Commit 872857a84e18f4bf9b56b298309a977b2ce77b5b
1 parent
f2be142979
Exists in
master
and in
4 other branches
Documentation/networking/ixgbe.txt: Update ixgbe documentation
Update Intel Wired LAN ixgbe documentation. Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Showing 1 changed file with 136 additions and 75 deletions Side-by-side Diff
Documentation/networking/ixgbe.txt
1 | 1 | Linux Base Driver for 10 Gigabit PCI Express Intel(R) Network Connection |
2 | 2 | ======================================================================== |
3 | 3 | |
4 | -March 10, 2009 | |
4 | +Intel Gigabit Linux driver. | |
5 | +Copyright(c) 1999 - 2010 Intel Corporation. | |
5 | 6 | |
6 | - | |
7 | 7 | Contents |
8 | 8 | ======== |
9 | 9 | |
10 | -- In This Release | |
11 | 10 | - Identifying Your Adapter |
12 | -- Building and Installation | |
13 | 11 | - Additional Configurations |
12 | +- Performance Tuning | |
13 | +- Known Issues | |
14 | 14 | - Support |
15 | 15 | |
16 | +Identifying Your Adapter | |
17 | +======================== | |
16 | 18 | |
19 | +The driver in this release is compatible with 82598 and 82599-based Intel | |
20 | +Network Connections. | |
17 | 21 | |
18 | -In This Release | |
19 | -=============== | |
22 | +For more information on how to identify your adapter, go to the Adapter & | |
23 | +Driver ID Guide at: | |
20 | 24 | |
21 | -This file describes the ixgbe Linux Base Driver for the 10 Gigabit PCI | |
22 | -Express Intel(R) Network Connection. This driver includes support for | |
23 | -Itanium(R)2-based systems. | |
25 | + http://support.intel.com/support/network/sb/CS-012904.htm | |
24 | 26 | |
25 | -For questions related to hardware requirements, refer to the documentation | |
26 | -supplied with your 10 Gigabit adapter. All hardware requirements listed apply | |
27 | -to use with Linux. | |
27 | +SFP+ Devices with Pluggable Optics | |
28 | +---------------------------------- | |
28 | 29 | |
29 | -The following features are available in this kernel: | |
30 | - - Native VLANs | |
31 | - - Channel Bonding (teaming) | |
32 | - - SNMP | |
33 | - - Generic Receive Offload | |
34 | - - Data Center Bridging | |
30 | +82599-BASED ADAPTERS | |
35 | 31 | |
36 | -Channel Bonding documentation can be found in the Linux kernel source: | |
37 | -/Documentation/networking/bonding.txt | |
32 | +NOTES: If your 82599-based Intel(R) Network Adapter came with Intel optics, or | |
33 | +is an Intel(R) Ethernet Server Adapter X520-2, then it only supports Intel | |
34 | +optics and/or the direct attach cables listed below. | |
38 | 35 | |
39 | -Ethtool, lspci, and ifconfig can be used to display device and driver | |
40 | -specific information. | |
36 | +When 82599-based SFP+ devices are connected back to back, they should be set to | |
37 | +the same Speed setting via Ethtool. Results may vary if you mix speed settings. | |
38 | +82598-based adapters support all passive direct attach cables that comply | |
39 | +with SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach | |
40 | +cables are not supported. | |
41 | 41 | |
42 | +Supplier Type Part Numbers | |
42 | 43 | |
43 | -Identifying Your Adapter | |
44 | -======================== | |
44 | +SR Modules | |
45 | +Intel DUAL RATE 1G/10G SFP+ SR (bailed) FTLX8571D3BCV-IT | |
46 | +Intel DUAL RATE 1G/10G SFP+ SR (bailed) AFBR-703SDDZ-IN1 | |
47 | +Intel DUAL RATE 1G/10G SFP+ SR (bailed) AFBR-703SDZ-IN2 | |
48 | +LR Modules | |
49 | +Intel DUAL RATE 1G/10G SFP+ LR (bailed) FTLX1471D3BCV-IT | |
50 | +Intel DUAL RATE 1G/10G SFP+ LR (bailed) AFCT-701SDDZ-IN1 | |
51 | +Intel DUAL RATE 1G/10G SFP+ LR (bailed) AFCT-701SDZ-IN2 | |
45 | 52 | |
46 | -This driver supports devices based on the 82598 controller and the 82599 | |
47 | -controller. | |
53 | +The following is a list of 3rd party SFP+ modules and direct attach cables that | |
54 | +have received some testing. Not all modules are applicable to all devices. | |
48 | 55 | |
49 | -For specific information on identifying which adapter you have, please visit: | |
56 | +Supplier Type Part Numbers | |
50 | 57 | |
51 | - http://support.intel.com/support/network/sb/CS-008441.htm | |
58 | +Finisar SFP+ SR bailed, 10g single rate FTLX8571D3BCL | |
59 | +Avago SFP+ SR bailed, 10g single rate AFBR-700SDZ | |
60 | +Finisar SFP+ LR bailed, 10g single rate FTLX1471D3BCL | |
52 | 61 | |
62 | +Finisar DUAL RATE 1G/10G SFP+ SR (No Bail) FTLX8571D3QCV-IT | |
63 | +Avago DUAL RATE 1G/10G SFP+ SR (No Bail) AFBR-703SDZ-IN1 | |
64 | +Finisar DUAL RATE 1G/10G SFP+ LR (No Bail) FTLX1471D3QCV-IT | |
65 | +Avago DUAL RATE 1G/10G SFP+ LR (No Bail) AFCT-701SDZ-IN1 | |
66 | +Finistar 1000BASE-T SFP FCLF8522P2BTL | |
67 | +Avago 1000BASE-T SFP ABCU-5710RZ | |
53 | 68 | |
54 | -Building and Installation | |
55 | -========================= | |
69 | +82599-based adapters support all passive and active limiting direct attach | |
70 | +cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications. | |
56 | 71 | |
57 | -select m for "Intel(R) 10GbE PCI Express adapters support" located at: | |
58 | - Location: | |
59 | - -> Device Drivers | |
60 | - -> Network device support (NETDEVICES [=y]) | |
61 | - -> Ethernet (10000 Mbit) (NETDEV_10000 [=y]) | |
72 | +Laser turns off for SFP+ when ifconfig down | |
73 | +------------------------------------------- | |
74 | +"ifconfig down" turns off the laser for 82599-based SFP+ fiber adapters. | |
75 | +"ifconfig up" turns on the later. | |
62 | 76 | |
63 | -1. make modules & make modules_install | |
64 | 77 | |
65 | -2. Load the module: | |
78 | +82598-BASED ADAPTERS | |
66 | 79 | |
67 | -# modprobe ixgbe | |
80 | +NOTES for 82598-Based Adapters: | |
81 | +- Intel(R) Network Adapters that support removable optical modules only support | |
82 | + their original module type (i.e., the Intel(R) 10 Gigabit SR Dual Port | |
83 | + Express Module only supports SR optical modules). If you plug in a different | |
84 | + type of module, the driver will not load. | |
85 | +- Hot Swapping/hot plugging optical modules is not supported. | |
86 | +- Only single speed, 10 gigabit modules are supported. | |
87 | +- LAN on Motherboard (LOMs) may support DA, SR, or LR modules. Other module | |
88 | + types are not supported. Please see your system documentation for details. | |
68 | 89 | |
69 | - The insmod command can be used if the full | |
70 | - path to the driver module is specified. For example: | |
90 | +The following is a list of 3rd party SFP+ modules and direct attach cables that | |
91 | +have received some testing. Not all modules are applicable to all devices. | |
71 | 92 | |
72 | - insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgbe/ixgbe.ko | |
93 | +Supplier Type Part Numbers | |
73 | 94 | |
74 | - With 2.6 based kernels also make sure that older ixgbe drivers are | |
75 | - removed from the kernel, before loading the new module: | |
95 | +Finisar SFP+ SR bailed, 10g single rate FTLX8571D3BCL | |
96 | +Avago SFP+ SR bailed, 10g single rate AFBR-700SDZ | |
97 | +Finisar SFP+ LR bailed, 10g single rate FTLX1471D3BCL | |
76 | 98 | |
77 | - rmmod ixgbe; modprobe ixgbe | |
99 | +82598-based adapters support all passive direct attach cables that comply | |
100 | +with SFF-8431 v4.1 and SFF-8472 v10.4 specifications. Active direct attach | |
101 | +cables are not supported. | |
78 | 102 | |
79 | -3. Assign an IP address to the interface by entering the following, where | |
80 | - x is the interface number: | |
81 | 103 | |
82 | - ifconfig ethx <IP_address> | |
104 | +Flow Control | |
105 | +------------ | |
106 | +Ethernet Flow Control (IEEE 802.3x) can be configured with ethtool to enable | |
107 | +receiving and transmitting pause frames for ixgbe. When TX is enabled, PAUSE | |
108 | +frames are generated when the receive packet buffer crosses a predefined | |
109 | +threshold. When rx is enabled, the transmit unit will halt for the time delay | |
110 | +specified when a PAUSE frame is received. | |
83 | 111 | |
84 | -4. Verify that the interface works. Enter the following, where <IP_address> | |
85 | - is the IP address for another machine on the same subnet as the interface | |
86 | - that is being tested: | |
112 | +Flow Control is enabled by default. If you want to disable a flow control | |
113 | +capable link partner, use Ethtool: | |
87 | 114 | |
88 | - ping <IP_address> | |
115 | + ethtool -A eth? autoneg off RX off TX off | |
89 | 116 | |
117 | +NOTE: For 82598 backplane cards entering 1 gig mode, flow control default | |
118 | +behavior is changed to off. Flow control in 1 gig mode on these devices can | |
119 | +lead to Tx hangs. | |
90 | 120 | |
91 | 121 | Additional Configurations |
92 | 122 | ========================= |
93 | 123 | |
94 | - Viewing Link Messages | |
95 | - --------------------- | |
96 | - Link messages will not be displayed to the console if the distribution is | |
97 | - restricting system messages. In order to see network driver link messages on | |
98 | - your console, set dmesg to eight by entering the following: | |
99 | - | |
100 | - dmesg -n 8 | |
101 | - | |
102 | - NOTE: This setting is not saved across reboots. | |
103 | - | |
104 | - | |
105 | 124 | Jumbo Frames |
106 | 125 | ------------ |
107 | 126 | The driver supports Jumbo Frames for all adapters. Jumbo Frames support is |
108 | 127 | |
... | ... | @@ -123,13 +142,8 @@ |
123 | 142 | other protocols besides TCP. It's also safe to use with configurations that |
124 | 143 | are problematic for LRO, namely bridging and iSCSI. |
125 | 144 | |
126 | - GRO is enabled by default in the driver. Future versions of ethtool will | |
127 | - support disabling and re-enabling GRO on the fly. | |
128 | - | |
129 | - | |
130 | 145 | Data Center Bridging, aka DCB |
131 | 146 | ----------------------------- |
132 | - | |
133 | 147 | DCB is a configuration Quality of Service implementation in hardware. |
134 | 148 | It uses the VLAN priority tag (802.1p) to filter traffic. That means |
135 | 149 | that there are 8 different priorities that traffic can be filtered into. |
136 | 150 | |
137 | 151 | |
138 | 152 | |
139 | 153 | |
140 | 154 | |
... | ... | @@ -163,24 +177,71 @@ |
163 | 177 | |
164 | 178 | http://e1000.sf.net |
165 | 179 | |
166 | - | |
167 | 180 | Ethtool |
168 | 181 | ------- |
169 | 182 | The driver utilizes the ethtool interface for driver configuration and |
170 | - diagnostics, as well as displaying statistical information. Ethtool | |
171 | - version 3.0 or later is required for this functionality. | |
183 | + diagnostics, as well as displaying statistical information. The latest | |
184 | + Ethtool version is required for this functionality. | |
172 | 185 | |
173 | 186 | The latest release of ethtool can be found from |
174 | 187 | http://sourceforge.net/projects/gkernel. |
175 | 188 | |
176 | - | |
177 | - NAPI | |
189 | + FCoE | |
178 | 190 | ---- |
191 | + This release of the ixgbe driver contains new code to enable users to use | |
192 | + Fiber Channel over Ethernet (FCoE) and Data Center Bridging (DCB) | |
193 | + functionality that is supported by the 82598-based hardware. This code has | |
194 | + no default effect on the regular driver operation, and configuring DCB and | |
195 | + FCoE is outside the scope of this driver README. Refer to | |
196 | + http://www.open-fcoe.org/ for FCoE project information and contact | |
197 | + e1000-eedc@lists.sourceforge.net for DCB information. | |
179 | 198 | |
180 | - NAPI (Rx polling mode) is supported in the ixgbe driver. NAPI is enabled | |
181 | - by default in the driver. | |
199 | + MAC and VLAN anti-spoofing feature | |
200 | + ---------------------------------- | |
201 | + When a malicious driver attempts to send a spoofed packet, it is dropped by | |
202 | + the hardware and not transmitted. An interrupt is sent to the PF driver | |
203 | + notifying it of the spoof attempt. | |
182 | 204 | |
183 | - See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI. | |
205 | + When a spoofed packet is detected the PF driver will send the following | |
206 | + message to the system log (displayed by the "dmesg" command): | |
207 | + | |
208 | + Spoof event(s) detected on VF (n) | |
209 | + | |
210 | + Where n=the VF that attempted to do the spoofing. | |
211 | + | |
212 | + | |
213 | +Performance Tuning | |
214 | +================== | |
215 | + | |
216 | +An excellent article on performance tuning can be found at: | |
217 | + | |
218 | +http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf | |
219 | + | |
220 | + | |
221 | +Known Issues | |
222 | +============ | |
223 | + | |
224 | + Enabling SR-IOV in a 32-bit Microsoft* Windows* Server 2008 Guest OS using | |
225 | + Intel (R) 82576-based GbE or Intel (R) 82599-based 10GbE controller under KVM | |
226 | + ----------------------------------------------------------------------------- | |
227 | + KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This | |
228 | + includes traditional PCIe devices, as well as SR-IOV-capable devices using | |
229 | + Intel 82576-based and 82599-based controllers. | |
230 | + | |
231 | + While direct assignment of a PCIe device or an SR-IOV Virtual Function (VF) | |
232 | + to a Linux-based VM running 2.6.32 or later kernel works fine, there is a | |
233 | + known issue with Microsoft Windows Server 2008 VM that results in a "yellow | |
234 | + bang" error. This problem is within the KVM VMM itself, not the Intel driver, | |
235 | + or the SR-IOV logic of the VMM, but rather that KVM emulates an older CPU | |
236 | + model for the guests, and this older CPU model does not support MSI-X | |
237 | + interrupts, which is a requirement for Intel SR-IOV. | |
238 | + | |
239 | + If you wish to use the Intel 82576 or 82599-based controllers in SR-IOV mode | |
240 | + with KVM and a Microsoft Windows Server 2008 guest try the following | |
241 | + workaround. The workaround is to tell KVM to emulate a different model of CPU | |
242 | + when using qemu to create the KVM guest: | |
243 | + | |
244 | + "-cpu qemu64,model=13" | |
184 | 245 | |
185 | 246 | |
186 | 247 | Support |