linux/Documentation/networking/e1000e.txt
<<
>>
Prefs
   1Linux* Driver for Intel(R) Network Connection
   2=============================================
   3
   4Intel Gigabit Linux driver.
   5Copyright(c) 1999 - 2010 Intel Corporation.
   6
   7Contents
   8========
   9
  10- Identifying Your Adapter
  11- Command Line Parameters
  12- Additional Configurations
  13- Support
  14
  15Identifying Your Adapter
  16========================
  17
  18The e1000e driver supports all PCI Express Intel(R) Gigabit Network
  19Connections, except those that are 82575, 82576 and 82580-based*.
  20
  21* NOTE: The Intel(R) PRO/1000 P Dual Port Server Adapter is supported by
  22  the e1000 driver, not the e1000e driver due to the 82546 part being used
  23  behind a PCI Express bridge.
  24
  25For more information on how to identify your adapter, go to the Adapter &
  26Driver ID Guide at:
  27
  28    http://support.intel.com/support/go/network/adapter/idguide.htm
  29
  30For the latest Intel network drivers for Linux, refer to the following
  31website.  In the search field, enter your adapter name or type, or use the
  32networking link on the left to search for your adapter:
  33
  34    http://support.intel.com/support/go/network/adapter/home.htm
  35
  36Command Line Parameters
  37=======================
  38
  39The default value for each parameter is generally the recommended setting,
  40unless otherwise noted.
  41
  42NOTES:  For more information about the InterruptThrottleRate,
  43        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
  44        parameters, see the application note at:
  45        http://www.intel.com/design/network/applnots/ap450.htm
  46
  47InterruptThrottleRate
  48---------------------
  49Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
  50                                   4=simplified balancing)
  51Default Value: 3
  52
  53The driver can limit the amount of interrupts per second that the adapter
  54will generate for incoming packets. It does this by writing a value to the
  55adapter that is based on the maximum amount of interrupts that the adapter
  56will generate per second.
  57
  58Setting InterruptThrottleRate to a value greater or equal to 100
  59will program the adapter to send out a maximum of that many interrupts
  60per second, even if more packets have come in. This reduces interrupt
  61load on the system and can lower CPU utilization under heavy load,
  62but will increase latency as packets are not processed as quickly.
  63
  64The default behaviour of the driver previously assumed a static
  65InterruptThrottleRate value of 8000, providing a good fallback value for
  66all traffic types, but lacking in small packet performance and latency.
  67The hardware can handle many more small packets per second however, and
  68for this reason an adaptive interrupt moderation algorithm was implemented.
  69
  70The driver has two adaptive modes (setting 1 or 3) in which
  71it dynamically adjusts the InterruptThrottleRate value based on the traffic
  72that it receives. After determining the type of incoming traffic in the last
  73timeframe, it will adjust the InterruptThrottleRate to an appropriate value
  74for that traffic.
  75
  76The algorithm classifies the incoming traffic every interval into
  77classes.  Once the class is determined, the InterruptThrottleRate value is
  78adjusted to suit that traffic type the best. There are three classes defined:
  79"Bulk traffic", for large amounts of packets of normal size; "Low latency",
  80for small amounts of traffic and/or a significant percentage of small
  81packets; and "Lowest latency", for almost completely small packets or
  82minimal traffic.
  83
  84In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
  85for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
  86latency" or "Lowest latency" class, the InterruptThrottleRate is increased
  87stepwise to 20000. This default mode is suitable for most applications.
  88
  89For situations where low latency is vital such as cluster or
  90grid computing, the algorithm can reduce latency even more when
  91InterruptThrottleRate is set to mode 1. In this mode, which operates
  92the same as mode 3, the InterruptThrottleRate will be increased stepwise to
  9370000 for traffic in class "Lowest latency".
  94
  95In simplified mode the interrupt rate is based on the ratio of TX and
  96RX traffic.  If the bytes per second rate is approximately equal, the
  97interrupt rate will drop as low as 2000 interrupts per second.  If the
  98traffic is mostly transmit or mostly receive, the interrupt rate could
  99be as high as 8000.
 100
 101Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 102and may improve small packet latency, but is generally not suitable
 103for bulk throughput traffic.
 104
 105NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
 106       RxAbsIntDelay parameters.  In other words, minimizing the receive
 107       and/or transmit absolute delays does not force the controller to
 108       generate more interrupts than what the Interrupt Throttle Rate
 109       allows.
 110
 111NOTE:  When e1000e is loaded with default settings and multiple adapters
 112       are in use simultaneously, the CPU utilization may increase non-
 113       linearly.  In order to limit the CPU utilization without impacting
 114       the overall throughput, we recommend that you load the driver as
 115       follows:
 116
 117           modprobe e1000e InterruptThrottleRate=3000,3000,3000
 118
 119       This sets the InterruptThrottleRate to 3000 interrupts/sec for
 120       the first, second, and third instances of the driver.  The range
 121       of 2000 to 3000 interrupts per second works on a majority of
 122       systems and is a good starting point, but the optimal value will
 123       be platform-specific.  If CPU utilization is not a concern, use
 124       RX_POLLING (NAPI) and default driver settings.
 125
 126RxIntDelay
 127----------
 128Valid Range:   0-65535 (0=off)
 129Default Value: 0
 130
 131This value delays the generation of receive interrupts in units of 1.024
 132microseconds.  Receive interrupt reduction can improve CPU efficiency if
 133properly tuned for specific network traffic.  Increasing this value adds
 134extra latency to frame reception and can end up decreasing the throughput
 135of TCP traffic.  If the system is reporting dropped receives, this value
 136may be set too high, causing the driver to run out of available receive
 137descriptors.
 138
 139CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
 140          hang (stop transmitting) under certain network conditions.  If
 141          this occurs a NETDEV WATCHDOG message is logged in the system
 142          event log.  In addition, the controller is automatically reset,
 143          restoring the network connection.  To eliminate the potential
 144          for the hang ensure that RxIntDelay is set to 0.
 145
 146RxAbsIntDelay
 147-------------
 148Valid Range:   0-65535 (0=off)
 149Default Value: 8
 150
 151This value, in units of 1.024 microseconds, limits the delay in which a
 152receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
 153this value ensures that an interrupt is generated after the initial
 154packet is received within the set amount of time.  Proper tuning,
 155along with RxIntDelay, may improve traffic throughput in specific network
 156conditions.
 157
 158TxIntDelay
 159----------
 160Valid Range:   0-65535 (0=off)
 161Default Value: 8
 162
 163This value delays the generation of transmit interrupts in units of
 1641.024 microseconds.  Transmit interrupt reduction can improve CPU
 165efficiency if properly tuned for specific network traffic.  If the
 166system is reporting dropped transmits, this value may be set too high
 167causing the driver to run out of available transmit descriptors.
 168
 169TxAbsIntDelay
 170-------------
 171Valid Range:   0-65535 (0=off)
 172Default Value: 32
 173
 174This value, in units of 1.024 microseconds, limits the delay in which a
 175transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
 176this value ensures that an interrupt is generated after the initial
 177packet is sent on the wire within the set amount of time.  Proper tuning,
 178along with TxIntDelay, may improve traffic throughput in specific
 179network conditions.
 180
 181Copybreak
 182---------
 183Valid Range:   0-xxxxxxx (0=off)
 184Default Value: 256
 185
 186Driver copies all packets below or equaling this size to a fresh RX
 187buffer before handing it up the stack.
 188
 189This parameter is different than other parameters, in that it is a
 190single (not 1,1,1 etc.) parameter applied to all driver instances and
 191it is also available during runtime at
 192/sys/module/e1000e/parameters/copybreak
 193
 194SmartPowerDownEnable
 195--------------------
 196Valid Range: 0-1
 197Default Value:  0 (disabled)
 198
 199Allows PHY to turn off in lower power states. The user can set this parameter
 200in supported chipsets.
 201
 202KumeranLockLoss
 203---------------
 204Valid Range: 0-1
 205Default Value: 1 (enabled)
 206
 207This workaround skips resetting the PHY at shutdown for the initial
 208silicon releases of ICH8 systems.
 209
 210IntMode
 211-------
 212Valid Range: 0-2 (0=legacy, 1=MSI, 2=MSI-X)
 213Default Value: 2
 214
 215Allows changing the interrupt mode at module load time, without requiring a
 216recompile. If the driver load fails to enable a specific interrupt mode, the
 217driver will try other interrupt modes, from least to most compatible.  The
 218interrupt order is MSI-X, MSI, Legacy.  If specifying MSI (IntMode=1)
 219interrupts, only MSI and Legacy will be attempted.
 220
 221CrcStripping
 222------------
 223Valid Range: 0-1
 224Default Value: 1 (enabled)
 225
 226Strip the CRC from received packets before sending up the network stack.  If
 227you have a machine with a BMC enabled but cannot receive IPMI traffic after
 228loading or enabling the driver, try disabling this feature.
 229
 230WriteProtectNVM
 231---------------
 232Valid Range: 0,1
 233Default Value: 1
 234
 235If set to 1, configure the hardware to ignore all write/erase cycles to the
 236GbE region in the ICHx NVM (in order to prevent accidental corruption of the
 237NVM). This feature can be disabled by setting the parameter to 0 during initial
 238driver load.
 239NOTE: The machine must be power cycled (full off/on) when enabling NVM writes
 240via setting the parameter to zero. Once the NVM has been locked (via the
 241parameter at 1 when the driver loads) it cannot be unlocked except via power
 242cycle.
 243
 244Additional Configurations
 245=========================
 246
 247  Jumbo Frames
 248  ------------
 249  Jumbo Frames support is enabled by changing the MTU to a value larger than
 250  the default of 1500.  Use the ifconfig command to increase the MTU size.
 251  For example:
 252
 253       ifconfig eth<x> mtu 9000 up
 254
 255  This setting is not saved across reboots.
 256
 257  Notes:
 258
 259  - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
 260    with the maximum Jumbo Frames size of 9234 bytes.
 261
 262  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
 263    poor performance or loss of link.
 264
 265  - Some adapters limit Jumbo Frames sized packets to a maximum of
 266    4096 bytes and some adapters do not support Jumbo Frames.
 267
 268  Ethtool
 269  -------
 270  The driver utilizes the ethtool interface for driver configuration and
 271  diagnostics, as well as displaying statistical information.  We
 272  strongly recommend downloading the latest version of ethtool at:
 273
 274  http://ftp.kernel.org/pub/software/network/ethtool/
 275
 276  Speed and Duplex
 277  ----------------
 278  Speed and Duplex are configured through the ethtool* utility. For
 279  instructions,  refer to the ethtool man page.
 280
 281  Enabling Wake on LAN* (WoL)
 282  ---------------------------
 283  WoL is configured through the ethtool* utility. For instructions on
 284  enabling WoL with ethtool, refer to the ethtool man page.
 285
 286  WoL will be enabled on the system during the next shut down or reboot.
 287  For this driver version, in order to enable WoL, the e1000e driver must be
 288  loaded when shutting down or rebooting the system.
 289
 290  In most cases Wake On LAN is only supported on port A for multiple port
 291  adapters. To verify if a port supports Wake on Lan run ethtool eth<X>.
 292
 293Support
 294=======
 295
 296For general information, go to the Intel support website at:
 297
 298    www.intel.com/support/
 299
 300or the Intel Wired Networking project hosted by Sourceforge at:
 301
 302    http://sourceforge.net/projects/e1000
 303
 304If an issue is identified with the released source code on the supported
 305kernel with a supported adapter, email the specific information related
 306to the issue to e1000-devel@lists.sf.net
 307
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.