enabled for parts supporting EEE) | This option allows for the ability of IEEE802.3az (a.k.a. Energy Efficient Ethernet or EEE) to be advertised to the link partner on parts supporting EEE. EEE saves energy by putting the device into a low-power state when the link is idle, but only when the link partner also supports EEE and after the feature has been enabled during link negotiation. It is not necessary to disable the advertisement of EEE when connected with a link partner that does not support EEE. |
| Node | 0-n 0 - n: where n is the number of the NUMA node that should be used to allocate memory for this adapter port. -1: uses the driver default of allocating memory on whichever processor is running insmod/modprobe. |
-1 (off) | The Node parameter will allow you to pick which NUMA node you want to have the adapter allocate memory from. All driver structures, in-memory queues, and receive buffers will be allocated on the node specified. This parameter is only useful when interrupt affinity is specified, otherwise some portion of the time the interrupt could run on a different core than the memory is allocated on, causing slower memory access and impacting throughput, CPU, or both. |
Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to your distribution documentation. If during this process you are asked for the driver or module name, the name for the Linux Base Driver for the Gigabit family of adapters is e1000e.
alias eth0 e1000e
alias eth1 e1000e
options e1000e IntMode=2,1
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU) to a value larger than the default value of 1500. Use the ifconfig command to increase the MTU size. For example:
ifconfig eth<x> mtu 9000 up
This setting is not saved across reboots. The setting change can be made permanent by adding MTU=9000 to the file: /etc/sysconfig/network-scripts/ifcfg-eth<x> (Red Hat distributions). Other distributions may store this setting in a different location.
|
|
NOTES:
|
The driver utilizes the ethtool interface for driver configuration and diagnostics, as well as displaying statistical information. ethtool version 3 or later is required for this functionality, although we strongly recommend downloading the latest version at:
http://ftp.kernel.org/pub/software/network/ethtool/.
|
NOTE: When validating enable/disable tests on some parts (82578, for example) you need to add a few seconds between tests when working with ethtool. |
Speed and Duplex are configured through the ethtool* utility. ethtool is included with all versions of Red Hat after Red Hat 7.2. For other Linux distributions, download and install ethtool from the following website: http://ftp.kernel.org/pub/software/network/ethtool/.
WoL is configured through the ethtool* utility. ethtool is included with all versions of Red Hat after Red Hat 7.2. For other Linux distributions, download and install ethtool from the following website: http://ftp.kernel.org/pub/software/network/ethtool/.
For instructions on enabling WoL with ethtool, refer to the website listed above.
WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e1000e driver must be loaded prior to shutting down or suspending the system.
|
|
NOTES: Wake On LAN is only supported on port A for the
following devices:
|
NAPI (Rx polling mode) is supported in the e1000e driver. NAPI is enabled by default.
To disable NAPI, compile the driver module, passing in a configuration option:
# make CFLAGS_EXTRA=-DE1000E_NO_NAPI install
See ftp://robur.slu.se/pub/Linux/net-development/NAPI/usenix-paper.tgz for more information on NAPI.
|
|
NOTE: After installing the driver, if your Intel Network Connection is not working, verify that you have installed the correct driver. |
In some cases ports 3 and 4 don't pass traffic and report 'Detected Tx Unit
Hang' followed by 'NETDEV WATCHDOG: ethX: transmit timed out' errors. Ports 1
and 2 don't show any errors and will pass traffic.
This issue MAY be resolved by updating to the latest kernel and BIOS. The
user is encouraged to run an OS that fully supports MSI interrupts. You can
check your system's BIOS by downloading the Linux Firmware Developer Kit that
can be obtained at http://www.linuxfirmwarekit.org/
Adapters that have 4 ports behind a PCIe bridge may be incompatible with some
systems. The user should run the Linux firmware kit from
http://www.linuxfirmwarekit.org/ to test their BIOS, if they have interrupt or "missing
interface" problems, especially with older kernels.
Several adapters with the 82573 chipset display "TX unit hang" messages during normal operation with the e1000e driver. The issue appears both with TSO enabled and disabled, and is caused by a power management function that is enabled in the EEPROM. Early releases of the chipsets to vendors had the EEPROM bit that enabled the feature. After the issue was discovered newer adapters were released with the feature disabled in the EEPROM.
If you encounter the problem in an adapter, and the chipset is an 82573-based one, you can verify that your adapter needs the fix by using ethtool:
# ethtool -e eth0
Offset Values
------ ------
0x0000 00 12 34 56 fe dc 30 0d 46 f7 f4 00 ff ff ff ff
0x0010 ff ff ff ff 6b 02 8c 10 d9 15 8c 10 86 80 de 83
^^
The value at offset 0x001e (de) has bit 0 unset. This enables the problematic power saving feature. In this case, the EEPROM needs to read "df" at offset 0x001e.
A one-time EEPROM fix is available as a shell script. This script will verify that the adapter is applicable to the fix and if the fix is needed or not. If the fix is required, it applies the change to the EEPROM and updates the checksum. The user must reboot the system after applying the fix if changes were made to the EEPROM.
Example output of the script:
# bash fixeep-82573-dspd.sh eth0 eth0: is a "82573E Gigabit Ethernet Controller" This fixup is applicable to your hardware executing command: ethtool -E eth0 magic 0x109a8086 offset 0x1e value 0xdf Change made. You *MUST* reboot your machine before changes take effect!
The script can be downloaded at http://e1000.sourceforge.net/files/fixeep-82573-dspd.sh
If you have an Intel PCI Express adapter running at 10mbps or 100mbps, half-duplex, you may observe occasional dropped receive packets. There are no workarounds for this problem in this network configuration. The network must be updated to operate in full-duplex, and/or 1000mbps only.
When trying to compile the driver by running make install, the following error may occur: "Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree and entering:
# make include/linux/version.h
Degradation in throughput performance may be observed in some Jumbo frames environments. If this is observed, increasing the application's socket buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific application manual and /usr/src/linux*/Documentation/networking/ip-sysctl.txt for more details.
There is a known issue using Jumbo frames when connected to a Foundry BigIron 8000 switch. This is a 3rd party limitation. If you experience loss of packets, lower the MTU size.
Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if
the available memory is heavily fragmented. This issue may be seen with PCI-X
adapters or with packet split disabled. This can be reduced or eliminated by
changing the amount of available memory for receive buffer allocation, by
increasing /proc/sys/vm/min_free_kbytes.
Due to the default ARP behavior on Linux, it is not possible to have one system on two IP networks in the same Ethernet broadcast domain (non-partitioned switch) behave as expected. All Ethernet interfaces will respond to IP traffic for any IP address assigned to the system. This results in unbalanced receive traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5)
|
|
NOTE: This setting is not saved across reboots. The
configuration change can be made permanent by adding the line:
|
In order to disable receive flow control using ethtool, you must turn off auto-negotiation on the same command line.
For example:
ethtool -A eth? autoneg off rx off
In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging the
network cable while ethtool -p is running will cause the system to
become unresponsive to keyboard commands, except for control-alt-delete.
Restarting the system appears to be the only remedy.
Kernel panics and instability may be observed on any MSI-X hardware if you use irqbalance with kernels between 2.6.19 and 2.6.21. If such problems are encountered, you may disable the irqbalance daemon or upgrade to a newer kernel.
Page allocation failure. order:0 errors may occur under stress with kernels 2.6.25 and above. This is caused by the way the Linux kernel reports this stressed condition.
This issue can be worked around by specifying "pci=nommconf" in the kernel
boot parameter or by using another kernel boot parameter
"memmap=128M$0x100000000" which marks 128 MB region at 4GB as reserved and
therefore OS won't use these RAM pages.
This issue is fixed in kernel version 2.6.21, where the kernel tries to
dynamically find out the mmconfig size by looking at the number of buses that
the mmconfig segment maps to.
This issue won't be seen on 32bit version of EL5, as in that case, the kernel
sees that RAM is located around the 256MB window and avoids using the mmconfig
space.
If a system based on the 82577, 82578, or 82579 controller is connected to a hub, the Activity LED will blink for all network traffic present on the hub. Connecting the system to a switch or router will filter out most traffic not addressed to the local port.
With some Phy and switch combinations, link can take longer than expected. This can be an issue on Linux distributions that timeout when checking for link prior to acquiring a DHCP address; however there is usually a way to work around this (e.g. set LINKDELAY in the interface configuration on RHEL).
Internal stress testing with jumbo frames shows the reliability on some 82566 and 82567 devices is improved in certain corner cases by disabling the Early Receive feature. Doing so can impact Tx performance. To reduce the impact, the packet buffer sizes and relevant flow control settings are modified accordingly.
This driver supports upstream kernel versions 2.6.30 (or higher) x86_64.
Supported Operating Systems: SLES 11 SP1 x86_64, RHEL 5.3/5.4 x86_64.
The igbvf driver supports 82576-based virtual function devices that can only be
activated on kernels that support SR-IOV. SR-IOV requires the correct
platform and OS support.
The igbvf driver requires the igb driver, version 2.0 or later. The igbvf driver
supports virtual functions generated by the igb driver with a max_vfs value of 1
or greater. For more information on the max_vfs parameter refer to the section
on the the igb driver.
The guest OS loading the igbvf driver must support MSI-X interrupts.
This driver is only supported as a loadable module at this time. Intel is not
supplying patches against the kernel source to allow for static linking of the
driver. For questions related to hardware requirements, refer to the
documentation supplied with your Intel Gigabit adapter. All hardware
requirements listed apply to use with Linux.
Instructions on updating ethtool can be found in the section Additional
Configurations later in this document.
VLANs: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
To build a binary RPM* package of this driver, run 'rpmbuild -tb <filename.tar.gz>'. Replace <filename.tar.gz> with the specific filename of the driver.
|
|
NOTE: For the build to work properly, the currently running kernel MUST match the version and configuration of the installed kernel sources. If you have just recompiled the kernel reboot the system now. |
RPM functionality has only been tested in Red Hat distributions.
Move the base driver tar file to the directory of your
choice. For example, use ' /home/username/igbvf or /usr/local/src/igbvf.'.
Untar/unzip the archive:
tar zxf igbvf-x.x.x.tar.gz
Change to the driver src directory:
cd igbvf-<x.x.x>/src/
Compile the driver module:
# make install
The binary will be installed as:
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/igbvf/igbvf.[k]o
The install location listed above is the default location.
This may differ for various Linux distributions.
Load the module using either the insmod or modprobe command:
modprobe igbvf
insmod igbvf
Note that for 2.6 kernels the insmod command can be used if the full path to the driver module is specified. For example:
insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/igbvf/igbvf.ko
With 2.6 based kernels also make sure that older e1000e drivers are removed from the kernel, before loading the new module:
rmmod igbvf; modprobe igbvf
Assign an IP address to the interface by entering the following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where <IP_address> is the IP address for another machine on the same subnet as the interface that is being tested:
ping <IP_address>
Troubleshooting: Some systems have trouble supporting MSI and/or MSI-X interrupts. If you believe your system needs to disable this style of interrupt, the driver can be built and installed with the command:
make CFLAGS_EXTRA=-DDISABLE_PCI_MSI install
Normally the driver will generate an interrupt every two seconds, so if you can see that you're no longer getting interrupts in cat /proc/interrupts for the ethX igbvf device, then this workaround may be necessary.
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe igbvf [<option>=<VAL1>,<VAL2>,...]
For example:
modprobe igbvf InterruptThrottleRate=16000,16000
The default value for each parameter is generally the recommended setting, unless otherwise noted.
|
|
NOTES:
|
| Parameter Name | Valid Range/Settings | Default | Description |
|---|---|---|---|
| InterruptThrottleRate | 0,1,3,100-100000 (0=off, 1=dynamic, 3=dynamic conservative) |
3 |
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to
the adapter that is based on the maximum amount of interrupts that the
adapter will generate per second. Setting InterruptThrottleRate to a value greater or equal to 100 will program the adapter to send out a maximum of that many interrupts per second, even if more packets have come in. This reduces interrupt load on the system and can lower CPU utilization under heavy load, but will increase latency as packets are not processed as quickly. The default behaviour of the driver previously assumed a static InterruptThrottleRate value of 8000, providing a good fallback value for all traffic types, but lacking in small packet performance and latency. The hardware can handle many more small packets per second however, and for this reason an adaptive interrupt moderation algorithm was implemented. The driver has two adaptive modes (setting 1 or 3) in which it dynamically adjusts the InterruptThrottleRate value based on the traffic that it receives. After determining the type of incoming traffic in the last timeframe, it will adjust the InterruptThrottleRate to an appropriate value for that traffic. The algorithm classifies the incoming traffic every interval into classes. Once the class is determined, the InterruptThrottleRate value is adjusted to suit that traffic type the best. There are three classes defined: "Bulk traffic", for large amounts of packets of normal size; "Low latency", for small amounts of traffic and/or a significant percentage of small packets; and "Lowest latency", for almost completely small packets or minimal traffic. In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is increased stepwise to 20000. This default mode is suitable for most applications. For situations where low latency is vital such as cluster or grid computing, the algorithm can reduce latency even more when InterruptThrottleRate is set to mode 1. In this mode, which operates the same as mode 3, the InterruptThrottleRate will be increased stepwise to 70000 for traffic in class "Lowest latency". Setting InterruptThrottleRate to 0 turns off any interrupt moderation and may improve small packet latency, but is generally not suitable for bulk throughput traffic
modprobe igbvf InterruptThrottleRate=3000,3000,3000 This sets the InterruptThrottleRate to 3000 interrupts/sec for the first, second, and third instances of the driver. The range of 2000 to 3000 interrupts per second works on a majority of systems and is a good starting point, but the optimal value will be platform-specific. If CPU utilization is not a concern, use default driver settings. |
Configuring a network driver to load properly when the system is started is
distribution dependent. Typically, the configuration process involves adding an
alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing other
system startup scripts and/or configuration files. Many popular Linux
distributions ship with tools to make these changes for you. To learn the proper
way to configure a network device for your system, refer to your distribution
documentation. If during this process you are asked for the driver or module
name, the name for the Linux Base Driver for the Gigabit Family of Adapters is
igbvf.
As an example, if you install the igbvf driver for two Gigabit adapters (eth0
and eth1) and want to set the interrupt mode to MSI-X and MSI respectively, add
the following to modules.conf or /etc/modprobe.conf:
alias eth0 igbvf
alias eth1 igbvf
options igbvf InterruptThrottleRate=3,1
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
Jumbo Frames support is enabled by changing the MTU to a value larger than the default of 1500. Use the ifconfig command to increase the MTU size.
For example:
ifconfig eth<x> mtu 9000 up
This setting is not saved across reboots. It can be made permanent if you add:
MTU=9000
to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example applies to the Red Hat distributions; other distributions may store this setting in a different location.
|
|
NOTES:
|
|
|
NOTE: After installing the driver, if your Intel Network Connection is not working, verify that you have installed the correct driver. |
When trying to compile the driver by running make install, the following
error may occur:
"Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree
and entering:
make include/linux/version.h.
Due to the default ARP behavior on Linux, it is not possible to have one
system on two IP networks in the same Ethernet broadcast domain (non-partitioned
switch) behave as expected. All Ethernet interfaces will respond to IP traffic
for any IP address assigned to the system. This results in unbalanced receive
traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by
entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5),
|
|
NOTE: This setting is not saved across reboots. The configuration change can be made permanent by adding the line: net.ipv4.conf.all.arp_filter = 1 to the file /etc/sysctl.conf or, |
Due to a known general compatibility issue with LRO and routing, do not use
LRO when routing packets.
Build error with Asianux 3.0 - redefinition of typedef 'irq_handler_t'
Some systems may experience build issues due to redefinition of irq_handler_t. To resolve this issue build the driver (step 4 above) using the command:
make CFLAGS_EXTRA=-DAX_RELEASE_CODE=1 install
Kernel panics and instability may be observed on any MSI-X hardware if you
use irqbalance with kernels between 2.6.19 and 2.6.21. If such problems are
encountered, you may disable the irqbalance daemon or upgrade to a newer kernel.
Page allocation failure. order:0 errors may occur under stress with kernels 2.6.25 and above. This is caused by the way the Linux kernel reports this stressed condition.
Do not remove the igbvf driver from Dom0 while Virtual Functions (VFs) are assigned to guests. VFs must first use the xm "pci-detach" command to hot-plug the VF device out of the VM it is assigned to or else shut down the VM.
Do not unload the PF driver (igb) while VFs are assigned to guests.
Using kernel versions earlier than 3.2, do not unload the PF driver with active VFs. Doing this will cause your VFs to stop working until you reload the PF driver and may cause a spontaneous reboot of your system.
Last modified on 11/03/11 4:12p Revision
|
NOTES: This release includes the ixgbe and ixgbevf Linux* Base Drivers for the Intel Ethernet 10 Gigabit Family of Adapters. |
 |
Warning: The ixgbe driver compiles by default with the LRO (Large Receive Offload) feature enabled. This option offers the lowest CPU utilization for receives, but is completely incompatible with *routing/ip forwarding* and *bridging*. If enabling ip forwarding or bridging is a requirement, it is necessary to disable LRO using compile time options as noted in the LRO section later in this document. The result of not disabling LRO when combined with ip forwarding or bridging can be low throughput or even a kernel panic. |
The Linux* base driver supports the 2.6.x
and 3.x kernels, and includes support for any Linux supported system, including
Itanium(R)2, x86_64, i686, and PPC.
These drivers are only supported as a loadable module at this time. Intel is not
supplying patches against the kernel source to allow for static linking of the
driver. A version of the driver may already be included by your distribution
and/or the kernel.org kernel. For questions related to hardware requirements, refer to the
documentation supplied with your Intel adapter. All hardware
requirements listed apply to use with Linux.
The following features are now available in supported kernels:
Native VLANs
Channel Bonding (teaming)
SNMP
Generic Receive Offload
Data Center Bridging
Channel Bonding documentation can be found in the Linux kernel source: /Documentation/networking/bonding.txt
The driver information previously displayed in the /proc file system is not supported in this release. Alternatively, you can use ethtool (version 1.6 or later), lspci, and ifconfig to obtain the same information. Instructions on updating ethtool can be found in the section Additional Configurations later in this document.
The driver in this release is compatible with 82598, 82599 and X540-based Intel Ethernet Network Connections.
For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at:
http://support.intel.com/support/go/network/adapter/proidguide.htm
For the latest Intel network drivers for Linux, refer to the following website. Select the link for your adapter.
http://support.intel.com/support/go/network/adapter/home.htm
|
|
NOTES:
|
| Supplier | Type | Part Numbers |
| SR Modules | ||
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | AFBR-703SDZ-IN2 |
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | FTLX8571D3BCV-IT |
| Intel | DUAL RATE 1G/10G SFP+ SR (bailed) | AFBR-703SDDZ-IN1 |
| LR Modules | ||
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | FTLX1471D3BCV-IT |
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | AFCT-701SDZ-IN2 |
| Intel | DUAL RATE 1G/10G SFP+ LR (bailed) | AFCT-701SDDZ-IN1 |
The following is a list of 3rd party SFP+ modules and direct attach cables that have received some testing. Not all modules are applicable to all devices.
| Supplier | Type | Part Numbers |
| Finisar | SFP+ SR bailed, 10g single rate | FTLX8571D3BCL |
| Avago | SFP+ SR bailed, 10g single rate | AFBR-700SDZ |
| Finisar | SFP+ LR bailed, 10g single rate | FTLX1471D3BCL |
| Finisar | DUAL RATE 1G/10G SFP+ SR (No Bail) | FTLX8571D3QCV-IT |
| Avago | DUAL RATE 1G/10G SFP+ SR (No Bail) | AFBR-703SDZ-IN1 |
| Finisar | DUAL RATE 1G/10G SFP+ LR (No Bail) | FTLX1471D3QCV-IT |
| Avago | DUAL RATE 1G/10G SFP+ LR (No Bail) | AFCT-701SDZ-IN1 |
| Finisar | 1000BASE-T SFP | FCLF8522P2BTL |
| Avago | 1000BASE-T SFP | ABCU-5710RZ |
82599-based adapters support all passive and active limiting direct attach cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
"ifconfig ethX down" turns off the laser for 82599-based SFP+ fiber adapters. "ifconfig ethX up" turns on the laser.
|
|
NOTES:
|
The following is a list of SFP+ modules and direct attach cables that have received some testing. Not all modules are applicable to all devices.
| Supplier | Type | Part Numbers |
| Finisar | SFP+ SR bailed, 10g single rate | FTLX8571D3BCL |
| Avago | SFP+ SR bailed, 10g single rate | AFBR-700SDZ |
| Finisar | SFP+ LR bailed, 10g single rate | FTLX1471D3BCL |
82598-based adapters support all passive direct attach cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach cables are not supported.
THIRD PARTY OPTIC MODULES AND CABLES REFERRED TO ABOVE ARE LISTED ONLY FOR THE PURPOSE OF HIGHLIGHTING THIRD PARTY SPECIFICATIONS AND POTENTIAL COMPATIBILITY, AND ARE NOT RECOMMENDATIONS OR ENDORSEMENT OR SPONSORSHIP OF ANY THIRD PARTYS PRODUCT BY INTEL. INTEL IS NOT ENDORSING OR PROMOTING PRODUCTS MADE BY ANY THIRD PARTY AND THE THIRD PARTY REFERENCE IS PROVIDED ONLY TO SHARE INFORMATION REGARDING CERTAIN OPTIC MODULES AND CABLES WITH THE ABOVE SPECIFICATIONS. THERE MAY BE OTHER MANUFACTURERS OR SUPPLIERS, PRODUCING OR SUPPLYING OPTIC MODULES AND CABLES WITH SIMILAR OR MATCHING DESCRIPTIONS. CUSTOMERS MUST USE THEIR OWN DISCRETION AND DILIGENCE TO PURCHASE OPTIC MODULES AND CABLES FROM ANY THIRD PARTY OF THEIR CHOICE. CUSTOMERS ARE SOLELY RESPONSIBLE FOR ASSESSING THE SUITABILITY OF THE PRODUCT AND/OR DEVICES AND FOR THE SELECTION OF THE VENDOR FOR PURCHASING ANY PRODUCT. THE OPTIC MODULES AND CABLES REFERRED TO ABOVE ARE NOT WARRANTED OR SUPPORTED BY INTEL. INTEL ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF SUCH THIRD PARTY PRODUCTS OR SELECTION OF VENDOR BY CUSTOMERS.
To build a binary RPM* package of this driver, run 'rpmbuild -tb ixgbe.tar.gz'.
|
NOTE: For the build to work properly, the currently running kernel
MUST match the version and configuration of the installed kernel sources. If you have just
recompiled the kernel, reboot the system before building. RPM functionality has only been tested in Red Hat distributions. |
To manually build this driver:
Move the base driver tar file to the directory of your choice. For example, use '/home/username/ixgbe' or '/usr/local/src/ixgbe'.
Untar/unzip the archive:
tar zxf ixgbe-x.x.x.tar.gz
Change to the driver src directory:
cd ixgbe-x.x.x/src/
Compile the driver module:
make install
The binary will be installed as:
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgbe/ixgbe.[k]o
The install location listed above is the default location. This may differ for various Linux distributions.
Load the module:
For kernel 2.6.x, use the modprobe command -
modprobe ixgbe <parameter>=<value>
Note that for 2.6 kernels the insmod command can be used if the full
path to the driver module is specified. For example:
insmod
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgbe/ixgbe.ko
With 2.6 based kernels also make sure that older ixgbe drivers are removed from the kernel, before loading the new module:
rmmod ixgbe; modprobe ixgbe
Assign an IP address to the interface by entering the following, where x is the interface number:
ifconfig ethX <IP_address> netmask <netmask>
Verify that the interface works. Enter the following, where <IP_address> is the IP address of another machine on the same subnet as the interface that is being tested:
ping <IP_address>
If your kernel supports DCA, the driver will build by default with DCA enabled.
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe ixgbe [<option>=<VAL1>,<VAL2>,...]
For example:
modprobe ixgbe InterruptThrottleRate=16000,16000
The default value for each parameter is generally the recommended setting, unless otherwise noted.
Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves adding an alias line to /etc/modules.conf or etc/modprobe.conf, as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to your distribution documentation. If during this process you are asked for the driver or module name, the name for the Linux Base Driver for the 10 Gigabit Family of Adapters is ixgbe.
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
The driver supports Jumbo Frames for all adapters. Jumbo Frames support is enabled by changing the MTU to a value larger than the default of 1500. The maximum value for the MTU is 16110. Use the ifconfig command to increase the MTU size. For example, enter the following where <x> is the interface number:
ifconfig ethX mtu 9000 up
The maximum MTU setting for Jumbo Frames is 16110. This value coincides with
the maximum Jumbo Frames size of 16128. This driver will attempt to
use multiple page sized buffers to receive each jumbo packet. This should help
to avoid buffer starvation issues when allocating receive packets.
The driver utilizes the ethtool interface for driver configuration and diagnostics, as well as displaying statistical information. The latest ethtool version is required for this functionality.
The latest release of ethtool can be found at: http://ftp.kernel.org/pub/software/network/ethtool/.
NAPI (Rx polling mode) is supported in the ixgbe driver. NAPI is enabled or disabled based on the configuration of the kernel. To override the default, use the following compile-time flags.
You can tell if NAPI is enabled in the driver by looking at the version number of the driver. It will contain the string -NAPI if NAPI is enabled.
To enable NAPI, compile the driver module, passing in a configuration option:
make CFLAGS_EXTRA=-DIXGBE_NAPI install
|
|
NOTE: This will not do anything if NAPI is disabled in the kernel. |
To disable NAPI, compile the driver module, passing in a configuration
option:
make
CFLAGS_EXTRA=-DIXGBE_NO_NAPI install
See ftp://robur.slu.se/pub/Linux/net-development/NAPI/usenix-paper.tgz for more information on NAPI.
Large Receive Offload (LRO) is a technique for increasing inbound throughput of high-bandwidth network connections by reducing CPU overhead. It works by aggregating multiple incoming packets from a single stream into a larger buffer before they are passed higher up the networking stack, thus reducing the number of packets that have to be processed. LRO combines multiple Ethernet frames into a single receive in the stack, thereby potentially decreasing CPU utilization for receives.
IXGBE_NO_LRO is a compile time flag. The user can enable it
at compile time to remove support for LRO from the driver. The flag is used by
adding
CFLAGS_EXTRA="-DIXGBE_NO_LRO" to the make file when it's being compiled.
make CFLAGS_EXTRA="-DIXGBE_NO_LRO" install
You can verify that the driver is using LRO by looking at these counters in ethtool:
lro_flushed - the total number of receives using LRO.
lro_aggregated - counts the total number of Ethernet packets that were combined.
|
|
NOTE: IPv6 and UDP are not supported by LRO. |
82599 and X540-based adapters support HW based
receive side coalescing (RSC) which can merge multiple frames from the same IPv4
TCP/IP flow into a single structure that can span one or more descriptors. It
works similarly to SW Large receive offload technique. By default
HW RSC is enabled and SW LRO can not be used for 82599 and X540-based adapters unless HW RSC is disabled.
IXGBE_NO_HW_RSC is a compile time flag. The
user can enable it at compile time to remove support for HW RSC from the driver.
The flag is used by adding CFLAGS_EXTRA="-DIXGBE_NO_HW_RSC" to the make file
when it's being compiled.
make CFLAGS_EXTRA="-DIXGBE_NO_HW_RSC" install
You can verify that the driver is using HW RSC by looking at the counter in ethtool:
hw_rsc_count - counts the total number of Ethernet packets that were being combined.
When in a non-Napi (or Interrupt) mode, this counter indicates that the stack is dropping packets. There is an adjustable parameter in the stack that allows you to adjust the amount of backlog. We recommend increasing the netdev_max_backlog if the counter goes up.
# sysctl -a |grep netdev_max_backlog
net.core.netdev_max_backlog = 1000
# sysctl -e net.core.netdev_max_backlog=10000
net.core.netdev_max_backlog = 10000
Flow control is enabled by default. If you want to disable a flow
control capable link partner, use ethtool:
ethtool -A eth? autoneg off rx off tx off
When a malicious driver attempts to send a spoofed packet, it is dropped
by the hardware and not transmitted. An interrupt is sent to the PF driver
notifying it of the spoof attempt.
When a spoofed packet is detected the PF driver will send the following
message to the system log (displayed by the "dmesg" command):
ixgbe ethX: ixgbe_spoof_check: n spoofed packets detected
Where x=the PF interface# n=the VF that attempted to do the spoofing.
You can set a MAC address of a Virtual Function (VF), a default VLAN and the rate limit using the IProute2 tool. Download the latest version of the iproute2 tool from Sourceforge if your version does not have all the features you require.
Some adapters do not support Wake on LAN. To determine if your adapter supports Wake on LAN, run
ethtool ethX
An excellent article on performance tuning can be found at:
http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf
|
|
NOTE: After installing the driver, if your Intel Ethernet Network Connection is not working, verify that you have installed the correct driver. |
Kernel panics and instability may be observed on any MSI-X hardware if you use irqbalance with kernels between 2.6.19 and 2.6.21. If such problems are encountered, you may disable the irqbalance daemon or upgrade to a newer kernel.
When trying to compile the driver by running make install, the following error may occur: "Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree and entering:
make include/linux/version.h
Due to a known general compatibility issue with LRO and routing, do not use LRO when routing or bridging packets.
LRO is incompatible with iSCSI target or initiator traffic. A panic may occur when iSCSI traffic is received through the ixgbe driver with LRO enabled. To workaround this, the driver should be built and installed with:
# make CFLAGS_EXTRA=-DIXGBE_NO_LRO install
Degradation in throughput performance may be observed in some Jumbo frames environments. If this is observed, increasing the application's socket buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific application manual and /usr/src/linux*/Documentation/networking/ip-sysctl.txt for more details.
Due to the ARP behavior on Linux, it is not possible to have one system on two IP networks in the same Ethernet broadcast domain (non-partitioned switch) behave as expected. All Ethernet interfaces will respond to IP traffic for any IP address assigned to the system. This results in unbalanced receive traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5), or install the interfaces in separate broadcast domains (either in different switches or in a switch partitioned to VLANs).
Under small packets UDP stress test with 10GbE driver, the Linux system may drop UDP packets due to the fullness of socket buffers. You may want to change the driver's Flow Control variables to the minimum value for controlling packet reception.
Or you can increase the kernel's default buffer sizes for UDP by changing the values in
/proc/sys/net/core/rmem_default and rmem_max
In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging the network cable while ethtool -p is running will cause the system to become unresponsive to keyboard commands, except for control-alt-delete. Restarting the system appears to be the only remedy.
82598-based hardware can re-establish link quickly and when connected to some
switches, rapid resets within the driver may cause the switch port to become
isolated due to "link flap". This is typically indicated by a yellow instead of
a green link light. Several operations may cause this problem, such as
repeatedly running ethtool commands that cause a reset.
A potential workaround is to use the Cisco IOS command "no errdisable detect
cause all" from the Global Configuration prompt which enables the switch to keep
the interfaces up, regardless of errors.
A known issue may cause a kernel panic or hang after installing an 82598AT-based Intel(R) 10 Gigabit AT Server Adapter in a Red Hat Enterprise Linux 4.7, 5.1, or 5.2 system. The ixgbe driver for both the install kernel and the runtime kernel can create this panic if the 82598AT adapter is installed. Red Hat may release a security update that contains a fix for the panic that you can download using RHN (Red Hat Network) or Intel recommends that you install the ixgbe-1.3.31.5 driver or newer BEFORE installing the hardware.
Page allocation failure. order:0 errors may occur under stress with kernels 2.6.25 and above. This is caused by the way the Linux kernel reports this stressed condition.
In order for DCB to work correctly, GSO (Generic Segmentation Offload aka software TSO) must be disabled using ethtool. By default since the hardware supports TSO (hardware offload of segmentation) GSO will not be running. The GSO state can be queried with ethtool using ethtool -k ethX.
Due to known hardware limitations, RSS can only filter in a maximum of 16
receive queues.
82599 and X540-based network connections support up to 64 queues.
Due to a known kernel issue, GRO must be turned off when routing/bridging. GRO can be turned off via ethtool.
ethtool -K ethX gro off
where ethX is the ethernet interface you're trying to modify.
Some PCI-E x8 slots are actually configured as x4 slots. These slots have insufficient bandwidth for full 10Gbe line rate with dual port and quad port 10GbE devices. The driver can detect this situation and will write the following message in the system log: PCI-Express bandwidth available for this card is not sufficient for optimal performance. For optimal performance a x8 PCI-Express slot is required.
If this error occurs, moving your adapter to a true x8 slot will resolve the issue.
Due to kernel limitations, port type can only be correctly displayed on kernel 2.6.33 or greater.
Do not remove the ixgbe driver from Dom0 while Virtual Functions (VFs) are assigned to guests. VFs must first use the xm "pci-detach" command to hot-plug the VF device out of the VM it is assigned to or else shut down the VM.
Do not unload the PF driver (ixgbe) while VFs are assigned to guests.
When there are active VFs, "ethtool -t" will only run the link test. The driver will also log in syslog that VFs should be shut down to run a full diags test.
This is a known SLES-10 SP3 issue. After requesting interrupts for MSI-X vectors, system may panic.
Currently the only known workaround is to build the drivers with CFLAGS_EXTRA=-DDISABLE_PCI_MSI if the driver need to be loaded/unloaded. Otherwise the driver can be loaded once and will be safe, but unloading it will lead to the issue.
"-cpu qemu64,model=13"
Due to recent kernel changes, loading an out of tree driver will cause the kernel to be tainted.
For configurations where the auto-negotiation process takes more than 5 seconds, the boot script may fail with the following message:
ethX: failed. No link present. Check cable?
If this error appears even though the presence of a link can be confirmed using ethtool ethX, try setting
LINKDELAY=5 in /etc/sysconfig/network-scripts/ifcfg-ethX.
NOTE: Link time can take up to 30 seconds. Adjust LINKDELAY value accordingly.
Using kernel versions earlier than 3.2, do not unload the PF driver with active VFs. Doing this will cause your VFs to stop working until you reload the PF driver and may cause a spontaneous reboot of your system.
For general information, go to the Intel support website at:
If an issue is identified with the released source code on the supported kernel with a supported adapter, email the specific information related to the issue to linux.nics@intel.com.
This driver supports upstream kernel versions 2.6.30 (or higher) x86_64.
Supported Operating Systems: SLES 11 SP1 x86_64, RHEL 5.3/5.4 x86_64.
The ixgbevf driver supports 82599 and X540-based virtual function devices that can only be
activated on kernels that support SR-IOV. SR-IOV requires the correct
platform and OS support.
The ixgbevf driver requires the ixgbe driver, version 2.0 or later.
The ixgbevf driver supports virtual functions generated by the ixgbe driver with a max_vfs value of 1 or greater.
For more information on the max_vfs parameter refer to the section on the the ixgbe driver.
The guest OS loading the ixgbevf driver must support MSI-X interrupts.
This driver is only supported as a loadable module at this time.
Intel is not supplying patches against the kernel source to allow for static linking of the driver.
For questions related to hardware requirements, refer to the documentation supplied with your Intel Gigabit adapter.
All hardware requirements listed apply to use with Linux.
Instructions on updating ethtool can be found in the section Additional Configurations later in this document.
VLANs: There is a limit of a total of 64 shared VLANs to 1 or more VFs.
To build a binary RPM* package of this driver, run 'rpmbuild -tb <filename.tar.gz>'. Replace <filename.tar.gz> with the specific filename of the driver.
|
|
NOTE: For the build to work properly, the currently running kernel MUST match the version and configuration of the installed kernel sources. If you have just recompiled the kernel reboot the system now. |
RPM functionality has only been tested in Red Hat distributions.
Move the base driver tar file to the directory of your choice. For example, use ' /home/username/ ixgbevf or /usr/local/src/ ixgbevf.'.
Untar/unzip the archive: tar zxf ixgbevf-x.x.x.tar.gz
Change to the driver src directory: cd ixgbevf-<x.x.x>/src/
Compile the driver module:
# make install
The binary will be installed as:
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgbevf/ixgbevf.[k]o
The install location listed above is the default location. This may differ for various Linux distributions.
Load the module using either the insmod or modprobe
command:
modprobe ixgbevf
insmod ixgbevf
Note that for 2.6 kernels the insmod command can be used if the full path
to the driver module is specified. For example:
insmod
/lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgbevf/ixgbevf.ko
With 2.6 based kernels also make sure that older e1000e drivers are removed from the kernel, before loading the new module:
rmmod ixgbevf; modprobe ixgbevf
Assign an IP address to the interface by entering the
following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where
<IP_address>
is the IP address for another machine on the same subnet as the interface
that is being tested:
ping <IP_address>
If the driver is built as a module, the following optional parameters are used by entering them on the command line with the modprobe command using this syntax:
modprobe ixgbevf [<option>=<VAL1>,<VAL2>,...]
For example:
modprobe ixgbevf InterruptThrottleRate=16000,16000
The default value for each parameter is generally the recommended setting, unless otherwise noted.
|
|
NOTES:
|
| Parameter Name | Valid Range/Settings | Default | Description |
|---|---|---|---|
| InterruptThrottleRate | 0,1,956-488281 (0=off, 1=dynamic) |
8000 |
The driver can limit the amount of interrupts per second that the adapter
will generate for incoming packets. It does this by writing a value to
the adapter that is based on the maximum amount of interrupts that the
adapter will generate per second. Setting InterruptThrottleRate to a value greater or equal to 100 will program the adapter to send out a maximum of that many interrupts per second, even if more packets have come in. This reduces interrupt load on the system and can lower CPU utilization under heavy load, but will increase latency as packets are not processed as quickly. The default behaviour of the driver previously assumed a static InterruptThrottleRate value of 8000, providing a good fallback value for all traffic types, but lacking in small packet performance and latency. The hardware can handle many more small packets per second however, and for this reason an adaptive interrupt moderation algorithm was implemented. The driver has one adaptive mode (setting 1) in which it dynamically adjusts the InterruptThrottleRate value based on the traffic that it receives. After determining the type of incoming traffic in the last timeframe, it will adjust the InterruptThrottleRate to an appropriate value for that traffic. The algorithm classifies the incoming traffic every interval into classes. Once the class is determined, the InterruptThrottleRate value is adjusted to suit that traffic type the best. There are three classes defined: "Bulk traffic", for large amounts of packets of normal size; "Low latency", for small amounts of traffic and/or a significant percentage of small packets; and "Lowest latency", for almost completely small packets or minimal traffic. In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low latency" or "Lowest latency" class, the InterruptThrottleRate is increased stepwise to 20000. This default mode is suitable for most applications. For situations where low latency is vital such as cluster or grid computing, the algorithm can reduce latency even more when InterruptThrottleRate is set to mode 1. In this mode, the InterruptThrottleRate will be increased stepwise to 70000 for traffic in class "Lowest latency". Setting InterruptThrottleRate to 0 turns off any interrupt moderation and may improve small packet latency, but is generally not suitable for bulk throughput traffic
modprobe ixgbevf InterruptThrottleRate=3000,3000,3000 This sets the InterruptThrottleRate to 3000 interrupts/sec for the first, second, and third instances of the driver. The range of 2000 to 3000 interrupts per second works on a majority of systems and is a good starting point, but the optimal value will be platform-specific. If CPU utilization is not a concern, use default driver settings. |
Configuring a network driver to load properly when the system is started is
distribution dependent. Typically, the configuration process involves adding an
alias line to /etc/modules.conf or /etc/modprobe.conf as well as editing other
system startup scripts and/or configuration files. Many popular Linux
distributions ship with tools to make these changes for you. To learn the proper
way to configure a network device for your system, refer to your distribution
documentation. If during this process you are asked for the driver or module
name, the name for the Linux Base Driver for the Gigabit Family of Adapters is
ixgbevf.
As an example, if you install the ixgbevf driver for two Gigabit adapters (eth0
and ethX) and want to set the interrupt mode to MSI-X and MSI respectively, add
the following to modules.conf or /etc/modprobe.conf:
alias eth0 ixgbevf
alias eth1 ixgbevf
options ixgbevf InterruptThrottleRate=3,1
Link messages will not be displayed to the console if the distribution is restricting system messages. In order to see network driver link messages on your console, set dmesg to eight by entering the following:
dmesg -n 8
|
|
NOTE: This setting is not saved across reboots. |
MACVLAN
ixgbevf supports MACVLAN on those kernels that have the feature included. Kernel support for MACVLAN can be tested by checking if the MACVLAN driver is loaded. The user can run 'lsmod | grep macvlan' to see if the MACVLAN driver is loaded or run 'modprobe macvlan' to try to load the MACVLAN driver.
It may be necessary to update to a recent release of the iproute2 package to get support of MACVLAN via the 'ip' command.
|
|
NOTE: After installing the driver, if your Intel Network Connection is not working, verify that you have installed the correct driver. |
When trying to compile the driver by running make install, the following
error may occur:
"Linux kernel source not configured - missing version.h"
To solve this issue, create the version.h file by going to the Linux source tree
and entering:
make include/linux/version.h.
Due to the default ARP behavior on Linux, it is not possible to have one
system on two IP networks in the same Ethernet broadcast domain (non-partitioned
switch) behave as expected. All Ethernet interfaces will respond to IP traffic
for any IP address assigned to the system. This results in unbalanced receive
traffic.
If you have multiple interfaces in a server, either turn on ARP filtering by
entering:
echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
(this only works if your kernel's version is higher than 2.4.5)
|
|
NOTE: This setting is not saved across reboots. The configuration change can be made permanent by adding the line: net.ipv4.conf.all.arp_filter = 1 to the file /etc/sysctl.conf or, |
Some systems may experience build issues due to redefinition of irq_handler_t. To resolve this issue build the driver (step 4 above) using the command:
make CFLAGS_EXTRA=-DAX_RELEASE_CODE=1 install
Kernel panics and instability may be observed on any MSI-X hardware if you use irqbalance with kernels between 2.6.19 and 2.6.21. If such problems are encountered, you may disable the irqbalance daemon or upgrade to a newer kernel.
Page allocation failure. order:0 errors may occur under stress with kernels 2.6.25 and above. This is caused by the way the Linux kernel reports this stressed condition.
Using kernel versions earlier than 3.2, do not unload the PF driver with active VFs. Doing this will cause your VFs to stop working until you reload the PF driver and may cause a spontaneous reboot of your system.
For general information, go to the Intel support website at:
If an issue is identified with the released source code on the supported kernel with a supported adapter, email the specific information related to the issue to linux.nics@intel.com.
Last modified on 11/10/11 2:04p 10/22/04 9:45a
Copyright © 2002 - 2012 Intel Corporation. All rights reserved.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel Corporation assumes no responsibility for errors or omissions in this document. Nor does Intel make any commitment to update the information contained herein.
Intel, Itanium, and Pentium are trademarks of Intel Corporation in the U.S. and other countries.
*Other names and brands may be claimed as the property of others.
Last modified on 1/25/11 10:21p Revision
PROXGB/DOCS/LINUX/license.htm 0000755 0000000 0000000 00000035273 11654245266 012560 0 ustar
INTEL SOFTWARE LICENSE AGREEMENT
IMPORTANT - READ BEFORE COPYING, INSTALLING OR USING.
Do not copy, install, or use this software and any associated materials (collectively, the “Software”) provided under this license agreement (“Agreement”) until you have carefully read the following terms and conditions.
By copying, installing, or otherwise using the Software, you agree to be bound by the terms of this Agreement. If you do not agree to the terms of this Agreement, do not copy, install, or use the Software.
Please Note:
SITE LICENSE: You may copy the Software onto your organization’s computers for your organization’s use, and you may make a reasonable number of back-up copies of the Software, subject to these conditions:
SINGLE USER LICENSE: You may copy the Software onto a single computer for your personal use, and you may make one back-up copy of the Software, subject to these conditions:
OEM LICENSE: You may reproduce and distribute the Software only as an integral part of or incorporated in your product, as a standalone Software maintenance update for existing end users of your products, excluding any other standalone products, or as a component of a larger Software distribution, including but not limited to the distribution of an installation image or a Guest Virtual Machine image, subject to these conditions:
LICENSE RESTRICTIONS. You may NOT: (i) use or copy the Materials except as provided in this Agreement; (ii) rent or lease the Materials to any third party; (iii) assign this Agreement or transfer the Materials without the express written consent of Intel; (iv) modify, adapt, or translate the Materials in whole or in part except as provided in this Agreement; (v) reverse engineer, decompile, or disassemble the Materials; (vi) attempt to modify or tamper with the normal function of a license manager that regulates usage of the Materials; (vii) distribute, sublicense or transfer the Source Code form of any components of the Materials, Redistributables and Sample Source and derivatives thereof to any third party except as provided in this Agreement.
NO OTHER RIGHTS. No rights or licenses are granted by Intel to you, expressly or by implication, with respect to any proprietary information or patent, copyright, mask work, trademark, trade secret, or other intellectual property right owned or controlled by Intel, except as expressly provided in this Agreement. Except as expressly provided herein, no license or right is granted to you directly or by implication, inducement, estoppel, or otherwise. Specifically, Intel grants no express or implied right to you under Intel patents, copyrights, trademarks, or other intellectual property rights.
OWNERSHIP OF SOFTWARE AND COPYRIGHTS. The Software is licensed, not sold. Title to all copies of the Software remains with Intel. The Software is copyrighted and protected by the laws of the United States and other countries and international treaty provisions. You may not remove any copyright notices from the Software. You agree to prevent any unauthorized copying of the Software. Intel may make changes to the Software, or to items referenced therein, at any time without notice, but is not obligated to support or update the Software. You may transfer the Software only if the recipient agrees to be fully bound by these terms and if you retain no copies of the Software.
ADDITIONAL TERMS FOR PRE-RELEASE SOFTWARE. If the Software you are installing or using under this Agreement is pre-commercial release or is labeled or otherwise represented as “alpha-“ or “beta-“ versions of the Software ("pre-release Software"), then the following terms apply.
To the extent that any provision in this Section conflicts with any other term(s) or condition(s) in this Agreement with respect to pre-release Software, this Section shall supersede the other term(s) or condition(s), but only to the extent necessary to resolve the conflict.
You understand and acknowledge that the Software is pre-release Software, does not represent the final Software from Intel, and may contain errors and other problems that could cause data loss, system failures, or other errors.
The pre-release Software is provided to you "as-is" and Intel disclaims any warranty or liability to you for any damages that arise out of the use of the pre-release Software.
You acknowledge that Intel has not promised that pre-release Software will be released in the future, that Intel has no express or implied obligation to you to release the pre-release Software and that Intel may not introduce Software that is compatible with the pre-release Software. You acknowledge that the entirety of any research or development you perform that is related to the pre-release Software or to any product making use of or associated with the pre-release Software is done at your own risk.
If Intel has provided you with pre-release Software pursuant to a separate written agreement, your use of the pre-release Software is also governed by such agreement.
LIMITED MEDIA WARRANTY. If the Software has been delivered by Intel on physical media, Intel warrants the media to be free from material physical defects for a period of ninety days after delivery by Intel. If such a defect is found, return the media to Intel for replacement or alternate delivery of the Software as Intel may select.
EXCLUSION OF OTHER WARRANTIES. EXCEPT AS PROVIDED ABOVE, THE SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. Intel does not warrant or assume responsibility for the accuracy or completeness of any information, text, graphics, links, or other items contained within the Software.
LIMITATION OF LIABILITY. IN NO EVENT SHALL INTEL OR ITS SUPPLIERS BE LIABLE FOR ANY DAMAGES WHATSOEVER (INCLUDING, WITHOUT LIMITATION, LOST PROFITS, BUSINESS INTERRUPTION, OR LOST INFORMATION) ARISING OUT OF THE USE OF OR INABILITY TO USE THE SOFTWARE, EVEN IF INTEL HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. SOME JURISDICTIONS PROHIBIT EXCLUSION OR LIMITATION OF LIABILITY FOR IMPLIED WARRANTIES OR CONSEQUENTIAL OR INCIDENTAL DAMAGES, SO THE ABOVE LIMITATION MAY NOT APPLY TO YOU. YOU MAY ALSO HAVE OTHER LEGAL RIGHTS THAT VARY FROM JURISDICTION TO JURISDICTION. In the event that you use the Software in conjunction with a virtual (“emulated”) device designed to appear as an Intel component product, you acknowledge that Intel is neither the author nor the creator of the virtual (“emulated”) device. You understand and acknowledge that Intel makes no representations about the correct operation of the Software when used with a virtual (“emulated”) device, that Intel did not design the Software to operate in conjunction with the virtual (“emulated”) device, and that the Software may not be capable of correct operation in conjunction with the virtual (“emulated”) device. You agree to assume the risk that the Software may not operate properly in conjunction with the virtual (“emulated”) device. You agree to indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with the use of the Software in conjunction with the virtual (“emulated”) device, even if such claim alleges that Intel was negligent regarding the design or manufacture of the Software.
UNAUTHORIZED USE. THE SOFTWARE IS NOT DESIGNED, INTENDED, OR AUTHORIZED FOR USE IN ANY TYPE OF SYSTEM OR APPLICATION IN WHICH THE FAILURE OF THE SOFTWARE COULD CREATE A SITUATION WHERE PERSONAL INJURY OR DEATH MAY OCCUR (E.G MEDICAL SYSTEMS, LIFE SUSTAINING OR LIFE SAVING SYSTEMS). If you use the Software for any such unintended or unauthorized use, you shall indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with such unintended or unauthorized use, even if such claim alleges that Intel was negligent regarding the design or manufacture of the part.
TERMINATION OF THIS AGREEMENT. Intel may terminate this Agreement at any time if you violate its terms. Upon termination, you will immediately destroy the Software or return all copies of the Software to Intel.
APPLICABLE LAWS. Claims arising under this Agreement shall be governed by the laws of the State of California, without regard to principles of conflict of laws. You agree that the terms of the United Nations Convention on Contracts for the Sale of Goods do not apply to this Agreement. You may not export the Software in violation of applicable export laws and regulations. Intel is not obligated under any other agreements unless they are in writing and signed by an authorized representative of Intel.
GOVERNMENT RESTRICTED RIGHTS. The enclosed Software and documentation were developed at private expense, and are provided with “RESTRICTED RIGHTS.” Use, duplication, or disclosure by the Government is subject to restrictions as set forth in FAR 52.227-14 and DFARS 252.227-7013 et seq. or its successor. The use of this product by the Government constitutes acknowledgement of Intel’s proprietary rights in the Software. Contractor or Manufacturer is Intel.
LANGUAGE; TRANSLATIONS. In the event that the English language version of this Agreement is accompanied by any other version translated into any other language, such translated version is provided for convenience purposes only and the English language version shall control.
Last modified on 5/15/11 10:56p Revision
Intel provides the following packages for managing 100, Gigabit and 10 Gigabit Families of Adapters for Linux* operating systems.
Base Drivers
For base driver features, installation, configuration, and command line parameter
information, refer to:
For Gigabit adapters: e1000.htm
For 10 Gigabit adapters: ixgbe.htm
For 100 adapters: Driver updates for 100 adapters can be found at http://www.sourceforge.net/projects/e1000
For general information and support, see the Support page.
If an issue is identified with the released source code on the supported kernel with a supported adapter, email the specific information related to the issue to linux.nics@intel.com.
Last modified on 4/20/11 3:22p Revision
Intel support is available on the web or by phone. Support offers the most up-to-date information about Intel products, including installation instructions, troubleshooting tips, and general product information.
Support: http://www.intel.com/support
Corporate Site for Network Products: http://www.intel.com/products/ethernet/overview.htm
Last modified on 5/12/10 3:26p Revision
Intel adapters have built-in self-test diagnostics, such as I/O conflicts, memory faults, EEPROM operability, and basic transmit/receive operation. This can help determine if there is a hardware fault due to the adapter or cable connectivity. This testing capability is built into the adapter and is accessed via the driver. Ethtool (version 1.6 or later) is used as the interface for the diagnostic tests and results.
Ethtool is an open-source program that can be used as an interface to provide driver configuration and diagnostics, as well as displaying statistical information.
Ethtool is available at: http://sourceforge.net/projects/gkernel. See the ethtool man page for complete information on usage.
To invoke diagnostics from ethtool, enter this command:
ethtool -t <EthX>
where <EthX> is the name of the Ethernet device under test (e.g., "eth0").
Here is a sample of the diagnostics output:
The test result is PASS Register test (offline).......... Passed EEPROM test (offline).......... Passed Interrupt test (offline).......... Passed Loopback test (offline).......... Passed Link test (on/offline).......... Passed
By default, the more comprehensive "offline" test set is invoked. This will momentarily disrupt any active traffic on the device under test. The set of available diagnostic tests is determined internally by the NIC. The tests that are run are determined by the ethtool command line parameters.
The following tests are common to many Intel adapters:
| Test Name | Description | Test Results |
|---|---|---|
| Register Test | Test patterns are written, read and verified through the adapter's device registers to ensure proper functionality. | Test failure may indicate a faulty adapter. |
| FIFO Test | This utility will write test bit patterns to the adapter's FIFO buffers, to make sure the FIFOs are working properly. Not all adapters have FIFO buffers, so it may not appear in your test results. | Test failure may indicate a faulty adapter. |
| EEPROM Test | This test is run if the adapter is equipped with this type of memory. It tests both the readability of the EEPROM and the integrity of the data via checksum. | Test failure may indicate a faulty adapter. |
| Interrupt Test | This tests the adapter's ability to generate an interrupt. This test sets the interrupt cause register and reads the interrupt set register, verifying the adapter correctly registered an internal interrupt. | Test failure may indicate a faulty adapter. |
| Loopback Test | There are two internal loopback tests: MAC (media access controller) Loopback and PHY (LAN controller) Loopback. Neither test requires an external loopback connection or responder. These tests set the adapter in the appropriate loopback mode and send packets back through the adapter's receive circuitry and logic. | Test failure may indicate a faulty adapter. |
| Link Test | This checks to see whether or not the adapter has established link with its link partner. | If this test fails, check the cable connection and the status of the link partner. |
Last modified on 12/20/06 8:55a Revision
Adapter Testing and Diagnostics
Copyright © 2002-2011
Intel Corporation.
Legal Information
Last modified on 11/04/11 11:38a Revision
PROXGB/DOCS/LINUX/top_lnx.htm 0000755 0000000 0000000 00000000566 11662465060 012611 0 ustar
| User Guides Home |
There are many simple, easy-to-fix problems related to network problems. Review each one of these before going further.
Check the cable. Use the best available cabling for the intended data rate.
Check that the cable is securely attached at both points.
For copper connections, make sure the cable is a 4-pair Category-5 or better.
Make sure the cable length does not exceed specifications.
Perform a cable test.
Replace the cable.
Check the link partner (switch, hub, etc.).
Make sure the link partner is active and can send and receive traffic.
Make sure the adapter and link partner settings match one another, or are set to auto-negotiate.
Make sure the port is enabled.
Re-connect to another available port or another link partner.
Look for adapter hardware problems.
Re-seat the adapter.
Insert the adapter in another slot.
Check for conflicting or incompatible hardware devices and settings.
Replace the adapter.
Check the driver software.
Make sure you are using the latest appropriate drivers for your adapter from the Intel support website.
Disable (or unload), then re-enable (reload) the driver or adapter.
Check for conflicting settings. Disable advanced settings such as teaming or VLANs to see if it corrects the problem.
Re-install the drivers.
Check for recent changes to hardware, software or the network, that may have disrupted communications.
Check the adapter release notes (readme.txt).
The Known Issues section may have specific troubleshooting information for your configuration.
Check the Intel support website for possible documented issues.
Select your adapter from the adapter family list.
Check the Frequently Asked questions section.
Check the Knowledge Base.
Check your process monitor and other system monitors.
Check to see that there is sufficient processor and memory capacity to perform networking activity.
Look for any unusual activity (or lack of activity).
Use network testing programs to check for basic connectivity.
Check your BIOS version and settings.
Use the latest appropriate BIOS for your computer.
Make sure the settings are appropriate for your computer.
Reboot the computer.
The following troubleshooting table assumes that you have already reviewed the
common problems and solutions.
| Problem | Solution | ||
|
Your computer cannot find the adapter |
Make sure your adapter slots are compatible for the type of adapter you are using:
|
||
|
Diagnostics pass but the connection fails |
Make sure the cable is securely attached, is the proper type and does not exceed the recommended lengths. Try running the Sender-Responder diagnostic Test. Make sure the duplex mode and speed setting on the adapter matches the setting on the switch. |
||
|
Another adapter stops working after you installed the Intel® Network Adapter |
Make sure your PCI BIOS is current. See PCI / PCI-X / PCI Express Configuration. Check for interrupt conflicts and sharing problems. Make sure the other adapter supports shared interrupts. Also, make sure your operating system supports shared interrupts. Unload all PCI device drivers, then reload all drivers. |
||
| Adapter unable to connect to switch at correct speed. Gigabit adapter connects at 100 Mbps and 10 gigabit adapter connects at 1000 Mbps. |
This is applicable only to copper-based connections. Make sure the adapter and the link partner are set to auto-negotiate. Verify that you are running the latest operating system revision for your switch and that the switch is compliant with the proper IEEE standard:
|
||
|
The adapter stops working without apparent cause |
Run the adapter and network tests described under "Test the Adapter". |
||
|
The Link indicator light is off |
Run the adapter and network tests described under "Test the Adapter". Make sure the proper (and latest) driver is loaded. Make sure that the link partner is configured to auto-negotiate (or forced to match adapter) Verify that the switch is IEEE 802.3ad-compliant. |
||
| The link light is on, but communications are not properly established |
Make sure the proper (and latest) driver is loaded. Both the adapter and its link partner must be set to either auto-detect or manually set to the same speed and duplex settings.
|
||
| RX or TX light is off |
Network may be idle; try creating traffic while monitoring the lights. |
||
| The diagnostic utility reports the adapter is "Not enabled by BIOS" |
The PCI BIOS isn't configuring the adapter correctly. See PCI / PCI-X / PCI Express Configuration. |
||
| The computer hangs when the drivers are loaded |
Try changing the PCI BIOS interrupt settings. See PCI / PCI-X / PCI Express Configuration. |
||
| The Fan Fail LED of the 10 Gigabit AT Server Adapter is on (red) | The fan cooling solution is not functioning properly. Contact customer support for further instructions. |
When configuring a multi-adapter environment, you must upgrade all Intel adapters in the computer to the latest software.
If the computer has trouble detecting all adapters, consider the following:
If you enable Wake on LAN* (WoL) on more than two adapters, the Wake on LAN feature may overdraw your systems auxiliary power supply, resulting in the inability to boot the system and other unpredictable problems. For multiple desktop/management adapters, it is recommended that you install one adapter at a time and use the IBAUtil utility (ibautil.exe in \APPS\BOOTAGNT) to disable the WoL feature on adapters that do not require WoL capabilities. On server adapters, the WoL feature is disabled by default.
Adapters with Intel Boot Agent enabled will require a portion of the limited start up memory for each adapter enabled. Disable the service on adapters that do not need to boot Pre-Boot Execution Environment (PXE).
If the adapter is not recognized by your OS or if it does not work you may need to change some BIOS settings. Try the following only if you are having problems with the adapter and are familiar with BIOS settings.
Check to see that the "Plug-and-Play" setting is compatible with the operating system you are using.
Make sure the slot is enabled.
Install the adapter in a bus-master slot.
Configure interrupts for level-triggering, as opposed to edge-triggering.
Reserve interrupts and/or memory addresses. This prevents multiple buses or bus slots from using the same interrupts. Check the BIOS for IRQ options for PCI / PCI-X / PCIe.
Here are some examples of BIOS parameters:
PCI / PCI-X / PCIe slot #: Slot where the adapter is installed
Master: ENABLED
Slave: ENABLED
Latency timer: 40 - 80
Interrupt: Choose any one of several that the BIOS provides.
Edge-level: Level
The exact wording of the parameters varies with different computers.
Attaining the best speed requires that many components are operating at peak efficiency. Among them are the following:
Cable quality and length - Do not exceed the maximum recommended length for your cable type. Shorter lengths often provide better results. Check for loose or damaged connectors. Check the cable for kinked or damaged sections.
Bus speed and traffic - The PCI bus speed accommodates the slowest PCI card installed. Check to see if you have a card that is slowing down your system.
Processor and Memory - Check your performance monitoring programs to see if traffic is being affected by your processor speed, available memory or other processes.
Transmission frame size - Your network performance may be enhanced by adjusting or maximizing the transmission frame size. Operating systems, switches and adapters will impose varying limits on maximum frame size. See the discussion on Jumbo Frames for your OS.
Operating System - Networking feature implementation will vary by operating system version, such as offloading and multiprocessor threading.
Last modified on 8/21/08 11:09a Revision
PROXGB/DOCS/LINUX/warning.gif 0000755 0000000 0000000 00000000764 11651733270 012547 0 ustar GIF89a ﭭ便{{sskkccZZRRJJBB9911))!!))!!!!!!!!!! , @pH$rlx$r ҬRp.Zir@*8BH)Y8]2 "F"l } "s!Pa% Ia#
' r$$ R ] R'""
XL JNo E^NۀE@
YPې
2 ]`eC @
l B::V@ "jHD0eR҄^H 3N@ ; PROXGB/DOCS/LINUX/warranty.htm 0000755 0000000 0000000 00000013240 11651733270 012765 0 ustar
Intel warrants to the original owner that the adapter product delivered in this package will be free from defects in material and workmanship. This warranty does not cover the adapter product if it is damaged in the process of being installed or improperly used.
THE ABOVE WARRANTY IS IN LIEU OF ANY OTHER WARRANTY, WHETHER EXPRESS, IMPLIED OR STATUTORY, INCLUDING BUT NOT LIMITED TO ANY WARRANTY OF NONINFRINGEMENT OF INTELLECTUAL PROPERTY, MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE ARISING OUT OF ANY PROPOSAL, SPECIFICATION, OR SAMPLE.
This warranty does not cover replacement of adapter products damaged by abuse, accident, misuse, neglect, alteration, repair, disaster, improper installation, or improper testing. If the adapter product is found to be defective, Intel, at its option, will replace or repair the hardware product at no charge except as set forth below, or refund your purchase price provided that you deliver the adapter product along with a Return Material Authorization (RMA) number (see below), along with proof of purchase (if not registered), either to the dealer from whom you purchased it or to Intel with an explanation of any deficiency. If you ship the adapter product, you must assume the risk of damage or loss in transit. You must use the original container (or the equivalent) and pay the shipping charge.
Intel may replace or repair the adapter product with either new or reconditioned parts, and any adapter product, or part thereof replaced by Intel becomes Intel's property. Repaired or replaced adapter products will be returned to you at the same revision level as received or higher, at Intel's option. Intel reserves the right to replace discontinued adapter products with an equivalent current generation adapter product.
Before returning any adapter product, contact Intel Customer Support and obtain a Return Material Authorization (RMA) number by calling +1 916-377-7000.
If the Customer Support Group verifies that the adapter product is defective, they will have the RMA department issue you an RMA number to place on the outer package of the adapter product. Intel cannot accept any product without an RMA number on the package.
Return the adapter product to the place of purchase for a refund or replacement.
Intel wants you to be completely satisfied with the Intel adapter product that you have purchased. Any time within ninety (90) days of purchase, you may return your Intel adapter to the original place of purchase for a full refund of the purchase price from your dealer. Resellers and distributors, respectively, accepting returns and refunding money back to their customers may return Intel adapters to their original place of purchase. Intel guarantees that it will accept returns under this policy and refund the original purchase price to customers purchasing directly from Intel.
INTEL'S SOLE LIABILITY HEREUNDER SHALL BE LIMITED TO DIRECT, OBJECTIVELY MEASURABLE DAMAGES. IN NO EVENT SHALL INTEL HAVE ANY LIABILITY FOR ANY INDIRECT OR SPECULATIVE DAMAGES (INCLUDING, WITHOUT LIMITING THE FOREGOING, CONSEQUENTIAL, INCIDENTAL, AND SPECIAL DAMAGES) INCLUDING, BUT NOT LIMITED TO, INFRINGEMENT OF INTELLECTUAL PROPERTY, REPROCUREMENT COSTS, LOSS OF USE, BUSINESS INTERRUPTIONS, LOSS OF GOODWILL, AND LOSS OF PROFITS, WHETHER ANY SUCH DAMAGES ARISE OUT OF CONTRACT NEGLIGENCE, TORT, OR UNDER ANY WARRANTY, IRRESPECTIVE OF WHETHER INTEL HAS ADVANCE NOTICE OF THE POSSIBILITY OF ANY SUCH DAMAGES. NOTWITHSTANDING THE FOREGOING, INTEL'S TOTAL LIABILITY FOR ALL CLAIMS UNDER THIS AGREEMENT SHALL NOT EXCEED THE PRICE PAID FOR THE PRODUCT. THESE LIMITATIONS ON POTENTIAL LIABILITIES WERE AN ESSENTIAL ELEMENT IN SETTING THE PRODUCT PRICE. INTEL NEITHER ASSUMES NOR AUTHORIZES ANYONE TO ASSUME FOR IT ANY OTHER LIABILITIES.
Some states do not allow the exclusion or limitation of incidental or consequential damages, so the above limitations may not apply to you.
Critical Control Applications: Intel specifically disclaims liability for use of the adapter product in critical control applications (including, for example only, safety or health care control systems, nuclear energy control systems, or air or ground traffic control systems) by Licensee or Sublicensees, and such use is entirely at the user's risk. Licensee agrees to defend, indemnify, and hold Intel harmless from and against any and all claims arising out of use of the adapter product in such applications by Licensee or Sublicensees.
Software: Software provided with the adapter product is not covered under the hardware warranty described above. See the applicable software license agreement which shipped with the adapter product for details on any software warranty.
Last modified on 7/23/02 10:42a Revision
These condensed instructions are intended for experienced users and cover basic hardware and software installation only. English
Traditional Chinese
|
German
|
French |
Japanese |
Italian
|
Portuguese |
Korean |
Spanish
|
Simplified Chinese |
Last modified on 12/06/07 3:00p Revision
ػγԴߡСȲ塱װȲμķĵ
ж¼ǣжIJ۵IJ۸ǡʹһͷIJ۶κ⣬DzҪͼװһ PCI Express ͷ̵IJС
ȹ̵ز̶ۣ֧ܡ
װػǡԴߡ
Ӣض® ̫λͭ ʹ 6 š6a ţ 7 ̫ߡ
Ӣض® ̫λ SFP+ ɲιˣ ģ̵ָʾװģӵ
Ӣض® ̫λ SC ж²ǡ SC ֧ϵ TX/RX ˿ڡ
Ӣض® ̫λ LC ж²ǡ LC Ĺѧ䣬ƣʹ SCת¡
Ӣض® ̫λ CX4 ߱ IEEE Std 802.3ak 54 ĹҪĵ½ͷӦ MDI Ͳף IEC 61076-3-113 壩
װָʾ
|
|
ע
|
Windows ʱΪӲҪװȷ
ʱWindows ߰װһ Windows פӲ
ʾװ˳ CD ϵ
װ Windows פӦ´ǣ Ӣضӡ ԶдڳʱӢض CDװ ť autorun ڡ
ҪĶ RPM* rpmbuild -tb <ļ.tar.gz>øľļ <ļ.tar.gz>
|
|
ע Ҫʹ汾ȷУǰеں˵İ汾ñ밲װںԴ±ںˣӦϵͳ RPM ܽ Red Hat ϲԹ |
tar ļѡĿ¼磬ʹ home/username/ixgb /usr/local/src/ixgb
ѹõļ <x.x.x> ѹļİ汾ţ
tar zxf ixgb-<x.x.x>.tar.gz
л src Ŀ¼£ <x.x.x> ѹļİ汾ţ
cd ixgb-<x.x.x>/src/
ģ飺
make install
ļװΪ
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
гİװλΪĬλáǶijЩ Linux ˵һȷ
װģ飺
insmod ixgb <>=<ֵ>
ָ IP ַӿڿУ<x> ǽӿڿţ
ifconfig eth<x> <IP ַ>
֤ӿڿ <IP ַ>뱻ӿڿλͬһһ̨ IP ַ
ping <IP ַ>
Ϊ FreeBSD ںˣ汾 4.8 ¶
|
|
ע 밲װںԴԱģ顣 |
ָʾУxxx Ϊ汾 tar ļ
tar ļѡĿ¼磬ʹ/home/username/ixgb
/usr/local/src/ixgb
ѹõļ
tar xfz ixgb-x.x.x.tar.gz
⽫һ ixgb-x.x.x Ŀ¼
Ҫװ man ҳ
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Ҫصеϵͳϣִ²裺
cd ixgb-x.x.x
make
cd ixgb-x.x.x/src
make load
ҪΪӿָ IP ַ,
ifconfig ixgb<interface_num>
<IP_address>
֤ӿڿУ<IP_address> 뱻ӿڿλͬһһ̨ IP ַ
ping <IP_address>
ҪϵͳʱԶ
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
༭ /boot/loader.confһУ
if_ixgb_load="YES"
ںˣμ 8
༭ /etc/rc.confʵ
ifconfig_ixgb<interface_num>
Ŀ
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
÷ʾ
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
ע⣺ Ҫȡμ ifconfig man ҳ
Ҫںˣ룺
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
༭ /usr/src/sys/conf/files.i386 ļ£
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
/usr/src/sys/conf/files.i386 ļƳһУڣ
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
༭ /usr/src/sys/i386/conf еںļ磺GENERIC MYKERNEL
ȷһдڣ
device ixgb
벢װںˡϵͳʹں˸Ч
йرں˵ĸϢѯ FreeBSD ϵͳĵ
йظϢμӢضCDڵûָӢض֧վ http://www.intel.com/p/zh_CN/support/
ڣ 20071011 3:49 汾
Ȩ® 2002 - 2012 ꣬Ӣض˾Ȩ
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Ӣض˾ԱĵеĴ©ΡӢض˾Ը±ĵеϢκγŵ
ӢضںͱӢض˾ң̱ꡣ
*漰Ƽ̱ڸʲ
ڣ 2011125 10:21 汾
PROXGB/DOCS/QUICK/CHS/license.htm 0000755 0000000 0000000 00000022166 11730046352 013135 0 ustar
ӢضЭ
Ҫ - ڸơװʹǰĶЭ
ڸơװʹմ֤Э飨“Э”ṩıκιϣܳΪ“”֮ǰϸĶ¸
һơװʹñܱͬЭиԼͬⱾЭеκơװʹñ
ע⣺
վ֤ ԽƵ֯ļԹ֯ʹãҲĿıݣǣ
û֤: ԽƵ̨ϹʹãҲһݣǣ
OEM ֤ ԸƺͷǣIJƷɷָһֻϵIJƷеһ֡вƷûṩĶάԸʱųκƷһϴһڰװӳķӳƣ
Ȩơ ã (i) Ա“Э”δ涨ķʽʹûƱ“”(ii) “”κε(iii) δӢضȷͬ£öɱ“Э”ת“”(iv) Ա“Э”δ涨ķʽġֲת“”(v) “”ִз̡ࣻ(vi) ͼĻ۸ڿ“”÷֤ܣ (vii) Ա“Э”δ涨ķʽ“”“·ַ”Լ“ʾԴ”ƷκԴʽתڻתøκε
Ȩ ڴЭȷṩɣӢضȷʾķʽṩκйӢضӵлƵרϢרȨ̱ꡢҵܣ֪ʶȨȨ֤Ǵ˳ȷûκɻȨֱӷʽͨʾյֹԻʽ˵ӢضӢضרȨ̱֪ʶȨκȷȨ
ȨͰȨ “”ֻʹɣdzۡӢضԱиӵȨȨУҺ͵ķԼʹԼıôӱɾκΰȨֹͬԱδȨĸơӢضʱĴе֪ͨûֻ֧´ֻ÷ͬȫܱԼҲκθʱſתñ
ԤĶ ݴЭаװʹõԤҵл߱ΪʽʾΪ“alpha-”“beta-”棨Ԥá
ڱйԤκ뱾Эκͻ£̶ֽȽܽ˳ͻΪޡ
˽ⲢϱԤӢض汾ҿܰһЩ⣬˻ᵼݶʧϵͳϻԤ“ԭ”ṩӢضʹñԤɵʧṩκεеκΡ
ӢضδδдԤı֤ӢضûȷʾʾᷢбԤӢضܲƳ뱾ԤݵԱԤκʹû뱾ԤصIJƷеȫκоеȫա
ӢضһǩЭṩԤԸԤʹͬʱܸЭԼ
ý嵣 ӢضʵýʽṩӢض֤ýӢضṩʮʱڲʵϵ覴áҵȱݣ뽫ý巵صӢضиӢضѡƷн
ų ֤֮⣬“ԭ”ṩκκȷ֤ҵԡȨضĿĵı֤ Ӣض˾ԱаκϢ֡ͼΡӻĿȷԻԲҲеΡ
ơ Ӣض乩Ӧ̾ʹûʹñκʧҵжϻʧϢΣʹӢض֪ЩĿԡijЩϽֹųĵȻżȻƿܻܲϽȨ һʾΪӢضƷ⣨ģ⣩豸ͱʹãӢضǸ⣨ģ⣩豸ߡⲢӢض֤ʹһ⣨ģ⣩豸ʱȷУӢضδƱ⣨ģ⣩豸Эͬϱ⣨ģ⣩豸ЭͬʱȷͬԱ⣨ģ⣩豸ȷķճеȫΡͬ뱾⣨ģ⣩豸ʹصκβƷΡֱӻ⣨ʹӢضƻ챾ڹʧ⡢֧üʦѣӢضְԱ֧߲ȷ䲻ʧ
δȨʹá ּڣȨκڱʱܻᵼ¸˺κϵͳӦóҽϵͳάϵͳϵͳȣκЩԻδȨ;ʹñͬԻδȨ;йصIJƷΡֱӻ⣨ʹӢضڲƻ췽ڹʧ⡢֧üʦѣ뱣ӢضְԱ֧߲ȷ䲻ʧ
Эֹ ΥЭӢضκʱֹЭ顣ЭֹٱиƷ黹Ӣض
÷ɣ ɴЭӦܼݷɹƣǷɵִԭͬ⣬ϹʻۺͬԼµôЭ顣Υõijڷɼ³ڱӢضκЭ鸺ΣӢضȨĴǩд
Ȩ ĵʹ˽˷ÿֻṩ“Ȩ”ʹáƻ FAR 52.227-14 DFARS 252.227-7013 et seq. ơԱƷʹӦΪӢضԱȨԼ˻ΪӢض
ԣ룺 Э֮Ӣİ汾κ֮汾෭汾֮ĿĽΪṩӢİ汾Լ
201151510:56 汾
Ӣضԭʼӵ֤߱汾˰װƷڲϺշȱݡ˵ڰװлʹòIJƷ
ϵκȷڲַ֪ʶȨҵԡضĿĻκν顢Ʒκε
˵ǸáżȻ¹ʡá졢ѡװԶƷֱƷȱݣӢضѸӲƷƷͻľ̻ͻӢضṩ˻RMAţģ֤δעᣩӢض˻úַӢض⡣Ʒеʧķաʹԭʼװ֧ͬ˷ѡ
ӢضʹµĻµIJƷ˻صƷ䲿ΪӢضIJƲƷ˻ظ汾ڻյIJƷúְ汾ӢضӢض൱ĵǰƷͣƷȨ
˻κƷ֮ǰӢضͻ֧ϵԻ˻RMAţ绰룺+1 916-377-7000
ͻ֧֤ӲƷȱݣǻ RMA Ϊ䷢ RMA ţ뽫ӲƷװϡӢضܽܰװû RMA ŵκβƷ
ӢضϣԹӢضȫ⡣ڹƷʮ90ڽӢضصԭַԻȡӹӦ̴ʱȫ˿˻ͷ˿ķ̺ʹ̿ɽӢض˻ԭӢض֤߽˻˻ֱӢضĿͻ
ӢضĶνֱӵĿɿ۲ʧκ£κμԻͶʧǰġԡżȻԺʧַ֪ʶȨعɱʹʧҵжϡʧʧʧںͬȨĻǸκεҲӢضǷȱ֪ͨʧĿԣӢضŲ𡣾ˣӢضڱЭ涨ܽӦԲƷ֧ļ۸ЩڿεDzƷ۵ҪءӢضеҲδȨκ˳еκΡ
ijЩݲųżȻԻʧƿܲ
ؼԿӦã Ӣضرְ֤֤ڹؼԿӦУΪȫϵͳԭܿϵͳ߿л潻ͨϵͳʹñƷӢضŲķȫûе֤ͬ⣬ά⳥֧Ӣض֤¼֤ڴӦʹñƷκҪ
뱾һṩӲ֮Сйκ飬ıƷ֤Э顣
2002 7 23 10:42 汾6
qéޤUquCpGuHYΡvw˪ܡAХѦұzAC
q~ߡAñqŦXdѲdKCziHϥΤds٭nѡAoˤ|yˮ`AOФnէפjѪ PCI tsw˨촡ѤC
íTaNdJѡAéTwج[C
Nq~߸˦^CJquC
Intel® AӺ 10 Gigabit ɤd ϥO 6BO 6aBO 7 AӺlusC
t SFP+ iJǪ Intel® AӺ 10 Gigabit AdG ھڼҲջsytӪӦw˼Ҳըóslu
t SC Y Intel® AӺ 10 Gigabit ֺdG Uçsֳs~ߡCN SC ֱYJtdج[W TX/RX s𤺡C
t LC Y Intel® AӺ 10 Gigabit ֺdG Uçsֳs~ߡCN LC YJdCpGluWPtd۲ (]A׳W)AhiѦұNlu䥦Y (Ҧp SC)C
Intel® AӺ 10 Gigabit CX4 dG luŦX IEEE Std 802.3ak, Clause 54 ( 54 ) WCWwluYO IEC 61076-3-113 ҩwq MDI latch-type receptacle (u®y)C
ҰʹqÿӥHUXʵ{w˻C
|
|
`NG
|
Windows ҰʮɡAd|QswCnw˥TXʵ{C
줶dAWindows |w Windows `nXʵ{αҰuMsWwv FC
pGFҰʪܡAпӴܨӱqʸˤФwXʵ{C
pGw˪O Windows `nXʵ{ (F|X{)AдJ Intel CD ФAb Intel su ۰ʰܮɡA@UuwXʵ{Mnv sӧsXʵ{C۰ʰ|X{C
nإ߳oXʵ{Gi RPM* ʥ]Aа 'rpmbuild -tb <filename.tar.gz>'CXʵ{SwɮצW٨N <filename.tar.gz>C
|
|
`NG nϫإ߾A@~Aثe檺֤Pw˪֤ߨӷβպA@wn۲šCpGz譫ssĶ֤ߡAаWsҰʨtΡC RPM \ʶȦb Red Hat ǻչLC |
N¦Xʵ{ tar ɮײzܪؿCҦpAϥ '/home/username/ixgb' '/usr/local/src/ixgb'.
UntarAYOɡA䤤 <x.x.x> OXʵ{ tar XG
tar zxf ixgb-<x.x.x>.tar.gz
ܧXʵ{ src ؿA䤤 <x.x.x> OXʵ{ tar XG
cd ixgb-<x.x.x>/src/
sĶXʵ{ҲաG
make install
GiɮױNQwˬG
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
WCw˦mOw]mCǦmYǯSw Linux ǻӻiणTC
w˼ҲաG
insmod ixgb <parameter>=<value>
JHUOӫ IP }A䤤 <x> OXG
ifconfig eth<x> <IP_address>
TwiHA@~CJHUءAB <IP_address> OQծɡAۦPlBnWt~@q IP }G
ping <IP_address>
oXʵ{}oOFtX FreeBSD ֤ߡA 4.8 ΧsϥΪC
|
|
`NG z@wnwˮ֤ߨӷ~sĶXʵ{ҲաC |
bUAx.x.x OXʵ{ tar ɮתW٤Xʵ{C
N¦Xʵ{ tar ɮײzܪؿCҦpAϥ /home/username/ixgb
/usr/local/src/ixgbC
Ѱ tar/YӰOɡG
tar xfz ixgb-x.x.x.tar.gz
p|إߤ@ ixgb-x.x.x ؿC
nw˻G
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
nNXʵ{J檺tΤAаHUBJG
cd ixgb-x.x.x
make
Ϊ
cd ixgb-<x.x.x>/src/
make load
n IP }줶dAпJG
ifconfig ixgb<interface_num>
<IP_address>
TwiHA@~CJHUءAB <IP_address> OQծɡAۦPlBnWt~@q IP }G
ping <IP_address>
pGznXʵ{btαҰʮɦ۰ʸJܡG
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
s /boot/loader.confAsWUG
if_ixgb_load="YES"
Ϊ
NXʵ{sĶ֤ߤ (аѾ\ 8)C
s /etc/rc.confAMإ߾A
ifconfig_ixgb<interface_num>
JG
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
ϥνdҡG
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
`NG YݨUAаѦ ifconfig C
pGznNXʵ{sĶ֤ߤܡAпJG
cd ixgb-<x.x.x>/src/
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
s /usr/src/sys/conf/files.i386 ɮסAMsWUG
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
q /usr/src/sys/conf/files.i386 ɮײHUUApG
oǦsbܡG
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
s֤߲պAɮ (ҦpAGENERIC MYKERNEL) in
/usr/src/sys/i386/confATwUsbG
device ixgb
sĶæwˮ֤ߡCtΥs}~֤ߧsͮġC
YݽsĶ֤ߪ䥦TAаѦ FreeBSD @~tλC
YݧhTAаѦ Intel CD ФmϥΪ̫nn Intel 䴩G http://www.intel.com/p/zh_TW/support/C
Wq 2007/10/11AU 3:49 q
ۧ@v © 2002 - 2012 Intel CorporationCOd@vQC
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel q糧~βtdCIntel 礣惡B]tTsӿաC
IntelBItanium P Pentium Intel qbHΨLaӼСC
* 䥦W٩M~Pi~gŧiLҦ̤]C
Wq 2011/1/25AU 10:21 q
PROXGB/DOCS/QUICK/CHT/license.htm 0000755 0000000 0000000 00000023046 11730046352 013134 0 ustar
INTEL nvX
n - ƻsBw˩ΨϥΫeХ\ŪC
ԲӾ\ŪHUکMeAФŽƻsBwˡBΨϥΥvX (²١uXѡv) ҤUѪonM (`١unv)C
unƻsBw˩ΨϥΦunvANܱzPNuuXѡvڡCpGzPNuXvڡAФnƻsBwˡBΨϥΦunvC
Ъ`NG
{vG ziHNunvƻszqqHKbqϥΡA]iHƻsXzƥتunv ƥƥAOݨUCG
@ϥΪ̱v G ziHNunvƻs@qWAzӤHγ~AåBiHs@@unvƥƥAݭnUCG
OEM vG zȯHz~@ξXBz~{@ϥΪ̰Wߦunv@s (䥦Wߦ~~)BΥHjunvǻ (]AAAǻw˼vγXȵv) ӹ惡unviƻsMǻAݿuoDZWwG
vC ziHG (i) FuXvѻ~AziHϥΩνƻsuơvF(ii) Nuơv~ĤTF(iii) g Intel TѭPNAiHouijѡvuơvF(iv) Fuijѡvѻ~AiHγקBsBĶuơvF(v) iHϦVu{BѽsBΩѦuơvF(vi) խקܰʳWduơvγ~vgz`\F(vii) FuXѡvѻ~ANuơvBuiAǻơvBMudҨӷXvHέlͤeuӷXvǻBAvBĤTC
LLvQC DuXvҴѪTvQA_hLשܩηtܡAIntel ¤z Intel ֦α]vTαMQBۧ@vBn@~BӼСBӷ~KΨLz]vvQαvCBTzH~ASvv|γzLqܡBBT½ѩΨL覡¤zCSOOAb Intel qBۧ@vBӼСBΨ䥦z]vWdUAIntel ¤zܩηtܪvQC
nҦvMۧ@vC unvOvϥΡAO_CunvҦƥҦv IntelCunvMLaۧ@vMkߡAHΰڱҫO@CziHunvۧ@v`NƶCzPNwLH惡unvi楼gvƻsCIntel i|HɦbtqpUA惡unvΦBΪضiASunvi䴩ΧsqȡCߦb̧PNuoDZڳWwAåBzSOdunvƥpUAz~iHNunvLHC
wn骺䥦ڡC pGھڥuXѡvWdUw˩ΨϥΪunvOwӷ~μХܬunvuեΪv("wn")AHUڴNAΩzC
wunvApGuϬqvһPuXѡvکαĬAuϬqveWV䥦کαĤOAĤOȭѨMĬ𪺥ndC
zFѨû{unvOwunvAäN Intel Ѫ̲סunvA䤤i]t~M䥦iyƿBtάG١BΨ䥦~DCwunvHuˡvѡA]ϥιwunvҤް_l`AIntel bŧGKOTγdC
z{ Intel |ӿեӱN|XwunvAåB Intel zSܩηtܪqȭnXwunvBӥB Intel iण|XPwunvۮeunvCz{Az檺sζ}oYPwunvBΪ̨ϥλPwunv~isζ}oӬsIѱzۦӾC
pG Intel ̷ӥt~@ѭXѪeѱzwunvAz惡wunvϥΤ]ݭn즹XѪWdC
COTC pGunvO Intel HC鴣ѡAIntel OҦCb Intel eXEQѤ|ƤW岫CpGo{岫AбNCeٵ Intel HK Intel ܭnsΥH䥦keunvzC
LOTKC DpHWҴѡAunv̡u{pvѦӤtܩηtܤOA]AAʡBI`LHvqBξAXYإγ~OC Intel Oҥ礣Ӿᦹunvҥ]tTBrBϤBsΨLؤTΧʡC
dC bpUAINTEL Ψӳ]ϥΥ~εLkϥΥ~Ҳͪl`A (]AAȭAQlB~_BθT) tdAY INTEL wgDl`iʥOpC]YǥqkҰϤ\tܫOToηN~ladKέAҥHAHWiणAΩzCHzҦbҰϦөwAzi٦䥦kvQC X֨ϥΡunvM (“”) ˸m (]pتOnH Intel ~e{) ɡAzT{ Intel JO (“”) ˸m@̡A]Oгy̡CzFѨû{Aft ("") ˸mϥήɡAunvTϥ Intel ܡBIntel ]punvNOnX (“”) ˸mϥΡBåBApGX (“”) ˸mϥΡAunviLk`ާ@CX (“") ˸mϥήɡAzPNӾunviLk`@~ICzPNO٩M@ Intel Ψ䰪¾BlqBΪݤq|]unvX (") ˸mϥγyζ~dBӤHˮ`BΦ`vӤް_ҦߡBOΡBl`B}PBHΫ߮vOӨˮ`AYϦv Intel bunv]pλsyWҲOpC
vϥΡC n骺]pBNϡBαvγ~OϥΩnGٴNiyӤH˩Φ` (ҦpAtΡBͨtΡBαϥͨt) tΩθ˸mCzYѩWzDwwΫDvγ~ӨϥΡunvAzO٨ëO Intel ΨDƪ̡BlqΪݾcAݩӾ]DwwΫDvγ~Ҭ~dBHˮ`Φ`nAӪζͤҦvQDiBBl`BXAHΦXz߮vOΡAYϳonź Intel b]pλsy Client ɦҲPC
XѲפC pGzHϨڳWwAIntel HɥiHפuXvCXפAzߨPunvαNҦunvƥ IntelC
AΪkߡC תk߽ĬhA̷ӦuXvWdް_vץѥ[{kߺzCzPNupXꤽvufP⫴vAΩuXѡvCziHHϾAΪ~PkMWw~PunvCDgv Intel NHѭܨñWA_hAھڥXAIntel SdθqȡC
FvQC WunvMOpHX}oAHuvQvѨϥΡCuFvϥΡBƻsBo FAR52.227-14 M DFAR252.227-7013 ΨWwCuFvϥΦ~Ncӻ{ Intel 惡unvMvCӥ]өλsytӬO IntelC
yF½ĶC pGuXv^媩H䥦y½ĶA½ĶȥHKϥάتѡA@ӥH^媩DC
Wq 2011/5/15AU 10:56 q
Intel VҦ̫OҡAboӥ]ˤd~A|ƩMuW岫CpGӤd~bw˴lΨϥΤAKboOT[dC
WzOTiHN䥦ެOܡBtܩΪkwOTA]A]ȭ^z]DIǩʡBSγ~APʡBAΩʫOTBΦ]ijBWνdΪOTC
oOT[\]ݥΡBN~B~ΡBBB״_BaBw˩Τըld~CpGo{d~岫AIntel |ۦܧKOέ״_w鲣~AOHU]ߪp~AΪ̬OApGzѸӤd~Mh٧Ʊv (RMA) X (аѦҥHU) HʶRҩ (pG|U) zʶR~sө IntelAôѷ岫A]iHhٱzʶRBCpGzBeӤd~Ah]lοICz@wnϥέӪe]ά۵^äIBeOΡC
Intel i|ΥsνվLsӧέ״_Ӥd~AåBA Intel bd~Ϊ̬Os Intel ]C״_Χd~A| Intel ܥHɪۦPΧeٵzCIntel OdΥثe۵d~d~vQC
h٥d~eAХqܨ +1 916-377-7000 sIntel Ȥ䴩èoh٧Ʊv]RMA^XC
pGȤ䴩sաTwӤd~岫AL̷| RMA o@ RMA XzKbd~]˥~C]ˤWS RMA XAIntel N~C
Intel ƱzzʶR Intel d~NCqʶR_EQ]90^ѤɭԡAziHNz Intel dʶRBAqsӳBoʶRBBhڡCӧOhfðhڵӧOȤ᪺APөMtPӥiN Intel dhٵL̪ʶRBCIntel OұNھڦFhfñNʶRBhٵV Intel ʶRȤC
INTEL bߤ@dB[iqalCbpUAINTEL Ҥβqʪl`td]]AoʡBN~BMSl`^]AAȭAIǴz]vBAʶROΡBLkϥΡBӷ~_BhABHQlo]BHϡBήھڥOTް_alAY INTEL ƥwo즹aliʳqOpCeO_פΡAھڦXAINTEL ߪ`dNWLӲ~ICoǼbdO~]wnCINTEL qwαvHӾ䥦dC
YǦ{\ưέN~olaA]AWziणAΩzC
nε{G Intel SOn v̡ Av̡ bnε{ (]AAȭ|ҨϥΡAwʩΰdUtΡB֯tΡBΪŤΦaqt) ϥΦd~tdAϥΪ̥惡إγ~Ӿ᧹ICv̡ PNO@BO١Bä Intel ] v̡ Av̡ HΤ覡ϥΤd~Ӥް_MҦ߶ˮ`C Av̡C
nG Hd~Ѫn餣bWzwOT[\dCаѦHd~ѪAγnvXѥHnOTԲӸơC
Wq 2002 ~ 7 23 W 10:42 6
Schalten Sie den Computer aus und ziehen Sie den Netzstecker aus der Steckdose. Wenn Sie eine Hot-Plug-Installation ausfhren, lesen Sie zuerst die Serverdokumentation.
Entfernen Sie die Computerabdeckung und die Blende des Adaptersteckplatzes, der fr Ihren Adapter passt. Sie knnen ohne negative Folgen einen Steckplatz benutzen, der lnger ist als der Anschluss Ihres Adapters; versuchen Sie jedoch nicht, den Adapter in einem Steckplatz zu installieren, der krzer ist als der PCI-Express-Anschluss.
Setzen Sie den Adapter fest in den Steckplatz ein und befestigen Sie die Halterung.
Bringen Sie die Computerabdeckung wieder an. Stecken Sie die Netzverbindung ein.
Intel® Ethernet 10-Gigabit-Kupfer-Adapter: Verwenden Sie Ethernetkabel der Kategorie 6, 6a oder 7.
Intel® Ethernet 10-Gigabit-Server-Adapter mit anschliebarem SFP+-Optics-Modul: Installieren Sie das Modul und schlieen Sie das Kabel entsprechend den Herstelleranweisungen fr das Modul an.
Intel® Ethernet 10-Gigabit-Glasfaseradapter mit SC-Steckverbinder: Entfernen Sie die Abdeckung des Glasfaseranschlusses und bewahren Sie sie gut auf. Stecken Sie einen SC-Glasfaser-Steckverbinder in die TX/RX-Anschlsse der Adapterklammer.
Intel® Ethernet 10-Gigabit-Glasfaseradapter mit LC-Steckverbinder: Entfernen Sie die Abdeckung des Glasfaseranschlusses und bewahren Sie sie gut auf. Stecken Sie einen LC-Steckverbinder in den Adapter. Sie knnen Kabel anderer Verbindungstypen (wie SC) verwenden, wenn die Kabel den optischen Spezifikationen des Adapters, einschlielich der Lngenbegrenzung, entsprechen.
Intel® Ethernet 10-Gigabit-CX4-Adapter: Die Kabel mssen den Spezifikationen des IEEE-Standards 802.3ak, Klausel 54 entsprechen. Der erforderliche Kabelanschluss ist ein aufklappbarer MDI-Steckplatz wie in IEC 61076-3-113 definiert.
Starten Sie den Computer und folgen Sie nachfolgenden Anweisungen zur Treiberinstallation.
|
|
HINWEISE:
|
Beim Start von Windows wird der Adapter als neue Hardware erkannt. So installieren Sie den Treiber richtig:
Der Adapter wird erkannt, und Windows installiert entweder einen in Windows residenten Treiber oder startet den Assistent fr das Suchen neuer Hardware .
Wenn der Assistent gestartet wird, folgen Sie den Aufforderungen, um den Treiber von der CD dieses Pakets zu installieren.
Wenn ein in Windows residenter Treiber installiert wird (Assistent wird nicht angezeigt), aktualisieren Sie den Treiber durch Einlegen der Intel CD. Klicken Sie auf die Schaltflche Treiber und Software installieren , wenn das Fenster Intel Netzwerkanschlsse angezeigt wird.
Um ein binres RPM*-Paket dieses Treibers zu erstellen, fhren Sie 'rpmbuild -tb <dateiname.tar.gz>' aus. Ersetzen Sie <dateiname.tar.gz> mit dem Dateinamen des Treibers.
|
|
HINWEIS: Damit das erstellte Paket ordnungsgem funktioniert, MUSS der gegenwrtig ausgefhrte Kernel mit der Version und der Konfiguration der installierten Kernelquellen bereinstimmen. Wenn Sie den Kernel gerade neu kompiliert haben, fhren Sie jetzt einen Systemneustart aus. Die RPM-Funktionalitt wurde bisher nur in Red Hat-Verteilungen getestet. |
Verschieben Sie die Basistreiber-Tardatei in ein Verzeichnis Ihrer Wahl. Verwenden Sie beispielsweise '/home/username/ixgb' oder '/usr/local/src/ixgb'.
Entpacken/dekomprimieren Sie das Archiv, wobei <x.x.x> die Versionsnummer des Treibertars ist:
tar zxf ixgb-<x.x.x>.tar.gz
Wechseln Sie durch folgende Eingabe zum src-Verzeichnis des Treibers ber, wobei <x.x.x> die Versionsnummer des Treibertars ist:
cd ixgb-<x.x.x>/src/
Kompilieren Sie das Treibermodul:
make install
Die Binrdatei wird installiert als:
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
Die oben aufgefhrten Installationsverzeichnisse sind die Standardverzeichnisse. Sie sind mglicherweise fr bestimmte Linux-Distributionen nicht richtig.
Installieren Sie das Modul:
insmod ixgb <parameter>=<value>
Weisen Sie der Schnittstelle durch folgende Eingabe eine IP-Adresse zu, wobei <x> fr die Schnittstellennummer steht:
ifconfig eth<x> <IP_address>
Prfen Sie, ob die Schnittstelle funktioniert. Geben Sie Folgendes ein, wobei <IP_address> die IP-Adresse eines anderen Computers in dem Subnetz ist, in dem die Schnittstelle getestet wird:
ping <IP-Adresse>
Dieser Treiber wurde fr die Verwendung mit FreeBSD-Kernel Version 4.8 oder hher entwickelt.
|
|
HINWEIS: Sie mssen Kernelquellen installiert haben, damit Sie das Treibermodul kompilieren knnen. |
Bei den untenstehenden Anleitungen ist x.x.x die Treiberversion, wie sie im Namen der Treibertardatei angegeben ist.
Verschieben Sie die Basistreiber-Tardatei in ein Verzeichnis Ihrer Wahl. Verwenden Sie beispielsweise /home/username/ixgb oder
/usr/local/src/ixgb.
Dekomprimieren Sie das Archiv:
tar xfz ixgb-x.x.x.tar.gz
Hierdurch wird das Verzeichnis ixgb-x.x.x erstellt.
So installieren Sie die man-Seite:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Um den Treiber in einem laufenden System zu laden, fhren Sie die folgenden Schritte aus:
cd ixgb-x.x.x
make
ODER
cd ixgb-x.x.x/src
make load
Um der Schnittstelle eine IP-Adresse zuzuweisen, geben Sie Folgendes ein:
ifconfig ixgb<Schnittstellennummer>
<IP-Adresse>
Prfen Sie, ob die Schnittstelle funktioniert. Geben Sie Folgendes ein, wobei <IP_address> die IP-Adresse eines anderen Computers in dem Subnetz ist, in dem die Schnittstelle getestet wird:
ping <IP_address>
Wenn Sie mchten, dass der Treiber beim Hochfahren des Systems automatisch geladen wird, fhren Sie Folgendes aus:
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Bearbeiten Sie /boot/loader.conf und fgen Sie folgende Zeile hinzu:
if_ixgb_load="YES"
ODER
kompilieren Sie den Treiber im Kernel (siehe Punkt 8).
Bearbeiten Sie /etc/rc.conf und erstellen Sie den geeigneten
ifconfig_ixgb<interface_num>
Eintrag:
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
Beispiel:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
HINWEIS: Hilfe finden Sie auf der ifconfig man-Seite.
Wenn Sie den Treiber in den Kernel kompilieren mchten, geben Sie Folgendes ein:
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Bearbeiten Sie die Datei /usr/src/sys/conf/files.i386 und fgen Sie folgende Zeile hinzu:
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Entfernen Sie die folgenden Zeilen aus der Datei /usr/src/sys/conf/files.i386, wenn sie
vorhanden sind:
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Entfernen Sie die Kernelkonfigurationsdatei (GENERIC oder MYKERNEL) in
/usr/src/sys/i386/conf und stellen Sie sicher, dass die folgende Zeile vorhanden ist:
device ixgb
Kompilieren Sie und installieren Sie den Kernel. Damit die Kernel-Aktualisierungen wirksam werden, ist ein Systemneustart erforderlich.
Weitere Informationen ber das Kompilieren des Kernels finden Sie in der Dokumentation ber das FreeBSD-Betriebssystem.
Weitere Informationen finden Sie im Benutzerhandbuch auf der Intel CD oder der Intel Support-Website: http://www.intel.com/p/de_DE/support/.
Zuletzt berarbeitet am 11.10.07 15:49 Revision
Copyright © 2002 2012 Intel Corporation. Alle Rechte vorbehalten.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel Corporation bernimmt keine Verantwortung fr Fehler oder Auslassungen in diesem Dokument. Auerdem macht Intel keinerlei Zusagen, dessen Inhalt zu aktualisieren.
Intel, Itanium und Pentium sind Marken der Intel Corporation in den USA und anderen Lndern.
*Andere Marken oder Produktnamen sind Eigentum der jeweiligen Inhaber.
Stand: 25.01.2011 22:21 Revision
PROXGB/DOCS/QUICK/DEU/license.htm 0000755 0000000 0000000 00000041656 11730046352 013142 0 ustar
INTEL SOFTWARE-LIZENZVEREINBARUNG
WICHTIG BITTE LESEN SIE DIESE VEREINBARUNG VOR DEM KOPIEREN, INSTALLIEREN ODER VERWENDEN DER SOFTWARE.
Lesen Sie die folgenden Nutzungsbedingungen, bevor Sie diese Software oder zugehrige Ressourcen (gemeinsam als Software“ bezeichnet), die unter dieser Lizenzvereinbarung (Vereinbarung“) bereitgestellt werden, kopieren, installieren oder verwenden.
Durch Kopieren, Installieren oder anderweitigen Einsatz der Software erklren Sie sich mit den Bestimmungen dieser Vereinbarung einverstanden. Wenn Sie die Bedingungen dieser Vereinbarung nicht akzeptieren, drfen Sie die Software nicht kopieren, installieren oder einsetzen.
Bitte beachten Sie:
STANDORTLIZENZ: Sie drfen die Software auf Computer Ihrer Organisation zum firmeninternen Gebrauch kopieren und von der Software unter folgenden Bedingungen eine angemessene Anzahl an Sicherungskopien erstellen:
EINZELBENUTZERLIZENZ: Sie drfen die Software auf einen einzelnen Computer fr Ihren persnlichen Gebrauch kopieren und von der Software unter folgenden Bedingungen eine Sicherungskopie erstellen:
OEM-LIZENZ: Die Software darf nur als wichtiger Bestandteil Ihres Produkts bzw. integriert in Ihr Produkt oder als Standalone-Softwareaktualisierung zur Wartung fr bestehende Endanwender Ihrer Produkte unter Ausschluss aller anderen Standalone-Produkte, oder als Komponente einer greren Softwareverteilung, einschlielich der Verteilung eines Installations-Images oder eines Gast-VM-Images, reproduziert und verteilt werden, und zwar unter Vorbehalt folgender Bedingungen:
LIZENZEINSCHRNKUNGEN. Sie drfen NICHT: (i) das Material auf andere Weise als in diesem Vertrag vereinbart einsetzen oder kopieren; (ii) das Material an eine beliebige Drittpartei vermieten oder verpachten; (iii) diesen Vertrag oder das Material ohne ausdrckliche schriftliche Genehmigung von Intel bertragen; (iv) das Material in seiner Gnze oder Teile davon verndern, bearbeiten oder bersetzen, auer wie in diesem Vertrag vorgesehen; (v) das Material zurckentwickeln, dekompilieren oder disassemblieren; (vi) versuchen, die normale Funktion eines Lizenzmanagers, der den Einsatz des Materials steuert, abzundern oder zu manipulieren; (vii) das Quellcode-Format irgendwelcher Komponenten des Materials, der neu verteilbaren Dateien und der Beispielsquelle und alle Ableitungen davon auer wie in diesem Vertrag vorgesehen an eine Drittpartei verbreiten, in Unterlizenz vergeben oder bertragen.
KEINE ANDEREN RECHTE. Es werden Ihnen von Intel keine anderen Rechte oder Lizenzen, sei es ausdrcklich oder konkludent, in Bezug auf die proprietren Informationen oder Patente, Urheberrechte, Topographien, Marken, Betriebsgeheimnisse oder andere Rechte an geistigem Eigentum erteilt, die Intel gehren oder von Intel kontrolliert werden, sofern dies nicht ausdrcklich in dieser Vereinbarung erwhnt ist. Soweit nicht ausdrcklich hier angegeben, werden Ihnen weder ausdrcklich noch konkludent Lizenzen oder Rechte gewhrt bzw. eingerumt. Intel gewhrt Ihnen keine ausdrcklichen oder konkludenten Rechte an Patenten, Urheberrechten und Marken von Intel oder andere Rechte an geistigem Eigentum.
EIGENTUM AN SOFTWARE UND URHEBERRECHTEN. Fr die Software wird eine Lizenz gewhrt; sie wird nicht verkauft. Das Eigentum aller Kopien der Software verbleibt bei Intel. Die Software ist urheberrechtlich und durch die Gesetze der Vereinigten Staaten von Amerika und anderer Lnder sowie durch internationale Abkommen geschtzt. Urheberrechtshinweise drfen nicht aus der Software entfernt werden. Sie erklren hiermit Ihr Einverstndnis, das unerlaubte Kopieren der Software zu verhindern. Intel kann die Software oder darin erwhnte Elemente jederzeit und ohne Vorankndigung ndern. Intel ist jedoch nicht dazu verpflichtet, die Software zu untersttzen oder zu aktualisieren. Sie drfen die Software nur bertragen, wenn sich der Empfnger uneingeschrnkt mit diesen Bedingungen einverstanden erklrt, und Sie keine Kopien der Software behalten.
ZUSTZLICHE BEDINGUNGEN FR PRE-RELEASE-SOFTWARE. Wenn die Software, die Sie unter dieser Vereinbarung installieren oder verwenden, eine nicht kommerziell vertriebene Pre-Release-Version ist oder als Alpha“- oder Beta“-Version der Software (Pre-Release-Software“) gekennzeichnet ist, gelten folgende Bedingungen.
Sollte eine Bedingung in diesem Abschnitt in Bezug auf Pre-Release-Software in Widerspruch zu anderen Bedingungen dieser Vereinbarung stehen, so ersetzt dieser Abschnitt die anderen Bedingungen, aber nur in dem Ausma, wie es zur Vermeidung des Widerspruchs erforderlich ist.
Sie verstehen und erkennen an, dass es sich bei dieser Software um Pre-Release-Software und nicht die endgltige Software von Intel handelt. Sie kann Fehler und andere Probleme aufweisen, die zu Datenverlust, Systemausfall oder anderen Fehlern fhren knnen. Die Pre-Release-Software wird wie besehen“ bereitgestellt und Intel schliet jegliche Garantie oder Haftung fr Schden, die aus dem Gebrauch der Pre-Release-Software entstehen knnen, aus.
Sie erkennen an, dass Intel keine Zusage gemacht hat, in Zukunft Pre-Release-Software zu verffentlichen und dass Intel Ihnen gegenber keine ausdrckliche oder konkludente Verpflichtung zur Verffentlichung der Pre-Release-Software hat und dass Intel mglicherweise keine Software verffentlicht, die mit der Pre-Release-Software kompatibel ist. Sie stimmen zu, dass die Gesamtheit aller Forschungs- und Entwicklungsarbeiten, die Sie in Zusammenhang mit der Pre-Release-Software oder einem Produkt, das die Pre-Release-Software nutzt oder damit verknpft ist, durchfhren, auf Ihr eigenes Risiko erfolgt.
Wenn Intel Ihnen entsprechend einer eigenen schriftlichen Vereinbarung Pre-Release-Software zur Verfgung gestellt hat, unterliegt Ihr Gebrauch der Pre-Release-Software ebenfalls dieser Vereinbarung.
BESCHRNKTE GARANTIE FR DATENTRGER. Wenn die Software von Intel auf einem Datentrger geliefert wurde, garantiert Intel fr einen Zeitraum von neunzig Tagen nach der Lieferung durch Intel, dass der Datentrger frei von Materialschden ist. Falls der Datentrger beschdigt ist, knnen Sie ihn an Intel zurckgeben. Intel entscheidet in diesem Fall, ob der Datentrger ersetzt oder ob die Software auf einem anderen Weg an Sie ausgeliefert wird.
AUSSCHLUSS ANDERER GARANTIEN. MIT AUSNAHME DER OBEN GENANNTEN GARANTIE WIRD DIE SOFTWARE IM VORLIEGENDEN ZUSTAND UND OHNE AUSDRCKLICHE ODER STILLSCHWEIGENDE GARANTIEN JEDER ART, EINSCHLIESSLICH FR DEN HANDELSWERT, DIE EINHALTUNG DER RECHTE VON DRITTEN ODER DIE EIGNUNG FR EINEN BESTIMMTEN ZWECK, GELIEFERT. Intel bernimmt keine Garantie oder Verantwortung fr die Richtigkeit oder Vollstndigkeit der Informationen, des Texts, der Grafiken, Verknpfungen oder anderer Elemente, die in der Software enthalten sind.
HAFTUNGSBESCHRNKUNG. UNTER KEINEN UMSTNDEN HAFTEN INTEL ODER DRITTHERSTELLER FR IRGENDWELCHE SCHDEN (EINSCHLIESSLICH UND UNEINGESCHRNKT ALLE GEWINNVERLUSTE, BETRIEBSUNTERBRECHUNGEN ODER INFORMATIONSVERLUSTE), DIE DURCH DIE VERWENDUNG ODER DIE NICHTVERWENDBARKEIT DER SOFTWARE AUFTRETEN; DIES GILT AUCH FR FLLE, IN DENEN INTEL AUF DIE MGLICHKEIT SOLCHER SCHDEN HINGEWIESEN WURDE. IN EINIGEN GERICHTSBARKEITEN IST DER AUSSCHLUSS ODER DIE EINSCHRNKUNG DER HAFTUNG FR STILLSCHWEIGENDE GEWHRLEISTUNGEN ODER FR MITTELBARE BZW. BEILUFIG ENTSTANDENE SCHDEN NICHT ZULSSIG, SO DASS DIE OBEN AUFGEFHRTE EINSCHRNKUNG MGLICHERWEISE AUF SIE NICHT ZUTRIFFT. SIE HABEN UNTER UMSTNDEN NOCH ANDERE RECHTE, DIE JE NACH GERICHTSBARKEIT VARIIEREN KNNEN. Fr den Fall, dass Sie die Software in Verbindung mit einem virtuellen (emulierten“) Gert verwenden, das so konzipiert ist, dass es als Intel Komponente erkannt wird, erkennen Sie an, dass Intel weder der Urheber noch der Hersteller des virtuellen (emulierten“) Gerts ist. Sie verstehen und erkennen an, dass Intel keine Zusicherungen ber den korrekten Betrieb der Software macht, wenn diese mit einem virtuellen (emulierten“) Gert verwendet wird, dass Intel die Software nicht fr den Betrieb mit einem virtuellen (emulierten“) Gert entwickelt hat und dass die Software mglicherweise in Verbindung mit einem virtuellen (emulierten“) Gert nicht korrekt funktioniert. Sie stimmen zu, das Risiko zu bernehmen, dass die Software mglicherweise in Verbindung mit einem virtuellen (emulierten“) Gert nicht korrekt funktioniert. Sie stimmen zu, dass Sie Intel und seine Geschftsfhrer, Niederlassungen und verbundenen Unternehmen von allen Ansprchen, Kosten, Schden, Auslagen sowie Anwaltskosten freistellen, die sich direkt oder indirekt aus einem Anspruch auf Produkthaftung, Krperverletzung oder Tod ergeben und im Zusammenhang mit dem Gebrauch der Software in Verbindung mit einem virtuellen (emulierten“) Gert stehen, selbst dann, wenn im Anspruch vorgebracht wird, dass Intel im Design oder der Herstellung der Software fahrlssig handelte.
UNBEFUGTER GEBRAUCH. DIE SOFTWARE WURDE NICHT FR DEN EINSATZ IN SYSTEMEN ODER ANWENDUNGEN KONZIPIERT, IN DENEN DER AUSFALL DER SOFTWARE ZU PERSONENVERLETZUNG ODER LEBENSBEDROHLICHEN SITUATIONEN FHREN KNNTE (Z. B. IN MEDIZINISCHEN SYSTEMEN ODER LEBENSRETTUNGS- ODER LEBENSERHALTUNGSSYSTEMEN). Sollten Sie die Software fr solche nicht vorgesehenen oder nicht genehmigten Zwecke einsetzen, stellen Sie Intel und seine Geschftsfhrer, Niederlassungen und verbundenen Unternehmen von allen Ansprchen, Kosten, Schden, Auslagen sowie Anwaltskosten frei, die sich direkt oder indirekt aus einem Anspruch auf Produkthaftung, Krperverletzung oder Tod ergeben und in Verbindung mit dem nicht vorgesehenen oder nicht genehmigten Einsatz stehen, selbst dann, wenn im Anspruch vorgebracht wird, dass Intel im Design oder der Herstellung dieses Teils fahrlssig handelte.
BEENDIGUNG DIESER VEREINBARUNG. Diese Vereinbarung kann von Intel jederzeit beendet werden, wenn Sie die genannten Bestimmungen nicht einhalten. Wird die Vereinbarung beendet, sind Sie dazu verpflichtet, die Software entweder umgehend zu lschen oder alle Kopien der Software an Intel zurckzugeben.
ANWENDBARES RECHT. Ansprche, die im Rahmen dieser Vereinbarung erhoben werden, unterliegen dem Recht des US-Bundesstaats Kalifornien, ungeachtet der Prinzipien zur Gesetzeskollision. Sie erklren sich damit einverstanden, dass das bereinkommen der Vereinten Nationen ber Vertrge ber den internationalen Warenkauf in Bezug auf diesen Vertrag nicht zutrifft. Sie drfen die Software nicht exportieren, wenn der Export gegen geltende Exportgesetze und -bestimmungen verstt. Intel ist an keine anderen Vereinbarungen gebunden, es sei denn, sie liegen in schriftlicher Form vor und wurden von einem autorisierten Reprsentanten von Intel unterzeichnet.
EINGESCHRNKTE RECHTE DER US-REGIERUNG. Die im Lieferumfang enthaltene Software und Dokumentation wurden mit privaten finanziellen Mitteln entwickelt und werden mit EINGESCHRNKTEN RECHTEN“ bereitgestellt. Die Verwendung, Vervielfltigung oder Verffentlichung durch Regierungsbehrden unterliegt den Bestimmungen, die in FAR 52.227-14 und DFARS 252.227-7013 ff. oder einer entsprechenden Aktualisierung aufgefhrt sind. Die Verwendung dieses Produkts durch US-Regierungsbehrden erfolgt unter Anerkennung der diesbezglichen Eigentumsrechte von Intel. Auftraggeber oder Hersteller ist Intel.
SPRACHE; BERSETZUNGEN. Sollte die englische Version dieses Vertrags zusammen mit einer in eine andere Sprache bersetzten Version ausgeliefert werden, dient diese bersetzte Version ausschlielich zu Informationszwecken; die englische Version ist die einzige rechtsgltige Version.
Zuletzt berarbeitet 15.05.2011 22:56 Revision
Intel garantiert dem ursprnglichen Eigentmer, dass das in diesem Paket gelieferte Adapterprodukt frei von Material- und Herstellungsfehlern ist. Das Adapterprodukt fllt nicht unter diese Garantie, wenn es whrend der Installation beschdigt oder unsachgem verwendet wurde.
DIE OBIGE GARANTIE ERSETZT ALLE ANDEREN AUSDRCKLICHEN, STILLSCHWEIGENDEN ODER GESETZLICHEN GARANTIEN, EINSCHLIESSLICH, ABER NICHT BESCHRNKT AUF IRGENDWELCHE GARANTIEN DER EINHALTUNG DER RECHTE DRITTER AN GEISTIGEM EIGENTUM, DER MARKTGNGIGEN QUALITT, DER EIGNUNG FR EINEN BESTIMMTEN ZWECK, DIE SICH AUS EINEM VORSCHLAG, EINER SPEZIFIKATION ODER EINEM BEISPIEL BZW. EINER PROBE ERGEBEN.
Diese Garantie gilt nicht fr den Austausch von Adapterprodukten, die durch Mutwilligkeit, Unfall, Zweckentfremdung, Nachlssigkeit, Reparaturen, Katastrophen, unsachgeme Installation oder unsachgemes Testen beschdigt wurden. Wird das Adapterprodukt als defekt eingestuft, wird Intel nach eigenem Ermessen das Hardwareprodukt wie unten erlutert kostenfrei ersetzen oder reparieren oder Ihnen den Kaufpreis zurckerstatten, vorausgesetzt, dass Sie das Adapterprodukt zusammen mit einer Return-Material-Authorization-(RMA-)Nummer (siehe unten) und einem Kaufnachweis (falls nicht registriert) an den Hndler, wo Sie es erworben haben, oder an Intel mit einer Beschreibung jeglichen Defekts zurckgeben. Wenn Sie das Adapterprodukt einschicken, bernehmen Sie das Risiko fr Schden am Produkt oder Verlust des Produkts whrend des Transports. Sie mssen die Originalverpackung (oder eine gleichwertige Verpackung) verwenden und das Porto bezahlen.
Intel kann das Adapterprodukt durch neue oder aufbereitete Teile ersetzen oder reparieren. Jedes von Intel ersetzte Adapterprodukt oder Teile davon gehen in das Eigentum von Intel ber. Reparierte oder ersetzte Adapterprodukte werden nach dem Ermessen von Intel mit derselben Revisionsstufe wie empfangen oder hher an Sie zurckgegeben. Intel behlt sich das Recht vor, eingestellte Adapterprodukte durch ein gleichwertiges Adapterprodukt der aktuellen Generation zu ersetzen.
Wenden Sie sich vor der Rckgabe eines Adapterprodukts unter +1 916-377-7000 an den Kundensupport von Intel, um eine Return-Material-Authorization-(RMA-)Nummer anzufordern.
Wenn die Kundensupportgruppe den Defekt des Adapterprodukts besttigt, wird die RMA-Abteilung Ihnen eine RMA-Nummer ausstellen, die Sie an der Auenverpackung des Adapterprodukts anbringen. Intel akzeptiert nur Produkte mit einer RMA-Nummer auf der Verpackung.
Geben Sie das Adapterprodukt fr eine Rckerstattung des Kaufpreises oder Ersatz an den Verkaufsort zurck.
Intel mchte, dass Sie mit dem gekauften Intel Adapterprodukt rundum zufrieden sind. Sie knnen in einem Zeitraum von neunzig (90) Tagen ab Kaufdatum Ihren Intel Adapter fr eine volle Rckerstattung des Kaufpreises durch den Hndler an den ursprnglichen Verkaufsort zurckgeben. Fachhndler und Distributoren, die Retouren akzeptieren und ihren Kunden Geld zurckerstatten, knnen Intel Adapter an den ursprnglichen Verkaufsort zurckgeben. Intel garantiert die Annahme von Retouren unter dieser Richtlinie und die Rckerstattung des ursprnglichen Kaufpreises an Kunden, die direkt von Intel kaufen.
DIE EINZIGE HAFTUNG VON INTEL UNTER DIESER VEREINBARUNG IST BESCHRNKT AUF DIREKTE, OBJEKTIV MESSBARE SCHDEN. UNTER KEINEN UMSTNDEN HAFTET INTEL FR JEGLICHE INDIREKTEN ODER SPEKULATIVEN SCHDEN (EINSCHLIESSLICH, ABER OHNE EINSCHRNKUNG DES VORHERGEHENDEN, FOLGESCHDEN, NEBENSCHDEN ODER SONDERSCHDEN), EINSCHLIESSLICH, ABER NICHT BESCHRNKT AUF DIE EINHALTUNG DER RECHTE DRITTER AN GEISTIGEM EIGENTUM, KOSTEN DER NEUBESCHAFFUNG, UNBRAUCHBARKEIT, GESCHFTSAUSFLLEN, VERLUST DES GESCHFTSWERTS UND GEWINNVERLUSTEN, EGAL OB SICH SOLCHE SCHDEN AUS VERTRAGLICHER FAHRLSSIGKEIT, UNERLAUBTEM HANDELN ODER UNTER JEGLICHER GARANTIE ERGEBEN, UNGEACHTET DESSEN, OB INTEL VON DER MGLICHKEIT SOLCHER SCHDEN IM VORAUS KENNTNIS HATTE. UNGEACHTET DES VORHERGEHENDEN BERSTEIGT DIE GESAMTHAFTUNG VON INTEL FR ALLE ANSPRCHE UNTER DIESER VEREINBARUNG NICHT DEN FR DAS PRODUKT BEZAHLTEN PREIS. DIESE BESCHRNKUNGEN POTENZIELLER HAFTUNGSANSPRCHE TRUGEN WESENTLICH ZUR BESTIMMUNG DES PRODUKTPREISES BEI. INTEL BERNIMMT KEINE WEITEREN HAFTUNGEN UND AUTORISIERT NIEMANDEN, AN SEINER STELLE JEGLICHE WEITEREN HAFTUNGEN ZU BERNEHMEN.
In einigen Gerichtsbarkeiten ist der Ausschluss oder die Beschrnkung von Neben- oder Folgeschden nicht zulssig, sodass die oben ausgefhrten Beschrnkungen mglicherweise auf Sie nicht zutreffen.
Kritische Steuerungsanwendungen: Intel lehnt insbesondere die Haftung fr die Verwendung des Adapterprodukts in kritischen Steuerungsanwendungen (einschlielich, nur als Beispiel, Sicherheits- oder medizinische Steuerungssysteme, Kernenergie-Steuerungssysteme oder Luft- und Bodenverkehrs-Steuerungssysteme) durch den Lizenznehmer oder Unterlizenznehmer ab. Eine solche Verwendung geschieht einzig auf Risiko des Benutzers. Der Lizenznehmer willigt ein, Intel vor allen Ansprchen, die sich aus der Verwendung des Adapterprodukts in solchen Anwendungen durch den Lizenznehmer oder Unterlizenznehmer ergeben, zu schtzen, freizuhalten und schadlos zu halten.
Software: Die mit dem Adapterprodukt gelieferte Software fllt nicht unter die oben ausgefhrte Hardwaregarantie. Einzelheiten zu eventuellen Softwaregarantien finden Sie in der zutreffenden Softwarelizenzvereinbarung im Lieferumfang des Adapterprodukts.
Zuletzt berarbeitet 23.7.02 10.42 Revision 6
Turn off the computer and unplug the power cord. If performing a "hot plug" install, see your server documentation first.
Remove the computer cover and the adapter slot cover from the slot that matches your adapter. You may utilize a slot that is longer than your adapter’s connector with no harm, but do not attempt to install in a slot that is shorter than the PCI Express connector.
Firmly place the adapter into the slot and secure the bracket.
Replace the computer cover. Plug in the power cord.
Intel® Ethernet 10 Gigabit copper adapters: Use Category 6, Category 6a, or Category 7 Ethernet cabling.
Intel® Ethernet 10 Gigabit Server Adapter with SFP+ pluggable optics: Install the module and attach the cable according to the module manufacturer’s directions
Intel® Ethernet 10 Gigabit fiber adapters with SC connector: Remove and save the fiber optic connector cover. Insert a SC fiber optic connector into the TX/RX ports on the adapter bracket.
Intel® Ethernet 10 Gigabit fiber adapters with LC connector: Remove and save the fiber optic connector cover. Insert an LC connector into the adapter. Conversion cables to other connector types (such as SC) may be used if the cabling matches the optical specifications of the adapter, including length limitations.
Intel® Ethernet 10 Gigabit CX4 adapters: Physical cabling must meet IEEE Std 802.3ak, Clause 54 specifications. The required cable connector is an MDI latch-type receptacle, as defined by IEC 61076-3-113.
Start your computer and follow the driver installation instructions below.
|
|
NOTES:
|
The adapter is detected as new hardware when Windows starts. To install the correct driver:
The adapter is detected and Windows either installs a Windows resident driver or starts the Found New Hardware wizard.
If the wizard starts, follow the prompts to install the driver from the CD in this package.
If a Windows resident driver installs (wizard does not appear), update the driver by inserting the Intel CD and clicking the Install Drivers and Software button when the Intel Network Connections autorun window appears.
To build a binary RPM* package of this driver, run 'rpmbuild -tb <filename.tar.gz>'. Replace <filename.tar.gz> with the specific file name of the driver.
|
|
NOTE: For the build to work properly, the currently running kernel
MUST match the version and configuration of the installed kernel sources. If you have just
recompiled the kernel reboot the system now. RPM functionality has only been tested in Red Hat distributions. |
Move the base driver tar file to the directory of your
choice. For example, use '/home/username/ixgb' or '/usr/local/src/ixgb'.
Untar/unzip the archive, where <x.x.x> is the version number for the driver tar:
tar zxf ixgb-<x.x.x>.tar.gz
Change to the driver src directory, where <x.x.x> is the version number for the driver tar:
cd ixgb-<x.x.x>/src/
Compile the driver module:
make install
The binary will be installed as:
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
The install locations listed above are the default locations. They might not be correct for certain Linux distributions.
Install the module:
insmod ixgb <parameter>=<value>
Assign an IP address to the interface by entering the following, where <x> is the interface number:
ifconfig eth<x> <IP_address>
Verify that the interface works. Enter the following, where <IP_address> is the IP address of another machine on the same subnet as the interface that is being tested:
ping <IP_address>
This driver has been developed for use with FreeBSD kernel, versions 4.8 and later.
|
|
NOTE: You must have kernel sources installed in order to compile the driver module. |
In the instructions below, x.x.x is the driver version as indicated in the name of the driver tar file.
Move the base driver tar file to the directory of your choice. For
example, use /home/username/ixgb or
/usr/local/src/ixgb.
Untar/unzip the archive:
tar xfz ixgb-x.x.x.tar.gz
This will create an ixgb-x.x.x directory.
To install man page:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
To load the driver onto a running system, perform the following steps:
cd ixgb-x.x.x
make
OR
cd ixgb-x.x.x/src
make load
To assign an IP address to the interface, enter the following:
ifconfig ixgb<interface_num>
<IP_address>
Verify that the interface works. Enter the following, where <IP_address>
is the IP address for another machine on the same subnet as the interface
that is being tested:
ping <IP_address>
If you want the driver to load automatically when the system is booted:
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Edit /boot/loader.conf, and add the following line:
if_ixgb_load="YES"
OR
compile the driver into the kernel (see item 8).
Edit /etc/rc.conf, and create the appropriate
ifconfig_ixgb<interface_num>
entry:
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
Example usage:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
NOTE: For assistance, see the ifconfig man page.
If you want to compile the driver into the kernel, enter:
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Edit the /usr/src/sys/conf/files.i386 file, and add the following line:
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Remove the following lines from the /usr/src/sys/conf/files.i386 file, if
they exist:
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Edit the kernel configuration file (i.e., GENERIC or MYKERNEL) in
/usr/src/sys/i386/conf, and ensure the following line is present:
device ixgb
Compile and install the kernel. The system must be reboot for the kernel
updates to take affect.
For additional information on compiling the kernel, consult the FreeBSD operating system documentation.
For more information, see the User's Guide on the Intel CD or Intel support web site: http://support.intel.com.
Last modified on 10/11/07 3:49p Revision
Copyright © 2002 - 2012 Intel Corporation. All rights reserved.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel Corporation assumes no responsibility for errors or omissions in this document. Nor does Intel make any commitment to update the information contained herein.
Intel, Itanium, and Pentium are trademarks of Intel Corporation in the U.S. and other countries.
*Other names and brands may be claimed as the property of others.
Last modified on 1/25/11 10:21p Revision
PROXGB/DOCS/QUICK/ENU/license.htm 0000755 0000000 0000000 00000035273 11654245266 013164 0 ustar
INTEL SOFTWARE LICENSE AGREEMENT
IMPORTANT - READ BEFORE COPYING, INSTALLING OR USING.
Do not copy, install, or use this software and any associated materials (collectively, the “Software”) provided under this license agreement (“Agreement”) until you have carefully read the following terms and conditions.
By copying, installing, or otherwise using the Software, you agree to be bound by the terms of this Agreement. If you do not agree to the terms of this Agreement, do not copy, install, or use the Software.
Please Note:
SITE LICENSE: You may copy the Software onto your organization’s computers for your organization’s use, and you may make a reasonable number of back-up copies of the Software, subject to these conditions:
SINGLE USER LICENSE: You may copy the Software onto a single computer for your personal use, and you may make one back-up copy of the Software, subject to these conditions:
OEM LICENSE: You may reproduce and distribute the Software only as an integral part of or incorporated in your product, as a standalone Software maintenance update for existing end users of your products, excluding any other standalone products, or as a component of a larger Software distribution, including but not limited to the distribution of an installation image or a Guest Virtual Machine image, subject to these conditions:
LICENSE RESTRICTIONS. You may NOT: (i) use or copy the Materials except as provided in this Agreement; (ii) rent or lease the Materials to any third party; (iii) assign this Agreement or transfer the Materials without the express written consent of Intel; (iv) modify, adapt, or translate the Materials in whole or in part except as provided in this Agreement; (v) reverse engineer, decompile, or disassemble the Materials; (vi) attempt to modify or tamper with the normal function of a license manager that regulates usage of the Materials; (vii) distribute, sublicense or transfer the Source Code form of any components of the Materials, Redistributables and Sample Source and derivatives thereof to any third party except as provided in this Agreement.
NO OTHER RIGHTS. No rights or licenses are granted by Intel to you, expressly or by implication, with respect to any proprietary information or patent, copyright, mask work, trademark, trade secret, or other intellectual property right owned or controlled by Intel, except as expressly provided in this Agreement. Except as expressly provided herein, no license or right is granted to you directly or by implication, inducement, estoppel, or otherwise. Specifically, Intel grants no express or implied right to you under Intel patents, copyrights, trademarks, or other intellectual property rights.
OWNERSHIP OF SOFTWARE AND COPYRIGHTS. The Software is licensed, not sold. Title to all copies of the Software remains with Intel. The Software is copyrighted and protected by the laws of the United States and other countries and international treaty provisions. You may not remove any copyright notices from the Software. You agree to prevent any unauthorized copying of the Software. Intel may make changes to the Software, or to items referenced therein, at any time without notice, but is not obligated to support or update the Software. You may transfer the Software only if the recipient agrees to be fully bound by these terms and if you retain no copies of the Software.
ADDITIONAL TERMS FOR PRE-RELEASE SOFTWARE. If the Software you are installing or using under this Agreement is pre-commercial release or is labeled or otherwise represented as “alpha-“ or “beta-“ versions of the Software ("pre-release Software"), then the following terms apply.
To the extent that any provision in this Section conflicts with any other term(s) or condition(s) in this Agreement with respect to pre-release Software, this Section shall supersede the other term(s) or condition(s), but only to the extent necessary to resolve the conflict.
You understand and acknowledge that the Software is pre-release Software, does not represent the final Software from Intel, and may contain errors and other problems that could cause data loss, system failures, or other errors.
The pre-release Software is provided to you "as-is" and Intel disclaims any warranty or liability to you for any damages that arise out of the use of the pre-release Software.
You acknowledge that Intel has not promised that pre-release Software will be released in the future, that Intel has no express or implied obligation to you to release the pre-release Software and that Intel may not introduce Software that is compatible with the pre-release Software. You acknowledge that the entirety of any research or development you perform that is related to the pre-release Software or to any product making use of or associated with the pre-release Software is done at your own risk.
If Intel has provided you with pre-release Software pursuant to a separate written agreement, your use of the pre-release Software is also governed by such agreement.
LIMITED MEDIA WARRANTY. If the Software has been delivered by Intel on physical media, Intel warrants the media to be free from material physical defects for a period of ninety days after delivery by Intel. If such a defect is found, return the media to Intel for replacement or alternate delivery of the Software as Intel may select.
EXCLUSION OF OTHER WARRANTIES. EXCEPT AS PROVIDED ABOVE, THE SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. Intel does not warrant or assume responsibility for the accuracy or completeness of any information, text, graphics, links, or other items contained within the Software.
LIMITATION OF LIABILITY. IN NO EVENT SHALL INTEL OR ITS SUPPLIERS BE LIABLE FOR ANY DAMAGES WHATSOEVER (INCLUDING, WITHOUT LIMITATION, LOST PROFITS, BUSINESS INTERRUPTION, OR LOST INFORMATION) ARISING OUT OF THE USE OF OR INABILITY TO USE THE SOFTWARE, EVEN IF INTEL HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. SOME JURISDICTIONS PROHIBIT EXCLUSION OR LIMITATION OF LIABILITY FOR IMPLIED WARRANTIES OR CONSEQUENTIAL OR INCIDENTAL DAMAGES, SO THE ABOVE LIMITATION MAY NOT APPLY TO YOU. YOU MAY ALSO HAVE OTHER LEGAL RIGHTS THAT VARY FROM JURISDICTION TO JURISDICTION. In the event that you use the Software in conjunction with a virtual (“emulated”) device designed to appear as an Intel component product, you acknowledge that Intel is neither the author nor the creator of the virtual (“emulated”) device. You understand and acknowledge that Intel makes no representations about the correct operation of the Software when used with a virtual (“emulated”) device, that Intel did not design the Software to operate in conjunction with the virtual (“emulated”) device, and that the Software may not be capable of correct operation in conjunction with the virtual (“emulated”) device. You agree to assume the risk that the Software may not operate properly in conjunction with the virtual (“emulated”) device. You agree to indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with the use of the Software in conjunction with the virtual (“emulated”) device, even if such claim alleges that Intel was negligent regarding the design or manufacture of the Software.
UNAUTHORIZED USE. THE SOFTWARE IS NOT DESIGNED, INTENDED, OR AUTHORIZED FOR USE IN ANY TYPE OF SYSTEM OR APPLICATION IN WHICH THE FAILURE OF THE SOFTWARE COULD CREATE A SITUATION WHERE PERSONAL INJURY OR DEATH MAY OCCUR (E.G MEDICAL SYSTEMS, LIFE SUSTAINING OR LIFE SAVING SYSTEMS). If you use the Software for any such unintended or unauthorized use, you shall indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with such unintended or unauthorized use, even if such claim alleges that Intel was negligent regarding the design or manufacture of the part.
TERMINATION OF THIS AGREEMENT. Intel may terminate this Agreement at any time if you violate its terms. Upon termination, you will immediately destroy the Software or return all copies of the Software to Intel.
APPLICABLE LAWS. Claims arising under this Agreement shall be governed by the laws of the State of California, without regard to principles of conflict of laws. You agree that the terms of the United Nations Convention on Contracts for the Sale of Goods do not apply to this Agreement. You may not export the Software in violation of applicable export laws and regulations. Intel is not obligated under any other agreements unless they are in writing and signed by an authorized representative of Intel.
GOVERNMENT RESTRICTED RIGHTS. The enclosed Software and documentation were developed at private expense, and are provided with “RESTRICTED RIGHTS.” Use, duplication, or disclosure by the Government is subject to restrictions as set forth in FAR 52.227-14 and DFARS 252.227-7013 et seq. or its successor. The use of this product by the Government constitutes acknowledgement of Intel’s proprietary rights in the Software. Contractor or Manufacturer is Intel.
LANGUAGE; TRANSLATIONS. In the event that the English language version of this Agreement is accompanied by any other version translated into any other language, such translated version is provided for convenience purposes only and the English language version shall control.
Last modified on 5/15/11 10:56p Revision
Intel warrants to the original owner that the adapter product delivered in this package will be free from defects in material and workmanship. This warranty does not cover the adapter product if it is damaged in the process of being installed or improperly used.
THE ABOVE WARRANTY IS IN LIEU OF ANY OTHER WARRANTY, WHETHER EXPRESS, IMPLIED OR STATUTORY, INCLUDING BUT NOT LIMITED TO ANY WARRANTY OF NONINFRINGEMENT OF INTELLECTUAL PROPERTY, MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE ARISING OUT OF ANY PROPOSAL, SPECIFICATION, OR SAMPLE.
This warranty does not cover replacement of adapter products damaged by abuse, accident, misuse, neglect, alteration, repair, disaster, improper installation, or improper testing. If the adapter product is found to be defective, Intel, at its option, will replace or repair the hardware product at no charge except as set forth below, or refund your purchase price provided that you deliver the adapter product along with a Return Material Authorization (RMA) number (see below), along with proof of purchase (if not registered), either to the dealer from whom you purchased it or to Intel with an explanation of any deficiency. If you ship the adapter product, you must assume the risk of damage or loss in transit. You must use the original container (or the equivalent) and pay the shipping charge.
Intel may replace or repair the adapter product with either new or reconditioned parts, and any adapter product, or part thereof replaced by Intel becomes Intel's property. Repaired or replaced adapter products will be returned to you at the same revision level as received or higher, at Intel's option. Intel reserves the right to replace discontinued adapter products with an equivalent current generation adapter product.
Before returning any adapter product, contact Intel Customer Support and obtain a Return Material Authorization (RMA) number by calling +1 916-377-7000.
If the Customer Support Group verifies that the adapter product is defective, they will have the RMA department issue you an RMA number to place on the outer package of the adapter product. Intel cannot accept any product without an RMA number on the package.
Return the adapter product to the place of purchase for a refund or replacement.
Intel wants you to be completely satisfied with the Intel adapter product that you have purchased. Any time within ninety (90) days of purchase, you may return your Intel adapter to the original place of purchase for a full refund of the purchase price from your dealer. Resellers and distributors, respectively, accepting returns and refunding money back to their customers may return Intel adapters to their original place of purchase. Intel guarantees that it will accept returns under this policy and refund the original purchase price to customers purchasing directly from Intel.
INTEL'S SOLE LIABILITY HEREUNDER SHALL BE LIMITED TO DIRECT, OBJECTIVELY MEASURABLE DAMAGES. IN NO EVENT SHALL INTEL HAVE ANY LIABILITY FOR ANY INDIRECT OR SPECULATIVE DAMAGES (INCLUDING, WITHOUT LIMITING THE FOREGOING, CONSEQUENTIAL, INCIDENTAL, AND SPECIAL DAMAGES) INCLUDING, BUT NOT LIMITED TO, INFRINGEMENT OF INTELLECTUAL PROPERTY, REPROCUREMENT COSTS, LOSS OF USE, BUSINESS INTERRUPTIONS, LOSS OF GOODWILL, AND LOSS OF PROFITS, WHETHER ANY SUCH DAMAGES ARISE OUT OF CONTRACT NEGLIGENCE, TORT, OR UNDER ANY WARRANTY, IRRESPECTIVE OF WHETHER INTEL HAS ADVANCE NOTICE OF THE POSSIBILITY OF ANY SUCH DAMAGES. NOTWITHSTANDING THE FOREGOING, INTEL'S TOTAL LIABILITY FOR ALL CLAIMS UNDER THIS AGREEMENT SHALL NOT EXCEED THE PRICE PAID FOR THE PRODUCT. THESE LIMITATIONS ON POTENTIAL LIABILITIES WERE AN ESSENTIAL ELEMENT IN SETTING THE PRODUCT PRICE. INTEL NEITHER ASSUMES NOR AUTHORIZES ANYONE TO ASSUME FOR IT ANY OTHER LIABILITIES.
Some states do not allow the exclusion or limitation of incidental or consequential damages, so the above limitations may not apply to you.
Critical Control Applications: Intel specifically disclaims liability for use of the adapter product in critical control applications (including, for example only, safety or health care control systems, nuclear energy control systems, or air or ground traffic control systems) by Licensee or Sublicensees, and such use is entirely at the user's risk. Licensee agrees to defend, indemnify, and hold Intel harmless from and against any and all claims arising out of use of the adapter product in such applications by Licensee or Sublicensees.
Software: Software provided with the adapter product is not covered under the hardware warranty described above. See the applicable software license agreement which shipped with the adapter product for details on any software warranty.
Last modified on 7/23/02 10:42a Revision
Apague su PC y desconecte el cable de energa. Si va a realizar una instalacin de "conexin en funcionamiento", consulte primero la documentacin de su servidor.
Quite la cubierta del sistema y la cubierta de la ranura del adaptador en la ranura que corresponde al adaptador. Puede utilizar una ranura ms larga que el conector del adaptador sin problemas, pero no intente realizar la instalacin en una ranura ms corta que el conector PCI Express.
Coloque de manera segura el adaptador en la ranura y asegure el soporte.
Vuelva a colocar la cubierta de su PC. Conecte el cable de energa.
Adaptadores de Ethernet Intel® de 10 Gigabits de cobre: Utilice cables Ethernet de Categora 6, Categora 6a o Categora 7.
Adaptador de Ethernet Intel® de 10 Gigabits con ptica acoplable SFP+: Instale el mdulo y conecte el cable segn las instrucciones del fabricante del mdulo
Adaptadores de Ethernet Intel® de 10 Gigabits de fibra con conector SC: Retire y guarde la cubierta del conector de fibra ptica. Introduzca un conector de fibra ptica SC en los puertos transmisin/recepcin del soporte del adaptador.
Adaptadores de Ethernet Intel® de 10 Gigabits de fibra con conector LC: Retire y guarde la cubierta del conector de fibra ptica. Inserte un conector LC en el adaptador. Puede utilizar cables de conversin a otros tipos de conector (como SC) si el cableado se ajusta a las especificaciones pticas del adaptador, incluyendo las limitaciones de longitud.
Adaptadores CX4 de Ethernet Intel® de 10 Gigabits: Las caractersticas fsicas del cable deben satisfacer las especificaciones IEEE Std 802.3ak, clusula 54. El conector de cable requerido es un receptculo tipo cierre MDI, tal como lo define IEC 61076-3-113.
Inicie su PC y siga las instrucciones de instalacin de los controladores que se ofrecen a continuacin.
|
|
NOTAS:
|
El adaptador se detecta como hardware nuevo cuando Windows se inicia. Para instalar el controlador correcto:
El adaptador se detecta y Windows instala un controlador residente de Windows o inicia el asistente Nuevo hardware encontrado .
Si se inicia el asistente, siga las indicaciones para instalar el controlador desde el CD que se suministra.
Si se instala un controlador residente de Windows (no aparece el asistente), inserte el CD de Intel y haga clic en el botn Instalar los controladores y el software para actualizar el controlador cuando la ventana de ejecucin automtica Conexiones de red Intel aparece.
Para compilar un paquete RPM* binario de este controlador, ejecute 'rpmbuild -tb <nombre_de_archivo.tar.gz>'. Sustituya <nombrearchivo.tar.gz> por el nombre de archivo especfico del controlador.
|
|
NOTA: Para que la creacin funcione correctamente, el kernel en ejecucin DEBE coincidir con la versin y configuracin de las fuentes instaladas del kernel. Si acaba de recompilar el kernel, reinicie el sistema. El funcionamiento de RPM slo se ha probado con las distribuciones Red Hat. |
Mueva el archivo con la extensin tar del controlador base al directorio que seleccione. Por ejemplo, utilice '/home/username/ixgb' o '/usr/local/src/ixgb'.
Para descomprimir el archivo, escriba lo siguiente, donde <x.x.x> es el nmero de versin del archivo tar del controlador:
tar zxf ixgb-<x.x.x>.tar.gz
Vaya al directorio src del controlador. donde <x.x.x> es el nmero de versin del archivo tar del controlador:
cd ixgb-<x.x.x>/src/
Compile el mdulo del controlador:
make install
El binario se instalar como:
/lib/modules/[VERSION_DEL_KERNEL]/kernel/drivers/net/ixgb.o
Las ubicaciones de instalacin descritas anteriormente son las predeterminadas, y es posible que no sean correctas para determinadas distribuciones de Linux.
Instale el mdulo:
insmod ixgb <parmetro>=<valor>
Asigne una direccin IP a la interfaz. Para ello, escriba lo siguiente, donde <x> es el nmero de interfaz:
ifconfig eth<x> <direccin_IP>
Compruebe que funcione la interfaz. Introduzca lo siguiente, donde <direccin_IP> es la direccin IP de otra mquina situada en la misma subred que la interfaz que se est probando:
ping <direccin_IP>
Este controlador ha sido desarrollado para utilizarse con las versiones 4.8 y posteriores del kernel FreeBSD.
|
|
NOTA: Debe contar con los recursos de kernel ya instalados para poder compilar el mdulo de controlador. |
En las instrucciones a continuacin, x.x.x es la versin del controlador segn se indica en el nombre del archivo tar del controlador.
Mueva el archivo con la extensin tar del controlador base al directorio que seleccione. Por ejemplo, utilice /home/username/ixgb o
/usr/local/src/ixgb.
Descomprima el archivo tar o zip:
tar xfz ixgb-x.x.x.tar.gz
Esto crear un directorio ixgb-x.x.x.
Para instalar una pgina man:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Para cargar el controlador en un sistema en ejecucin, realice los pasos siguientes:
cd ixgb-x.x.x
make
O BIEN
cd ixgb-x.x.x/src
make load
Para asignar una direccin IP a la interfaz, escriba lo siguiente:
ifconfig ixgb<nm_interfaz>
<direccin_IP>
Compruebe que funcione la interfaz. Introduzca lo siguiente, donde <direccin_IP> es la direccin IP de otra mquina situada en la misma subred que la interfaz que se est probando:
ping <direccin_IP>
Si desea que el controlador se cargue automticamente cuando se inicie el sistema:
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Modifique /boot/loader.conf, y agregue la siguiente lnea:
if_ixgb_load="YES"
O BIEN
compile el controlador en el kernel (consulte el punto 8).
Edite /etc/rc.conf y cree la entrada
ifconfig_ixgb<nm_interfaz>
correspondiente:
ifconfig_ixgb<nm_interfaz>="<configuracin_ifconfig>"
Ejemplo de uso:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
NOTA: Para obtener ayuda, consulte la pgina man de ifconfig.
Si desea compilar el controlador en el kernel, teclee:
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Edite el archivo /usr/src/sys/conf/files.i386 y aada la lnea siguiente:
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Elimine las lneas siguientes del archivo /usr/src/sys/conf/files.i386, si
existen:
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Edite el archivo de configuracin de kernel (o sea, GENERIC o MYKERNEL) en
/usr/src/sys/i386/conf, y compruebe que existe la lnea siguiente:
device ixgb
Compile e instale el kernel. Debe reiniciarse el sistema para que tengan efecto las actualizaciones del kernel.
Para obtener informacin adicional acerca de cmo compilar el kernel, consulte la documentacin del sistema operativo FreeBSD.
Para obtener ms informacin, consulte la Gua de usuario en el CD de Intel o el sitio web de asistencia de Intel: http://www.intel.com/p/es_XL/support/.
ltima modificacin: 1-10-07 15:49 Revisin
Copyright © 2002 - 2012 Intel Corporation. Reservados todos los derechos.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 EE.UU.
Intel Corporation no asume ninguna responsabilidad por los errores y omisiones en esta gua. Del mismo modo, Intel no se compromete de ninguna forma a actualizar la informacin aqu contenida.
Intel, Itanium y Pentium son marcas comerciales de Intel Corporation en los EE.UU. y en otros pases.
* Otros nombres y marcas pueden ser reclamados como propiedad de terceras partes.
ltima modificacin a fecha de 25-1-11 22:21 Revisin 26
PROXGB/DOCS/QUICK/ESN/license.htm 0000755 0000000 0000000 00000040167 11730046352 013146 0 ustar
CONTRATO DE LICENCIA DE SOFTWARE DE INTEL
IMPORTANTE: LASE ANTES DE COPIAR, INSTALAR O UTILIZAR.
No copie, instale ni utilice este software y cualquier material asociado (colectivamente, el “Software”) proporcionado con este contrato de licencia (“Contrato”) hasta que haya ledo atentamente los siguientes trminos y condiciones.
Al copiar, instalar o utilizar el Software de otro modo, acepta que estar sujeto por los trminos de este Contrato. Si no est de acuerdo con los trminos de este Contrato, no copie, instale ni utilice el Software.
Tenga en cuenta que:
LICENCIA DE SITIO: Puede copiar el Software en los sistemas de su organizacin para el uso de sta, y podr efectuar un nmero prudente de copias de seguridad del Software, sujeto a las siguientes condiciones:
LICENCIA DE USUARIO NICO: Puede copiar el Software en un nico sistema para su uso personal, no comercial, y realizar una copia de seguridad del Software con estas condiciones:
LICENCIA DE OEM: Solo puede reproducir y distribuir el Software como parte integral de, o incorporado en su producto, como actualizacin independiente de mantenimiento del Software para usuarios finales existentes de sus productos, excluidos otros productos independientes, o como componente de una distribucin de Software mayor, incluyendo, aunque sin limitarse a ella, la distribucin de una imagen de instalacin o una imagen de mquina virtual invitada, con estas condiciones:
RESTRICCIONES DE LA LICENCIA. Usted NO podr: (i) utilizar o copiar los Materiales excepto como se indica en este Contrato; (ii) alquilar o proporcionar en "leasing" los Materiales a terceros; (iii) asignar este Contrato o transferir los Materiales sin el consentimiento expreso por escrito de Intel; (iv) modificar, adaptar o traducir los Materiales en su totalidad o en parte, excepto segn lo previsto en este Contrato; (v) aplicar ingeniera inversa, descompilar o desensamblar los Materiales; (vi) intentar modificar o alterar el funcionamiento normal de un gestor de licencias que regule el uso de los Materiales; (vii) distribuir, sublicenciar o transferir el formato de Cdigo fuente de cualquier componente de los Materiales, Redistribuibles y Cdigo fuente de ejemplo y sus derivados a terceros excepto segn lo previsto en este Contrato.
NO EXISTEN OTROS DERECHOS. Intel no le concede otros derechos o licencias, de manera expresa o implcita, con respecto a cualquier informacin de titularidad o patente, copyright, topografa de circuito integrado, marca comercial, secretos comerciales, u otros derechos de titularidad de propiedad intelectual o controlados por Intel, a excepcin de lo que se establece expresamente en este Contrato. Salvo lo previsto expresamente en este documento, no se le concede ninguna licencia o derecho, de manera directa o implcita, incentivo, impedimento legal o de otra manera. Especficamente, Intel no le concede ningn derecho expreso o implcito bajo patentes, copyrights, marcas comerciales u otros derechos de propiedad intelectual de Intel.
PROPIEDAD DEL MATERIAL Y LOS "COPYRIGHTS". El Software se otorga con licencia, no se vende. Intel mantiene el ttulo de propiedad de todas las copias del Software. El Software dispone de sus correspondientes derechos de autor, y est amparado por la legislacin estadounidense y de otros pases, as como por disposiciones de tratados internacionales. No est permitido eliminar del Software ninguna nota sobre los derechos de autor. Acepta evitar cualquier copia no autorizada del Software. Intel puede introducir modificaciones en el Software, o en elementos a los que se hace referencia en el mismo, en cualquier momento y sin previo aviso, sin tener obligacin de prestar asistencia tcnica o actualizar el Software. Slo podr transferir el Software si el receptor acepta por completo estos trminos y usted no retiene copia alguna del mismo.
TRMINOS ADICIONALES PARA SOFTWARE PREVIO A LA VERSIN. Si el Software que est instalando o utilizando bajo este Contrato es una versin previa a la comercializacin, o est etiquetada o representada de otra manera como versiones “alfa“ o “beta“ del Software ("Software previo a la versin"), se aplican los trminos siguientes.
Hasta el extremo que cualquier disposicin de esta Seccin est en conflicto con otro(s) trmino(s) o condicin(es) de este Contrato respecto al Software previo a la versin, esta Seccin prevalecer sobre otro(s) trmino(s) o condicin(es), pero slo hasta el extremo necesario para resolver el conflicto.
Entiende y reconoce que el Software es Software previo a la versin, no representa el Software final de Intel, y puede contener errores y otros problemas que podran causar la prdida de datos, fallos del sistema u otros errores. El Software previo a la versin se proporciona "como est" e Intel rechaza toda garanta o responsabilidad hacia usted por cualquier dao causado por el uso del Software previo a la versin.
Reconoce que Intel no ha prometido que el Software previo a la versin se comercializar en el futuro, que Intel no tiene ninguna obligacin expresa o implcita hacia usted de comercializar el Software previo a la versin y que Intel puede presentar Software que no sea compatible con el Software previo a la versin. Reconoce que la totalidad de cualquier investigacin o desarrollo relacionado con el Software previo a la versin o con cualquier producto que utilice o est asociado con el Software previo a la versin se realizar por su cuenta y riesgo.
Si Intel le ha proporcionado Software previo a la versin segn los trminos de un contrato escrito por separado, su uso del Software previo a la versin tambin est regido por dicho contrato.
GARANTA LIMITADA DEL MEDIO. Si Intel ha entregado el software en soporte fsico, garantiza que dicho soporte est libre de defectos fsicos de material durante un perodo de noventa das tras la entrega. Si encuentra algn defecto semejante, devuelva el soporte a Intel para reemplazarlo o para que Intel le entregue el Software de otro modo, a discrecin de Intel.
EXCLUSIN DE OTRAS GARANTAS. EXCEPTO LO YA DISPUESTO, SE PROPORCIONA EL SOFTWARE EN EL ESTADO QUE SE ENCUENTRA Y SIN GARANTAS EXPRESAS O IMPLCITAS DE NINGN TIPO, ENTRE OTRAS, GARANTAS DE COMERCIABILIDAD, AUSENCIA DE VIOLACIONES O IDONEIDAD PARA UN FIN DETERMINADO. Intel no garantiza ni asume responsabilidad en cuanto a la exactitud o integridad de cualquier informacin, texto, grficos, enlaces u otros elementos contenidos en el Software.
LIMITACIN DE RESPONSABILIDAD. INTEL Y SUS PROVEEDORES NO SERN RESPONSABLES EN NINGN CASO DE NINGUNA CLASE DE DAO (INCLUYENDO, PERO SIN LIMITARSE A ELLO, LA PRDIDA DE BENEFICIOS, LA INTERRUPCIN DE LA ACTIVIDAD COMERCIAL O LA PRDIDA DE INFORMACIN) DERIVADO DE LA UTILIZACIN O DE LA IMPOSIBILIDAD DE UTILIZAR EL SOFTWARE, INCLUSO EN EL CASO DE QUE INTEL HAYA TENIDO CONOCIMIENTO DE LA POSIBILIDAD DE DICHO DAO. EN CIERTAS JURISDICCIONES SE PROHBE LA EXCLUSIN O LIMITACIN DE RESPONSABILIDAD RESPECTO A GARANTAS IMPLCITAS O DAOS INDIRECTOS O CASUALES, POR LO QUE LAS LIMITACIONES MENCIONADAS PUEDEN NO SER APLICABLES EN SU CASO. ASIMISMO, ES POSIBLE QUE TENGA OTROS DERECHOS LEGALES QUE VAREN DE UNA JURISDICCIN A OTRA. En caso de que utilice el Software junto con un dispositivo virtual (“emulado”) diseado para aparecer como un producto de componente de Intel, reconoce que Intel no es el autor ni el creador del dispositivo virtual (“emulado”). Entiende y reconoce que Intel no hace ninguna declaracin sobre el funcionamiento correcto del Software cuando se utiliza con un dispositivo virtual (“emulado”), que Intel no dise el Software para que funcione conjuntamente con el dispositivo virtual (“emulado”) y que el Software puede no ser capaz de corregir el funcionamiento conjuntamente con el dispositivo virtual (“emulado”). Acepta asumir el riesgo de que el Software no funcione de forma correcta conjuntamente con el dispositivo virtual (“emulado”). Acepta indemnizar y mantener a Intel, sus directores, subsidiarias y afiliados libres de toda responsabilidad contra cualquier demanda, costo, dao y gasto y honorarios razonables de abogados que surjan de, directa o indirectamente, cualquier reclamo por productos defectuosos, daos personales o muerte relacionadas con el uso no previsto o no autorizado del Software conjuntamente con el dispositivo virtual (“emulado”), incluso si dicha accin se basa en que Intel fue negligente con respecto al diseo o fabricacin del Software.
USO NO AUTORIZADO. EL SOFTWARE NO EST DISEADO, PREVISTO O AUTORIZADO PARA SU USO EN CUALQUIER TIPO DE SISTEMA O APLICACIN EN LA QUE UN FALLO DE SOFTWARE PODRA CREAR UNA SITUACIN DONDE SE PRODUJERAN LESIONES PERSONALES O LA MUERTE (POR EJEMPLO, SISTEMAS MDICOS, DE SOPORTE VITAL O PARA SALVAR VIDAS). Si utiliza el Software para cualquier uso no previsto o no autorizado, deber indemnizar y considerar sin responsabilidad a Intel y sus directores, subsidiarias y afiliados contra cualquier demanda, costo, dao y gasto y honorarios razonables de abogados que surjan de, directa o indirectamente, cualquier reclamo por productos defectuosos, daos personales o muerte relacionadas con dicho uso no previsto o no autorizado, incluso si dicha accin se basa en que Intel fue negligente con respecto al diseo o fabricacin del componente.
RESCISIN DE ESTE CONTRATO. Si infringe los trminos de este Contrato, Intel puede rescindirlo en cualquier momento. Tras la rescisin, usted deber destruir inmediatamente el Software o devolver a Intel todas las copias del mismo.
LEGISLACIN APLICABLE. Las reclamaciones que surjan bajo este Contrato estarn regidas por las leyes del estado de California, independientemente de los principios de conflicto de leyes. Acepta que los trminos de la Convencin sobre contratos para la venta internacional de bienes de las Naciones Unidas no se aplican a este Contrato. Se prohbe exportar el Software si dicho acto violara cualquier ley o reglamento aplicable sobre exportaciones. Intel no est obligada por ningn otro contrato, a menos que ste se haya realizado por escrito y est firmado por un representante autorizado de Intel.
DERECHOS RESTRINGIDOS DEL ESTADO. El Software y la documentacin incluidos se desarrollaron a cargo de una iniciativa privada y se proporcionan con “DERECHOS LIMITADOS”. Su uso, reproduccin o divulgacin por el Gobierno est sujeto a las restricciones establecidas en FAR 52.227-14 y DFAR 252.227-7013 y siguientes o sus sucesoras. El uso de este producto por parte del Gobierno constituye el reconocimiento de los derechos de titularidad de Intel sobre el mismo. El contratista o fabricante es Intel.
IDIOMA; TRADUCCIONES. En el caso de que la versin en ingls de este Contrato est acompaada por cualquier otra versin traducida a otro idioma, dicha versin traducida slo se ofrece a ttulo informativo y prevalecer la versin en ingls.
ltima actualizacin 15/05/11 10:56p Revisin
Intel garantiza al propietario original que el producto de adaptador proporcionado en este paquete no tendr defectos en el material o en la manufactura. Esta garanta no cubre el producto de adaptador si ste se daa durante el proceso de instalacin o si se utiliza de forma indebida.
LA GARANTA ANTERIOR TOMA EL LUGAR DE CUALQUIER OTRA GARANTA, YA SEA EXPLCITA, IMPLCITA O ESTABLECIDA POR LA LEY, INCLUSO SIN LIMITACIN CUALQUIER GARANTA DE FALTA DE CUMPLIMIENTO DE PROPIEDAD INTELECTUAL, COMERCIABILIDAD O IDONEIDAD PARA UN PROPSITO PARTICULAR QUE SURGIESE DE CUALQUIER PROPUESTA, ESPECIFICACIN O MUESTRA.
Esta garanta no cubre el reemplazo de productos de adaptador daados por abuso, accidente, uso indebido, negligencia, alteracin, reparacin, desastre, instalacin incorrecta o prueba inapropiada. Si se determina que el producto de adaptador est defectuoso, Intel, a su propia discrecin, reemplazar o reparar el producto de hardware sin ningn cargo con excepcin de lo estipulado ms adelante, o bien, reembolsar el precio de compra siempre y cuando usted entregue el producto de adaptador junto con un nmero de Autorizacin de devolucin de material (RMA) (vase ms adelante) y junto con la prueba de compra (si no se ha registrado), ya sea al distribuidor a travs del cual lo adquiri o a Intel, con una explicacin de cualquier deficiencia. Si enva el producto de adaptador, usted asume el riesgo de dao o prdida durante el transporte. Usted debe utilizar el contenedor original (o su equivalente) y pagar por el cargo de transporte.
Intel puede reemplazar o reparar el producto de adaptador ya sea con piezas nuevas o reacondicionadas, y cualquier producto de adaptador o pieza del mismo que Intel reemplace se convierte en propiedad de Intel. Los productos de adaptador reparados o reemplazados se devolvern a usted con el mismo nivel de revisin que se recibi o uno ms alto, a la discrecin de Intel. Intel se reserva el derecho de reemplazar los productos de adaptador descontinuados con un producto de adaptador de una generacin actual equivalente
Antes de devolver cualquier producto de adaptador, comunquese con la Asistencia al cliente Intel y obtenga un nmero de Autorizacin de devolucin de material (RMA). Para ello, llame al +1 916-377-7000.
Si el grupo de asistencia al cliente verifica que el producto de adaptador est defectuoso, harn que el departamento de RMA emita un nmero RMA, el cual debe colocarse en la parte externa del paquete del producto de adaptador. Intel no aceptar ningn producto que no contenga un nmero RMA en el paquete.
Devuelva el producto de adaptador al punto de venta para obtener un reembolso o reemplazo.
Intel desea su total satisfaccin con el producto de adaptador Intel que ha comprado. En cualquier momento dentro de los noventa (90) das a partir de la compra, usted puede devolver el adaptador Intel al punto de venta original para obtener el reembolso total del precio de compra a travs del distribuidor. Los vendedores y distribuidores, respectivamente, que acepten devoluciones y reembolsen dinero a sus clientes pueden devolver los adaptadores Intel a sus puntos de venta originales. Intel garantiza que aceptar las devoluciones bajo esta poltica y que reembolsar el precio de compra original a los clientes que compren directamente a travs de Intel.
LA NICA RESPONSABILIDAD DE INTEL ESTIPULADA EN ESTE DOCUMENTO SE LIMITAR A LOS DAOS DIRECTOS QUE PUEDAN MEDIRSE DE FORMA OBJETIVA. BAJO NINGUNA CIRCUNSTANCIA INTEL TENDR NINGUNA RESPONSABILIDAD POR CUALQUIER DAO INDIRECTO O ESPECULATIVO (INCLUSO SIN LIMITACIN LOS DAOS PRECEDENTES, CONSIGUIENTES, FORTUITOS Y ESPECIALES) LO CUAL INCLUYE, SIN LIMITACIN, EL INCUMPLIMIENTO DE PROPIEDAD INTELECTUAL, LOS COSTOS DE READQUISICIN, LA PRDIDA DE USO, LAS INTERRUPCIONES COMERCIALES, LA PRDIDA DE REPUTACIN Y LA PRDIDA DE GANANCIAS, YA SEA QUE CUALQUIERA DE ESOS DAOS SURJAN POR NEGLIGENCIA CONTRACTUAL, RESPONSABILIDAD EXTRACONTRACTUAL O BAJO CUALQUIER GARANTA, INDEPENDIENTEMENTE DE SI INTEL RECIBE UN AVISO POR ANTICIPADO DE LA POSIBILIDAD DE CUALQUIERA DE ESTOS DAOS. A PESAR DE LO ANTERIORMENTE MENCIONADO, LA RESPONSABILIDAD TOTAL DE INTEL PARA CUALQUIER RECLAMO QUE SURJA BAJO ESTE CONTRATO NO EXCEDER EL PRECIO PAGADO POR EL PRODUCTO. ESTAS LIMITACIONES DE RESPONSABILIDADES POSIBLES CONSTITUYERON UN ELEMENTO ESENCIAL EN LA FIJACIN DEL PRECIO DEL PRODUCTO. INTEL NO ASUME NI AUTORIZA QUE NADIE ASUMA NINGUNA OTRA RESPONSABILIDAD EN SU NOMBRE.
Algunos estados no permiten la exclusin o limitacin de daos fortuitos o consiguientes, de modo que las limitaciones anteriores podran no aplicarse en su caso.
Aplicaciones de control crtico: Intel de forma especfica niega cualquier responsabilidad por el uso del producto de adaptador en aplicaciones de control crtico (incluso, solamente como ejemplo, los sistemas de control de atencin mdica, los sistemas de control de energa nuclear o los sistemas de control de trfico areo o terrestre) por los Titulares de licencia o los Titulares de sublicencia, y dicho uso se realiza bajo el riesgo total del usuario. El Titular de licencia acuerda defender, indemnizar y asumir responsabilidad ante Intel por cualquier reclamo que surgiese del uso del producto de adaptador en dichas aplicaciones del Titular de licencia o Titulares de sublicencia.
Software: El software proporcionado con el producto de adaptador no est cubierto bajo la garanta de hardware descrita anteriormente. Consulte el contrato de licencia de software correspondiente, el cual acompaa al producto del adaptador, para obtener detalles sobre la garanta de software.
ltima modificacin: 23-7-02 10:42 Revisin 6
Mettez l'ordinateur hors tension et dbranchez le cordon d'alimentation. En cas d'installation sans arrt du serveur, reportez-vous tout d'abord la documentation du serveur.
Retirez le panneau de l'ordinateur et le panneau du connecteur de carte correspondant votre carte. Vous pouvez utiliser sans inconvnient un emplacement plus long que le connecteur de la carte, mais n'essayez pas d'installer la carte dans un emplacement plus court que le connecteur PCI Express.
Enfoncez fermement la carte dans l'emplacement et fixez le support.
Remettez le panneau de l'ordinateur en place. Branchez le cordon d'alimentation.
Cartes 10 Gigabit Ethernet Intel® cuivre : Utilisez des cbles Ethernet de catgorie 6, 6a ou 7.
Carte 10 Gigabit Ethernet Intel® pour serveurs avec fibre optique enfichable SFP+ : Installez le module et branchez le cble conformment aux instructions du fabricant du module.
Cartes 10 Gigabit Ethernet Intel® fibre avec connecteur SC : Retirez le panneau du connecteur fibre optique et mettez-le de ct. Insrez un connecteur SC fibre optique dans les ports TX/RX du support de la carte.
Cartes 10 Gigabit Ethernet Intel® fibre avec connecteur LC : Retirez le panneau du connecteur fibre optique et mettez-le de ct. Insrez un connecteur LC dans la carte. Les cbles de conversion pour d'autres types de connecteur (p. ex., un connecteur SC) peuvent tre utiliss si le cblage est conforme aux spcifications optiques de la carte, y compris les limites de longueur.
Cartes 10 Gigabit Ethernet Intel® CX4 : Le cblage physique doit tre conforme aux spcifications IEEE Std 802.3ak, clause 54. Le connecteur de cble requis est un connecteur verrou MDI, tel que dfini par IEC 61076-3-113.
Dmarrez votre ordinateur et suivez les instructions d'installation des pilotes ci-dessous.
|
|
REMARQUES :
|
La carte est dtecte en tant que nouveau matriel lors de dmarrage de Windows. Pour installer le pilote correct :
La carte est dtecte et Windows installe un pilote rsidant sous Windows ou dmarre l'Assistant Nouveau matriel dtect .
Si l'assistant dmarre, suivez les invites pour installer le pilote depuis le CD fourni avec la carte.
Si un pilote rsidant sous Windows s'installe (l'assistant ne dmarre pas), mettez jour le pilote en insrant le CD Intel et en cliquant sur le bouton Installer les pilotes lorsque la fentre d'excution automatique de Connexions rseau Intel s'affiche.
Pour crer un paquage RPM* binaire de ce pilote, excutez "rpmbuild -tb <nom_de_fichier.tar.gz>". Remplacez <filename.tar.gz> par le nom de fichier spcifique du pilote.
|
|
REMARQUE : pour que la compilation fonctionne correctement, le noyau en cours d'excution DOIT correspondre la version et la configuration des sources de noyau installes. Si vous venez de recompiler le noyau, redmarrez l'ordinateur maintenant. La fonctionnalit RPM a t teste uniquement sur les distributions Red Hat. |
Placez le fichier tar du pilote de base dans le rpertoire de votre choix. Par exemple, utilisez "/home/username/ixgb" ou "/usr/local/src/ixgb".
Dballez/dcompressez l'archive en entrant la commande suivante, o <x.x.x> correspond au numro de version du paquetage du pilote :
tar zxf ixgb-<x.x.x>.tar.gz
Passez au rpertoire src du pilote en entrant la commande suivante, o <x.x.x> correspond au numro de version du paquetage du pilote :
cd ixgb-<x.x.x>/src/
Compilez le module du pilote :
make install
Les instructions binaires sont installes comme suit :
/lib/modules/[VERSION_NOYAU]/kernel/drivers/net/ixgb.o
Les emplacements d'installation rpertoris ci-dessus sont les emplacements par dfaut. Il se peut qu'ils ne soient pas corrects sur certaines distributions Linux.
Installez le module :
insmod ixgb <paramtre>=<valeur>
Affectez une adresse IP l'interface en entrant la commande suivante, o <x> correspond au numro d'interface :
ifconfig eth<x> <adresse_IP>
Vrifiez que l'interface fonctionne. Entrez ce qui suit, o <adresse_IP> est l'adresse IP d'un autre ordinateur du mme sous-rseau que l'interface soumis au test :
ping <adresse_IP>
Ce pilote a t dvelopp pour tre utilis avec le noyau FreeBSD, versions 4.8 et ultrieures.
|
|
REMARQUE : les sources du noyau doivent tre installes pour compiler le module du pilote. |
Dans les instructions ci-dessous, x.x.x est la version du pilote telle qu'indique dans le nom du fichier tar du pilote.
Placez le fichier tar du pilote de base dans le rpertoire de votre choix. Par exemple, utilisez /home/nom de l'utilisateur/ixgb ou
/usr/local/src/ixgb.
Dcompressez l'archive :
tar xfz ixgb-x.x.x.tar.gz
Cela cre un rpertoire ixgb-x.x.x.
Pour installer man page :
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Pour charger le pilote sur un ordinateur en marche, excutez les tapes suivantes :
cd ixgb-x.x.x
make
OU
cd ixgb-x.x.x/src
make load
Pour affecter une adresse IP l'interface, entrez ce qui suit :
ifconfig ixgb<num_interface>
<adresse_IP>
Vrifiez que l'interface fonctionne. Entrez ce qui suit, o <adresse_IP> est l'adresse IP d'un autre ordinateur du mme sous-rseau que l'interface soumis au test :
ping <adresse_IP>
Si vous voulez que le pilote se charge automatiquement lors de l'amorage de l'ordinateur :
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Modifiez le fichier /boot/loader.conf, puis ajoutez la ligne suivante :
if_ixgb_load="YES"
OU
compilez le pilote dans le noyau (voir la section 8).
Modifiez /etc/rc.conf et crez l'entre
ifconfig_ixgb<num_interface>
approprie :
ifconfig_ixgb<num_interface>="<paramtres_ifconfig>"
Exemple d'utilisation :
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
REMARQUE : pour obtenir de l'aide, voir ifconfig man page.
Si vous voulez compiler le pilote dans le noyau, entrez :
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Modifiez le fichier /usr/src/sys/conf/files.i386 et ajoutez la ligne suivante :
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Supprimez les lignes suivantes du fichier /usr/src/sys/conf/files.i386, si
elles existent :
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Modifiez le fichier de configuration du noyau ( savoir, GENERIC ou MYKERNEL) dans
/usr/src/sys/i386/conf et assurez-vous que la ligne suivante est prsente :
device ixgb
Compilez et installez le noyau. Le systme doit tre redmarr pour que les mises jour du noyau soient prises en compte.
Pour obtenir des informations complmentaires sur la compilation du noyau, consultez la documentation du systme d'exploitation FreeBSD.
Pour de plus amples informations, voir le Guide de l'utilisateur du CD Intel ou sur le site Web d'assistance Intel : http://www.intel.com/p/fr_FR/support/.
Dernire mise jour le 11/10/07 15h49 Rvision
Copyright © 2002 - 2012 Intel Corporation. Tous droits rservs.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OREGON 97124-6497 tats-Unis
Intel Corporation dcline toute responsabilit pour toute erreur ou omission dans ce document. Intel ne s'engage aucunement mettre jour les informations contenues dans ce document.
Intel, Itanium et Pentium sont des marques de commerce d'Intel Corporation aux tats-Unis et dans d'autres pays.
* Les autres marques et noms de produits sont des marques commerciales appartenant leurs propritaires respectifs.
Informations concernant la garantie
Dernire modification le 25/01/11 22h21 Rvision
PROXGB/DOCS/QUICK/FRA/license.htm 0000755 0000000 0000000 00000040536 11730046352 013131 0 ustar
CONTRAT DE LICENCE DU LOGICIEL INTEL
IMPORTANT - LIRE AVANT TOUTE TENTATIVE DE COPIE, D'INSTALLATION OU D'UTILISATION :
Ne copiez pas, n'installez pas et n'utilisez pas ce logiciel ni tout lment associ (appels collectivement le Logiciel ) fournis dans le cadre de ce contrat de licence ( Contrat ) tant que vous n'avez pas lu attentivement les conditions gnrales suivantes.
En copiant, installant ou autrement utilisant le Logiciel, vous acceptez d'tre li aux modalits de ce Contrat. Si vous n'acceptez pas les modalits de ce Contrat, ne copiez pas, n'installez pas et n'utilisez pas le Logiciel.
Veuillez noter :
LICENCE DE SITE. Vous pouvez copier le Logiciel sur les ordinateurs de votre organisation afin qu'il soit utilis dans le cadre des activits de l'organisation et vous pouvez sauvegarder un nombre raisonnable de copies du Logiciel, conformment ces conditions :
LICENCE UTILISATEUR UNIQUE. Vous pouvez copier le Logiciel sur un seul ordinateur pour une utilisation personnelle, et vous pouvez effectuer une copie de sauvegarde du Logiciel, conformment ces conditions :
LICENCE OEM. Vous pouvez reproduire et distribuer le Logiciel uniquement s'il fait partie intgrante ou est incorpor votre produit, comme une mise jour de maintenance de Logiciel autonome pour les utilisateurs existants de vos produits, l'exclusion de tout autre produit autonome, ou en tant que composant d'une distribution plus tendue du Logiciel, y compris, mais sans s'y limiter, la distribution d'une image d'installation ou d'une image d'Ordinateur Virtuel Invit, sous rserve de ces conditions :
RESTRICTIONS DE LA LICENCE. Vous ne pouvez PAS : (i) utiliser ou copier les lments sauf comme stipul dans ce Contrat ; (ii) louer ou offrir en location-bail les lments un tiers ; (iii) affecter ce Contrat ou transfrer les lments sans autorisation crite expresse d'Intel ; (iv) modifier, adapter ou traduire tout ou partie des lments sauf comme stipul dans ce Contrat ; (v) reconstituer la logique, dcompiler ou dsassembler les lments ; (vi) tenter de modifier ou d'altrer la fonction normale du gestionnaire de licence qui rgit l'utilisation des lments ; (vii) distribuer, offrir des sous-licences ou transfrer le Code source de tout composant des lments, des Redistribuables et de la source d'exemple et de produits drivs un tiers sauf comme stipul dans ce Contrat.
EXCLUSION DES AUTRES DROITS. Aucun droit ou licence ne vous est accord par Intel, de manire explicite ou implicite, en ce qui concerne toute information ou tout brevet propritaire, droit d'auteur, moyen de masquage, marque commerciale, secret industriel ou tout autre droit de proprit intellectuelle contrl par Intel, sauf stipulation contraire dcrite dans ce Contrat. Sauf comme stipul dans la prsente, aucune licence et aucun droit ne vous est accord, directement ou implicitement, de faon induite, par prclusion, ou autre. Spcifiquement, Intel ne vous accorde aucun droit expresse ou induit concernant les brevets, droits d'auteur, marques de commerce ou droits de proprit intellectuelle d'Intel.
PROPRIT DU LOGICIEL ET COPYRIGHT (DROITS D'AUTEUR). Le Logiciel est offert sous licence, il n'est pas vendu. Intel demeure propritaire de toutes les copies du Logiciel. Le logiciel est protg par les lois sur les droits d'auteur, les lois en vigueur aux tats-Unis et dans d'autres pays, ainsi que par les dispositions de traits internationaux. Vous n'tes pas autoris retirer la mention de copyright du Logiciel. Vous acceptez de prvenir toute copie non autorise du Logiciel. Intel peut modifier le Logiciel ou des lments rfrencs dans ce document, tout moment et sans pravis, mais n'est pas dans l'obligation de mettre jour le Logiciel ni d'offrir une assistance. Vous pouvez transfrer le Logiciel uniquement si le bnficiaire accepte d'tre li par ces modalits et si vous ne conservez aucune copie du Logiciel.
MODALITS COMPLMENTAIRES CONCERNANT LA VERSION PRLIMINAIRE DU LOGICIEL. Si le Logiciel que vous installez ou utilisez dans le cadre de ce Contrat est une version de prcommercialisation ou s'il est tiquet ou autrement reprsent comme une version alpha ou bta du Logiciel ( Logiciel prliminaire ), les modalits suivantes sont applicables.
Dans l'ventualit ou des clauses de cette Section entreraient en conflit avec d'autres modalits de ce Contrat concernant le Logiciel prliminaire, cette Section remplacerait les autres modalits, mais uniquement dans la mesure ncessaire la rsolution du conflit.
Vous comprenez et reconnaissez que le Logiciel est un Logiciel prliminaire, qu'il ne reprsente pas la version finale du Logiciel d'Intel, et qu'il peut contenir des erreurs et d'autres problmes pouvant entraner des pertes de donnes, des pannes de systme et d'autres erreurs. Le Logiciel prliminaire vous est fourni en l'tat et Intel n'met aucune garantie et rejette toute responsabilit votre gard concernant les dommages issus de l'utilisation du Logiciel prliminaire.
Vous reconnaissez qu'Intel n'a pas promis que le Logiciel prliminaire serait commercialis l'avenir, qu'Intel n'a aucune obligation expresse ou induite envers vous concernant la commercialisation du Logiciel prliminaire et qu'il est possible qu'Intel n'introduise pas de Logiciel compatible avec le Logiciel prliminaire. Vous reconnaissez que les efforts de recherche et de dveloppement que vous consentez concernant le Logiciel prliminaire ou tout produit utilisant ou associ au Logiciel prliminaire le sont vos propres risques.
Si Intel vous a fourni un Logiciel prliminaire dans le cadre d'un accord crit spar, votre utilisation du Logiciel prliminaire est galement rgie par l'accord en question.
GARANTIE LIMITE DU SUPPORT. Si le logiciel a t remis par Intel sur un support physique, Intel garantit que celui-ci est exempt de dfauts matriels pendant une priode de quatre-vingt-dix jours compter de la date de livraison par Intel. Si un tel dfaut est dtect, renvoyez le support Intel qui pourra choisir de le remplacer ou d'employer une autre mthode de livraison.
EXCLUSION DE TOUTE AUTRE GARANTIE. L'EXCEPTION DES CAS CI-DESSUS, LE LOGICIEL EST FOURNI EN L'TAT , SANS GARANTIE EXPRESSE OU IMPLICITE D'AUCUNE SORTE, NOTAMMENT TOUTE GARANTIE DE QUALIT MARCHANDE, D'ABSENCE DE CONTREFAON OU D'ADQUATION UN USAGE PARTICULIER. Intel ne garantit pas la prcision ni l'exhaustivit des informations, des textes, des graphiques, des liens ou d'autres lments contenus dans le Logiciel et ne peut en tre tenu responsable.
LIMITATION DE RESPONSABILIT. EN AUCUN CAS INTEL OU SES FOURNISSEURS NE POURRONT TRE TENUS POUR RESPONSABLES DE TOUT DOMMAGE, DE QUELQUE NATURE QUE CE SOIT (Y COMPRIS, MAIS DE MANIRE NON LIMITATIVE, TOUTE PERTE DE BNFICES, INTERRUPTION D'ACTIVIT OU PERTE D'INFORMATIONS), RSULTANT DE L'UTILISATION OU DE L'IMPOSSIBILIT D'UTILISER LE LOGICIEL, ET CE MME SI INTEL A T PRVENU DE L'VENTUALIT DE TELS DOMMAGES. CERTAINES JURIDICTIONS N'AUTORISENT PAS L'EXCLUSION OU LA LIMITATION DE RESPONSABILIT POUR LES GARANTIES IMPLICITES OU LES DOMMAGES INDIRECTS OU ACCESSOIRES, DE SORTE QUE LA LIMITATION CI-DESSUS PEUT NE PAS VOUS TRE APPLICABLE. VOUS POUVEZ GALEMENT DISPOSER D'AUTRES DROITS QUI VARIENT DE JURIDICTION EN JURIDICTION. Dans l'ventualit o vous utilisez le Logiciel conjointement avec un priphrique virtuel ( mul ) conu pour apparatre comme un composant Intel, vous reconnaissez qu'Intel n'est ni l'auteur ni le crateur du priphrique virtuel ( mul ). Vous comprenez et reconnaissez qu'Intel ne fait aucune reprsentation concernant le fonctionnement correct du Logiciel lorsqu'il est utilis avec un priphrique virtuel ( mul ), qu'Intel n'a pas conu le Logiciel pour qu'il fonctionne conjointement avec le priphrique virtuel ( mul ), et qu'il est possible que le Logiciel ne soit pas capable de fonctionner correctement conjointement avec le priphrique virtuel ( mul ). Vous acceptez d'assumer le risque que le Logiciel ne fonctionne pas correctement conjointement avec le priphrique virtuel ( mul ). Vous acceptez d'indemniser Intel et ses responsables et filiales et de les protger contre les plaintes, cots, dommages, dpenses et honoraires d'avocat ventuels issus, directement ou indirectement de toute plainte concernant la responsabilit du produit, des blessures ou la mort associes l'utilisation du Logiciel conjointement avec le priphrique virtuel ( mul ), mme si cette plainte prtend qu'Intel a t ngligent concernant la conception ou la fabrication du Logiciel.
UTILISATION NON AUTORISE. LE LOGICIEL N'EST PAS CONU, PRVU OU AUTORIS POUR UNE UTILISATION AVEC TOUT TYPE DE SYSTME OU D'APPLICATION DONT UNE DFAILLANCE LOGICIELLE POURRAIT ENTRANER DES BLESSURES OU LA MORT (PAR EX., SYSTMES MDICAUX, SYSTMES DE MAINTIEN DE LA VIE OU DE SURVIE). Si vous utilisez le Logiciel dans un cadre non prvu ou non autoris, vous acceptez d'indemniser Intel et ses responsables et filiales et de les protger contre les plaintes, cots, dommages, dpenses et honoraires d'avocat ventuels issus, directement ou indirectement de toute plainte concernant la responsabilit du produit, des blessures ou la mort associes l'utilisation du Logiciel dans un cadre non prvu ou non autoris, mme si cette plainte prtend qu'Intel a t ngligent concernant la conception ou la fabrication de la pice.
RSILIATION DE CE CONTRAT. Intel peut rsilier ce contrat tout moment si vous n'en respectez pas les termes. Dans ce cas, vous devez immdiatement dtruire le Logiciel et retourner toutes les copies dudit Logiciel Intel.
LOIS APPLICABLES. Les plaintes dposes dans le cadre de ce Contrat seront rgies par les lois de l'tat de Californie, sans considration pour les principes de conflit de lois. Vous acceptez que les termes de la Convention des Nations Unies sur les contrats de vente internationale de marchandises ne s'appliquent pas ce Contrat. Vous n'tes pas autoris exporter le Logiciel en infraction des lois et des rgulations d'exportation applicables. Intel n'est contraint par aucun autre contrat moins que celui-ci ne soit tabli par crit et sign par un reprsentant autoris d'Intel.
LIMITATION DES DROITS DU GOUVERNEMENT. Le Logiciel et la documentation inclus ont t dvelopps avec des fonds privs, et sont fournis avec des DROITS RESTREINTS . L'utilisation, la duplication ou la diffusion par le gouvernement est soumise des restrictions comme indiqu dans les clauses FAR.52.227-14 et DFAR.252.227-7013 et suivantes ou leurs successeurs. L'utilisation de ce produit par le Gouvernement constitue une reconnaissance des droits de proprit d'Intel sur le Logiciel. Le sous-traitant ou le fabricant est Intel.
LANGUE ; TRADUCTIONS. Au cas o la version en langue anglaise de cet Accord est accompagne d’une autre version traduite dans une autre langue, la version traduite est fournie uniquement pour des raisons de commodit et seule la version anglaise fait foi.
Dernire mise jour le 15/05/11 22h56 Rvision
Intel garantit au propritaire original que la carte livre dans ce coffret est dpourvue de tout dfaut de matriel ou de fabrication. Cette garantie ne couvre pas la carte si elle a t endommage au cours de l'installation ou utilise de faon incorrecte.
LA GARANTIE CI-DESSUS REMPLACE TOUTE AUTRE GARANTIE, EXPLICITE, IMPLICITE OU RGLEMENTAIRE, Y COMPRIS MAIS SANS S'Y LIMITER, LES GARANTIES DE QUALIT MARCHANDE, DE RESPECT DES DROITS DE PROPRIT INTELLECTUELLE OU DADAPTATION UN USAGE PARTICULIER QUI DCOULERAIT DUNE PROPOSITION, DUNE SPCIFICATION OU BIEN DUN CHANTILLON
Cette garantie ne couvre pas le remplacement des cartes endommages suite une utilisation non conforme aux instructions, un usage inappropri, la ngligence, un accident, un abus, une altration, une rparation, un dsastre, une installation incorrecte ou un test incorrect. Si la carte est dfectueuse, Intel pourra, sa discrtion, remplacer ou rparer gratuitement le matriel sauf dans les cas dcrits ci-dessous, ou rembourser le prix d'achat condition que vous retourniez la carte avec un numro d'autorisation de retour (RMA) [voir ci-dessous], une preuve d'achat (si votre produit n'a pas t enregistr), soit au fournisseur chez qui vous avez achet la carte, soit Intel, en incluant une description du problme. Les risques de dommage ou de perte associs l'envoi du produit sont votre responsabilit. Vous devez utiliser l'emballage original (ou un emballage similaire) et payer les frais d'envoi.
Intel peut remplacer ou rparer la carte en utilisant des pices nouvelles ou remises neuf, et toute carte ou pice de carte remplace par Intel deviendra la proprit d'Intel. Les cartes rpares ou remplaces vous seront retournes au mme niveau de rvision reu ou un niveau suprieur, la discrtion d'Intel. Intel se rserve le droit de remplacer les cartes abandonnes par une carte quivalente de la gnration actuelle.
Avant de retourner une carte, contactez le support client d'Intel et obtenez un numro d'autorisation de retour (RMA) en appelant le +1 (916) 377-7000.
Aprs vrification par le groupe de support client que le produit est dfectueux, le groupe demandera au service RMA d'mettre un numro RMA que vous devrez apposer sur le carton d'envoi de la carte. Intel n'acceptera aucun produit sans numro RMA appos sur le colis.
retournez la carte au lieu d'achat pour obtenir un remboursement ou une carte de remplacement.
Votre entire satisfaction des cartes Intel que vous avez achetes est trs importante pour Intel. Pour une priode de quatre-vingt dix (90) jours compter de la date d'achat, vous pouvez retourner la carte Intel au lieu d'achat original pour obtenir un remboursement total. Les revendeurs et les distributeurs acceptant les retours et remboursant leurs clients, respectivement, peuvent retourner les cartes Intel au lieu d'achat original. En vertu de la prsente, Intel garantit que les retours seront accepts et que le prix d'achat original sera rembours aux clients qui ont achets leur produit directement auprs d'Intel.
SELON CETTE GARANTIE, LA RESPONSABILIT D'INTEL SERA LIMITE AUX DOMMAGES DIRECTS ET MESURABLES OBJECTIVEMENT. INTEL NE SERA EN AUCUN CAS RESPONSABLE DES DOMMAGES INDIRECTS OU SPCULATIFS (Y COMPRIS ET SANS LIMITATION, LES DOMMAGES CONSCUTIFS, ACCIDENTELS ET SPCIAUX), Y COMPRIS, MAIS SANS S'Y LIMITER, LE RESPECT DE LA PROPRIT INTELLECTUELLE, LES COTS DE RAPPROVISIONNEMENT, LA PERTE D'UTILISATION, LES INTERRUPTIONS DACTIVITS ET LA PERTE DE BNFICES, QUE CES DOMMAGES DCOULENT D'UNE NGLIGENCE CONTRACTUELLE, D'UNE FAUTE, OU DE TOUTE GARANTIE, MME SI INTEL A T NOTIFI DE LA POSSIBILIT DE TELS DOMMAGES. NONOBSTANT CE QUI PRCDE, LA RESPONSABILIT TOTALE D'INTEL EN CAS DE RECOURS LI AU PRSENT CONTRAT NE POURRA DPASSER LE PRIX D'ACHAT PAY POUR LE PRODUIT. CES LIMITATIONS DES RESPONSABILITS POTENTIELLES CONSTITUAIENT UN LMENT ESSENTIEL POUR LA DTERMINATION DU PRIX DU PRODUIT. INTEL N'ASSUME NI N'AUTORISE QUICONQUE ASSUMER TOUTES AUTRES RESPONSABILITS.
Certains pays n'autorisent pas l'exclusion ou la limitation des dommages accidentels ou conscutifs, auquel cas les limitations susmentionnes peuvent ne pas vous tre applicables.
Applications de contrle critiques : Intel dcline toute responsabilit en cas d'utilisation de la carte dans des applications de contrle critiques (comme par exemple, les systmes de contrle mdicaux, de la scurit, de l'nergie nuclaire ou du trafic arien) par le dtenteur de la licence ou les sous-licencis. Ceux-ci assument tous les risques lis une telle utilisation. Le dtenteur de la licence accepte de dfendre, d'indemniser et de protger Intel contre les rclamations dcoulant de l'utilisation de la carte dans de telles applications par le dtenteur de la licence ou les sous-licencis.
Logiciel : Le logiciel fourni avec la carte n'est pas couvert par la garantie sur le matriel dcrite ci-dessus. Reportez-vous au contrat de licence logicielle appropri livr avec la carte pour plus d'informations sur les garanties logicielles.
Dernire mise jour le 23 juillet 2002 10h42 Rvision 6
Spegnere il computer e disinserire il cavo di alimentazione. Se si sta eseguendo un'installazione "a caldo", consultare la documentazione del server prima di proseguire.
Rimuovere il coperchio del computer e la protezione dello slot della scheda. Si pu utilizzare uno slot pi lungo del connettore della scheda di rete senza che questo provochi alcun danno, mentre non bisogna tentare di installarla in uno slot pi corto del connettore PCI Express.
Inserire saldamente la scheda nello slot e fissare la staffa di supporto.
Chiudere il coperchio del computer. Inserire il cavo di alimentazione.
Schede di rete Ethernet Intel® 10 Gigabit in rame: usare cavi Ethernet di categoria 6, 6a o 7.
Scheda di rete Ethernet Intel® 10 Gigabit per server con fibra ottica SFP+ collegabile: installare il modulo e collegare il cavo seguendo le istruzioni del produttore del modulo.
Schede di rete Ethernet Intel®10 Gigabit in fibra con connettore SC: rimuovere e riporre la copertura del connettore a fibre ottiche. Inserire un connettore SC a fibre ottiche nelle porte TX/RX della staffa di supporto della scheda di rete.
Schede di rete Ethernet Intel® 10 Gigabit in fibra con connettore LC: rimuovere e riporre la copertura del connettore a fibre ottiche. Inserire un connettore LC nella scheda di rete. possibile usare cavi per convertire altri tipi di connettori (come SC) se tali cavi soddisfano le specifiche ottiche della scheda, lunghezza inclusa.
Schede di rete Ethernet Intel®10 Gigabit CX4: i cavi devono essere conformi alle specifiche dello standard IEEE Std 802.3ak, articolo 54. Il connettore richiesto per il cavo deve essere una presa MDI con chiusura, conformemente a quanto indicato nello standard IEC 61076-3-113.
Avviare il computer e seguire le istruzioni per l'installazione del driver riportate di seguito.
|
|
NOTE:
|
La scheda viene rilevata come nuovo hardware all'avvio di Windows. Per installare il driver corretto:
La scheda viene rilevata e Windows installa un driver residente di Windows o avvia Installazione guidata nuovo hardware .
Se viene eseguita la procedura guidata, seguire le richieste per installare il driver dal CD allegato al prodotto.
Se viene installato un driver residente di Windows (non viene eseguita l'installazione guidata), aggiornare il driver inserendo il CD di Intel e facendo clic sul pulsante Installa i driver e il software quando viene visualizzata la finestra Intel Network Connections .
Per generare un package binario RPM* di questo driver, eseguire 'rpmbuild -tb <nomefile.tar.gz>'. Sostituire <nomefile.tar.gz> con il nome file specifico del driver.
|
|
NOTA: affinch il processo di build funzioni correttamente, il kernel al momento in esecuzione DEVE corrispondere alla versione dei sorgenti del kernel installati. Se stato appena ricompilato il kernel riavviare il sistema. Le funzionalit RPM sono state testate soltanto con le distribuzioni Red Hat. |
Spostare il file tar del driver di base in una directory di propria scelta. Ad esempio, usare '/home/nomeutente/ixgb' o '/usr/local/src/ixgb'.
Annullare l'archiviazione/compressione dell'archivio, dove <x.x.x> il numero di versione del file tar del driver:
tar zxf ixgb-<x.x.x>.tar.gz
Passare alla directory src del driver, dove <x.x.x> il numero di versione del file tar del driver:
cd ixgb-<x.x.x>/src/
Compilare il modulo del driver:
make install
Il file binario verr installato come:
/lib/modules/<VERSIONE_KERNEL>/kernel/drivers/net/ixgb.o
Le posizioni di installazione elencate pi indietro sono le posizioni predefinite. Potrebbero non essere corrette per alcune distribuzioni di Linux.
Installare il modulo:
insmod ixgb <parametro>=<valore>
Assegnare un indirizzo IP all'interfaccia inserendo l'istruzione seguente, dove <x> il numero di interfaccia:
ifconfig eth<x> <indirizzo_IP>
Verificare che l'interfaccia funzioni. Inserire la stringa seguente, in cui <indirizzo_IP> l'indirizzo IP di un altro sistema sulla stessa subnet dell'interfaccia da testare:
ping <indirizzo_IP>
Questo driver stato sviluppato per l'uso con il kernel FreeBSD, versioni 4.8 e successive.
|
|
NOTA: necessario disporre dei sorgenti del kernel installati per poter compilare il modulo del driver. |
Nelle istruzioni seguenti, x.x.x la versione del driver come indicato nel nome del file tar del driver.
Spostare il file tar del driver di base in una directory di propria scelta. Ad esempio, usare /home/username/ixgb o
/usr/local/src/ixgb.
Scompattare l'archivio:
tar zxf ixgb-<x.x.x>.tar.gz
In questo modo verr creata una directory ixgb-x.x.x.
Per installare la pagina man:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Per caricare il driver in un sistema in esecuzione, eseguire i seguenti passi:
cd ixgb-x.x.x
make
O
cd ixgb-x.x.x/src
make load
Per assegnare un indirizzo IP all'interfaccia, inserire:
ifconfig ixgb<num_interfaccia>
<indirizzo_IP>
Verificare che l'interfaccia funzioni. Inserire la stringa seguente, in cui <indirizzo_IP> l'indirizzo IP di un altro sistema sulla stessa subnet dell'interfaccia da testare:
ping <indirizzo_IP>
Se si desidera che il driver venga caricato automaticamente all'avvio del sistema:
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Modificare /boot/loader.conf e aggiungere la riga seguente:
if_ixgb_load="YES"
OPPURE
compilare il driver nel kernel (vedere il punto 8).
Modificare /etc/rc.conf e creare la voce opportuna
ifconfig_ixgb<num_interfaccia>:
ifconfig_ixgb<num_interfaccia>="<impostazioni_ifconfig>"
Esempio di utilizzo:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
NOTA: per aiuto, consultare la pagina man ifconfig.
Se si desidera compilare il driver nel kernel, inserire:
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Modificare il file /usr/src/sys/conf/files.i386 e aggiungere la riga seguente:
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Rimuovere le righe seguenti dal file /usr/src/sys/conf/files.i386 file, se
esistono:
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Modificare il file di configurazione del kernel (cio, GENERIC o MYKERNEL) in
/usr/src/sys/i386/conf e accertarsi che sia presente la riga seguente:
device ixgb
Compilare e installare il kernel. Per rendere effettivi gli aggiornamenti del kernel, necessario riavviare il sistema.
Per ulteriori informazioni sulla compilazione del kernel, consultare la documentazione del sistema operativo FreeBSD.
Per ulteriori informazioni, vedere la Guida dell'utente inclusa nel CD Intel o il sito Web del supporto Intel: http://www.intel.com/p/it_IT/support/.
Ultima modifica: 11/10/07 15:49 Revisione
Copyright © 2002 - 2012 Intel Corporation. Tutti i diritti riservati.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel Corporation non si assume alcuna responsabilit per eventuali errori o omissioni presenti in questo documento. Inoltre, Intel non si assume alcun impegno di aggiornare le informazioni ivi contenute.
Intel, Itanium e Pentium sono marchi registrati di Intel Corporation negli Stati Uniti e in altri paesi.
*Gli altri marchi e nomi potrebbero essere propriet di terzi.
Ultima modifica: 25/1/11 22:21 Revisione
PROXGB/DOCS/QUICK/ITA/license.htm 0000755 0000000 0000000 00000040270 11730046352 013131 0 ustar
CONTRATTO DI LICENZA DEL SOFTWARE INTEL
IMPORTANTE - LEGGERE PRIMA DI COPIARE, INSTALLARE O UTILIZZARE.
Non copiare, installare o usare questo software e l’eventuale materiale ad esso associato (definiti collettivamente con il termine “Software”) che sono forniti in base al presente Contratto di licenza (“Contratto”) senza avere prima letto attentamente i termini e le condizioni che seguono.
Copiando, installando o altrimenti utilizzando il Software, si accetta di essere vincolati dai termini di questo Contratto. Se non si accettano i termini di questo Contratto, non copiare, installare o usare il Software.
Notare:
LICENZA DI SITO: possibile copiare il Software sui computer di una azienda per un utilizzo interno all'azienda stessa ed possibile effettuare un numero ragionevole di copie di backup del Software, vincolate da queste condizioni:
LICENZA PER UTENTE SINGOLO: possibile copiare il Software su un singolo computer per uso personale ed possibile effettuare una copia di backup del Software, vincolata da queste condizioni:
LICENZA OEM: possibile riprodurre e distribuire il Software solo come parte integrante e incorporata del prodotto dell'OEM oppure come aggiornamento autonomo di manutenzione del Software per gli utenti esistenti dell'OEM, con l'esclusione degli altri prodotti autonomi o come componente di una distribuzione del Software pi ampia, compresa, ma non limitata a, la distribuzione di un'immagine di installazione o di una macchina virtuale guest, e rispettando queste condizioni:
LIMITAZIONI DELLA LICENZA. Il Licenziatario NON potr: (i) utilizzare o copiare i Materiali tranne per quanto previsto da questo Contratto; (ii) affittare o noleggiare i Materiali a terze parti; (iii) assegnare questo Contratto o trasferire i Materiali senza espresso consenso scritto da parte di Intel; (iv) modificare, adattare o tradurre i Materiali in tutto o in parte tranne per quanto previsto dal presente Contratto; (v) decodificare, decompilare o disassemblare i Materiali; (vi) cercare di modificare o manomettere la normale funzione di un gestore delle licenze che regola l'utilizzo dei Materiali; (vii) distribuire, concedere in sottolicenza o trasferire il Codice sorgente di alcun componente dei Materiali, dei Ridistribuibili e del Sorgente di esempio e loro derivati a terze parti tranne quanto previsto dal presente Contratto.
NESSUN ALTRO DIRITTO. Intel non concede al Licenziatario altri diritti o licenze, sia in modo esplicito che implicito, in riferimento alle informazioni proprietarie o di brevetto, ai copyright, ai mask work, ai marchi di fabbrica, ai segreti commerciali e ad altri diritti di propriet intellettuale che sono di propriet o controllati da Intel, eccetto nei casi espressamente previsti dal presente Contratto. Fatto salvo per quanto esplicitamente previsto nel presente documento, al Licenziatario non sono concesse altre licenze o diritti diretti, impliciti, indotti, derivanti da dichiarazioni verbali non corrette o di altra natura. In particolare, Intel non garantisce alcun diritto esplicito o implicito su brevetti, copyright, marchi di fabbrica o altri diritti relativi alla propriet intellettuale.
PROPRIET DEL SOFTWARE E COPYRIGHT. Il Software viene concesso in licenza e non venduto. La titolarit di tutte le copie del Software appartiene a Intel. Il Software protetto da copyright, dalle leggi degli Stati Uniti e di altre nazioni oltre che dalle disposizioni previste dai trattati internazionali. Il Licenziatario non pu rimuovere alcun avviso di copyright dal Software. Il Licenziatario accetta di impedire qualsiasi copia non autorizzata del Software. Intel pu apportare modifiche al Software, o agli elementi che a esso fanno riferimento, in qualsiasi momento e senza preavviso, ma non obbligata a supportare o aggiornare il Software. Il Licenziatario pu trasferire il Software soltanto se il destinatario dichiara di accettare di essere vincolato dai termini di questo Contratto e se il Licenziatario non conserva alcuna copia del Software.
TERMINI AGGIUNTIVI PER IL SOFTWARE DI PRE-RELEASE. Se il Software che si sta installando o utilizzando in base a questo Contratto una release preliminare o etichettato o altrimenti denominato versione “alfa“ o “beta“ del Software ("Software di pre-release"), si applicano i seguenti termini.
Nel caso in cui una disposizione di questa Sezione sia in conflitto con altri termini o condizioni di questo Contratto in relazione al Software di pre-release, questa Sezione avr la priorit su tali termini e condizioni, ma solo nei limiti necessari per risolvere il conflitto.
Il Licenziatario riconosce e accetta che il Software un Software di pre-release, non rappresenta il Software finale di Intel e potrebbe contenere errori e altri problemi che potrebbero causare la perdita di dati, il malfunzionamento del sistema o altri errori. Il Software di pre-release fornito "come tale" e Intel declina qualsiasi garanzia o responsabilit nei confronti del Licenziatario per gli eventuali danni causati dall'uso del Software di pre-release.
Il Licenziatario riconosce che Intel non ha promesso il futuro rilascio del Software di pre-release, non ha alcun obbligo espresso o implicito di rilasciare al Licenziatario il Software di pre-release e che Intel potrebbe introdurre un Software non compatibile con il Software di pre-release. Il Licenziatario riconosce che tutte le attivit di ricerca o sviluppo che esegue, relative al Software di pre-release o a qualsiasi prodotto che fa uso o associato con il Software pre-release, sono eseguite a proprio rischio.
Se Intel ha fornito al Licenziatario il Software di pre-release conformemente a un contratto scritto separato, l'uso del Software di pre-release regolamentato anche da tale contratto.
GARANZIA LIMITATA SUI SUPPORTI. Se il Software stato fornito da Intel su un supporto fisico, Intel garantisce che il supporto privo di difetti intrinseci e dei materiali per un periodo di novanta giorni dalla sua consegna da parte di Intel. Nel caso in cui siano rilevati difetti, restituire il supporto a Intel per ottenerne la sostituzione o per ricevere il Software in altro modo stabilito a discrezione di Intel.
ESCLUSIONE DI ALTRE GARANZIE. AD ECCEZIONE DI QUANTO PREVISTO IN PRECEDENZA, IL SOFTWARE CONCESSO IN LICENZA VIENE FORNITO 'COS COME ', SENZA ALCUNA GARANZIA ESPLICITA O IMPLICITA, COMPRESE LE GARANZIE DI COMMERCIABILIT, DI CONFORMIT ALLE NORME O IDONEIT A UN FINE PARTICOLARE. Intel non garantisce n si assume alcuna responsabilit riguardo l'accuratezza o la completezza delle informazioni, del testo, delle immagini, dei collegamenti o di altri elementi contenuti nel Software.
LIMITAZIONI DI RESPONSABILIT. INTEL O I SUOI FORNITORI NON SARANNO IN ALCUN CASO RESPONSABILI PER EVENTUALI DANNI DI QUALSIASI NATURA (COMPRESI, SENZA LIMITAZIONE, LE PERDITE DI PROFITTO, L'INTERRUZIONE DELL'ATTIVIT COMMERCIALE O LA PERDITA DI DATI) DERIVANTI DALL'USO O DALL'IMPOSSIBILIT DI USARE IL SOFTWARE, ANCHE NEL CASO IN CUI INTEL SIA STATA INFORMATA DELLA POSSIBILIT DI TALI DANNI. ALCUNE GIURISDIZIONI PROIBISCONO L'ESCLUSIONE O LA LIMITAZIONE DELLA RESPONSABILIT RELATIVAMENTE ALLE GARANZIE IMPLICITE O AI DANNI CONSEQUENZIALI E ACCIDENTALI; DI CONSEGUENZA, LA SUDDETTA LIMITAZIONE POTREBBE NON ESSERE APPLICABILE A TUTTI I CASI. POTREBBERO INOLTRE ESSERE PREVISTI ALTRI DIRITTI LEGALI CHE VARIANO DA GIURISDIZIONE A GIURISDIZIONE. Nel caso in cui il Licenziatario usi il Software con un dispositivo virtuale (“emulato”) destinato ad apparire come un componente Intel, il Licenziatario riconosce che Intel non n l'autore n il creatore del dispositivo virtuale (“emulato”). Il Licenziatario riconosce e accetta che Intel non fornisce alcuna garanzia relativamente alla correttezza del funzionamento del Software quando usato con un dispositivo virtuale (“emulato”), che Intel non ha progettato il Software per il funzionamento con il dispositivo virtuale (“emulato”) e che il Software potrebbe non funzionare correttamente con il dispositivo virtuale (“emulato”). Il Licenziatario accetta di assumersi il rischio che il Software potrebbe non funzionare correttamente con il dispositivo virtuale (“emulato”). Il Licenziatario accetta di rimborsare e manlevare Intel e i suoi funzionari, le sue societ collegate o controllate, di qualsiasi rivendicazione, costo, danno, spesa, spesa legale derivanti, direttamente o indirettamente, da qualsiasi rivendicazione di responsabilit del prodotto, lesione personale o decesso associati all'uso del Software con il dispositivo virtuale (“emulato”), anche se tale rivendicazione sostiene che Intel abbia agito in modo negligente nella progettazione o costruzione del Software.
USO NON AUTORIZZATO. IL SOFTWARE NON PROGETTATO, PREVISTO O AUTORIZZATO PER ESSERE UTILIZZATO IN QUALSIASI SISTEMA O APPLICAZIONE IN CUI IL FALLIMENTO DEL SOFTWARE POTREBBE CREARE UNA SITUAZIONE DI LESIONE PERSONALE O DECESSO (AD ESEMPIO, SISTEMI MEDICALI, SALVAVITA O DI SOPRAVVIVENZA). Se il Licenziatario utilizza il Software per qualsiasi uso non previsto o non autorizzato, il Licenziatario dovr rimborsare e manlevare Intel e i suoi funzionari, dipendenti, direttori, filiali, rappresentanti, affiliate e agenti nei confronti di qualsiasi rivendicazione, costo, danno, spesa, spesa legale e spese di vario tipo derivanti, direttamente o indirettamente, da qualsiasi rivendicazione di responsabilit del prodotto, lesione personale o decesso associati a tale uso non previsto o non autorizzato, anche se tale rivendicazione ritiene Intel negligente per quanto riguarda la progettazione o la costruzione della parte.
RESCISSIONE DI QUESTO CONTRATTO. Intel pu rescindere il presente Contratto in qualsiasi momento, nel caso l'utente ne violi i termini. In seguito alla rescissione del contratto, il Licenziatario deve immediatamente distruggere tutte le copie del Software o restituirle a Intel.
LEGGI APPLICABILI. Le rivendicazioni derivanti dal, o relative al, presente Contratto saranno regolamentate dalle leggi vigenti nello Stato della California, senza considerazione dei principi di conflitto della legge. Il Licenziatario accetta che la Convenzione delle Nazioni Unite sui Contratti per la vendita di beni non si applica al presente Contratto. Il Licenziatario non pu esportare il Software trasgredendo le leggi e i regolamenti sulle esportazioni attualmente in vigore. Intel non vincolata da alcun altro contratto che non sia per iscritto e firmato da un rappresentante autorizzato di Intel.
DIRITTI LIMITATI DEL GOVERNO. Il Software e la documentazione forniti sono stati sviluppati privatamente e hanno “DIRITTI LIMITATI”. L'uso, la duplicazione o la divulgazione da parte del Governo sono soggetti alle limitazioni delle norme FAR 52.227-14 e DFAR 252.227-7013 et seq. o successive. L’uso di questo prodotto da parte del Governo equivale a riconoscere i diritti di propriet di Intel sul Software. Il contraente o il produttore Intel.
LINGUA; TRADUZIONI. Qualora la versione in lingua inglese del presente Contratto venisse fornita insieme a una versione tradotta in un'altra lingua, a titolo di riferimento, far fede unicamente la versione in lingua inglese.
Ultima modifica 15/5/11 22:56 Revisione
Intel garantisce al proprietario originario che la scheda di rete contenuta nella confezione non contiene difetti n dei materiali n di lavorazione. La presente garanzia non copre i danni del prodotto causati dall'installazione del prodotto stesso.
LA SUDDETTA GARANZIA SOSTITUISCE QUALSIASI ALTRA GARANZIA, ESPRESSA, IMPLICITA O OBBLIGATORIA, COMPRESA, MA NON LIMITATA A, QUALSIASI GARANZIA DI RISPETTO DELLA PROPRIET INTELLETTUALE, DI COMMERCIABILIT, DI IDONEIT AD UNO SCOPO PARTICOLARE, O QUALSIASI GARANZIA DERIVATA DA PROPOSTE, SPECIFICHE, CAMPIONI.
La presente garanzia non copre la sostituzione di schede di rete danneggiate in caso di abuso, incidente, uso improprio, negligenza, alterazione, riparazione, calamit, installazione errata o collaudo errato. Se la scheda di rete viene trovata altrimenti difettosa, Intel, a propria discrezione, la sostituir o riparer gratuitamente, eccetto che nei casi illustrati di seguito, purch la scheda di rete sia consegnata unitamente al codice di autorizzazione per la restituzione del materiale (RMA) (vedere pi avanti) all'azienda presso cui la si acquistata o a Intel, con copia della ricevuta di acquisto (se la scheda non stata registrata) e una descrizione del difetto riscontrato. In caso di spedizione del prodotto, l'utente si assume il rischio di danneggiamento o perdita durante il trasporto. Occorre usare il contenitore originale (o uno equivalente) e pagare le spese di spedizione.
Intel pu sostituire o riparare la scheda di rete con un prodotto o parti nuove o rigenerate, nel qual caso la scheda di rete o le parti restituite diventano propriet di Intel. Le schede di rete riparate o sostituite saranno restituite, a discrezione di Intel, con un livello di revisione pari o superiore al prodotto originale. Intel si riserva il diritto di sostituire la scheda di rete difettosa con un altro modello equivalente.
Prima di restituire una scheda di rete, necessario contattare il Servizio di assistenza clienti al numero +1 916-377-7000 e richiedere un codice di restituzione prodotto (RMA).
Se il Servizio di assistenza clienti determina che la scheda di rete effettivamente difettosa, chieder al reparto responsabile della restituzione dei prodotti di emettere un codice RMA da apporre sulla confezione del prodotto da restituire. La Intel non accetter prodotti sprovvisti del codice RMA sulla confezione.
Restituire la scheda di rete al rivenditore presso il quale stata acquistata per richiedere il rimborso o la sostituzione.
Intel desidera che i suoi clienti siano pienamente soddisfatti della scheda di rete Intel che hanno acquistato. Pertanto, permette loro di restituire la scheda acquistata presso il rivenditore e di richiedere il rimborso dell'intero prezzo pagato entro novanta (90) giorni dalla data di acquisto. I rivenditori e i distributori che accettano i prodotti restituiti e rimborsano i clienti possono a loro volta restituire le schede di rete Intel al fornitore dal quale le hanno acquistate. Intel garantisce la possibilit di restituire il prodotto e di richiedere il rimborso dell'intero prezzo pagato anche ai clienti che hanno acquistato le loro schede direttamente dalla Intel.
L'UNICA RESPONSABILIT DI INTEL DEFINITA DALLA PRESENTE GARANZIA LIMITATA AI DANNI DIRETTI E MISURABILI IN MODO OGGETTIVO. IN NESSUN CASO INTEL SAR CONSIDERATA RESPONSABILE PER DANNI INDIRETTI O IPOTETICI (INCLUSI, MA NON LIMITATI A, I DANNI PRECEDENTI, DERIVATI, INCIDENTALI E SPECIALI) INCLUSI, MA NON LIMITATI A, LA VIOLAZIONE DI PROPRIET INTELLETTUALE, I COSTI DI RIACQUISTO, LA PERDITA D'USO, L'INTERRUZIONE DELLE ATTIVIT COMMERCIALI, LA PERDITA DI AVVIAMENTO, LA PERDITA DI PROFITTI, INDIPENDENTEMENTE DAL FATTO CHE TALI DANNI SI VERIFICHINO SOTTO CONTRATTO, DA NEGLIGENZA, PER TORTO O SIANO COPERTI DA GARANZIA, E INDIPENDENTEMENTE DA EVENTUALI NOTIFICHE FATTE PERVENIRE ANTICIPATAMENTE A INTEL RELATIVAMENTE ALLA POSSIBILIT DEL VERIFICARSI DI TALI DANNI. NONOSTANTE QUANTO SOPRA RIPORTATO, LA RESPONSABILIT TOTALE DI INTEL PER TUTTI I RECLAMI REGOLATI IN BASE AL PRESENTE CONTRATTO NON PU SUPERARE IL PREZZO PAGATO PER IL PRODOTTO. TALI LIMITAZIONI DELLE RESPONSABILIT POTENZIALI HANNO RAPPRESENTATO UN ELEMENTO ESSENZIALE PER STABILIRE IL PREZZO DEL PRODOTTO. LA INTEL NON SI ASSUME N AUTORIZZA ALCUNO AD ASSUMERSI IN SUA VECE QUALUNQUE ALTRA RESPONSABILIT.
Alcuni stati non consentono l'esclusione o la limitazione dei danni incidentali o consequenziali, pertanto le suddette limitazioni potrebbero non essere applicabili all'utente.
Applicazioni di controllo critiche: la Intel disconosce specificamente la responsabilit per l'uso del prodotto hardware con applicazioni di comando fondamentali (compresi, solo a titolo di esempio, sistemi di comando per l'assistenza sanitaria, sistemi di comando per energia nucleare, o sistemi di comando per il traffico aereo o terrestre) da parte del Licenziatario o dei Sublicenziatari, e tale utilizzo totalmente a rischio e pericolo dell'utente. Il licenziatario concorda di sostenere, risarcire e ritenere Intel non responsabile di qualsivoglia reclamo derivato dall'uso del prodotto hardware in tali applicazioni da parte del Licenziatario o dei Sublicenziatari.
Software: il software fornito con la scheda di rete non coperto dalla garanzia hardware descritta in precedenza. Per informazioni sulle eventuali garanzie software, consultare il Contratto di licenza del software fornito con la scheda di rete.
Ultima modifica: 07/23/02 10:42a Revisione 6
Rs[^[̓dAdR[hRZg甲܂Buzbg vOvCXg[sꍇ́AŏɃT[o[̃}jAQƂĂB
Rs[^[̃Jo[OAA_v^[ɊYXbgA_v^[EXbgJo[O܂BA_v^[̃RlN^[XbggpĂ܂܂APCI Express RlN^[ZXbgɂ͎tȂłB
A_v^[ PCI Xbgɂƍ݁AuPbgŒ肵܂B
Rs[^[̃Jo[t܂BdR[hRZgɍ݂܂B
Ce(R) C[Tlbg 10 MKrbgA_v^[F JeS[ 6AJeS[ 6aA܂̓JeS[ 7 C[TlbgEP[ugp܂B
Ce(R) C[Tlbg 10 MKrbgET[o[EA_v^[ (SFP+ wvOE\^)F W[̎wɏ]ăW[CXg[ăP[uڑ܂
Ce(R) C[Tlbg 10 MKrbgEt@Co[EA_v^[ (SC RlN^[ڑ)F@ t@Co[RlN^[̃Jo[Oĕۊǂ܂BSC t@Co RlN^[ A_v^[uPbg TX/RX |[gɍ݂܂B
Ce(R) C[Tlbg 10 MKrbgEt@Co[EA_v^[ (LC RlN^[ڑ)F@ t@Co[RlN^[̃Jo[Oĕۊǂ܂BLC RlN^[A_v^[ɍ݂܂B̐܂߁AA_v^[̌t@Co[̎dlɃP[uꍇ́ASC ̂ق̃^CṽRlN^[ɕϊP[ugp邱Ƃł܂B
Ce(R) C[Tlbg 10 MKrbg CX4 A_v^[F IȃP[úAIEEE Std 802.3akAClause 54 ̎dlɍĂȂȂ܂BKvȃP[ũRlN^[́AIEC 61076-3-113 Œ`Ă MDI b`^Cṽ\PbgłB
Rs[^[NÃhCo[ECXg[菇ɏ]܂B
|
|
F
|
Windows NƁAA_v^[Vn[hEFAƂČo܂B̎菇ɏ]āAKȃhCo[CXg[܂B
A_v^[oAWindows ɂ Windows 풓hCo[CXg[邩AVn[hEFǍo EBU[hN܂B
EBU[hNꍇ́Aʂ̎wɏ]āÃpbP[Wɕt CD hCo[CXg[܂B
Windows 풓hCo[CXg[ꂽꍇ (EBU[h\Ȃꍇ) ́ACe CD }AmCe lbg[NERlNV n autoran EBhE\ꂽ mhCo[ƃ\tgEFÃCXg[ n {^NbNāAhCo[XV܂B
̃hCo[̃oCi[ RPM* pbP[W쐬ɂ́Aurpmbuild -tb <filename.tar.gz>vs܂ B<filename.tar.gz> ́̕AhCo[̃t@Cɒu܂ B
|
|
F rh@\ɂ́Aݎs̃J[l̃o[WƃCXg[ꂽJ[l \[X̐ݒ肪vKv܂BJ[lăRpC̏ꍇ́AVXeċNĂB RPM @\ Red Hat ł̂݃eXgĂ܂B |
Cӂ̃fBNg[Ƀx[X hCo[ tar t@Cړ܂BƂAu/home/username/ixgbv܂́u/usr/local/src/ixgbvfBNg[gp܂B
A[JCu𓀂܂Bi<x.x.x> ́AhCo[ tar ̃o[WԍłBj
tar zxf ixgb-<x.x.x>.tar.gz
hCo src fBNg[ɕύX܂Bi<x.x.x> ́AhCo[ tar ̃o[WԍłBj
cd ixgb-<x.x.x>/src/
hCo[ W[RpC܂B
make install
oCi[͎̂悤ɃCXg[܂B
/lib/modules/[J[l o[W]/kernel/drivers/net/ixgb.o
Ɏ̂́AftHg̃CXg[ꏊłBgpĂ Linux ɂẮÃCXg[ꏊgpȂꍇ܂B
W[CXg[܂B
insmod ixgb <p[^>=<l>
ȉ̂悤ɓ͂ăC^[tFCX IP AhX蓖Ă܂Bi<x> ̓C^[tFCXԍłBj
ifconfig eth<x> <IP AhX>
C^[tFCX@\邱ƂmF܂B̂悤ɓ͂܂B<IP AhX> ̕ɂ́AeXgC^[tFCXƓTulbgɂAʂ̃Rs[^[ IP AhX܂B
ping <IP AhX>
̃hCo[́AFreeBSD J[lAo[W 4.8 ȍ~Ŏgp悤ɍĂ܂B
|
|
F hCo[ W[RpCɂ́AJ[l \[XCXg[Ă邱ƂKvłB |
ȉ̎菇ŁAx.x.x ̓hCo[̃o[W\܂BhCo[̃o[W tar t@C̖OŊmFł܂B
Cӂ̃fBNg[Ƀx[X hCo[ tar t@Cړ܂BƂA /home/username/ixgb ܂
/usr/local/src/ixgb gp܂B
A[JC𓀂܂B
tar xfz ixgb-x.x.x.tar.gz
ɂāAixgb-x.x.x fBNg[쐬܂B
man y[WCXg[܂B
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
hCo[s̃VXeɃ[hɂ́A̎菇ɏ]܂B
cd ixgb-x.x.x
make
܂
cd ixgb-x.x.x/src
make load
C^[tFCX IP AhX蓖Ăɂ́Â悤ɓ͂܂B
ifconfig ixgb<interface_num>
<IP AhX>
C^[tFCX@\邱ƂmF܂B̂悤ɓ͂܂B<IP AhX> ̕ɂ́AeXgC^[tFCXƓTulbgɂAʂ̃Rs[^[ IP AhX܂B
ping <IP AhX>
VXe̋NɃhCo[IɃ[hɂ́Â悤ɓ͂܂B
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
/boot/loader.conf ҏWāA̍slj܂B
if_ixgb_load="YES"
܂
J[lɃhCo[RpC܂ (8 ̍ڂQ)B
/etc/rc.conf ҏWēKȃt@C쐬܂B
ifconfig_ixgb<interface_num>
Gg[F
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
gpF
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
F ڍׂɂẮAifconfig man y[WQƂĂB
hCo[J[lɃRpCɂ́Â悤ɓ͂܂B
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
/usr/src/sys/conf/files.i386 t@CҏWāA̍slj܂F
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
/usr/src/sys/conf/files.i386 t@CɎ̍sꍇ́A̍s
폜܂F
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
/usr/src/sys/i386/conf ŃJ[lݒt@C (Ȃ킿 GENERIC ܂ MYKERNEL) ҏWāA̍s邱ƂmF܂F
device ixgb
RpCăJ[lCXg[܂BJ[l̍XVLɂɂ́AVXeċNKv܂B
J[l̃RpC̏ڍׂɂẮAFreeBSD Iy[eBOEVXẽ}jAQƂĂB
ڍׂɂẮACe CD Ɏ^Ă[U[ KChACẽT|[g Web TCg http://www.intel.com/p/ja_JP/support/ QƂĂB
ŏIύXQOOVN 10 PP 3:49pm ԍ
Copyright (C) 2002 - 2012 Intel Corporation.All rights reserved.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
Intel Corporation ͖{ɋLڂĂě܂͋LژRɂāAؐӔC܂B܂A{̋LړeXV`ؕ܂B
IntelAItanium PentiuḿAčт̑̍ɂ Intel Corporation ̏WłB
* ̑̐i܂̓uh͊eL҂ɋAĂꍇ܂B
ŏIXV 2011N125 10:21pm ԍ
PROXGB/DOCS/QUICK/JPN/license.htm 0000755 0000000 0000000 00000034020 11730046352 013137 0 ustar
Ce \tgEFAgp_
dv - Rs[ACXg[A܂͎gp̑Oɂǂ݂B
ȉ̏𒍈Ӑ[ǂ݂ɂȂ܂ŁA{gp_ (u_v) ̉ɒ{\tgEFAъ֘A (ȉÂ u\tgEFAv Ƃ܂) Rs[ACXg[A܂͎gpȂłB
\tgEFARs[ACXg[A܂͎gpƁAql͖{_̏ɍS邱ƂɓӂꂽƂɂȂ܂B{_̏ɓӂȂꍇ́A\tgEFARs[ACXg[܂͎gpȂłB
ӎF
TCggp_F qĺA\tgEFAql̑gDgp邽߂ɂ̑gD̃Rs[^[Ƀ\tgEFARs[邱ƂłA\tgEFÃobNAbvƂđÓȐ̃Rs[쐬邱Ƃł܂BAȉ̏ɏ]ƂƂ܂B
VO[U[gp_F qĺA\tgEFA 1 ̃Rs[^[ɂqľlgpړIŃRs[邱ƂłA\tgEFÃobNAbvE Rs[ 1 쐬ł܂B̍ہAȉ̏Kp܂B
OEM gp_F qĺAql̐iɓꂽA܂͑gݍ܂ꂽƂāA邢͂ql̐i̊̃Gh[U[ɑX^hÃ\tgEFAEeiXEAbvf[g (ȊÔׂẴX^hAi͏O) A܂̓CXg[EC[W܂̓QXgz}ṼC[W̔zz܂ނɌ肳Ȃ傫ȃ\tgEFA̔zz 1 ̃R|[lgƂĂ̂݁A\tgEFAєzz邱Ƃł܂BAȉ̏ɏ]̂Ƃ܂B
CZX̐B ȉ̂Ƃ͍s܂B(i) {_ŒꂽꍇA{i̎gp܂͕B (ii) ȂO҂ɖ{iݗ^܂̓[X邱Ƃ͂ł܂B (iii) ʂɂCe̖IȋȂɖ{_蓖Ă{in邱Ƃ͂ł܂B (iv) {_ŋꂽꍇA{ȋŜ܂͈ꕔύXAA܂͂ق₭邱Ƃ͂ł܂B (v) {ĩo[XGWjAAtRpCAtAZu邱Ƃ͂ł܂B (vi) {i̎gpK郉CZXE}l[W[̐@\̕ύX܂͉݂邱Ƃ͂ł܂B (vii) {_ŋĂꍇA{îȂR|[lg̃\[XR[h`AĔzz\ȃ\[XAуTv\[Xт̔hȂO҂ɔzzATuCZXA܂͏n邱Ƃ͂ł܂B
ׂ̑̂Ă̌̏OB {_ɖIɋK肳Ă̂ACeЂ͂qlɑACeЂLуRg[铖ГƎ̏A쌠A}XN [NAWAƖ̋@Ȃ̒mILɊւAIAÎI킸AȂ錠CZXt^̂ł͂܂B{_ɖĂꍇAځAَIAUIA֔Ȃ킸ACZX܂͌n邱Ƃ͈܂BɁACéACe̓A쌠AWȂ̒mILɊւAI܂َ͖IȌ؏n邱Ƃ͂܂B
\tgEFȀLђ쌠B {\tgEFA̓CZXĂApꂽ̂ł͂܂B\tgEFAтׂ̂ẴRs[Ɋւ̏ĹACeɋA܂B\tgEFA͒쌠o^ĂAčƏO̖@Aэۏɂĕی삳Ă܂B\tgtgEFA̒쌠̍m邱Ƃ͂ł܂BqĺA\tgEFA̖fh~邱Ƃɍӂ̂Ƃ܂BCeł́Aʒm邱ƂȂł\tgEFA܂͂ɋLڂĂ鍀ڂɕύX邱ƂłA\tgEFAT|[g܂̓Abvf[g`܂Bl{_̊ɊSɏ邱ƂɓӂAnl\tgEFÃRs[ێȂꍇɂ̂݃\tgEFAn邱Ƃł܂B
v[XŃ\tgEFAp̒ljB {_̉ɃCXg[܂͎gp\tgEFAƃ[XÕv[XłłꍇA܂̓\tgEFÁuAt@v܂́ux[^vłƂĕ\ꂽꍇɂ́ȀKp܂B
v[XŃ\tgEFAɊւāÃZNV̂Ȃ{_̑̂܂͏ƖꍇɂẮÃZNV̏܂͏D悳܂ÂɕKvȔ͈݂͂̂Ɍ܂B
qĺA\tgEFAv[Xł̃\tgEFAłACe̍ŏI\tgEFAł͂ȂAf[^̑AVXeQA܂͑̃G[N\̂G[ё̖܂މ\邱Ƃ𗝉ďF܂Bv[XŃ\tgEFÁû܂܁vACéAv[XŃ\tgEFA̎gp琶邢Ȃ鑹QɑāAqlւ̕ۏ؍s킸AӔCؕ܂B
qĺACev[XŃ\tgEFAナ[XACéAqlāAv[XŃ\tgEFA[X閾I܂َ͖Iȋ`ǂ킸ACe̓v[XŃ\tgEFAƌ݊̂\tgEFAȂ\邱ƂF܂BqĺAv[XŃ\tgEFA܂̓v[XŃ\tgEFAgpA܂͊֘A邢Ȃ鐻iɊւĂqlsȂ郊T[`܂͊Jׂ͂Ăql̐ӔCɂčsƂF܂B
Ceʓȑʂɂ鍇ӂɏ]ĂqlɃv[Xł̃\tgEFAꍇAqlɂv[Xł̃\tgEFA̎gṕA̍ӏɂĂǗ܂B
}̂̌ۏB \tgEFACeɂ蕨IȔ}̏ŔzzꂽꍇACeł͔zB 90 ԁA}̂ɍގエѕIȕsȂƂۏ܂B̂悤ȌׂꍇA̔}̂CeɕԑĂB}̂̌܂̓CeI@Ń\tgEFA͂܂B
̑̕ۏ̏OB qɋK肷ۏA\tgEFÁû܂܁v܂Bi̕ۏA쌠̐NQȂƁAړIK̕ۏ܂߁Ȃ̕ۏɂ͖Eَ킸܂B Ceł́A\tgEFAɊ܂܂AeLXgAOtBbNANȂ̍ڂɂāA̐m⊮SɂĈؕۏAӔC܂B
ƐӎB ǂ̂悤ȏꍇɂĂACe܂͂̔[Ǝ҂́AQ̉\wEʍOɂƂĂA\tgEFA̎gp܂͂ꂪgpłȂƂɂĐȂ鑹Q (⎸vɋN鑹QAƖ̒fȂ܂ނɌ̂ł͂Ȃ) ɑĂAؐӔC܂B܂͒nɂẮAَ̕ۏAʓI܂͋IȑQ̏O܂͐ւĂꍇ܂B̏ꍇAL͓̐Kp܂B܂͒nɂ肨ql̖͑@IȌLꍇ܂B CẽR|[lgiƂČ悤ɐvꂽz (uG~[gꂽv) foCXƂ̑gݍ킹ɂ\tgEFAgpꍇAqĺACez (uG~[gꂽv) foCX̍҂܂͍쐬҂̂łȂƂF܂BqĺA\tgEFAz (uG~[gꂽv) foCXƂ̑gݍ킹ɂgpƂɂ́ACe̓\tgEFA̐ɂĐACe̓\tgEFAz (uG~[gꂽv) foCXƂ̑gݍ킹ɂ葀삷邽߂ɐvĂ炸Az (uG~[gꂽv) foCXƂ̑gݍ킹ŎgpƂɂ̓\tgEFA@\Ȃ\邱Ƃ𗝉AF܂BqĺAz (uG~[gꂽv) foCXƂ̑gݍ킹ŎgpꍇA\tgEFA@\Ȃ\댯邱Ƃz肷邱Ƃɓӂ܂BqĺAz (uG~[gꂽv) foCXƂ̑gݍ킹Ń\tgEFAgpꍇɂāAgpɊ֘Ai̐ӔCAlgQASɊւ锅ɂāAƂCeɐv܂͐ɂߎƎ咣ꍇłAɒړI܂͊ԐړIɋN锅AAQAp̈AёÓȊzٌ̕mp⏞ACeƂ̖AqЁA֘AЂɉ瑹Q^ȂƂɓӂ̂Ƃ܂B
FȂgpB {\tgEFÁA\tgEFA̕sl̂ւ̕܂͎SN\̂邢Ȃ^CṽVXeAvP[V(ƂAÃVXeAێuA~uȂ) ɂĂ̎gp̂߂ɐvAӐ}A܂͔FĂ܂Bql̓\tgEFAȂӐ}Ȃ܂͋ȂprɎgpꍇAgpɊ֘Ai̐ӔCAlgQASɊւ锅ɂāAƂCeɐv܂͐ɂߎƎ咣ꍇłAɒړI܂͊ԐړIɋN锅AAQAp̈AёÓȊzٌ̕mp⏞ACeƂ̖AqЁA֘AЂɉ瑹Q^ȂƂɓӂ̂Ƃ܂B
\'96\'7b_̏IB ql{_̏ɈᔽꍇACe͒ɖ{_邱Ƃł܂B{_IꍇAql͒Ƀ\tgEFA邩AׂẴRs[Ceɕԋp̂Ƃ܂B
@B {_琶鐿ɂ́AڐG@̌ɔ邩ǂɊWȂAAJÕJtHjAB̖@Kp܂BqĺA{_ɂ͍ەi_Ɋւ鍑Ȁ͓KpȂƂɓӂ܂BqĺAYAoɊւ@yыKɔă\tgEFAAo邱Ƃ͂ł܂BCéACě̂\҂̏̂鏑ʂɂȂȂ̌_̋`܂B
{̌̐B ꂽ\tgEFAƃhLg͎ɂJAu̐vt܂B {ɂgpAAJɂẮAFAR52.227-14ADFAR252.227-7013 et seq. ܂͂̌pKɋK肳Ă鐧܂B{ɂ{i̎gṕA\tgEFAɂCȅL̏FƂȂ܂B_҂܂͐҂̓CełB
A|F ̎gp_̉płɁAւ̖|łtĂꍇA̖|ł͂ql̕X}ĒĂ邾̂̂łApł@I͂D悳܂B
ŏIXV | 2011N515 10:56pm | ԍ
CéÃpbP[WŔzzA_v^-iɂāAގѐׂ̌ɑۏȉ㏊L҂ɒ܂BA_v^ĩCXg[̑܂͕sȎgpɂ鑹ɑẮA̕ۏ͓Kp܂B
q̕ۏ́ÂׂĂ̕ۏ؏i̕ۏAAَA܂͖@킸AmIY̐NQȂƁAiAāAdlA܂̓Tv琶ړIK̕ۏ܂߁Ȃ̕ۏɑēKp܂B
̕ۏ́ApAߎApAsӁAACAЊQAsKȃCXg[A܂͕sKȃeXgɂ鑹Q́A{ۏ̑ΏۂƂȂ܂BA_v^[iɌׂꍇ́ACe͈ȉɎw肵ꍇAqlׂ̐ Return Material Authorization (RMA) [ԕi] ̔ԍ (ȉQ)Aэw̏ؖ (o^ς݂łȂꍇ) ƂƂɍw̃fB[[܂̓CeɒoꍇɂāACӂɂn[hEFAǐ܂͏CŒ邩AA_v^[i̍wiԋ܂BqlA_v^[i𑗕tꍇ́AȂQ܂͕̊댯z肹˂Ȃ܂Bql͐iɕt̔ (܂͂Ɠ̂) gpAKv܂B
CéAA_v^[ǐA܂͐VKi܂͍ĐigpCsAA_v^[i܂̓CeɂꂽíACȅLƂȂ܂BCς݂܂͌ꂽA_v^íACeɂCӂɂÂƓrW x܂͂ȍ~łqlɖ߂܂BCéA~ɂȂA_v^[i̓̃A_v^[iƌ錠ۗL܂B
A_v^[iԕiOɁACẽJX^}[ T|[g 1 916-377-7000 ɓdbāAReturn Material Authorization (RMAAԕi) ԍ擾ĂB
JX^}[ T|[g O[vɂAA_v^[iɌׂ邱Ƃꂽꍇ́ARMA ɂA_v^[i̊Oɕt RMA ԍs܂BCéApbP[W RMA ԍ̂Ȃi͈؎t܂B
CéAqlwȂCẽA_v^[iɊSɖĂƎvĂ܂Bw 90 ȓ̊Ԃɂ́Aql̓CẽA_v^[wɕԕiAfB[[wiSz̕ԋ邱Ƃł܂BԕitAqlɕԋ郊Z[уfBXgr[^[͂ꂼACẽA_v^[̍wꏊɖ߂Ƃł܂BCéÃ|V[̉ɁACe璼ڍwql̕ԕitA̍wiqlɕԋ邱Ƃۏ܂B
̋Lڂɏ]ăCȇӖ́AځAqϓIɑ\ȑ݂̂Ɍ肳܂BCéAmIY̐NQȂƁAĒB̔pAgp̑AƖ̒fAcƌ̑Aїv̑܂ނɌ肳ȂAȂԐړI܂͐_IȑQɑA̐ӔC܂B܂Â悤ȑQ_̑ӖAs@sׁA܂͑̕ۏ̉ɐۂɂ炸ACȇQ̉\ɂĎOʒmĂۂȂ̂Ƃ܂BOqɂ炸A{_̉ɂׂĂ̔ɑCȇŚA{iɎxi邱Ƃ͂܂BݓIȐӔCɑ邱̐́AỉiݒɂĕKvȗvfłBCéAȂ҂̂ӔCz肷邱ƁAѐӔC̑zF邱Ƃ͂܂B
BɂẮAtI܂͌ʂƂĐ鑹Q̏O܂͐Ȃ߁AL̐qlɓKpȂꍇ܂B
NeBJERg[EAvP[VF Ce͓ɁA{A_v^[iCZV[܂̓TuCZV[NeBJERg[EAvP[V (ƂĂ̂S܂̓wXPAERg[EVXeAq̓Rg[EVXeA܂͍q@邢͒ňʃRg[EVXe܂) Ŏgpꍇɂ͈ؐӔC킸Â悤Ȏgp͊SɃ[U̐ӔCƂȂ܂BCZV[́ACZV[܂̓TuCZV[ɂ邻̂悤ȃAvP[Vɂ{A_v^[i̎gp琶邷ׂĂ̗vCeٌ삵AۏႵی삷邱Ƃɓ ̂Ƃ܂B
\tgEFAF A_v^[iƂƂɒ\tgEFAɂ́AL̃n[hEFAۏ͓Kp܂B\tgEFA̕ۏ̏ڍׂɂẮA{A_v^[iɓĂY\tgEFAgp_QƂĂB
ŏIύX2002N723 10:42a ԍ 6
ǻ ڵ带 ̽ϴ. " ÷" ġϷ Ͻʽÿ.
ǻ ش Ϳ ġϴ Կ մϴ. Ŀͺ ϴ , PCI ͽ Ŀͺ ª Կ ġ ʽÿ.
Կ Ų 귡Ŷ ܴ ϴ.
ǻ ٽ ڵ带 մϴ.
® ̴ 10 ⰡƮ : īװ 6, īװ 6a Ǵ īװ 7 ̴ ̺ Ͻʽÿ.
SFP+ ÷ ƽ ® ̴ 10 ⰡƮ : ü ħ ġ ̺
SC ĿͰ ִ ® ̴ 10 ⰡƮ : Ŀ иϿ Ͻʽÿ. SC ƽ Ŀ 귡Ŷ TX/RX Ʈ ʽÿ.
LC ĿͰ ִ ® ̴ 10 ⰡƮ : Ŀ иϿ Ͻʽÿ. LC Ŀ Ϳ ʽÿ. ̺ ´ 쿡 SC ٸ Ŀ ϴ ȯ ̺ ֽϴ.
® ̴ 10 ⰡƮ CX4 : ̺ IEEE Std 802.3ak, Clause 54 ؾ մϴ. ʿ ̺ Ŀʹ IEC 61076-3-113 MDI ġ Դϴ.
ǻ ϰ Ʒ ̹ ġ ȳ ʽÿ.
|
|
:
|
Windows ϵ Ͱ ߰ߵ˴ϴ. ùٸ ̹ ġϷ
Ͱ ǰ Windows Windows ̹ ġϰų ϵ ߰ 縦 մϴ.
簡 ۵Ǹ Ÿ Ű CD ̹ ġմϴ.
Windows ̹ ġϴ (簡 Ÿ ) CD ְ Ʈũ ڵ â Ÿ ̹ Ʈ ġ ߸ ŬϿ ̹ Ʈմϴ.
̹ ̳ʸ RPM* Ű Ϸ 'rpmbuild -tb <filename.tar.gz>' մϴ. ⼭ ̸ <filename.tar.gz> ̹ ش ̸ ٲٽʽÿ.
|
|
: 尡 ùٸ ۵Ϸ Ŀΰ ġ Ŀ ҽ ġؾ մϴ. Ŀ ٽ 쿡 ý ٽ մϴ. RPM Red Hat ǿ ƮǾϴ. |
丮 ̹ tar ̵մϴ. , '/home/username/ixgb' Ǵ '/usr/local/src/ixgb' մϴ.
̹ tar DZϴ. ⼭ <x.x.x> ̹ tar ȣԴϴ.
tar zxf ixgb-<x.x.x>.tar.gz
̹ src 丮 ̵մϴ. ⼭ <x.x.x> ̹ tar ȣԴϴ.
cd ixgb-<x.x.x>/src/
̹ մϴ.
make install
̳ʸ ġ˴ϴ.
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
ġ ġ ⺻ ġԴϴ. Ϻ Linux ǿ ̷ ġ ٸ ֽϴ.
ġմϴ.
insmod ixgb <parameter>=<value>
Ͽ ̽ IP ּҸ մϴ. ⼭ <x> ̽ ȣԴϴ.
ifconfig eth<x> <IP_ּ>
̽ ۵ϴ Ȯմϴ. Էմϴ. ⼭ <IP_ּ> Ʈ ̽ ݿ ִ ٸ ġ IP ּԴϴ.
ping <IP_ּ>
̹ FreeBSD Ŀ, 4.8 ̻ ϱ ߵ Դϴ.
|
|
: ̹ Ϸ Ŀ ҽ ġǾ ־ մϴ. |
Ʒ x.x.x ̹ tar ̸ ǥõǾ ִ ̹ Դϴ.
丮 ̹ tar ̵մϴ. , /home/username/ixgb Ǵ
/usr/local/src/ixgb մϴ.
Ǯ:
tar xfz ixgb-x.x.x.tar.gz
ixgb-x.x.x 丮 ˴ϴ.
man ġ:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
ýۿ ̹ εϷ ܰ踦 Ͻʽÿ.
cd ixgb-x.x.x
make
Ǵ
cd ixgb-x.x.x/src
make load
IP ּҸ ̽ ҴϷ ԷϽʽÿ.
ifconfig ixgb<interface_num>
<IP_ּ>
̽ ۵ϴ Ȯմϴ. Էմϴ. ⼭ <IP_ּ> Ʈ ̽ ݿ ִ ٸ ġ IP ּԴϴ.
ping <IP_ּ>
ý ̹ ڵ εϷ
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Edit/boot/loader.conf ϰ ߰մϴ.
if_ixgb_load="YES"
Ǵ
̹ Ŀη մϴ( 8 ).
/etc/rc.conf ϰ
ifconfig_ixgb<interface_num>
ϴ.
ifconfig_ixgb<interface_num>="<ifconfig_settings>"
:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
: ڼ ifconfig man Ͻʽÿ.
Ŀο ̹ Ϸ ԷϽʽÿ.
cd ixgb-x.x.x/src
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
/usr/src/sys/conf/files.i386 ϰ ߰մϴ.
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
/usr/src/sys/conf/files.i386 Ͽ մϴ.
(ִ )
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
/usr/src/sys/i386/conf Ŀ (, GENERIC Ǵ MYKERNEL) ϰ ִ Ȯմϴ.
device ixgb
Ŀ ϰ ġմϴ. Ŀ Ʈ Ϸ ý ؾ մϴ.
Ŀ Ͽ ڼ FreeBSD ü Ͻʽÿ.
ڼ CD ִ ȳ ϰų Ʈ http://www.intel.com/p/ko_KR/support/ 湮Ͻʽÿ.
: 07/10/11 3:49p
Copyright © 2002 - 2012 Intel Corporation. All rights reserved.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
ڻ å ʽϴ. ϵ ƮѴٴ ʽϴ.
, ״Ͼ Ƽ ̱ Ÿ ڻ ǥԴϴ.
*ٸ ̸ 귣 ٸ ȸ ֽϴ.
: 11/01/25 10:21p
PROXGB/DOCS/QUICK/KOR/license.htm 0000755 0000000 0000000 00000030127 11730046352 013147 0 ustar
Ʈ ̼
߿ - Ʈ , ġ Ǵ ϱ ݵ оñ ٶϴ.
Ʒ о ̼ ("") Ͽ Ǵ Ʈ ڷ("Ʈ") , ġ Ǵ Ͻʽÿ.
Ʈ , ġ Ǵ ϸ ´ٴ ϴ Դϴ. 뿡 Ʈ , ġ Ǵ ʽÿ.
:
Ʈ ̼: , ϴ ڽ ǻͿ Ʈ ϰ Ʈ ֽϴ.
̼: ؼ , ϴ 뵵 ǻ 뿡 Ʈ ϰ Ʈ ֽϴ.
OEM ̼: ϴ ǿ ǰ յ ·, ǰ ڸ Ʈ Ʈ · Ǵ Ը Ʈ ·θ Ʈ ֽϴ. ġ ̹ Ǵ ԽƮ ǻ ̹ ԵǸ ̿ ѵ ʽϴ.
̼ . ϴ (i) ༭ 츦 ϰ ڷ Ǵ , (ii) 3ڿ ڷ 뿩 Ǵ Ӵ; (iii) Ȯ 絵 Ǵ ڷ ; (iv) 츦 ϰ ڷ Ϻ Ǵ ü , Ǵ ȯ, (v) ڷ Ͼ, Ǵ , (vi) ڷ ϴ ̼ ϰų Ϸ õ, (vii) ༭ 츦 ϰ ڷ, Ű ҽ Ļ ҽ ڵ Ҹ 3ڿ , ̼ ο Ǵ ϴ ˴ϴ.
ٸ Ǹ . ༭ ϴ 츦 ϰ ϰų ϴ , Ư, ۱, ũ ũ, ǥ, Ǵ Ÿ ǿ Ǵ Ǹ ̼ ο ʽϴ. ̰ 츦 ϰ Ǵ Ͻ, , ݹݾ ̼ Ǵ Ǹ ο ʽϴ. Ư ڿ Ư, ۱, ǥ Ǵ Ÿ ǿ Ǵ Ǹ ο ʽϴ.
Ʈ ۱. Ʈ ̼ οǴ , ǸŵǴ ƴմϴ. Ʈ 纻 մϴ. Ʈ ۱ ϸ Ʈ ̱, ѹα Ÿ ۱ǹ ȣ ϴ. Ʈ ۱ κ ϸ ȵ˴ϴ. ϴ Ʈ 縦 ̶ մϴ. Ʈ Ʈ ϴ , Ʈ ̳ Ʈ ǹ ʽϴ. 絵 Ʈ 纻 ϰ ̼ ༭ ؼϰڴٰ 쿡 Ʈ 絵 ֽϴ.
Ʈ ߰ . ġ Ǵ ϴ Ʈ ̰ų Ʈ "" Ǵ "Ÿ" (" Ʈ")̶ ǥõ , ˴ϴ.
Ʈ Ͽ ༭ ٸ 浹ϴ ٸ 켱 , ̴ 浹 ذῡ ʿ κп մϴ.
ϴ Ʈ Ʈ ƴ϶ Ʈ, Ÿ ս, ý Ǵ ٸ ų ִ ԵǾ ִٴ ϰ մϴ. Ʈ "ִ ״" Ǹ Ʈ ϴ ؿ ̳ å մϴ.
ϴ Ʈ ȴٵ簡 Ʈ ̶ Ǵ ǹ ƴϸ Ʈ ȣȯǴ Ʈ ̶ մϴ. ϴ Ʈ ؼ ų Ʈ ǰ Ǵ Ʈ Ͽ ϴ Ǵ ߿ δ Ͽ ִٴ մϴ.
ڿ Ʈ 쿡 ش ൵ Ʈ 뿡 ˴ϴ.
̵ . ڿ ̵ · Ʈ , Ϸκ 90 ̵ ῡ մϴ. ̷ ߰ߵǸ ڿ ̵ ݼϿ ̵ ȯϰų ٸ ش Ʈ ֽϴ.
Ÿ . 츦 ϰ Ʈ ǰ, ħ Ǵ Ư ռ Ͽ Ǵ "ִ ״" ˴ϴ. , ؽƮ, , ũ Ǵ Ʈ Ե Ÿ Ȯ̳ Ϻ Ͽ ̳ åӵ մϴ.
å . Ǵ ش ڴ Ʈ Ǵ ( ս, ߴ Ǵ ս ϵ ̿ ѵ ) Ͽ 쿡 å , ̴ ɼ ˰ ־ ϴ Դϴ. Ϻ // ̳ Ļ Ǵ μ ؿ å ϰų ϴ Ƿ, ڿ ֽϴ. ϴ // ٸ Ǹ ֽϴ. ǰ Ÿ ("ķ̼ǵ") ġ Բ Ʈ , ϴ ("ķ̼ǵ") ġ Ǵ ڰ ƴ϶ մϴ. ϴ ("ķ̼ǵ") ġ Բ Ʈ ùٸ ۵Ѵٴ ǥ ("ķ̼ǵ") ġ ۵ϵ Ʈ ʾ Ʈ ("ķ̼ǵ") ġ ùٸ ۵ ִٴ ϰ մϴ. ϴ Ʈ ("ķ̼ǵ") ġ ùٸ ۵ ɼ Ѵٴ մϴ. ϴ ("ķ̼ǵ") ġ Ʈ ǰ å, λ Ǵ û , ϴ Ҽ, , , մ ȣ ڰ ӿ, ȸ 迭翡 ϰ ̵ ظ ʵ ̶ մϴ. ̴ û Ʈ Ǵ Ͽ ¸߾ٴ Ÿ ϴ 쿡 Դϴ.
. Ʈ Ʈ λ̳ ִ ý̳ о(: Ƿ ý, Ǵ ý) ϵ Ǵ ȵǾų ش ʾҽϴ. ǵ ų Ʈ , ϴ ǵ ų ǰ å, λ Ǵ û , ϴ Ҽ, , , մ ȣ ڰ ӿ, ȸ 迭翡 ϰ ̵ ظ ʵ ̶ մϴ.
. ֽϴ. Ǹ ڴ ٷ Ʈ ıϰų Ʈ 纻 ڷ ݼؾ մϴ.
. ϴ û 浹 ĶϾ ˴ϴ. ϴ ǰ Ÿſ UN ʴ´ٴ մϴ. ؼ Ʈ ϸ ȵ˴ϴ. ǥ ٸ Ͽ ǹ ʽϴ.
ѵ Ǹ. Ʈ ߵ ̸ “ѵ Ǹ" ˴ϴ. , Ǵ FAR 52.227-14 DFARS 252.227-7013 et seq. Ǵ ļ ϴ. Ʈ Ѵٴ Ͽ ǰ մϴ. Ǵ ڴ Դϴ.
; . ٸ ༭ , Ǹ θ Ǵ ⺻ ˴ϴ.
: 11/5/15 10:56p
ڿ Ű Ե ǰ ᳪ ۻ ڰ մϴ. ġ ջǾų ջ 쿡 ǰ ʽϴ.
, Ǵ ÷κ ϴ ħ, , Ư ռ Ͽ(̿ ѵ ) , Ǵ ο ٸ üմϴ.
, , , , , , 糭, ġ Ǵ Ʈ ջ ǰ ü 쿡 ʽϴ. ǰ ڰ ִ ǺǸ Ʒ ϰ ܵ ǴϿ ϵ ǰ ü Ǵ ϰų RMA(Return Material Authorization) ȣ(Ʒ ) ( ) Բ ڿ Ͽ ǰ 븮̳ ڿ ǰ ǰ Ű ȯ 帳ϴ. ǰ ϴ ļ̳ нǿ å Ͽ ֽϴ. ǰ Ǵ 縦 ϰ ۺ ҷ ֽʽÿ.
ǰ ǰ̳ ǰ üϰų ǰ ֽϴ. ڿ ü ǰ̳ ǰ ڿ ˴ϴ. ϰų ü ǰ Ǵܿ ÿ ϰų ǰ˴ϴ. ܵ ǰ ǰ ϴ ǰ ü Ǹ մϴ.
ǰ ǰϱ +1 916-377-7000 Ͽ RMA(Return Material Authorization) ȣ ʽÿ.
ΰ Ϳ ڰ Ȯϸ RMA μ RMA ȣ ߱Ͽ ǰ Ѹ鿡 ϵ ûմϴ. RMA ȣ ϵ ǰ ʽϴ.
ڿ е Ͻ ǰ Ͻñ⸦ մϴ. 90 ̳ ó ǰϽø Ű ȯ ֽϴ. ǰ Ƽ ǰ ȯ 븮 ش ó ֽϴ. ڿ å ǰ ϸ ڷκ Ű ȯ 帳ϴ.
å ̰ Ȯ ջθ ѵ˴ϴ. 쿡 ħ, , ս, ߴ, ս Ǵ ս Ͽ(̿ ѵ ) ջ ̵ ҹ Ÿ ؼ ο ϰ Ǵ ߷ ջ(, Ư ջ ϵ ̿ ѵ ) å ʽϴ. ڿ ջ ɼ ˰ ־ 쿡 ˴ϴ. 뿡 ұϰ, Ŭӿ å ѵ ǰ ʰ ʽϴ. åӿ ̷ ǰ ϴ ʼ Ǵ Դϴ. ٸ Ÿ å ʽϴ.
Ϻ Ǵ ջ ܳ Ƿ Ͽ ֽϴ.
߿ о: ڿ ̼ Ǵ ̼ ڰ Ǵ ǰ ý, ý, Ǵ ý ߿ о߿ ǰ å , 뿡 δ ڰ մϴ. ̼ ڴ ڽ Ǵ ̼ ڰ о߿ ǰ ϴ Ŭκ ظ ʵ ȣϰ ؾ մϴ.
Ʈ: ǰ Բ Ʈ ϵ ʽϴ. Ʈ ǰ Բ ش Ʈ ̼ ༭ Ͻʽÿ.
: 2002 7 23 10:42a : 6
Desligue o computador e desconecte o cabo de alimentao. Se executar uma instalao "hot plug", verifique primeiro a documentao do servidor.
Remova a tampa do computador e a tampa do slot correspondente ao seu adaptador. Voc pode usar um slot mais comprido que o conector de seu adaptador, mas no tente instalar o adaptador em um slot mais curto que o conector PCI Express.
Insira firmemente o adaptador no slot e prenda a braadeira.
Recoloque a tampa do computador. Ligue o fio de eletricidade.
Adaptadores de cobre Intel® Ethernet de 10 Gigabits Use cabos Ethernet categoria 6, categoria 6a ou categoria 7.
Adaptador para servidor Intel® Ethernet de 10 Gigabits com mdulos pticos plugveis SFP+: Instale o mdulo e conecte o cabo de acordo com as instrues do fabricante
Adaptadores de fibra Intel® Ethernet 10 Gigabit com conector SC: Remova e guarde a tampa do conector de fibra ptica. Insira um conector de fibra ptica SC nas portas TX/RX da braadeira do adaptador.
Adaptadores de fibra Intel® Ethernet 10 Gigabit com conector LC: Remova e guarde a tampa do conector de fibra tica. Insira um conector LC no adaptador. Podem ser usados cabos de converso para outros tipos de conectores (como, por exemplo, SC) se o cabeamento corresponder s especificaes ticas do adaptador, inclusive as limitaes de comprimento.
Adaptadores CX4 Intel® Ethernet de 10 Gigabits Os cabos fsicos precisam atender norma IEEE 802.3ak, clusula 54. O conector de cabo necessrio um receptculo do tipo trava MDI, como definido pelo IEC 61076-3-113.
Ligue o computador e siga as instrues de instalao do driver conforme abaixo.
|
|
NOTAS:
|
O adaptador detectado como novo hardware quando o Windows inicia. Para instalar o driver correto:
O adaptador detectado e o Windows instala um driver residente Windows ou inicia o assistente Novo hardware encontrado .
Se o assistente iniciar, siga os avisos para instalar o driver a partir do CD contido neste pacote.
Se for instalado um driver residente do Windows (o assistente no aparece), atualize o driver inserindo o CD da Intel e clicando no boto Instalar drivers e software quando aparecer a janela de execuo automtica de Conexes de rede Intel .
Para criar um pacote binrio RPM* desse driver, execute 'rpmbuild -tb <filename.tar.gz>'. Substitua <filename.tar.gz> com o nome do arquivo especfico do driver.
|
|
NOTA: Para o build funcionar corretamente, o kernel em execuo PRECISA corresponder verso e configurao da origem de kernel instalada. Se voc tiver recompilado o kernel, reinicialize agora o sistema. A funcionalidade RPM foi testada somente nas distribuies do Red Hat. |
Mova o arquivo tar do driver bsico para o diretrio de sua escolha. Por exemplo, use '/home/username/ixgb' ou '/usr/local/src/ixgb'.
Extraia (Untar/unzip) o arquivo digitando a seguinte opo abaixo, onde <x.x.x> representa o nmero da verso para o tar do driver:
tar zxf ixgb-<x.x.x>.tar.gz
Mude para o diretrio src, onde <x.x.x> representa o nmero da verso para o tar do driver:
cd ixgb-<x.x.x>/src/
Compile o mdulo do driver:
make install
O binrio ser instalado como:
/lib/modules/[KERNEL_VERSION]/kernel/drivers/net/ixgb.o
Os locais da instalao listados acima so os locais padro. Eles no podem corrigir certas distribuies de Linux.
Instale o mdulo:
insmod ixgb <parmetro>=<valor>
Atribua um endereo IP interface, digitando a seguinte informao, onde <x> representa o nmero da interface:
ifconfig eth<x> <IP_address>
Verifique se a interface funciona. Digite o seguinte, onde <endereo_IP> o endereo IP de uma outra mquina na mesma subrede da interface que est sendo testada:
ping <IP_address>
Esse driver foi desenvolvido para ser usado com o kernel FreeBSD, verses 4.8 e posteriores.
|
|
NOTA: Voc deve ter as fontes do kernel instaladas a fim de compilar o mdulo do driver. |
Nas instrues abaixo, x.x.x a verso do driver que est indicada no nome do arquivo do tar do driver.
Mova o arquivo tar do driver bsico para o diretrio de sua escolha. Por exemplo, use /home/username/ixgb ou
/usr/local/src/ixgb.
Untar/unzip o arquivo:
tar xfz ixgb-x.x.x.tar.gz
Essa ao criar um diretrio ixgb-x.x.x.
Para instalar a pgina man:
cd ixgb-x.x.x
gzip -c ixgb.4 > /usr/share/man/man4/ixgb.4.gz
Para carregar o driver em um sistema em funcionamento, execute os passos a seguir:
cd ixgb-x.x.x
make
OU
cd ixgb-<x.x.x>/src/
make load
Digite o seguinte para atribuir um endereo IP interface:
ifconfig ixgb<numero_da_interface>
<endereo_IP>
Verifique se a interface funciona. Digite a seguinte informao, onde que <endereo_IP> o endereo IP de outro computador na mesma sub-rede da interface que est sendo testada:
ping <endereo_IP>
Se quiser que o driver carregue automaticamente quando o sistema for inicializado:
cd ixgb-x.x.x/src
make load
cp if_ixgb.ko /modules
Edite o /boot/loader.conf e adicione a seguinte linha:
if_ixgb_load="YES"
OU
compile o driver no kernel (veja o item 8).
Edite /etc/rc.conf e crie o <numero_de_interface> adequado do ifconfig_ixgb
:
ifconfig_ixgb<numero_de_interface>="<ifconfig_settings>"
Exemplo de uso:
ifconfig_ixgb0="inet 192.168.10.1 netmask 255.255.255.0"
NOTA: Para assistncia, consulte a pgina do man do ifconfig.
Para compilar o driver no kernel, digite:
cd ixgb-<x.x.x>/src/
mkdir /usr/src/sys/dev/ixgb
cp if_ixgb* /usr/src/sys/dev/ixgb
cp ixgb* /usr/src/sys/dev/ixgb
cp Makefile.kernel /usr/src/sys/modules/ixgb/Makefile
Editar o arquivo /usr/src/sys/conf/files.i386 e adicionar a seguinte linha:
dev/ixgb/ixgb_hw.c optional ixgb
dev/ixgb/ixgb_ee.c optional ixgb
dev/ixgb/if_ixgb.c optional ixgb
Remova as seguintes linhas do arquivo /usr/src/sys/conf/files.i386, se elas existirem:
/dev/ixgb/if_ixgb_fx_hw.c optional ixgb
/dev/ixgb/if_ixgb_phy.c optional ixgb
Edite o arquivo de configurao do kernel (isto , GENERIC ou MYKERNEL) em
/usr/src/sys/i386/conf e certifique-se de que a seguinte linha esteja presente:
device ixgb
Compile e instale o kernel. O sistema deve ser reinicializado para que as atualizaes do kernel tenham efeito.
Para informaes adicionais sobre a compilao do kernel, consulte a documentao do sistema operacional FreeBSD.
Para obter mais informaes, consulte o Guia do usurio no CD Intel ou no site de suporte da Intel: http://www.intel.com/p/pt_BR/support/.
Data da ltima modificao: 10 de outubro de 2007 - 15h49 Reviso
Copyright © 2002 - 2012 Intel Corporation. Todos os direitos reservados.
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA
A Intel Corporation no assume nenhuma responsabilidade por erros ou omisses neste documento. A Intel tambm no assume nenhum compromisso de atualizar as informaes aqui contidas.
Intel, Itanium e Pentium so marcas comerciais da Intel Corporation nos Estados Unidos e em outros pases.
* Outras marcas e nomes podem ser propriedade de outras empresas.
ltima modificao: 25 de janeiro de 2011 s 22:21 Reviso
PROXGB/DOCS/QUICK/PTB/license.htm 0000755 0000000 0000000 00000036450 11730046352 013146 0 ustar
CONTRATO DE LICENA DE SOFTWARE INTEL
IMPORTANTE LEIA ANTES DE COPIAR, INSTALAR OU USAR.
No copie, no instale nem use este software ou qualquer material associado (coletivamente o “Software”) fornecido sob este contrato de licena (“Contrato”) antes de ler cuidadosamente os termos e condies a seguir.
Ao copiar, instalar ou usar o Software, voc indica que concorda em se submeter aos termos deste Contrato. Se no concordar com os termos deste Contrato, no copie, no instale nem use o Software.
Note o seguinte:
LICENA DE SITE. Voc poder copiar o Software nos computadores da sua empresa, para uso na sua empresa, e poder fazer um nmero razovel de cpias de backup do Software, de acordo com as seguintes condies:
LICENA PARA USURIO NICO. Voc poder fazer uma cpia do Software em um nico computador para o seu uso pessoal, e poder criar uma cpia de backup do Software, de acordo com as seguintes condies:
LICENA PARA FABRICANTES DE EQUIPAMENTOS ORIGINAIS (OEM): Voc pode reproduzir e distribuir o Software apenas como parte integrante ou na forma incorporada ao seu produto, como atualizao de manuteno do Software para usurios existentes dos seus produtos, excluindo-se quaisquer outros produtos individuais, ou como uma distribuio maior do Software, incluindo, mas no se limitando a, a distribuio de uma imagem de instalao ou uma imagem de mquina virtual convidada (Guest), com estas condies:
RESTRIES DA LICENA. Voc NO pode: (i) usar ou copiar os Materiais exceto nas formas estabelecidas neste Contrato; (ii) alugar ou fazer lease dos Materiais a terceiros; (iii) ceder este Contrato ou transferir os Materiais sem o consentimento expresso e por escrito da Intel; (iv) modificar, adaptar ou traduzir os Materiais, no todo ou em parte, exceto nas formas estabelecidas neste Contrato; (v) fazer engenharia reversa, descompilar ou desmontar os Materiais; (vi) tentar modificar ou adulterar o funcionamento normal do gerenciador de licenas que regulamenta o uso dos Materiais; (vii) distribuir, sublicenciar ou transferir o cdigo fonte de qualquer componente dos Materiais, dos Redistribuveis e das Fontes de Amostras e seus derivados para terceiros, exceto nas formas estabelecidas neste Contrato.
NENHUM OUTRO DIREITO. A Intel no outorga a voc direitos nem licenas, implcitos ou explcitos, em relao a informaes de propriedade ou patentes, direitos autorais, trabalho de mscara, segredo comercial ou outro direito de propriedade intelectual de propriedade ou de controle da Intel, exceto nas formas expressamente estabelecidas neste Contrato. Exceto nas formas expressamente estabelecidas neste Contrato, no concedida a voc nenhuma licena ou direito, direto ou implcito, por induo, embargo ou outra forma. Especificamente, a Intel no concede nenhum direito expresso ou implcito a voc em relao a patentes, direitos autorais, marcas comerciais ou outros direitos de propriedade intelectual da Intel.
PROPRIEDADE DO SOFTWARE E DIREITOS AUTORAIS. O Software licenciado, no vendido. O ttulo de todas as cpias do Software permanece com a Intel. O Software contm direitos autorais e est protegido por leis dos Estados Unidos e de outros pases e por provises de tratados internacionais. Voc no pode remover nenhum aviso de direitos autorais do Software. Voc concorda em impedir qualquer cpia no autorizada do Software. A Intel pode fazer alteraes ao Software ou aos itens aqui citados a qualquer momento sem aviso prvio, mas no est obrigada a oferecer suporte ou a atualizar o Software. O Software s poder ser transferido se o destinatrio concordar totalmente com estes termos e se voc no retiver nenhuma cpia do Software.
TERMOS ADICIONAIS PARA SOFTWARE DE PR LANAMENTO. Se o Software que voc est instalando ou usando sob os termos deste Contrato for uma verso de pr lanamento comercial, ou for uma verso “alfa“ ou “beta“ do Software ("Software de pr lanamento"), ento os termos a seguir se aplicaro.
Se alguma clusula desta Seo entrar em conflito com qualquer termo ou condio deste Contrato em relao a Software de pr lanamento, esta Seo ter precedncia sobre o(s) outro(s) termo(s) e condio(es), mas apenas at o ponto necessrio para resolver o conflito.
Voc entende e reconhece que o Software um Software de pr lanamento, no representa o Software final da Intel e pode conter erros e outros problemas que podem causar perda de dados, falhas de sistema ou outras falhas. O Software de pr lanamento fornecido a voc "no estado em que se encontra" e a Intel se exime de fornecer garantias e no se responsabiliza por danos que possam ocorrer como consequncia do uso deste Software de pr lanamento.
Voc reconhece que a Intel no prometeu que o Software de pr lanamento ser lanado no futuro, que a Intel no tem obrigao explcita ou implcita de lanar o Software de pr lanamento e que a Intel pode no lanar nenhum Software que seja compatvel com o Software de pr lanamento. Voc reconhece que a totalidade da pesquisa e desenvolvimento que voc fizer e que for relacionada ao Software de pr lanamento ou a qualquer produto que use ou que esteja associado ao Software de pr lanamento feita por sua conta e risco.
Se a Intel forneceu a voc o Software de pr lanamento sob um contrato escrito separado, o uso que voc fizer deste Software de pr lanamento regido tambm por tal contrato.
GARANTIA LIMITADA DA MDIA. Se o Software tiver sido entregue pela Intel em mdia fsica, a Intel garante esta mdia contra defeitos fsicos de material por um perodo de noventa (90) dias a partir da data de entrega. Se for detectado algum defeito fsico, devolva a mdia Intel para substituio ou remessa alternativa do Software, a critrio da Intel.
EXCLUSO DE OUTRAS GARANTIAS. EXCETO PELO DESCRITO ACIMA, O SOFTWARE FORNECIDO "NO ESTADO EM QUE SE ENCONTRA", SEM QUALQUER GARANTIA EXPRESSA OU IMPLCITA DE QUALQUER TIPO, INCLUINDO AS GARANTIAS DE ADEQUAO AO MERCADO, AUSNCIA DE INFRAO OU ADEQUAO A UMA FINALIDADE PARTICULAR. A Intel no oferece garantia nem assume responsabilidade pela exatido ou pela integridade de quaisquer informaes, textos, grficos, links ou outros itens contidos no Software.
LIMITAO DE RESPONSABILIDADE. SOB NENHUMA CIRCUNSTNCIA A INTEL OU SEUS FORNECEDORES SE RESPONSABILIZARO POR QUALQUER DANO (INCLUINDO, MAS NO SE LIMITANDO A, PERDA DE LUCROS, INTERRUPO DE NEGCIOS OU PERDA DE INFORMAES) RESULTANTE DO USO OU INCAPACIDADE DE USO DO SOFTWARE, MESMO QUANDO A INTEL TIVER SIDO AVISADA DA POSSIBILIDADE DE OCORRNCIA DE TAIS DANOS. ALGUMAS JURISDIES PROBEM A EXCLUSO OU LIMITAO DA RESPONSABILIDADE PARA GARANTIAS IMPLCITAS OU PARA DANOS CONSEQENCIAIS OU INCIDENTAIS; PORTANTO, A LIMITAO ACIMA PODE NO SE APLICAR A VOC. VOC PODE TAMBM TER OUTROS DIREITOS LEGAIS QUE VARIAM DE JURISDIO PARA JURISDIO. Se voc usar o Software em conjunto com um dispositivo virtual (“emulado”) e destinado a aparecer como um produto Intel, voc reconhece que a Intel no a autora nem a criadora do dispositivo virtual (“emulado”). Voc entende e reconhece que a Intel no faz nenhuma afirmao sobre a correta operao do Software quando ele usado em um dispositivo virtual (“emulado”), que a Intel no projetou o Software para operar com o dispositivo virtual (“emulado”), e que o Software pode no ser capaz de funcionar corretamente com o dispositivo virtual (“emulado”). Voc concorda em assumir o risco de que o Software possa no funcionar corretamente em conjunto com o dispositivo virtual (“emulado”). Voc concorda em indenizar a Intel e manter a Intel e seus funcionrios, suas subsidirias e suas afiliadas isentos de responsabilidade contra todos os processos judiciais, custos, danos e despesas, alm de custos advocatcios razoveis, resultantes, direta ou indiretamente, de qualquer reclamao de obrigaes do produto, leses corporais ou morte associadas ao uso do Software em conjunto com o dispositivo virtual (“emulado”), mesmo sob a alegao de que a Intel foi negligente em relao ao design ou fabricao do Software.
USO NO AUTORIZADO. O SOFTWARE NO FOI PROJETADO NEM DESTINADO OU AUTORIZADO PARA USO EM QUALQUER TIPO DE SISTEMA OU APLICAO EM QUE A FALHA DO SOFTWARE PODE CAUSAR LESES CORPORAIS OU MORTE (POR EXEMPLO, SISTEMAS MDICOS, SISTEMAS DE SALVAMENTO OU DE MANUTENO DA VIDA). Se usar o Software em qualquer destas aplicaes no autorizadas, voc ir indenizar a Intel e manter a Intel e seus funcionrios, suas subsidirias e suas afiliadas isentos de responsabilidade contra todos os processos judiciais, custos, danos e despesas, alm de custos advocatcios razoveis, resultantes, direta ou indiretamente, de qualquer reclamao de obrigaes do produto, leses corporais ou morte associadas a tal uso no autorizado, mesmo sob a alegao de que a Intel foi negligente em relao ao design ou fabricao do Software.
RESCISO DESSE CONTRATO. A Intel pode rescindir este Contrato a qualquer momento no caso de violao dos seus termos. Com a resciso, voc destruir imediatamente o Software ou devolver todas as suas cpias Intel.
LEIS QUE SE APLICAM. As aes judiciais oriundas deste Contrato sero governadas pelas leis do Estado da Califrnia, EUA, sem considerar conflitos com outras leis. Voc concorda que os termos da Conveno das Naes Unidas sobre Contratos de Venda de Bens no se aplica a este Contrato. Voc no poder exportar o Software em violao s leis e regulamentos aplicveis exportao. A Intel no est obrigada ao cumprimento de quaisquer outros contratos, a menos que se apresentem por escrito e estejam assinados por um representante autorizado da Intel.
DIREITOS RESTRITOS DO GOVERNO. Este Software e esta documentao foram desenvolvidos com capital privado e so fornecidos com “DIREITOS RESTRITOS”. O uso, a duplicao ou a divulgao pelo Governo esto sujeitos s restries estabelecidas em FAR 52,227-14 and DFARS 252,227-7013 et seq. ou s suas clusulas substitutas ou s leis sucessoras. O uso deste produto pelo governo indica o reconhecimento dos direitos de propriedade da Intel sobre o Software. A Intel o fabricante ou o contratante.
IDIOMA; TRADUES. Se a verso no idioma ingls deste Contrato for acompanhada por qualquer outra verso traduzida para qualquer outro idioma, essa verso traduzida ser fornecida somente a ttulo de convenincia e a verso gerada no idioma ingls ter prioridade de controle legal.
Modificado em 15/5/11 22:56 Reviso
A Intel garante ao propriedade original que o produto adaptador entregue neste pacote no contm defeitos fsicos nem de fabricao. Esta garantia no cobre o produto adaptador, se ele for danificado no processo de instalao ou por uso inadequado.
A GARANTIA ACIMA SUBSTITUI QUALQUER OUTRA GARANTIA, QUER SEJA EXPRESSA, IMPLCITA OU ESTATUTRIA, INCLUSIVE, MAS NO LIMITADA A, QUALQUER GARANTIA DE NO-VIOLAO DE PROPRIEDADE INTELECTUAL, COMERCIALIZAO, ADEQUAO A UM PROPSITO ESPECFICO DECORRENTE DE QUALQUER PROPOSTA, ESPECIFICAO OU AMOSTRA.
Esta garantia no cobre a substituio de produtos ADAPTADOR danificados por uso indevido, acidente, uso incorreto, negligncia, alterao, reparo, desastre, instalao incorreta ou teste inadequado. Se o produto ADAPTADOR for considerado defeituoso, a Intel, se assim decidir, substituir ou consertar o produto de hardware gratuitamente, exceto conforme especificado a seguir, ou reembolsar o valor de aquisio, desde que o produto ADAPTADOR seja entregue com um nmero RMA (Return Material Authorization Autorizao de Material Devolvido ver abaixo), juntamente com um comprovante de compra (se no estiver registrado), ao negociante onde o produto foi comprado ou Intel, com uma explicao do problema em questo. Se voc enviar o produto ADAPTADOR, assumir o risco de dados ou perda durante o transporte. Use a embalagem original (ou equivalente) e pague o frete.
A Intel pode substituir ou consertar o produto ADAPTADOR com peas novas ou recondicionadas, e o produto ADAPTADOR ou a parte substituda pela Intel se tornar propriedade da Intel. Os produtos ADAPTADOR consertados ou substitudos sero devolvidos a voc, com o mesmo nvel de reviso recebido ou nvel superior, a critrio da Intel. A Intel se reserva o direito de substituir os produtos ADAPTADOR fora de linha por um produto ADAPTADOR de gerao atual equivalente.
Antes de devolver qualquer produto ADAPTADOR, entre em contato com o Suporte ao Cliente Intel e obtenha um Nmero RMA (Return Material Authorization Autorizao de Material Devolvido), ligando para +1 916-377-7000.
Se o Grupo do Suporte ao Cliente confirmar que o produto ADAPTADOR est com defeito, o departamento de RMA emitir um Nmero RMA para ser colocado na embalagem externa do produto ADAPTADOR. A Intel no pode aceitar qualquer produto sem um Nmero RMA na embalagem.
Devolva o produto adaptador ao local de compra para obter um reembolso ou uma troca.
A Intel quer v-lo totalmente satisfeito com o adaptador Intel que voc comprou. A qualquer momento dentro do prazo de noventa (90) dias a partir da data de compra, voc pode devolver o adaptador Intel ao local original de compra, para obter de seu fornecedor o reembolso do valor de aquisio. Os integradores e distribuidores, respectivamente, que aceitarem devolues e reembolsarem seus clientes, podem devolver os adaptadores Intel ao local original de compra. A Intel garante que aceitar as devolues coberta por esta diretiva, e reembolsar o valor de aquisio inicial aos clientes que comprarem diretamente na Intel.
A UNICA RESPONSABILIDADE DA INTEL AQUI PREVISTA ESTAR LIMITADA AOS DANOS DIRETA E OBJETIVAMENTE AVALIVEIS. EM HIPTESE ALGUMA, A INTEL SE RESPONSABILIZAR POR QUAISQUER DANOS INDIRETOS OU ESPECULATIVOS (INCLUINDO, MAS NO LIMITADO A, OS DANOS CITADOS ANTERIORMENTE, CONSEQENTES, INCIDENTAIS E ESPECIAIS) INCLUSIVE, MAS NO LIMITADO A, VIOLAO DA PROPRIEDADE INTELECTUAL, CUSTOS DE REABASTECIMENTO, IMPOSSIBILIDADE DE USO, INTERRUPES DE NEGCIOS, PERDA DE REPUTAO E LUCROS CESSANTES, QUER ESSES DANOS SURJAM POR NEGLIGNCIA CONTRATUAL, RETALIAO OU SOB QUALQUER GARANTIA, A DESPEITO DE A INTEL TER SIDO AVISADA ANTECIPADAMENTE SOBRE A POSSIBILIDADE DESSES DANOS. INDEPENDENTEMENTE DO DISPOSTO ANTERIORMENTE, A RESPONSABILIDADE TOTAL DA INTEL POR TODAS AS REIVINDICAES PREVISTAS NESTE CONTRATO NO DEVER ULTRAPASSAR O PREO PAGO PELO PRODUTO. ESSAS LIMITAES SOBRE AS POSSVEIS RESPONSABILIDADE FORAM UM COMPONENTE FUNDAMENTAL AO ESTIPULAR O PREO DO PRODUTO. A INTEL NO ASSUME NEM AUTORIZA QUALQUER PESSOA A ASSUMIR QUAISQUER OUTRAS RESPONSABILIDADES EM SEU NOME.
Alguns estados no permitem a excluso ou limitao de danos incidental ou conseqentes, de modo que as limitaes citadas anteriormente podem no ser aplicveis ao seu caso.
Aplicaes de controle crtico: A Intel se isenta especificamente da responsabilidade pelo uso do produto ADAPTADOR em aplicaes de controle crtico (incluindo, apenas para fins de exemplo, os sistemas de controle de segurana ou tratamento de sade, sistemas de controle de energia nuclear ou os sistemas de controle do trfego areo ou terrestre) por Licenciado ou Sublicenciados, e tal uso ser um risco total do usurio. O Licenciado concorda em defender, indenizar e isentar a Intel de e contra quaisquer e todas as reivindicaes decorrentes do uso do produto adaptador em tais aplicaes pelos Licenciado ou Sublicenciados.
Software: O software fornecido com o produto ADAPTADOR no est coberto pela garantia de hardware descrita anteriormente. Consulte o contrato de licena do software aplicvel, que acompanha o produto ADAPTADOR, para obter detalhes sobre a garantia do software.
ltima modificao em 23.07.02 10:42 6
&HƬ{7;@ߚ>O- S$1p-0TIJw o _[5
ȋFv) pGJ)w<WG Y, :#{?>
3hKAN*QY$Br~vG>'LSk!Ai MlNp7 @v!ܘ4xrRnXWV!1= 7J=`6Q*:9x"pё .` pt
p[*r*n' t ;Kn[),bט -c#S)#0Ypl2U, ^P
v+ GP4-a}n=}PҼC)|~}@P2- "ɱ"P F^M J\s `]M3D E(E.S"!. k pT $PGm~Qhl[zbF/,e:>^'
̾ ]xߖz~>wBr s6~8r Ӓ%
1/@AK-L 5 1AOl)vF?kV+U7-N<6K|PAgF:\8=pB `fb_ $1ֈ.16cذaa
K@" =hQCF!E$ab)U, `˕1eΤYӦ0o@OAW6@9@ (*4(@@h`Ӕ
S@v $Y⇖&BbE Lx B
" I.fLC
2 tbdΡWJU@,` 3 p$š U8ME& !cgL; `V0Р'P
n^{ $MtAsYMM2snJ: B PvNR Н P%=eq: t% 6KtW q ` _ pKW1N$sYRV
p5S6K e0$p Px0 (
Wӓ>rhͤ( AÅ
BXE5nh@B!I8
u):J
x ! =DCds̰@0"h
+d O1
DV[e
2Ṭ(>Ax \ FH"3z@ #%,Ia
n:-C1VZ%TR VZT 77;!@`4(PA-(PQIV=s J=hUK" sTϳ85!PՋ]cp]E]{ (6(B 0(dmV8.E`pe9fxN R]`M e $b'@ObBЅ `;pԼK
)xf8p 7"aD`[zHyh1*@@f%h.N0fIG +Ö5H/PϡHL V8#sh!n6INhj_4c!p=`j:ߪְ -܄4p@[X8'Lt7;Chg_03%@GP ) F҂ e bA20B9iD
4+Ects =IQje\.QCC_h>( @tp 04!kt`
A h!3͂p,t6[p)UN.9&pa V `2f34& 1`%Cr[FQ)G @hDeP,Ya p
Z >0F5э< gf0\XRTଞ)!&2EgD,8RЉ la&ApBafI*eU^o`XR$eGSCPt!(hBW (n`A LD8@nvNH m6"Ax t y2x%t*-HB b I
PHSR>S):Ci$G=zXALPyB> \ `F@&d@LlziRj\c e%! TB J ]_4 3{:@Y@Y3pP)V * P$j@e N/XV] $8a(
p "!Z Gp D =mN}kq+` ȹNtD!Ηw:`'0&$@
W@tw]2vj 9Ԫl$U<ň қ2[F5Za\aD)15 V :ЁEOL`#t -mS f_f|8A(̬kurD'.ı5 (bA '
ժCw1d<wEMe( 0 !X|q)
51I;t .0
tρ=Z
G vM$f# * #7{A /sʁh
1.9J] K
:$[0aoUHV_D(`CWȀ
U*d(#@0P!D " c! @-( ,H7r nBnja#(=5T|nQHAp q
\ ~/X!U`*3+/V";vD++妪^7V 9nM\xQ.eJa# 4' , p )l 0 KHp 0 8ֻ~) pMK(XXa ! ÿ S !a <0p8Cb (4(P @Vš[ c
i8@=5X4i$h"r { P&B x7</P 6:W4`]0 X
#c'ɺ:?3$4r
#Բ ?7|C8sH I0 ((X 2SG)'i ɔ*,-88
SFh ˹,&>K0P`DXB 8cY HMhD4Hr"9[iy+Xu, +C+h9 hwdGww|>; K@`X6q zDXF\H &
D0,O4 ) p RxH ڻ=0' B`*SL=@FdtHHcN) i!),FjartS+`7-!-7h8 This driver and software are designed to operate with the following Intel® 10GbE
Server Adapters:
†Board ID # = A 6-digit code with a 3-digit extension;
printed on barcode sticker on the front of the card. See the Adapter & Driver ID Guide:
http://support.intel.com/support/go/network/adapter/home.htm
The following devices are not supported by Microsoft* Windows* 7: The following devices are not supported by Microsoft Windows Vista*: Some Intel® 10 Gigabit Network Adapters and Connections support SFP+
pluggable optical modules. Please see SFP+ Devices with Pluggable Optics
Depending on your copper adapter, the cabling type used is 10GBASE-T or CX4. Maximum lengths for Intel® 10 Gigabit Server Adapters and Connections that use 10GBASE-T on Category 6, Category 6a, or Category 7 wiring, twisted 4-pair
copper: Intel® 10 Gigabit Server Adapters and Connections automatically
accommodate either MDI or MDI-X connections. The auto-MDI-X feature of Intel
copper adapters allows you to directly connect two adapters without
using a cross-over cable. To ensure compliance with CISPR
24 and the EU's EN55024, Intel® 10 Gigabit Server Adapters and Connections should be used only with CAT 6a shielded
cables that are properly terminated according to the recommendations in
EN50174-2.
The IEEE standard defines a worst-case cable
length of 15 meters (49 ft.), based on 100 O, twinaxial cable
characteristics. However, commercial cable manufacturers may offer
enhanced products that will permit successful operation over greater
distances.
The following is a list of 3rd party SFP+ modules that have received some testing. Not all modules are applicable to all devices. The following is a list of SFP+ modules and direct attach cables that have
received some testing. Not all modules are applicable to all devices. THIRD PARTY OPTIC
MODULES AND CABLES REFERRED TO ABOVE ARE LISTED ONLY FOR THE PURPOSE OF
HIGHLIGHTING THIRD PARTY SPECIFICATIONS AND POTENTIAL COMPATIBILITY, AND ARE NOT
RECOMMENDATIONS OR ENDORSEMENT OR SPONSORSHIP OF ANY THIRD PARTY'S PRODUCT BY
INTEL. INTEL IS NOT ENDORSING OR PROMOTING PRODUCTS MADE BY ANY THIRD PARTY AND
THE THIRD PARTY REFERENCE IS PROVIDED ONLY TO SHARE INFORMATION REGARDING
CERTAIN OPTIC MODULES AND CABLES WITH THE ABOVE SPECIFICATIONS. THERE MAY BE
OTHER MANUFACTURERS OR SUPPLIERS, PRODUCING OR SUPPLYING OPTIC MODULES AND
CABLES WITH SIMILAR OR MATCHING DESCRIPTIONS. CUSTOMERS MUST USE THEIR OWN
DISCRETION AND DILIGENCE TO PURCHASE OPTIC MODULES AND CABLES FROM ANY THIRD PARTY OF THEIR CHOICE. CUSTOMERS ARE SOLELY
RESPONSIBLE FOR ASSESSING THE SUITABILITY OF THE PRODUCT AND/OR DEVICES AND FOR
THE SELECTION OF THE VENDOR FOR PURCHASING ANY PRODUCT. THE OPTIC MODULES AND
CABLES REFERRED TO ABOVE ARE NOT WARRANTED OR SUPPORTED BY INTEL. INTEL ASSUMES
NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY,
RELATING TO SALE AND/OR USE OF SUCH THIRD PARTY PRODUCTS OR SELECTION OF VENDOR
BY CUSTOMERS. Remove and save the fiber optic connector cover. Insert a fiber optic
cable into the ports on the
network adapter bracket as shown.
Most connectors and ports are keyed for proper orientation. If the cable
you are using is not keyed, check to be
sure the connector is oriented properly (transmit port connected to
receive port on the link partner, and vice versa).
For Intel® 10GbE LR Server Adapters:
For Intel® 10GbE SR Server Adapters: The adapter must be connected to a compatible link partner, such as an IEEE
802.3ae-compliant 10-gigabit switch, which is operating at the same laser
wavelength as the adapter. Conversion cables to other connector types (such as SC-to-LC) may be used
if the cabling matches the optical specifications of the adapter, including
length limitations.
qnc!@ N~2OV2e
]&qȊZ
Hj~[& .SA)yBiqg[wvpT-[WqF/#BXZ2'HJ)e#4C-Q:6cTbV+u)CB ?F].آ<2L*R`%$R ;H.(fGX䯳mg8vvP!: bb MPj ܾ̀7 apØ D Yr+G~4O:"piTX-S ŷ9KT;KG6ֹ&@`Xsӗ98c.s`o9B sn^C^ss窥*ʒ \̓6}Bm`slKW5q \Ԣ43fWyg*!EQl窨kD~nq:YݭP# e( #I~- ZMp^ Direct Cache Access enables a capable I/O device such as a network controller
to activate a pre-fetch engine in the CPU that loads arriving packet data into
the CPU cache for immediate access by the network stack process. This reduces
the number of memory access operations required to process each packet, reducing
CPU load and increasing throughput.
DCA takes advantage of high-speed cache and eliminates processor cycles required
to read packet headers and descriptors from system memory. To successfully install or uninstall the drivers or software, you must have
administrative privileges on the computer completing installation. Before installing or updating the drivers, insert your adapter(s) in the computer
and plug in the network cable. When Windows discovers the new adapter, it
attempts to find an acceptable Windows driver already installed with the operating
system. If found, the driver is installed without any user intervention. If Windows
cannot find the driver, the Found New Hardware Wizard window is
displayed. Regardless of whether or not Windows finds the driver, it is
recommended that you follow the procedure below to install the driver. Drivers
for all Intel adapters supported by this software release are installed. If you are installing drivers from the Product CD, insert
the CD. If you do not have the Product CD, download
drivers from the support website and transfer them to the system. If the Found New Hardware Wizard screen is displayed, click
Cancel. Start the autorun located on the CD. If you downloaded the
software package from the support website, the autorun automatically runs
after you have extracted the files. Click Install Drivers and Software. Follow the instructions in the install wizard. These instructions uninstall the drivers for all Intel adapters in a
system. From the Control Panel, double-click Add/Remove
Programs. Select Intel(R) Network Connections Drivers.
Click Add/Remove.
When the confirmation dialog displays, click OK. In the default mode, an Intel® Network Adapter using
copper connections will attempt to auto-negotiate with its link partner to
determine the best setting. If the adapter cannot establish link with the link partner
using auto-negotiation, you may need to manually configure the adapter and link
partner to identical settings to establish link and pass packets. This should
only be needed when attempting to link with an older switch that does not
support auto-negotiation or one that has been forced to a specific speed or
duplex
mode. Your link partner must match the setting you choose. Fiber-based adapters operate only in full duplex, and
only at their native speed. By default, auto-negotiation is enabled. Change this
setting only
to match your link partner.
Per the IEEE specification, gigabit speed is available only in full-duplex. The settings available when auto-negotiation is disabled are: 10 Mbps or 100 Mbps Full duplex (requires a full
duplex capable link partner set to full duplex). The adapter can send and receive
packets at the same time. You must set this mode manually. 10 Mbps or 100 Mbps Half duplex (requires a link
partner set to half duplex). The adapter performs one operation at a time;
it either sends or receives. You must set this mode manually. Auto-Negotiation 1000 Mbps. The adapter only
advertises gigabit speed at full duplex. Intel® 10 Gigabit adapters that support 1 gigabit
speed allow you to configure the Speed setting. If this option is not present,
your adapter only runs at its native speed. If the adapter cannot
establish link with the gigabit link partner using auto-negotiation, set the
adapter to 1 Gbps Full duplex. Intel 10 gigabit fiber-based adapters and SFP direct-attach devices operate only in full duplex, and
only at their native speed. Multi-speed 10 gigabit SFP+ fiber modules
support full duplex at 10 Gbps and 1 Gbps. The settings available when auto-negotiation is disabled are: 10 Mbps or 100 Mbps Full duplex (requires a full
duplex capable link partner set to full duplex). The adapter can send and receive
packets at the same time. You must set this mode manually. 10 Mbps or 100 Mbps Half duplex (requires a link
partner set to half duplex). The adapter performs one operation at a time;
it either sends or receives. You must set this mode manually.
Intel® network adapters are enabled for use in selected servers equipped with PCI Hot Plug support and running Microsoft* Windows*
operating systems.
For more information on setting up and using PCI Hot Plug support in your server, see your hardware and/or Hot Plug support
documentation for details.
PCI
Hot Plug only works when you hot plug an identical Intel network adapter.
Microsoft* Hyper-V* makes it possible for one or more operating systems to run
simultaneously on the same physical system as virtual machines. This allows
you to consolidate several servers onto one system, even if they are running
different operating systems. Intel® Network Adapters work with, and
within,
Microsoft Hyper-V virtual machines with their standard drivers and software.
See
http://www.intel.com/technology/advanced_comm/virtualization.htm for
more information on using Intel Network Adapters in virtualized
environments. When a Hyper-V Virtual NIC (VNIC) interface
is created in the parent partition, the VNIC takes on the MAC address of the
underlying physical NIC. The same is true when a VNIC is created on a team or
VLAN. Since the VNIC uses the MAC address of the underlying interface,
any operation that changes the MAC address of the interface
(for example, setting LAA on the interface, changing the primary adapter on a
team, etc.), will cause the VNIC
to lose connectivity. In order to prevent this loss of connectivity, Intel®
PROSet will not allow you to change settings that change the MAC address. Notes:
The virtual machine switch is part of the network I/O data path. It sits
between the physical NIC and the virtual machine NICs and routes packets to
the correct MAC address. Enabling Virtual Machine Queue (VMQ) offloading in
Intel(R) ProSet will automatically enable VMQ in the virtual machine switch.
For driver-only installations, you must manually enable VMQ in the virtual
machine switch. If you create ANS VLANs in the parent partition, and
you then create a Hyper-V Virtual NIC interface on an ANS VLAN, then
the Virtual NIC interface *must* have the same VLAN ID as the ANS VLAN. Using a
different VLAN ID or not setting a VLAN ID on the Virtual NIC interface will result in loss of communication on that interface. Virtual Switches bound to an ANS VLAN will have the same MAC address as the VLAN, which will have the same address as the underlying NIC or team. If you have several VLANs bound to a team and bind a virtual switch to each VLAN, all of the virtual switches will have the same MAC address. Clustering the virtual switches together will cause a network error in Microsoft’s cluster validation tool. In some cases, ignoring this error will not impact the performance of the cluster. However, such a cluster is not supported by Microsoft. Using Device Manger to give each of the virtual switches a unique address will resolve the issue. See the Microsoft Technet article Configure MAC Address Spoofing for Virtual Network Adapters for more information. Virtual Machine Queues (VMQ) cannot be enabled on a Hyper-V Virtual NIC interface bound to an ANS VLAN. If you want to use a team or VLAN as a virtual NIC you must follow these
steps:
Microsoft Windows Server* Core does not have a GUI interface. If you want to use an ANS Team or VLAN as a Virtual NIC, you must use the prosetcl.exe
utility, and
may need the nvspbind.exe utility, to set up the configuration. Use the prosetcl.exe utility
to create the team or VLAN. See the prosetcl.txt file for installation and usage
details. Use the nvspbind.exe utility to unbind the protocols on the team or
VLAN. The following is an example of the steps necessary to set up the
configuration. Enabling VMQ offloading increases receive and
transmit performance, as the adapter hardware is able to perform these tasks
faster than the operating system. Offloading also frees up CPU resources.
Filtering is based on MAC and/or VLAN filters.
CAUTION: Turn off and
unplug the server before removing the server's cover. Failure to do
so could endanger you and may damage the adapter or server.
CAUTION: Some PCI-Express
adapters may have a short connector, making them more fragile than
PCI adapters. Excessive force could break the connector. Use caution
when pressing the board in the slot.
CAUTION: Turn off and
unplug the server before removing the server's cover. Failure to do
so could endanger you and may damage the adapter or server.
CAUTION: Some PCI-Express
adapters may have a short connector, making them more fragile than
PCI adapters. Excessive force could break the connector. Use caution
when pressing the board in the slot. If your computer supports PCI Hot Plug, see your computer
documentation for special installation instructions.
Shut down the operating system. Turn off and unplug your computer. Then remove the cover. CAUTION: Turn off and unplug the
power before removing the computer's cover. Failure to do so could
endanger you and may damage the adapter or computer. Remove the cover bracket from a PCI
(v2.3 compliant) bus master slot, or a PCI-X (v1.0a compliant) slot. (This
adapter uses 3.3v signaling.) If you have configuration problems, see your computer's
documentation to determine if the PCI slots are bus master-enabled.
PCI and PCI-X bus theoretical speed designations are shown below: NOTE: Intel highly recommends installing a 10GbE
adapter in a 133MHz PCI-X slot. Slower slots will significantly
degrade adapter performance. Insert the adapter in an available PCI or PCI-X slot. Push the adapter into the slot until the adapter is firmly seated.
Secure the adapter bracket with a
screw, if required. Repeat steps 4 through 6 for each additional adapter to be
installed. Replace the computer cover and plug in the power cord. Turn the power on and start your operating system. N U ` lw=n.L.Ԕ-W `奺tЎ?O{.Xg @/e
@:Q A
߽9
E0 _ pikK}) ͨ |:ͯOѱ/H( F CpXiVp 3?*tI| VD0A 4V'C%NX w-d&" (ȄEJ
P+̤Ys ClE%@ UԊ3 d@2gDLdŮN,* "[qS9!lڄ
1Υ[wD KtJI*?4Bf6z΄bd?
M2YP,\`
"9udH=@&CvU ݻ' 60Jkx\saYmJLRDIQ (vEz*3 1Sz)հGlEvm@ *$8#?F :"HPB;,. 6Kh=X3gQ*Q?\
$pHA,6
Pے'tL(1@qD
Xb>sFꬲh/
{)fMH" H$=4(CTz2 1ƴ "( q'>1ɤ싢43]LJɚZdfl`-?4B
UB|1Lh<HÝ.[ | L'T%2E"*|(`rV3H8cUFghݯX
Сeg(h2 '
a%;8L 0 X,pwD,,(E6ɡd9s,_pK>DXcJB
9Y60w 4 b
N&`.F-03,f aID4vg=۳ՠe4
>^zj .QZ*&o9BvՑ28 >/ԝĈ,̒'(
68.8 *uUpGkq}BܣAz1îPG0Hr'% ׃2pR,̱bltV<+zg9yɳ/Ȑ0hY$jhh% j#xm@e>ԓ 0` BE!@@b%d`h#_g>%6_a .
1$
1 D 606d_<ԶL2c!
;0Y d_#WRIicFL!A-z" Intel® I/O
Acceleration Technology (Intel® I/OAT) is an Intel platform network technology that
accelerates, optimizes and seamlessly scales enterprise servers on Microsoft Windows
Server* and Linux* operating systems. Acceleration moves networking data to applications faster.
Optimization allows you to increase the load on your
servers without increasing power consumption. Seamless multiple port scaling gives you increased networking throughput from teaming along with reliable server and
application availability. Implementing Intel I/OAT requires no change to your existing network
configuration or existing security implementations. This is a platform-level solution for data movement. Thus, several
ingredients are necessary for a system to be Intel I/OAT capable: Your system memory channels should be fully populated. Intel recommends a
minimum of 4 GB of system memory or 1 GB per channel. Refer to your system guide
for specific information regarding memory channels. In a Windows environment, the following advanced settings must be enabled (see the Intel® PROSet link
in the left pane): Internet Protocol (IP) Security (IPSec) is a set of protocols used to help
secure the exchange of IP data. IP Security offloading is the assignment of
algorithm computations from software to hardware. Generally, CPU utilization
decreases and
network performance increases when offloading takes place. On Intel devices that support IPSec offloading features, you can
configure those features through Intel® PROSet.
For more information, select Intel PROSet in the Table of Contents (left pane)
of this window. NOTE: Large Send Offload (LSO) and
IPSec Offload are not compatible. LSO is automatically disabled when IPSec
Offload is enabled. This may reduce the performance of non-IPSec traffic.
Confining all of your IPSec traffic to one port and enabling IPSec Offload only
on that port may mitigate this issue. Jumbo frames are Ethernet frames that are larger than 1518 bytes. You can use
Jumbo Frames to reduce server CPU utilization and increase throughput. However, additional latency may be
introduced. Jumbo Frames are
supported at 1000 Mbps and 10Gbps. Using Jumbo Frames at 10 or 100 Mbps is not supported and may
result in poor performance or loss of link. End-to-end network hardware must support this capability; otherwise, packets
will be dropped. Jumbo Frames can be implemented simultaneously with VLANs and teaming. To configure Jumbo Frames at the switch, consult your network administrator
or switch user's guide. Restrictions: Jumbo frames are not supported in multi-vendor team
configurations. Supported protocols are limited to IP (TCP, UDP). Jumbo frames require compatible switch connections that
forward Jumbo Frames. Contact your switch vendor for more information. When standard sized Ethernet frames (64 to 1518 bytes) are
used, there is no benefit to configuring Jumbo Frames. The Jumbo Frames setting on the switch must be set to at least 8 bytes larger than the adapter
setting for Microsoft* Windows* operating systems, and at least 22 bytes larger for
all other operating systems. The Intel® PRO/1000 PL Network Connection supports
jumbo frames in Microsoft* Windows* operating systems only when Intel® PROSet
for Windows Device Manager is installed. The following devices do not support jumbo frames larger
than 4096 bytes: Intel® 82577LM Gigabit Network Connection Intel® 82578DM Gigabit Network Connection. The following devices do not support jumbo frames: Open Microsoft* Windows* Device Manager. Open Properties on your adapter. Click the Advanced tab. Select Jumbo Frames from the list of advanced features. Set your desired packet size (based on network capability). Click OK to apply the changes. All equipment on the network must also support the larger frame size. When
setting up Jumbo Frames on other network devices, be aware that different
network devices calculate Jumbo Frame size differently. Some devices include
the header information in the frame size while others do not. Intel adapters do
not include header information in the frame size. When configuring Jumbo
Frames on a switch, set the frame size four bytes higher for CRC, plus four
bytes if you are using VLANs or QoS packet tagging. Some adapter models come with a small bracket in the product
package, to be used in a low profile slot. If you need to install the adapter in
a low-profile slot, follow these instructions. Before handling the adapter, ground yourself to dissipate any static charge. Remove the two screws securing the standard bracket to the back
side of the adapter. Slide the bracket away from the adapter. Slide the low profile bracket onto the adapter. Attach the low profile bracket to the adapter using the
screws you removed in step 2. Carefully tighten the screws until they are seated. Do not over tighten. You may re-attach the standard sized bracket in the future
if necessary. Copyright © 2002 - 2012 Intel Corporation.
All rights reserved. Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 USA Intel Corporation assumes no responsibility for errors or omissions in this document.
Nor does Intel make any commitment to update the information contained herein. Intel, Itanium, and Pentium are trademarks of Intel Corporation in the U.S. and other countries. *Other names and brands may be claimed as the property of others. INTEL SOFTWARE LICENSE AGREEMENT IMPORTANT - READ BEFORE COPYING, INSTALLING OR USING. Do not copy, install, or use this software and any associated materials (collectively, the “Software”) provided under this license agreement (“Agreement”) until you have carefully read the following terms and conditions. By copying, installing, or otherwise using the Software, you agree to be bound by the terms of this Agreement.
If you do not agree to the terms of this Agreement, do not copy, install, or use the Software. Please Note: SITE LICENSE: You may copy the Software onto your organization’s computers for your organization’s use, and you may make a reasonable number of back-up copies of the Software, subject to these conditions: SINGLE USER LICENSE:
You may copy the Software onto a single computer for your personal use, and you may make one back-up copy of the Software, subject to these conditions: OEM LICENSE:
You may reproduce and distribute the Software only as an integral part of or incorporated in your product, as a standalone Software maintenance update for existing end users of your products, excluding any other standalone products, or as a component of a larger Software distribution, including but not limited to the distribution of an installation image or a Guest Virtual Machine image, subject to these conditions: LICENSE RESTRICTIONS.
You may NOT:
(i) use or copy the Materials except as provided in this Agreement;
(ii) rent or lease the Materials to any third party;
(iii) assign this Agreement or transfer the Materials without the express written consent of Intel;
(iv) modify, adapt, or translate the Materials in whole or in part except as provided in this Agreement;
(v) reverse engineer, decompile, or disassemble the Materials;
(vi) attempt to modify or tamper with the normal function of a license manager that regulates usage of the Materials;
(vii) distribute, sublicense or transfer the Source Code form of any components of the Materials, Redistributables and Sample Source and derivatives thereof to any third party except as provided in this Agreement. NO OTHER RIGHTS.
No rights or licenses are granted by Intel to you, expressly or by implication, with respect to any proprietary information or patent, copyright, mask work, trademark, trade secret, or other intellectual property right owned or controlled by Intel, except as expressly provided in this Agreement.
Except as expressly provided herein, no license or right is granted to you directly or by implication, inducement, estoppel, or otherwise.
Specifically, Intel grants no express or implied right to you under Intel patents, copyrights, trademarks, or other intellectual property rights. OWNERSHIP OF SOFTWARE AND COPYRIGHTS.
The Software is licensed, not sold.
Title to all copies of the Software remains with Intel.
The Software is copyrighted and protected by the laws of the United States and other countries and international treaty provisions.
You may not remove any copyright notices from the Software.
You agree to prevent any unauthorized copying of the Software.
Intel may make changes to the Software, or to items referenced therein, at any time without notice, but is not obligated to support or update the Software.
You may transfer the Software only if the recipient agrees to be fully bound by these terms and if you retain no copies of the Software. ADDITIONAL TERMS FOR PRE-RELEASE SOFTWARE.
If the Software you are installing or using under this Agreement is pre-commercial release or is labeled or otherwise represented as “alpha-“ or “beta-“ versions of the Software ("pre-release Software"), then the following terms apply. To the extent that any provision in this Section conflicts with any other term(s) or condition(s) in this Agreement with respect to pre-release Software, this Section shall supersede the other term(s) or condition(s), but only to the extent necessary to resolve the conflict. LIMITED MEDIA WARRANTY.
If the Software has been delivered by Intel on physical media, Intel warrants the media to be free from material physical defects for a period of ninety days after delivery by Intel.
If such a defect is found, return the media to Intel for replacement or alternate delivery of the Software as Intel may select. EXCLUSION OF OTHER WARRANTIES.
EXCEPT AS PROVIDED ABOVE, THE SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE.
Intel does not warrant or assume responsibility for the accuracy or completeness of any information, text, graphics, links, or other items contained within the Software. LIMITATION OF LIABILITY.
IN NO EVENT SHALL INTEL OR ITS SUPPLIERS BE LIABLE FOR ANY DAMAGES WHATSOEVER (INCLUDING, WITHOUT LIMITATION, LOST PROFITS, BUSINESS INTERRUPTION, OR LOST INFORMATION) ARISING OUT OF THE USE OF OR INABILITY TO USE THE SOFTWARE, EVEN IF INTEL HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
SOME JURISDICTIONS PROHIBIT EXCLUSION OR LIMITATION OF LIABILITY FOR IMPLIED WARRANTIES OR CONSEQUENTIAL OR INCIDENTAL DAMAGES, SO THE ABOVE LIMITATION MAY NOT APPLY TO YOU.
YOU MAY ALSO HAVE OTHER LEGAL RIGHTS THAT VARY FROM JURISDICTION TO JURISDICTION.
In the event that you use the Software in conjunction with a virtual (“emulated”) device designed to appear as an Intel component product, you acknowledge that Intel is neither the author nor the creator of the virtual (“emulated”) device.
You understand and acknowledge that Intel makes no representations about the correct operation of the Software when used with a virtual (“emulated”) device, that Intel did not design the Software to operate in conjunction with the virtual (“emulated”) device, and that the Software may not be capable of correct operation in conjunction with the virtual (“emulated”) device.
You agree to assume the risk that the Software may not operate properly in conjunction with the virtual (“emulated”) device.
You agree to indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with the use of the Software in conjunction with the virtual (“emulated”) device, even if such claim alleges that Intel was negligent regarding the design or manufacture of the Software. UNAUTHORIZED USE.
THE SOFTWARE IS NOT DESIGNED, INTENDED, OR AUTHORIZED FOR USE IN ANY TYPE OF SYSTEM OR APPLICATION IN WHICH THE FAILURE OF THE SOFTWARE COULD CREATE A SITUATION WHERE PERSONAL INJURY OR DEATH MAY OCCUR (E.G MEDICAL SYSTEMS, LIFE SUSTAINING OR LIFE SAVING SYSTEMS).
If you use the Software for any such unintended or unauthorized use, you shall indemnify and hold Intel and its officers, subsidiaries and affiliates harmless against all claims, costs, damages, and expenses, and reasonable attorney fees arising out of, directly or indirectly, any claim of product liability, personal injury or death associated with such unintended or unauthorized use, even if such claim alleges that Intel was negligent regarding the design or manufacture of the part. TERMINATION OF THIS AGREEMENT.
Intel may terminate this Agreement at any time if you violate its terms.
Upon termination, you will immediately destroy the Software or return all copies of the Software to Intel. APPLICABLE LAWS.
Claims arising under this Agreement shall be governed by the laws of the State of California, without regard to principles of conflict of laws.
You agree that the terms of the United Nations Convention on Contracts for the Sale of Goods do not apply to this Agreement.
You may not export the Software in violation of applicable export laws and regulations.
Intel is not obligated under any other agreements unless they are in writing and signed by an authorized representative of Intel. GOVERNMENT RESTRICTED RIGHTS.
The enclosed Software and documentation were developed at private expense, and are provided with “RESTRICTED RIGHTS.”
Use, duplication, or disclosure by the Government is subject to restrictions as set forth in FAR 52.227-14 and DFARS 252.227-7013 et seq. or its successor.
The use of this product by the Government constitutes acknowledgement of Intel’s proprietary rights in the Software.
Contractor or Manufacturer is Intel. LANGUAGE; TRANSLATIONS.
In the event that the English language version of this Agreement is accompanied by any other version translated into any other language, such translated version is provided for convenience purposes only and the English language version shall control. The Intel® Ethernet Converged Network Adapter X540-T1 has the following indicator lights: Label Indication Meaning The Intel® Ethernet Server Adapter X520-T2 has the
following indicator lights: Label Indication Meaning The Intel® 10 Gigabit AF DA Dual Port Server Adapter and
Intel® Ethernet Server Adapter X520 series of adapters have the
following indicator lights: Label Indication Meaning The Intel® 10 Gigabit AT Server Adapter has the following indicator
lights: Label Indication Meaning The Intel® 10 Gigabit CX4 Dual Port Server Adapter has the following indicator lights: Label Identity. Use the
"Identify Adapter" button in Intel
PROSet to control blinking. See Intel PROSet Help for more information. The Intel® 10 Gigabit XF SR and LR Server Adapters has the following indicator lights: Label Identity. Use the
"Identify Adapter" button in Intel
PROSet to control blinking. See Intel PROSet Help for more information. The Intel® 10 Gigabit XF SR Dual Port Server Adapters has the following indicator lights: Label Identity. Use the
"Identify Adapter" button in Intel
PROSet to control blinking. See Intel PROSet Help for more information. The LLI feature enables the network device to by-pass the configured
interrupt moderation scheme based on the type of data being received. It
configures which arriving TCP packets trigger an immediate interrupt, enabling
the system to handle the packet more quickly. Reduced data latency enables some
applications to gain faster access to network data.
LLI Options: You may evoke LLI for data packets containing a TCP PSH flag in the header or
for specified TCP ports. The
ability to remotely wake computers is an important development in computer
management. This feature has evolved over the last few years from a simple
remote power-on capability to a complex system interacting with a variety of
device and operating system (OS) power states.
The following adapters do not
support Wake on LAN* (WoL) operations
In early implementations of Remote
Wake-up, the computer could be started from a power-off state by sending a Magic
Packet. A Magic Packet is an Ethernet packet that contains an adapters MAC
address repeated 16 times in the data field. When an adapter receives a Magic
Packet containing its own MAC address, it activates the computers power. This
enables network administrators to perform off-hours maintenance at remote
locations without sending a technician out.
This early implementation did not
require an OS that was aware of remote wake-up. However, it did require a
computer that was equipped with a standby power supply and had the necessary
circuitry to allow the remote power control. These computers were typically
equipped with a feature named Advanced Power Management (APM). APM provided
BIOS-based power control.
Newer
computers feature Advanced Configuration and Power
Interface (ACPI), which
extends the APM concept to enable the OS to selectively control power. ACPI
supports a variety of power states. Each state represents a different level of
power, from fully powered up to completely powered down, with partial levels of
power in each intermediate state. Power states include:
Not all systems support being awakened from a powered-off state. Remote
wake-up can be initiated by a variety of user selectable packet types and is not
limited to the Magic Packet format. For more information about supported packet
types, see the operating system settings section.
The wake up capability of Intel gigabit adapters is based on patterns that
are sent by the OS. You may configure the driver to the following settings using
Intel® PROSet: OS Controlled - Accept all the patterns sent to the
OS. Directed Packets - Accepts only patterns containing
the Adapter's Ethernet address in the Ethernet Header or containing the IP
address, assigned to the adapter, in the IP header. Magic Packets - Accept only patterns containing 16
consecutive repetitions of the adapter's MAC address. Directed & Magic - Accepts the patterns of both directed packets and
magic packets. Choosing "Directed Packets" will also accept patterns of the
Address Resolution Protocol (ARP) querying the IP address assigned to the
adapter. Upon configuring multiple IP addresses to one adapter, the OS may
request to wake up on ARP patterns to all of the configured addresses. The
adapter will only awaken in response to ARP packets querying the first IP
address in the list.
A Wake on LAN cable is required
on all remote wake-up capable adapters when used in older WoL-capable
computers. These computers are generally equipped with a PCI 2.1 complaint bus
and the BIOS is typically designed for APM compliant power management.
The Wake on LAN cable is not usually required for computers equipped with a
PCI 2.2 compliant bus, as the wake up signal is routed through the PCI bus. This
is done through the PCI connector pin defined as PME (Power Management Event).
Many
of the newer ACPI computers also have a connector for the 3-pin Wake on LAN
cable for backwards compatibility with older WOL capable adapters. In this type
of computer, the WOL cable is still required for older 82558-based Intel®
PRO/100+ Management adapter model numbers PILA8900 and PILA8461.
Some
motherboards only support remote wake-up (or remote wake-up from S5 state)
in a particular slot. For example, the Intel® Desktop Board D815EPEA2 only
supports remote wake-up from a powered off (S5) state if the adapter is plugged
into PCI slot 2. It does, however, support remote wake-up from standby from any
slot. See the documentation that came with your system or motherboard for
details on remote wake-up support.
Early versions of the Intel
PRO/100+ Management adapter are +5 volt only. These models must have the 3-pin
cable attached for the remote wake-up function to work. These adapters are equipped with 3 LEDs on the adapter
bracket, whereas the PCI 2.2 compliant PRO/100 models have 2 LEDs on the adapter
bracket. The older +5 volt model adapters are not compliant to the PCI 2.2
specification and do not fit in a 3-volt only PCI slot due to the slot being
keyed differently.
Newer Intel network adapters are 3.3
volt, but work in a 5-volt slot also. They are keyed to fit either type of
slot.
If your computer requires the 3-pin
cable, the +5 volt standby power supply must supply
at least 0.2 amps at +5 volts for each adapter installed. For older PCI 2.1 compliant management adapters, the power supply must supply at least .6 amps. This value is usually
listed on the power supply label as +5SB, +5VSB or +5AUX.
If
your remote wake-up enabled computer is compliant to PCI specification 2.2, it does not require the 3-pin cable for remote wake-up. In these computers,
the 3.3 volt standby power supply must provide at least 0.2 amps for
each adapter installed. You may need to contact your computer
manufacturer to verify the standby current rating. Turning off the remote wake
up capability on the adapter by using the IBAUTIL utility reduces the power draw to
around 50 milliamps (.05 amps) per adapter.
You may need to
configure various
settings in the computer BIOS so that remote
wake-up will work.
Many ACPI
computers can be configured to work in APM mode. Check your BIOS settings to
determine which mode you are operating in.
In both APM and
ACPI computers, you may find settings for Wake on LAN under the Power Control
area and titled "Wake on LAN" and/or Wake on PME". Wake on LAN setting
refers to wake up events received through the 3-pin header cable. Wake on PME
refers to wake up events received through the PCI bus. To enable remote wake-up,
you should enable the setting that corresponds to your adapter connection. For
example, set Wake on LAN to enable if you are using the WOL cable.
In
ACPI computers operating in ACPI mode and using an ACPI aware OS, look for an ACPI specific setting. If you want to power up the system from a power off
state, set an ACPI specific setting such as "Wake on LAN from S5" to enable.
The Intel® PROSet Power Management tab replaces the standard Microsoft*
Windows* Power Management tab in Device Manager. It includes the Power Saver and
Wake on LAN* (WoL*) options that were previously included on the Advanced tab. The
standard Windows power management functionality is incorporated on the Intel
PROSet tab. The Intel PROSet Power Management tab includes several settings that control
the adapter's power consumption. For example, you can set the adapter to reduce
its power consumption if the cable is disconnected. If Reduce speed during standby is enabled, then Wake on Magic
Packet and/or Wake on directed packet must be enabled. If both of
these options are disabled, power is removed from the adapter during standby.
Wake on Magic Packet from power off state has no effect on this option. The Energy Efficient Ethernet (EEE) feature allows a capable device to enter Low Power Idle between bursts of network traffic. Both ends of a link must have EEE enabled for any power to be saved. Both ends of the link will resume full power when data needs to be transmitted. This transition may introduce a small amount of network latency. NOTES: The Intel® Auto Connect Battery Saver (ACBS) feature turns off the
adapter when link is down or the network cable is disconnected. After a timeout
period, the adapter will power off. When the network cable is reconnected and
link is restored, the NIC powers up and functionality is fully restored. ACBS only functions when the system is on
battery power. If the power cable is connected, ACBS will be automatically disabled.
If ACBS is active, the adapter will appear to be powered off. If you have Intel® PROSet
installed, on the Link Speed tab, the Link Status will indicate Speed: Not
connected. Power off. The Intel® System Idle Power Saver feature sets the adapter to negotiate the
lowest possible speed setting when the system and network are idle. When the
system activity is detected, the link will be negotiated to a higher speed. To support this feature, the adapter must be The
ability to remotely wake computers is an important development in computer
management. This feature has evolved over the last few years from a simple
remote power-on capability to a complex system interacting with a variety of
device and operating system power states.
More details are available here.
Microsoft Windows XP, Windows Vista*, Windows 7, Windows Server* 2003,
Windows Server 2008, and
Windows Server 2008 R2 are ACPI-capable. These operating systems do not
support wake from a power-off (S5) state, only from standby (S3) or hibernate
(S4). When shutting down the system,
they shutdown ACPI devices, including Intel adapters. This
disarms the adapters remote wake up capability. However, in some ACPI-capable
computers, the BIOS may have a setting that allows you to override the operating
system and
wake from an S5 state anyway. If there is no support for wake from S5 state in
your BIOS settings, you are limited to Wake From Standby when using
these operating systems in ACPI computers. For some adapters, the Power Management tab in Intel PROSet includes a
setting called
Wake on
Magic Packet from power off state. Enable this setting to explicitly allow wake up
with a Magic Packet* from shutdown under APM power management mode. In
ACPI-capable versions of Windows, the Intel PROSet Power Management tab includes
Wake on Magic Packet and Wake on directed packet settings. These controls the type of packets
that wake up the system from standby. Intel® Ready Access keeps your network connection active when the rest of
your system is in sleep or standby mode, so that content on your system is
readily accessible. Requests from other computers will wake up your computer. Welcome to the User's Guide for the Intel® 10 Gigabit Server
Adapters.
This guide covers hardware and software installation, setup procedures, and
troubleshooting tips for all Intel 10 Gigabit server adapters. To select a topic, click a link in the table of contents column to the
left. If you are installing a network adapter, follow this procedure. Make sure that the driver software on the Intel CD
supports the adapter you are installing. Review system
requirements here. Follow the installation procedure for
fiber-based adapters or copper-based adapters. Carefully attach the network cable(s). After the network adapter is in the computer,
install the
network driver. For Windows systems, install the Intel®
PROSet software. Test the network adapter. For more information, select
Test the Adapter in the table of contents. If you have any problems with basic installation, see
Troubleshooting.
Once you have installed the network adapter(s), you can set
other advanced features. The available features and the configuration process
varies with the adapter and your operating system. Welcome to the User's Guide for Intel® 10 Gigabit Server Adapters
installed in Itanium®-based computers. This guide covers hardware and software installation, setup procedures, and
troubleshooting tips for all Intel 10 Gigabit server adapters. To select a topic, click a link in the table of contents column to the
left. If you are installing a network adapter, follow this procedure. Make sure that the driver software on the Intel CD
supports the adapter you are installing. Review system
requirements. Follow the installation procedure for
fiber-based adapters or copper-based adapters. Carefully attach the network cable(s). After the network adapter is in the computer,
install the
network driver. For Windows systems, install the
Intel® PROSet software. Test the network adapter. For more information, select
Test the Adapter in the table of contents. If you have any problems with basic installation, see
Troubleshooting.
Once you have installed the network adapter(s), you can set
other advanced features. The available features and the configuration process
varies with the adapter and your operating system. Performance profiles allow you to quickly optimize the performance of your
Intel Ethernet Adapter. Selecting a performance profile will automatically
adjust some Advanced Settings to their optimum setting for the selected
application. For example, a standard server has optimal performance with only
two RSS (Receive-Side Scaling) queues, but a web server requires more RSS queues
for better scalability. You must install Intel® PROSet for Windows Device Manager to use
Performance profiles. Profiles are selected on the Advanced tab of the adapter's
property sheet. Performance Profiles are supported on Intel® 10GbE adapters. NOTE: Not all team types are available on all operating systems
or with all adapters. When you create a team with all members of the team supporting Performance
Profiles, you will be asked which profile to use at the time of team creation.
The profile will be synchronized across the team. If there is not a profile that
is supported by all team members then the only option will be Use Current
Settings. The team will be created normally. Adding an adapter to an existing
team works in much the same way. If you attempt to team an adapter that supports performance
profiles with an adapter that doesn't, the profile on the
supporting adapter will be set to Custom Settings and the team will be created
normally. Install the adapter in a PCI-E x8 slot. Use the proper cabling for the adapter you have. See
Attach the Network Cable for details. Enable Jumbo Frames, if your other network components can also be
configured for it. If your BIOS has an MMRBC (Maximum Memory Read Byte Count) adjustment,
change it from its default (usually 512) to 4096 (maximum). Increase the number of TCP and Socket resources from the default value.
For Windows based systems, we have not identified system parameters
other than the TCP Window Size which significantly impact performance. Increase the allocation size of Driver Resources (transmit/receive
buffers). However, most TCP traffic patterns work best with the transmit
buffer set to its default value, and the receive buffer set to its
minimum value. Install the adapter in a PCI-X bus slot with no other devices installed
in the same bus segment. Use the proper fiber cabling for the adapter you have. See
Attach the Network Cable for details. Enable Jumbo Frames, if your other network components can also be
configured for it. If your BIOS has an MMRBC (Maximum Memory Read Byte Count) adjustment,
change it from its default (usually 512) to 4096 (maximum). Increase the number of TCP and Socket resources from the default value.
For Windows based systems, we have not identified system parameters
other than the TCP Window Size which significantly impact performance. Increase the allocation size of Driver Resources (transmit/receive
buffers). However, most TCP traffic patterns work best with the transmit
buffer set to its default value, and the receive buffer set to its
minimum value. Intel® PROSet for Windows* Device Manager is an extension to the Windows
Device Manager. When you install the Intel PROSet software, additional tabs are
automatically added to Device Manager.
Intel PROSet for Windows Device Manager is installed from the Product CD with
the same process used to install drivers. You can select Intel PROSet for
Windows Device Manager and Advanced Network Services from the Install Options
dialog. Use Add/Remove programs from the Control Panel to uninstall Intel PROSet for
Windows Device Manager. You can use the command line utility prosetcl.exe to change most Intel PROSet
settings under Windows Server Core. Please refer to the help file prosetcl.txt located in
the \Program Files\Intel\DMIX\CL directory. For iSCSI Crash Dump cofiguration, use the CrashDmp.exe utility and refer to the CrashDmp.txt help file. The following devices do not support Intel PROSet for Windows Device Manager QoS allows the adapter to send and receive IEEE 802.3ac tagged frames.
802.3ac tagged frames include 802.1p priority-tagged frames and 802.1Q VLAN-tagged
frames. In order to implement QoS, the adapter must be connected to a switch
that supports and is configured for QoS. Priority-tagged frames allow
programs that deal with real-time events to make the most efficient use of network bandwidth. High priority
packets are processed before lower priority packets. To implement QoS, the adapter must be connected to a switch that
supports and is configured for 802.1p QoS. Tagging is enabled and disabled using the "QoS Packet Tagging"
field in the Advanced tab in Intel® PROSet. Once QoS is enabled in Intel PROSet, you can specify levels of priority based
on IEEE 802.1p/802.1Q frame tagging. Microsoft* Windows* Server* 2003 and Windows Server
2008 have a utility for 802.1p packet prioritization. For more
information, see the Windows system help and Microsoft's knowledge base. When required these products are
provided with the following Product Certification Markings: This device complies with Part 15 of the FCC Rules. Operation is subject to the following two conditions: CANADA ICES-003 CLASS A / CANADA NMB-003 CLASSE A Intel Corporation declares that the equipment described in this document is
in conformance with the requirements of the European Council Directive listed
below: Low Voltage Directive 2006/95/EC This product follows the provisions of the European Directive 1999/5/EC. Dette produkt er i overensstemmelse med det europiske direktiv 1999/5/EC. Dit product is in navolging van de bepalingen van Europees Directief
1999/5/EC. Tm tuote noudattaa EU-direktiivin 1999/5/EC mryksi. Ce produit est conforme aux exigences de la Directive Europenne 1999/5/EC. Dieses Produkt entspricht den Bestimmungen der Europischen Richtlinie
1999/5/EC. essi vara stenst regluger Evrpska Efnahags Bandalagsins nmer 1999/5/EC. Questo prodotto conforme alla Direttiva Europea 1999/5/EC. Dette produktet er i henhold til bestemmelsene i det europeiske direktivet
1999/5/EC. Este produto cumpre com as normas da Diretiva Europia 1999/5/EC. Este producto cumple con las normas del Directivo Europeo 1999/5/EC. Denna produkt har tillverkats i enlighet med EG-direktiv 1999/5/EC. This declaration is based upon compliance of the product to the following
standards: EN 55022:2006 +A1:2007 (CISPR 22 Class A) RF Emissions Control. Intel
Corporation
These server adapters may contain laser devices for communication use. These
devices are compliant with the requirements for Class 1 Laser Products and are
safe in the intended use. In normal operation the output of these laser devices
does not exceed the exposure limit of the eye and cannot cause harm.
For continued safe operation in case
of an abnormal circumstance, always have the provided laser connector cover in
place or a compatible fiber optics cable properly connected when power is
available to the product.
The Laser device must be factory serviced ONLY by the
responsible manufacturer! NO adjustments, service or maintenance is to be
performed otherwise.
Comply with FDA/CDRH per CFR21, subchapter J. Comply with EN60825-1:1994+A1+A2 Product recycling and end-of-life take-back systems and requirements vary by
country. Contact the retailer or distributor of this product for information about
product recycling and/or take-back. When required these products are
provided with the following Product Certification Markings: This equipment has been tested and
found to comply with the limits for a Class B digital device pursuant to Part 15
of the FCC rules. These limits are designed to provide reasonable protection
against harmful interference in a residential installation. This equipment
generates, uses and can radiate radio frequency energy and, if not installed and
used in accordance with the instructions, may cause harmful interference to
radio communications. However, there is no guarantee that interference will not
occur in a particular installation.
If this equipment does cause harmful
interference to radio or television reception, which can be determined by
turning the equipment off and on, the user is encouraged to try to correct the
interference by one or more of the following measures:
CAUTION:
If the device is changed or modified without permission from Intel, the
user may void his or her authority to operate the equipment. NOTE:
This device complies with Part 15 of the FCC Rules. Operation is subject to
the following two conditions: (1) this
device may not cause harmful interference, and (2) this device must accept
any interference received, including interference that may cause undesired
operation. CANADA ICES-003 CLASS B / CANADA NMB-003 CLASSE B Intel Corporation declares that the equipment described in this document is
in conformance with the requirements of the European Council Directive listed
below: 2006/95/EC Low Voltage Directive This product follows the provisions of the European Directive 1999/5/EC. Dette produkt er i overensstemmelse med det europiske direktiv 1999/5/EC. Dit product is in navolging van de bepalingen van Europees Directief
1999/5/EC. Tm tuote noudattaa EU-direktiivin 1999/5/EC mryksi. Ce produit est conforme aux exigences de la Directive Europenne 1999/5/EC. Dieses Produkt entspricht den Bestimmungen der Europischen Richtlinie
1999/5/EC. essi vara stenst regluger Evrpska Efnahags Bandalagsins nmer 1999/5/EC. Questo prodotto conforme alla Direttiva Europea 1999/5/EC. Dette produktet er i henhold til bestemmelsene i det europeiske direktivet
1999/5/EC. Este produto cumpre com as normas da Diretiva Europia 1999/5/EC. Este producto cumple con las normas del Directivo Europeo 1999/5/EC. Denna produkt har tillverkats i enlighet med EG-direktiv 1999/5/EC. This declaration is based upon compliance of the product to the following
standards: EN 55022:2006 +A1:2007 (CISPR 22 Class B) RF Emissions Control. Intel Corporation, Mailstop JF3-446
These server adapters may contain laser devices for communication use. These
devices are compliant with the requirements for Class 1 Laser Products and are
safe in the intended use. In normal operation the output of these laser devices
does not exceed the exposure limit of the eye and cannot cause harm.
For continued safe operation in case
of an abnormal circumstance, always have the provided laser connector cover in
place or a compatible fiber optics cable properly connected when power is
available to the product.
The Laser device must be factory serviced ONLY by the
responsible manufacturer! NO adjustments, service or maintenance is to be
performed otherwise.
CAUTION: Use of controls or adjustments or
performance of procedures other than those specified herein may result in
hazardous radiation exposure. Comply with FDA/CDRH per CFR21, subchapter J. Comply with EN60825-1:1994+A1+A2 Product recycling and end-of-life take-back systems and requirements vary by
country. Contact the retailer or distributor of this product for information about
product recycling and/or take-back. Before installing the Intel® 10GbE Server Adapter, check
your system for the following minimum configuration requirements. The Intel drivers for Itanium-based systems operate with the following operating
systems:
Before installing the Intel® 10GbE Server Adapter, check
your system for the following minimum configuration requirements. Intel supplies 64-bit drivers for the following operating systems: A platform that supports the Intel®
64 Architecture will run in either 64-bit mode or
32-bit compatibility mode. In order for it to run in 64-bit mode,
the following requirements must be met: When Receive Side Scaling (RSS) is enabled, all of the receive data
processing for a particular TCP connection is shared across multiple processors or processor cores. Without RSS
all of the processing is performed by a single processor, resulting in
less efficient system cache utilization. RSS is enabled on the Advanced tab of the adapter property sheet. If your
adapter does not support RSS, or if your operating system does not support it, the RSS setting will
not be displayed. This setting allocates queue space to buffer transactions between the network
adapter and CPU(s). This setting allows you to set the preferred starting RSS processor. Change
this setting if the current processor is dedicated to other processes. The
setting range is from 0 to the number of logical CPUs - 1. In Server 2008 R2,
RSS will only use CPUs in group 0 (CPUs 0 through 63). This setting allows you to choose the preferred NUMA (Non-Uniform Memory Access) node
to be used for memory allocations made by the network adapter. In addition the
system will attempt to use the CPUs from the preferred NUMA node first for the
purposes of RSS. On NUMA platforms, memory access latency is dependent on the
memory location. Allocation of memory from the closest node helps improve
performance. The Windows Task Manager shows the NUMA Node ID for each processor. The Save and
Restore Command Line Tool is a VBScript (SavResDX.vbs) that allows you to copy
the current adapter and team settings into a standalone file (such as on a
floppy disk) as a backup measure. In the event of a hard drive failure, you can
reinstate most of your former settings. The system on which you restore network configuration settings must have the same configuration
as the one on which the save was performed. cscript SavResDX.vbs save|restore [filename] SavResDX.vbs has the following command line options: To save the adapter settings to a file on a floppy diskette, do the
following. cscript SavResDX.vbs save a:\settings.txt To restore the adapter settings from a file on a floppy diskette, do the
following: cscript SavResDX.vbs restore
a:\settings.txtSupported Intel® 10GbE Server Adapters
Product Name
Board ID #†
Controller
Intel® Ethernet Converged Network Adapter X540-T1
X540
Intel® 82599 10 Gigabit Network Connection
NA
82599
Intel® Ethernet Controller X540-AT2
NA
X540
Intel® Ethernet Converged Network Adapter X540-T2
G35632-xxx
X540
Intel® X540 Virtual Function
n/a
n/a
Intel® 82599 10 Gigabit Dual Port Network Connection with FCoE
n/a
82599
Intel® 82599 10 Gigabit Dual Port Backplane Connection with FCoE
n/a
82599
Intel® Ethernet Server Adapter X520-T2
E95990-xxx
82599
Intel® Ethernet X520 10GbE Dual Port KX4-KR Mezz
n/a
82599
Intel® 82599 10 Gigabit TN Network Connection
n/a
82599
Intel® 82599 Virtual Function
n/a
n/a
Intel® Ethernet Mezzanine Adapter X520-KX4-2
E46189-xxx
82599
Intel® 82599 10 Gigabit CX4 Dual Port Network Connection
n/a
82599
Intel® Ethernet X520 10GbE Dual Port KX4 Mezz
n/a
82599
Intel® 82599 10 Gigabit Dual Port Backplane Connection
n/a
82599
Intel® 10 Gigabit AT2 Server Adapter
D80259-xxx
82598EB
Intel® 10 Gigabit BR KX4 Dual Port Network Connection
n/a
82599
Intel® 82599 Dual 10 Gigabit Network Connection
n/a
82599
Intel® Ethernet Server Adapter X520-1
E68787-xxx
E58551-xxx82599
Intel® Ethernet Server Adapter X520-2
E68785-xxx
E57138-xxx82599
Intel® 82598EB 10 Gigabit BX Network Connection
n/a
82598EB
Intel® 82598EB 10 Gigabit KX4 Network Connection
n/a
82598EB
Intel® 10 Gigabit AF DA Dual Port Server Adapter
E37002-xxx
82598EB
Intel® 10 Gigabit SR Dual Port Express Module
n/a
82598EB
Intel® 10 Gigabit AT Server Adapter
D79893-xxx
82598EB
Intel® 10 Gigabit CX4 Dual Port Server Adapter
E25335-xxx
82598EB
Intel® 10 Gigabit XF SR Server Adapter
E16791-xxx
82598EB
Intel® 10 Gigabit XF SR Dual Port Server Adapter
E15728-xxx
82598EB
Intel® 10 Gigabit XF LR Server Adapter
D95857-xxx
82598EB
Intel® 82598EB 10 Gigabit AT CX4 Network Connection
n/a
82598EB
Intel® 82598EB 10 Gigabit AF Dual Port Network Connection
n/a
82598EB
Intel® 82598EB 10GbE AF Network Connection
n/a
82598EB
Compatibility Notes
Last modified on 9/21/11 2:05p Revision
PROXGB/DOCS/SERVER/attnew.gif 0000755 0000000 0000000 00000017405 11656741062 012516 0 ustar GIF89a#d XVWsqrpnoUTUNMNzyzvuvpopnmnlkljijihifef_^_[Z[YXYWVWǮQQR||}yyzsstllmhhiddebbc^^_]]^YYZWWXUUVÿhikdeglmosuwoqs`abҟһƺ755DBBB@@PNNMKK][[ZXXvttsqqiggSRR~~}|||{{yxxutttssrqqqppnmmmllihhfeedcccbba```__]\\\[[YXXVUUrrroooZZZVVVSSSOOO , #d H/].\ȰÇ#JHŋ3jQ$FIBԱɓ(S\ɒ (H@͛8sq@̟6xIѣH1^g]H&JU~4mDկ`Êe(f(cP]˶-K8ʽ!ԭݻx7f+i#y <,_J!̸1[#GAsDZSF|ÌB̠C49BE^r҉M[b!_O\hr G#U{1\xFR'PÕC;cEرO dX?UCAݾ
cT߁:'`~ $ ߂7Its. /d("F\!7A,N'>H%-Ћ0t@cd8
x$d BZŔB*A =b \*E(0ULnOY9{0r'JA{zgfQN'e 'N$S>N蠝Vʖy梥FfwzI\ީ%VgBA0j#
d¨p
-aR1\چJd*x{ץ"zjX.Oij~꼘$)l$
itG!pK1R04|1^Feqg0;y|2?11-m2y16a ޞ~JWpܵ^?r!j?*
=~m r w1یT.n3T^n $X. ֞lavt>"gE>Q+{b9WSnU{ Hk])VmVOCF)($0/~ e)|tC.Y_fl])DY_Gq}-rKa x${B}s=SRN}R-k,zsȾB1 PN:kBHpw)BJ su@|cx!
\ dbBQp}v
obAء[Apyl!Oے(/0ܿO 7 o kTZ |!B:$XA .dP;ӰąkXG!-IPI0YÈ+zPMA H%J(gch̞DU ŏV
WF!X`r3+Ck)ōyQۗ Za%(|Z Ɲy5R܀Tg\U8[i_U%pn]Loi̚fO*) MN (^ަVHGm&Gw_ $*njn#kB#㸓C" O!렋3LHFD`400K,NDL)$ lq"cȓ,&Th[#?(dQB,D!E\8+I" @@"ŏRKb2#TDL8R7Գ9CO>́Ђ<>
sqPD+,$]F#Im'J+=n5AK $GPI M5!T;21+=+]I1 $WjU[$O$"B+Z8_1T"E3"$q\r
]|}eUXږoB^9UZ%;w!I]YupᅧT
;, +E| vFhhI#B9eD{e59f?a):P +27v_=
@> .K>6E,Ys&gCDى"H+¹^}y($) "l[OOv9b.;K.Ksc}`2(oY$}]csvc)(3([QhU CM( w5؝{cA:KvD* Gz&Â}O# }ᡫhm#Qr2[ F*!S ᲮzުWE4ӓ ,#$.-+,lBPᑡWhCP(?焸"&J=`#OZm2E*f̊ b''v}_tS<2g|VAF6ʍc8QwH '>ΌZ GH oD8?6K4$8&PCd%i1j'{!)x:b'MYE$'_<1]"
]y=
hU_J rD9 6sq~)/Q2Rh6ϦMH)~|8b3c몠Ϊ+$a%<%ϩ\bL>"esWJ.
SA+PA
t( њ*N@(H zz~N%r T
NSiX4:RhMuST4DDORt :B7j8
) tdIP5I TUXyGJ.raER ҡL?S@\3fBH14_STo $c< [ XFV!Xx@5G,-VAj$"e 4rKV
empu[<ָBn 57}tI]Y=pu r5-xD^Ps[ nN'AD
Ą/qoZ"LښPڄ`rLu0
ELQw'J)DŻJ[bg -s< ; PROXGB/DOCS/SERVER/box.gif 0000755 0000000 0000000 00000000747 11651733270 012002 0 ustar GIF89a M 3 ! , M I8ͻ`(dihlp,tmx|pH,$J 8ШtJZجvz zn|NnB. LJ+^̸ǐ#KL˘3k̹ϠC ; PROXGB/DOCS/SERVER/bsmi.gif 0000755 0000000 0000000 00000003431 11656741516 012144 0 ustar GIF89a\u , \u ڋH扦ʶ L
ĢL*̦ Ъ&
hn؆J 0خቷdF%(Hǖv8h0ih釶GyHZV*8J:iWj9WY[+7x;F| () ;*Ji]ƬMY>-N>[ ln,I>/ +{o|JP 'D 05 qP2ȑ$K<2ʕ,[| 3̙4kڼ3Ν<{ 4СDBҙKO4 ,,lile1!
kb՚V.nDOu1U|L,l!t#e-_P縤=_uav~$4O W{+ղKG63
] fzL3Uv+] 5jI]Cw\,rv7֛uwȖ[w7]Y']^!h5u!`YE 6a5T
nA^yWG1>>Rr@oC
YhبotУfU)?yEYg gv eO.)t^sϋr"Ħ4s8HYRlaI#bT~Xz{'Rjx0DɚxF 9B,VG䀣n9bG
lJdn7ꭱf:H1卄*OTNڦ {t
V FȣR& d=ihµma~z-5h,45[g9XG pLp p
/p? qO<"jl^_D^f BER u*hSV's*啂"_tLb|r3z2-n
X
i:"1t#j^: l2ҬdZkE^6ʟ[ ڴ
`R=W,lǙTk̕J2D?6u&shKyb ɲ'xL·"ޣ)H3y8/8c zN8{5"P{Y45b'7^&s8&+Yei+oi>{,k,g>Uԋ0u,e~\v.Ǚ+;ӓ# dgh%D=&9C8ZX<}'MoSːgNh
P3CVU 7Mw9^BGD(!K!g7} RCY#\7*Eٗ[%@ ́|y!D=b&@z XH:aG=Q 0,Pr,)OTrl+_ Kd P0A6f;t|ƴ'5-a Đ
jD1GUKhGΗ2S%3aJ!S ^^N ˗
(ɾ\ [g~%qNтI7͎ N7Od3U
G
Connect a 10GbE Copper Network Cable
10GBASE-T
CX4
Physical cabling characteristics for the Intel® CX4 Dual Port Server Adapter
must meet IEEE Std 802.3ak, Clause 54 specifications. The required cable
connector is an MDI latch-type receptacle, as defined by IEC 61076-3-113.
SFP+ Devices with Pluggable Optics
82599-Based Adapters
NOTES:
Supplier
Type
Part Numbers
SR Modules
Intel
DUAL RATE 1G/10G SFP+ SR (bailed)
AFBR-703SDZ-IN2
Intel
DUAL RATE 1G/10G SFP+ SR (bailed)
FTLX8571D3BCV-IT
Intel
DUAL RATE 1G/10G SFP+ SR (bailed)
AFBR-703SDDZ-IN1
LR Modules
Intel
DUAL RATE 1G/10G SFP+ LR (bailed)
FTLX1471D3BCV-IT
Intel
DUAL RATE 1G/10G SFP+ LR (bailed)
AFCT-701SDZ-IN2
Intel
DUAL RATE 1G/10G SFP+ LR (bailed)
AFCT-701SDDZ-IN1
Supplier
Type
Part Numbers
Finisar
SFP+ SR bailed, 10g single rate
FTLX8571D3BCL
Avago
SFP+ SR bailed, 10g single rate
AFBR-700SDZ
Finisar
SFP+ LR bailed, 10g single rate
FTLX1471D3BCL
Finisar
DUAL RATE 1G/10G SFP+ SR (No Bail)
FTLX8571D3QCV-IT
Avago
DUAL RATE 1G/10G SFP+ SR (No Bail)
AFBR-703SDZ-IN1
Finisar
DUAL RATE 1G/10G SFP+ LR (No Bail)
FTLX1471D3QCV-IT
Avago
DUAL RATE 1G/10G SFP+ LR (No Bail)
AFCT-701SDZ-IN1
Finisar
1000BASE-T SFP
FCLF8522P2BTL
Avago
1000BASE-T SFP
ABCU-5710RZ
82598-Based Adapters
NOTES:
Supplier
Type
Part Numbers
Finisar
SFP+ SR bailed, 10g single rate
FTLX8571D3BCL
Avago
SFP+ SR bailed, 10g single rate
AFBR-700SDZ
Finisar
SFP+ LR bailed, 10g single rate
FTLX1471D3BCL
Molex
1m - Twin-ax cable
74752-1101
Molex
3m - Twin-ax cable
74752-2301
Molex
5m - Twin-ax cable
74752-3501
Molex
10m - Twin-ax cable
74752-9004
Tyco
1m - Twin-ax cable
2032237-2
Tyco
3m - Twin-ax cable
2032237-4
Tyco
5m - Twin-ax cable
2032237-6
Tyco
10m - Twin-ax cable
1-2032237-1
Connect a 10GbE Fiber Network Cable
CAUTION: This product uses a Class 1M laser module. Viewing the
laser output with certain optical instruments designed for use at a distance (for example, telescopes and binoculars) may pose an
eye hazard.
Laser wavelength: 1310 nanometer (not visible).
Cable type to use: Single-mode fiber with 9.0m core diameter
Connector type: LC.
Maximum cable length: 10 kilometers.
Laser wavelength: 850 nanometer (not visible).
Cable type to use: Multi-mode fiber with 62.5m or 50m core diameter
Connector type: LC or SC.
Maximum cable length: 300 meters.
Last modified on 4/08/11 11:44a Revision Direct Cache Access (DCA)
NOTE:
DCA
requires support from the I/O device, system chipset, and CPU.
Last modified on 10/18/07 11:16a Revision
PROXGB/DOCS/SERVER/driv10gb.htm 0000755 0000000 0000000 00000007535 11656577024 012665 0 ustar
Installing and Uninstalling the Drivers
Before you begin
NOTES:
Install the Drivers in Microsoft* Windows*
NOTE:
This will update the drivers for all supported Intel®
network adapters in your system.
Uninstalling the Driver
Last modified on 8/04/10 8:48p Revision Set Up Speed and Duplex
CAUTION: Only experienced network administrators should
force speed and duplex manually. The settings at the switch must always
match the adapter settings. Adapter performance may suffer or your
adapter may not operate if you configure the adapter differently from
your switch.
Configuring Speed and Duplex in Microsoft* Windows*
Intel® Gigabit Network Adapter Considerations
Intel® 10 Gigabit Network Adapter Considerations
Intel® PRO/100 Network Adapter Considerations
Last modified on 12/30/09 3:51p Revision
PROXGB/DOCS/SERVER/hotwin.htm 0000755 0000000 0000000 00000003523 11656574604 012551 0 ustar
PCI Hot Plug Support for Microsoft* Windows* Operating Systems
NOTES:
Last modified on 9/03/07 4:49p Revision
Microsoft* Hyper-V* Overview
Using Intel® Network Adapters in a Hyper-V Environment
The Virtual Machine Switch
Using ANS VLANs
Using an ANS Team or VLAN as a Virtual NIC
Note: This applies only to virtual NICs created
on a team or VLAN. Virtual NICs created on a physical adapter do not
require these steps.
Note: This step is not required for the
team. When the Virtual NIC is created, its protocols are correctly
bound.
Command Line for Microsoft Windows Server* Core
Note: The nvspbind.exe utility is not needed
in Windows Server 2008 R2.
prosetcl.exe Team_CreateTeam 1,2,3 ALB Team1
nvspbind.exe -n
nvspbind.exe -d
aaaaaaaa-bbbb-cccc-dddddddddddddddd *
nvspbind.exe -e
tttttttt-uuuu-wwww-xxxxxxxxxxxxxxxx ms_netbios
nvspbind.exe -e tttttttt-uuuu-wwww-xxxxxxxxxxxxxxxx ms_tcpip
nvspbind.exe -e tttttttt-uuuu-wwww-xxxxxxxxxxxxxxxx ms_server
Virtual Machine Queue Offloading
Teaming Considerations
Last modified on 6/01/11 2:12p Revision
Insert the Adapter in the Computer
NOTE: If you are
replacing an existing adapter with a new adapter, you must re-install the
driver.
Insert a PCI Express Adapter in the Server
PCI-Express slots and adapters vary in the number of connectors present,
depending on the data lanes being supported.
NOTE: The Intel® 10 Gigabit AT Server
Adapter will only fit into x8 or larger PCI Express slots. Some systems have physical
x8 PCI Express slots that actually support lower speeds. Please check your system manual
to identify the slot.
Last modified on 9/02/10 3:12p Revision
Insert the Adapter in the Computer
NOTE: If you are
replacing an existing adapter with a new adapter, you must re-install the
driver.
Insert a PCI Express Adapter in the Server
PCI-Express slots and adapters vary in the number of connectors present,
depending on the data lanes being supported.
NOTE: The Intel® 10 Gigabit AT Server
Adapter will only fit into x8 or larger PCI Express slots. Some systems have physical
x8 PCI Express slots that actually support lower speeds. Please check your system manual
to identify the slot.
Insert a PCI-X Adapter in the Server
PCI-X slots are backward-compatible with 64-bit PCI
slots, and operate at 66, 100 or 133 MHz.
33 MHz
66 MHz
100 MHz
133 MHz
64-bit
"2x"
"4x"
"6x"
"8x"
If you get a PCI or PCI-X configuration error, see
Testing and Troubleshooting.
Last modified on 9/02/10 3:12p Revision Intel® I/O Acceleration Technology
System Requirements
Platform
The platform must be based on a server chipset and BIOS
that are Intel I/OAT capable.
Operating System
Network Connectivity Hardware
Intel I/OAT is supported on specific server adapters
and network connections available from Intel and other vendors. If you
have multiple network adapters in your system, Intel I/OAT will operate
automatically on the compatible models, while non-compatible adapters
will pass traffic normally.
Drivers and Connectivity Software
Intel I/OAT becomes active when all required software
support is loaded & enabled.
NOTES:
Tuning Your System
Memory
Windows Adapter Settings
Last modified on 3/07/11 2:01p Revision IP Security Offloading
Last modified on 8/28/08 3:57p Revision Jumbo Frames
NOTES:
Setting Up Jumbo Frames in Microsoft* Windows*
NOTE: Jumbo frames are not
supported in multi-vendor team configurations.
Last modified on 8/01/11 3:59p Revision Attaching the Low
Profile Bracket (Optional)
Last modified on 8/31/05 3:41p Revision Copyright and Legal Disclaimers
Last modified on 1/25/11 10:21p Revision
PROXGB/DOCS/SERVER/license.htm 0000755 0000000 0000000 00000035273 11654245266 012667 0 ustar
LICENSES:
You understand and acknowledge that the Software is pre-release Software, does not represent the final Software from Intel, and may contain errors and other problems that could cause data loss, system failures, or other errors.
The pre-release Software is provided to you "as-is" and Intel disclaims any warranty or liability to you for any damages that arise out of the use of the pre-release Software.
You acknowledge that Intel has not promised that pre-release Software will be released in the future, that Intel has no express or implied obligation to you to release the pre-release Software and that Intel may not introduce Software that is compatible with the pre-release Software. You acknowledge that the entirety of any research or development you perform that is related to the pre-release Software or to any product making use of or associated with the pre-release Software is done at your own risk.
If Intel has provided you with pre-release Software pursuant to a separate written agreement, your use of the pre-release Software is also governed by such agreement.
Last modified on 5/15/11 10:56p Revision Indicator Lights
Link
Off
Not linked to the LAN.
Green
Linked at 10Gb
Yellow
Linked at 1Gb
Activity
Off
No link.
Blinking On/Off
Actively transmitting or receiving data.
Link
Off
Not linked to the LAN.
On
Linked to the LAN.
Activity
Off
No link.
Blinking On/Off
Actively transmitting or receiving data.
GRN 10G
(A or B):
GreenOff
Not linked to the LAN.
On
Linked to the LAN.
ACT/LNK
(A or B): GreenOff
No link.
Blinking On/Off
Actively transmitting or receiving data.
ACT/LNK
Green on
The adapter is connected to a valid link
partner.
Green blinking
Data activity
Off
No link
Green blinking
Identity. Use the "Identify Adapter" button
in Intel PROSet or the BLINK command in IBAUtil to control blinking. See
Intel PROSet Help for more information.
1Gig/10Gig
Off
No link
Green
10 Gbps
Yellow
1 Gbps
FAN FAIL
Red
Over temperature event occurred. The adapter
will be shut down to avoid damage.
Indication
Meaning
A or B
On
The adapter is connected to a valid link
partner.
Blinking
Adapter is actively passing traffic.
Off
No link.
Indication
Meaning
ACT/LNK
On
The adapter is connected to a valid link
partner.
Blinking
Adapter is actively passing traffic.
Off
No link.
Indication
Meaning
ACT/LNK
On
The adapter is connected to a valid link
partner.
Blinking
Adapter is actively passing traffic.
Off
No link.
Last modified on 6/11/10 10:27a Revision Low Latency Interrupts (LLI)
NOTE: When LLI is enabled,
system CPU utilization may increase.
Use for packets with TCP
PSH flag:
Any incoming packet with the TCP PSH flag will trigger an immediate
interrupt. The PSH flag is set by the sending device.
Use for these TCP ports:
Every packet received on the specified
ports will trigger an immediate interrupt. Up to 8 ports may be
specified.
Last modified on 10/18/07 11:16a Revision
PROXGB/DOCS/SERVER/manage.htm 0000755 0000000 0000000 00000025213 11734015456 012461 0 ustar
Remote Wake-Up and Wake on LAN*
About Remote Wake-Up
NOTES:
Wake on Magic Packet
Advanced Configuration and Power Interface
Power State
Description
S0
On and fully operational
S1
System is in low power mode (sleep mode). The CPU clock is stopped, but RAM is powered on and being refreshed.
S2
Similar to S1, but power is removed from the CPU.
S3
Suspend to RAM (standby mode). Most components are shutdown. RAM remains operational.
S4
Suspend to disk (hibernate mode). The memory contents are swapped to the disk drive and then reloaded into RAM when the system is awakened.
S5
Power off
Wake Up Address Patterns
Physical Installation Issues
Wake on LAN Cable
For computers with a PCI 2.1 compliant bus
NOTE: Remote
Wake-Up from power-off (S5) is not supported on the following adapters in
computers using the PCI 2.1 bus. To use Remote Wake-Up on any of the
adapters listed below, the computer must have a PCI 2.2 compliant bus.
For computers with a PCI 2.2 compliant bus
Slot
Power
BIOS Settings
Last modified on 7/12/11 11:31p Revision
PROXGB/DOCS/SERVER/mang_win.htm 0000755 0000000 0000000 00000017540 11734015456 013034 0 ustar
Power Management
NOTES:
NOTE:
If your system has a Manageability Engine, the Link LED may stay lit even if
WoL is disabled.
Power Options
Energy Efficient Ethernet
Intel® Auto Connect Battery Saver
NOTE:
ACBS will not function on an adapter if the adapter has forced speed or
duplex settings. ACBS will only function if the adapter is set to
auto-detect or auto-negotiate.
Intel® System Idle Power Saver
Remote Wake-Up and Wake on LAN*
Wake on Intel® Ready Access
Last modified on 7/12/11 11:49p Revision Overview
NOTE: This guide refers only to drivers and features
available on IA-32-based computer platforms and platforms based on the Intel®
64 Architecture. These drivers are not compatible
with
Itanium®-based computers.
Installing the Network Adapter
If you are upgrading the driver software, start with step 6.
NOTE: Intel 10 Gigabit Server Adapters do not support
unattended driver installation.
Last modified on 11/22/10 3:51p Revision Overview
NOTE: This guide refers only to drivers and features
available on Itanium-based computers.
These drivers are not compatible on IA-32-based platforms, or platforms
based on the Intel® 64 Architecture.
Installing the Network Adapter
If you are upgrading the driver software, start with step 5.
NOTE: Intel 10 Gigabit Server Adapters do not support
unattended driver installation.
Last modified on 11/22/10 3:51p Revision Performance Profiles
Supported Adapters
Teaming Considerations
Last modified on 8/11/10 7:48p Revision
PROXGB/DOCS/SERVER/prform10.htm 0000755 0000000 0000000 00000013022 11656577024 012701 0 ustar
Getting the Most From Your PCI-E Intel® 10 Gigabit Server Adapter
NOTE: These adjustments
should be performed by a highly skilled network administrator. They are
not guaranteed to improve performance. Not all settings shown here may
be available through your BIOS, operating system or network driver
configuration. Linux users, see the README file in the Linux driver
package for Linux-specific performance enhancement details.
NOTE: Some PCI-E x8
slots are actually configured as x4 slots. These slots have insufficient
bandwidth for full 10Gbe line rate with dual port 10GbE devices. The
driver can detect
this situation and will write the following message in the system log:
PCI-Express
bandwidth available for this card is not sufficient for optimal
performance. For optimal
performance a x8 PCI-Express slot is required.
If this error occurs, moving your adapter to a true x8 slot will resolve
the issue.
NOTE: Some systems may
set the adapter's MMRBC to 4096 by default.
Getting the Most From Your PCI-X Intel® 10 Gigabit Server Adapter
NOTE: These adjustments
should be performed by a highly skilled network administrator. They are
not guaranteed to improve performance. Not all settings shown here may
be available through your BIOS, operating system or network driver
configuration. Linux users, see the README file in the Linux driver
package for Linux-specific performance enhancement details.
NOTE: Some systems may
set the adapter's MMRBC to 4096 by default.
Last modified on 12/07/10 4:48p Revision Intel® PROSet for Windows* Device Manager
NOTE: You must have administrator rights to
install or use Intel PROSet for Windows Device Manager.
Installing Intel PROSet for Windows Device Manager
Removing Intel PROSet for Windows Device Manager
Changing Intel PROSet Settings Under Windows Server Core
Compatibility Notes
Last modified on 8/04/10 8:12p Revision
PROXGB/DOCS/SERVER/qos10g.htm 0000755 0000000 0000000 00000003160 11656574604 012350 0 ustar
Quality of Service (QoS) Tagging for Microsoft* Windows
Server* 2003
Last modified on 4/01/09 3:35p Revision Regulatory Compliance Statements
Safety Compliance
EMC Compliance
Regulatory Compliance Markings
FCC Class A User Information
Note: This equipment has been tested and found to
comply with the limits for a Class A digital device, pursuant to Part 15
of the FCC rules. These limits are designed to provide reasonable
protection against harmful interference when the equipment is operated
in a commercial environment. This equipment generates, uses and can
radiate radio frequency energy and, if not installed and used in
accordance with the instructions, may cause harmful interference to
radio communications. Operation of this equipment in a residential area
is likely to cause harmful interference in which case the user will be
required to correct the interference at his own expense.
CAUTION: If the device is changed or modified without permission from Intel, the user may void his or her authority to operate the equipment.
Canadian Compliance (Industry Canada)
Manufacturer Declaration
European Community 
Manufacturer Declaration
EMC Directive 2004/108/EC
EN 55024:1998 +A1:2001 +A2:2003 (CISPR 24) Immunity to Electromagnetic
Disturbance.
EN 60950-1:2006 +A11:2009 Information Technology Equipment- Safety-Part 1:
General Requirements.
Mailstop JF3-446
5200 N.E. Elam Young Parkway
Hillsboro, Oregon 97124-6497
WARNING: This is a Class A product. In a
domestic environment this product may cause radio interference in which
case the user may be required to take adequate measures.
VCCI Class A Statement
BSMI Class A Statement
China RoHS Declaration
KCC Notice Class A (Republic of Korea Only)
Class 1M Laser Product
CAUTION: Use of controls or adjustments or
performance of procedures other than those specified herein may result in
hazardous radiation exposure.
These Class 1 Laser devices:
End-of-Life / Product Recycling
Last modified on 11/02/10 3:03p Revision Regulatory Compliance Statements
Copper Products
Fiber Products
Safety Compliance
EMC Compliance
Regulatory Compliance Markings
Class B Products
FCC Class B User Information
Canadian Compliance (Industry Canada)
Manufacturer Declaration
European CommunityManufacturer Declaration
2004/108/EC EMC Directive
EN 55024:1998 +A1:2001 +A2:2003 (CISPR 24) Immunity to Electromagnetic
Disturbance.
EN 60950-1:2006 +A11:2009 Information Technology Equipment- Safety-Part 1:
General Requirements.
5200 N.E. Elam Young Parkway
Hillsboro, OR 97124-6497
Phone 1-800-628-8686VCCI Class B Statement (Japan)
KCC Notice Class B (Republic of Korea Only)
BSMI Class A Notice (Taiwan)
China RoHS Declaration
Class 1 Laser Product
These Class 1 Laser devices:
End-of-Life / Product Recycling
Last modified on 11/02/10 3:03p Revision ᩖn-pmً-NN*~9{B |[n JB'>K Ր @~VK{ mT7chܔE˭GP+
yuk %V&b֙6 /L$J.U]~ ͈alab r& tix9Z}T2Ri@^z} _yF|$2 =i;q%_YZ"Yb딙
&9 .1) ޣl?1䷙ٛ]YBLX/ ɹuιMq.ߏnٹp@o[OzƎ 9IމNvW[k .Yx 驱$ !M)(
o ޡf TO?ґ@S/
$XA .dVҤeE5nq*NCĉSVU0dhK1e 0P5?:H*[%ZHl @iǏ#G M8UX9ISjjYia:bXcLU{V] st.Ot[`J1p^%m
System Requirements: Itanium®-based Computers
Hardware Compatibility
Supported 64-bit Operating Systems
Last modified on 11/01/10 3:28p Revision
System Requirements: IA-32 Computers
Hardware Compatibility
Supported 32-bit Operating Systems
Intel®
64 Architecture Platform Requirements
Last modified on 1/11/11 3:09p Revision
Receive Side Scaling
NOTES:
RSS Configuration
Receive Side Scaling Queues
Range
Starting RSS CPU
Preferred NUMA Node
Note: This setting only affects
NUMA systems. It will have no effect on non-NUMA systems.
Teaming
PROXGB/DOCS/SERVER/run.gif 0000755 0000000 0000000 00000000141 11654247274 012011 0 ustar GIF89a E
Saving and Restoring an Adapter's Configuration Settings
NOTES:
Command Line Syntax
save
Saves adapter and team settings that have been changed from the
default settings. When you restore with the resulting file, any
settings not contained in the file are assumed to be the default.
restore
Restores the settings.
filename
The file to save settings to or restore settings from. If no
filename is specified, the script default to WmiConf.txt.
Examples
Save Example
Restore Example
Last modified on 2/10/10 3:18p Revision