enable_func.rst revision a41e6ff1
1..  BSD LICENSE
2    Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
3    All rights reserved.
4
5    Redistribution and use in source and binary forms, with or without
6    modification, are permitted provided that the following conditions
7    are met:
8
9    * Redistributions of source code must retain the above copyright
10    notice, this list of conditions and the following disclaimer.
11    * Redistributions in binary form must reproduce the above copyright
12    notice, this list of conditions and the following disclaimer in
13    the documentation and/or other materials provided with the
14    distribution.
15    * Neither the name of Intel Corporation nor the names of its
16    contributors may be used to endorse or promote products derived
17    from this software without specific prior written permission.
18
19    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22    A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23    OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24    SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25    LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26    DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27    THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28    (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31.. _Enabling_Additional_Functionality:
32
33Enabling Additional Functionality
34=================================
35
36.. _High_Precision_Event_Timer:
37
38High Precision Event Timer HPET) Functionality
39----------------------------------------------
40
41BIOS Support
42~~~~~~~~~~~~
43
44The High Precision Timer (HPET) must be enabled in the platform BIOS if the HPET is to be used.
45Otherwise, the Time Stamp Counter (TSC) is used by default.
46The BIOS is typically accessed by pressing F2 while the platform is starting up.
47The user can then navigate to the HPET option. On the Crystal Forest platform BIOS, the path is:
48**Advanced -> PCH-IO Configuration -> High Precision Timer ->** (Change from Disabled to Enabled if necessary).
49
50On a system that has already booted, the following command can be issued to check if HPET is enabled::
51
52   grep hpet /proc/timer_list
53
54If no entries are returned, HPET must be enabled in the BIOS (as per the instructions above) and the system rebooted.
55
56Linux Kernel Support
57~~~~~~~~~~~~~~~~~~~~
58
59The DPDK makes use of the platform HPET timer by mapping the timer counter into the process address space, and as such,
60requires that the ``HPET_MMAP`` kernel configuration option be enabled.
61
62.. warning::
63
64    On Fedora, and other common distributions such as Ubuntu, the ``HPET_MMAP`` kernel option is not enabled by default.
65    To recompile the Linux kernel with this option enabled, please consult the distributions documentation for the relevant instructions.
66
67Enabling HPET in the DPDK
68~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
69
70By default, HPET support is disabled in the DPDK build configuration files.
71To use HPET, the ``CONFIG_RTE_LIBEAL_USE_HPET`` setting should be changed to ``y``, which will enable the HPET settings at compile time.
72
73For an application to use the ``rte_get_hpet_cycles()`` and ``rte_get_hpet_hz()`` API calls,
74and optionally to make the HPET the default time source for the rte_timer library,
75the new ``rte_eal_hpet_init()`` API call should be called at application initialization.
76This API call will ensure that the HPET is accessible, returning an error to the application if it is not,
77for example, if ``HPET_MMAP`` is not enabled in the kernel.
78The application can then determine what action to take, if any, if the HPET is not available at run-time.
79
80.. note::
81
82    For applications that require timing APIs, but not the HPET timer specifically,
83    it is recommended that the ``rte_get_timer_cycles()`` and ``rte_get_timer_hz()`` API calls be used instead of the HPET-specific APIs.
84    These generic APIs can work with either TSC or HPET time sources, depending on what is requested by an application call to ``rte_eal_hpet_init()``,
85    if any, and on what is available on the system at runtime.
86
87Running DPDK Applications Without Root Privileges
88--------------------------------------------------------
89
90Although applications using the DPDK use network ports and other hardware resources directly,
91with a number of small permission adjustments it is possible to run these applications as a user other than "root".
92To do so, the ownership, or permissions, on the following Linux file system objects should be adjusted to ensure that
93the Linux user account being used to run the DPDK application has access to them:
94
95*   All directories which serve as hugepage mount points, for example,   ``/mnt/huge``
96
97*   The userspace-io device files in  ``/dev``, for example,  ``/dev/uio0``, ``/dev/uio1``, and so on
98
99*   The userspace-io sysfs config and resource files, for example for ``uio0``::
100
101       /sys/class/uio/uio0/device/config
102       /sys/class/uio/uio0/device/resource*
103
104*   If the HPET is to be used,  ``/dev/hpet``
105
106.. note::
107
108    On some Linux installations, ``/dev/hugepages``  is also a hugepage mount point created by default.
109
110Power Management and Power Saving Functionality
111-----------------------------------------------
112
113Enhanced Intel SpeedStep® Technology must be enabled in the platform BIOS if the power management feature of DPDK is to be used.
114Otherwise, the sys file folder ``/sys/devices/system/cpu/cpu0/cpufreq`` will not exist, and the CPU frequency- based power management cannot be used.
115Consult the relevant BIOS documentation to determine how these settings can be accessed.
116
117For example, on some Intel reference platform BIOS variants, the path to Enhanced Intel SpeedStep® Technology is::
118
119   Advanced
120     -> Processor Configuration
121     -> Enhanced Intel SpeedStep® Tech
122
123In addition, C3 and C6 should be enabled as well for power management. The path of C3 and C6 on the same platform BIOS is::
124
125   Advanced
126     -> Processor Configuration
127     -> Processor C3 Advanced
128     -> Processor Configuration
129     -> Processor C6
130
131Using Linux Core Isolation to Reduce Context Switches
132-----------------------------------------------------
133
134While the threads used by an DPDK application are pinned to logical cores on the system,
135it is possible for the Linux scheduler to run other tasks on those cores also.
136To help prevent additional workloads from running on those cores,
137it is possible to use the ``isolcpus`` Linux kernel parameter to isolate them from the general Linux scheduler.
138
139For example, if DPDK applications are to run on logical cores 2, 4 and 6,
140the following should be added to the kernel parameter list:
141
142.. code-block:: console
143
144    isolcpus=2,4,6
145
146Loading the DPDK KNI Kernel Module
147----------------------------------
148
149To run the DPDK Kernel NIC Interface (KNI) sample application, an extra kernel module (the kni module) must be loaded into the running kernel.
150The module is found in the kmod sub-directory of the DPDK target directory.
151Similar to the loading of the ``igb_uio`` module, this module should be loaded using the insmod command as shown below
152(assuming that the current directory is the DPDK target directory):
153
154.. code-block:: console
155
156   insmod kmod/rte_kni.ko
157
158.. note::
159
160   See the "Kernel NIC Interface Sample Application" chapter in the *DPDK Sample Applications User Guide* for more details.
161
162Using Linux IOMMU Pass-Through to Run DPDK with Intel® VT-d
163-----------------------------------------------------------
164
165To enable Intel® VT-d in a Linux kernel, a number of kernel configuration options must be set. These include:
166
167*   ``IOMMU_SUPPORT``
168
169*   ``IOMMU_API``
170
171*   ``INTEL_IOMMU``
172
173In addition, to run the DPDK with Intel® VT-d, the ``iommu=pt`` kernel parameter must be used when using ``igb_uio`` driver.
174This results in pass-through of the DMAR (DMA Remapping) lookup in the host.
175Also, if ``INTEL_IOMMU_DEFAULT_ON`` is not set in the kernel, the ``intel_iommu=on`` kernel parameter must be used too.
176This ensures that the Intel IOMMU is being initialized as expected.
177
178Please note that while using ``iommu=pt`` is compulsory for ``igb_uio driver``, the ``vfio-pci`` driver can actually work with both ``iommu=pt`` and ``iommu=on``.
179
180High Performance of Small Packets on 40G NIC
181--------------------------------------------
182
183As there might be firmware fixes for performance enhancement in latest version
184of firmware image, the firmware update might be needed for getting high performance.
185Check with the local Intel's Network Division application engineers for firmware updates.
186Users should consult the release notes specific to a DPDK release to identify
187the validated firmware version for a NIC using the i40e driver.
188
189Use 16 Bytes RX Descriptor Size
190~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
191
192As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes size can provide helps to high performance of small packets.
193Configuration of ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` in config files can be changed to use 16 bytes size RX descriptors.
194
195High Performance and per Packet Latency Tradeoff
196~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
197
198Due to the hardware design, the interrupt signal inside NIC is needed for per
199packet descriptor write-back. The minimum interval of interrupts could be set
200at compile time by ``CONFIG_RTE_LIBRTE_I40E_ITR_INTERVAL`` in configuration files.
201Though there is a default configuration, the interval could be tuned by the
202users with that configuration item depends on what the user cares about more,
203performance or per packet latency.
204