1 .. SPDX-License-Identifier: GPL-2.0+
3 ==========================================================================
4 idpf Linux* Base Driver for the Intel(R) Infrastructure Data Path Function
5 ==========================================================================
7 Intel idpf Linux driver.
8 Copyright(C) 2023 Intel Corporation.
12 The idpf driver serves as both the Physical Function (PF) and Virtual Function
13 (VF) driver for the Intel(R) Infrastructure Data Path Function.
15 Driver information can be obtained using ethtool, lspci, and ip.
17 For questions related to hardware requirements, refer to the documentation
18 supplied with your Intel adapter. All hardware requirements listed apply to use
22 Identifying Your Adapter
23 ========================
24 For information on how to identify your adapter, and for the latest Intel
25 network drivers, refer to the Intel Support website:
26 http://www.intel.com/support
29 Additional Features and Configurations
30 ======================================
34 The driver utilizes the ethtool interface for driver configuration and
35 diagnostics, as well as displaying statistical information. The latest ethtool
36 version is required for this functionality. If you don't have one yet, you can
38 https://kernel.org/pub/software/network/ethtool/
43 Link messages will not be displayed to the console if the distribution is
44 restricting system messages. In order to see network driver link messages on
45 your console, set dmesg to eight by entering the following::
50 This setting is not saved across reboots.
55 Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU)
56 to a value larger than the default value of 1500.
58 Use the ip command to increase the MTU size. For example, enter the following
59 where <ethX> is the interface number::
61 # ip link set mtu 9000 dev <ethX>
62 # ip link set up dev <ethX>
65 The maximum MTU setting for jumbo frames is 9706. This corresponds to the
66 maximum jumbo frame size of 9728 bytes.
69 This driver will attempt to use multiple page sized buffers to receive
70 each jumbo packet. This should help to avoid buffer starvation issues when
71 allocating receive packets.
74 Packet loss may have a greater impact on throughput when you use jumbo
75 frames. If you observe a drop in performance after enabling jumbo frames,
76 enabling flow control may mitigate the issue.
79 Performance Optimization
80 ========================
81 Driver defaults are meant to fit a wide variety of workloads, but if further
82 optimization is required, we recommend experimenting with the following
86 Interrupt Rate Limiting
87 -----------------------
88 This driver supports an adaptive interrupt throttle rate (ITR) mechanism that
89 is tuned for general workloads. The user can customize the interrupt rate
90 control for specific workloads, via ethtool, adjusting the number of
91 microseconds between interrupts.
93 To set the interrupt rate manually, you must disable adaptive mode::
95 # ethtool -C <ethX> adaptive-rx off adaptive-tx off
97 For lower CPU utilization:
98 - Disable adaptive ITR and lower Rx and Tx interrupts. The examples below
99 affect every queue of the specified interface.
101 - Setting rx-usecs and tx-usecs to 80 will limit interrupts to about
102 12,500 interrupts per second per queue::
104 # ethtool -C <ethX> adaptive-rx off adaptive-tx off rx-usecs 80
108 - Disable adaptive ITR and ITR by setting rx-usecs and tx-usecs to 0
111 # ethtool -C <ethX> adaptive-rx off adaptive-tx off rx-usecs 0
114 Per-queue interrupt rate settings:
115 - The following examples are for queues 1 and 3, but you can adjust other
118 - To disable Rx adaptive ITR and set static Rx ITR to 10 microseconds or
119 about 100,000 interrupts/second, for queues 1 and 3::
121 # ethtool --per-queue <ethX> queue_mask 0xa --coalesce adaptive-rx off
124 - To show the current coalesce settings for queues 1 and 3::
126 # ethtool --per-queue <ethX> queue_mask 0xa --show-coalesce
130 Virtualized Environments
131 ------------------------
132 In addition to the other suggestions in this section, the following may be
133 helpful to optimize performance in VMs.
135 - Using the appropriate mechanism (vcpupin) in the VM, pin the CPUs to
136 individual LCPUs, making sure to use a set of CPUs included in the
137 device's local_cpulist: /sys/class/net/<ethX>/device/local_cpulist.
139 - Configure as many Rx/Tx queues in the VM as available. (See the idpf driver
140 documentation for the number of queues supported.) For example::
142 # ethtool -L <virt_interface> rx <max> tx <max>
147 For general information, go to the Intel support website at:
148 http://www.intel.com/support/
150 If an issue is identified with the released source code on a supported kernel
151 with a supported adapter, email the specific information related to the issue
152 to intel-wired-lan@lists.osuosl.org.
157 Intel is a trademark or registered trademark of Intel Corporation or its
158 subsidiaries in the United States and/or other countries.
160 * Other names and brands may be claimed as the property of others.