DPDK 17.05文档概述：快速入门与关键组件指南

需积分: 0 122 浏览量更新于2024-07-09 收藏 7.51MB PDF 举报

本资源是DPDK（Data Plane Development Kit）文档17.05版本的发布说明，日期为2017年2月18日。这份文档详细介绍了如何在Linux环境（Linux application, 或称linuxapp）中安装、配置和运行DPDK软件，旨在帮助用户快速入门。文档内容涵盖了多个方面： 1. **Getting Started Guide for Linux**：作为入门指南，这部分提供了一个简明的流程，包括安装步骤、编译和运行DPDK应用的基本指导，但重点在于快速启动，而非深入技术细节。 2. **Getting Started Guide for FreeBSD**：适用于FreeBSD操作系统的DPDK初学者，与Linux版指南相似，但针对该特定平台进行了定制。 3. **Sample Applications User Guides**：展示了如何使用预编好的样例应用程序，有助于理解DPDK的应用场景和实践。 4. **Programmer's Guide**：为开发者提供了更深入的编程参考，包括API文档和架构信息，适合对DPDK源码有深入了解的需求。 5. **How To Guides**：包含了各种实用技巧和解决问题的方法，有助于解决开发过程中遇到的技术问题。 6. **DPDK Tools User Guides**：介绍了DPDK提供的工具集，如性能监控、调试工具等，提升开发效率。 7. **Testpmd Application User Guide**：着重于测试工具testpmd的使用，用于验证和优化网络设备的性能。 8. **Network Interface Controller Drivers**：涵盖了与网络接口控制器相关的驱动程序，是实现硬件加速的基础。 9. **Crypto Device Drivers**：涉及加密设备驱动，对于处理安全敏感的数据传输至关重要。 10. **Xen Guide**：专为Xen虚拟化环境设计的DPDK指南，针对虚拟化场景下的优化和集成。 11. **Contributor's Guidelines**：为有兴趣参与DPDK开发的贡献者提供编码规范、提交代码的流程等信息。 12. **Release Notes**：这是关键文档，包含了新版本的主要特点、修复的问题、限制以及注意事项，还解答了常见问题。 13. **FAQ**：解答了文档中未详尽覆盖的常见疑问，便于用户快速获取答案。通过这份文档，用户可以根据自己的需求选择合适的章节进行学习，无论是快速搭建环境还是深入技术研究，都能找到相应的指导。DPDK作为高性能数据包处理套件，它的高效和灵活性对于网络和数据中心应用的开发者来说是不可或缺的资源。

DPDK documentation, Release 17.05.0-rc0

grep hpet /proc/timer_list

If no entries are returned, HPET must be enabled in the BIOS (as per the instructions above)

and the system rebooted.

Linux Kernel Support

The DPDK makes use of the platform HPET timer by mapping the timer counter into the pro-

cess address space, and as such, requires that the HPET_MMAP kernel conﬁguration option be

enabled.

Warning: On Fedora, and other common distributions such as Ubuntu, the HPET_MMAP

kernel option is not enabled by default. To recompile the Linux kernel with this option en-

abled, please consult the distributions documentation for the relevant instructions.

Enabling HPET in the DPDK

By default, HPET support is disabled in the DPDK build conﬁguration ﬁles. To use HPET,

the CONFIG_RTE_LIBEAL_USE_HPET setting should be changed to y, which will enable the

HPET settings at compile time.

For an application to use the rte_get_hpet_cycles() and rte_get_hpet_hz() API

calls, and optionally to make the HPET the default time source for the rte_timer library, the

new rte_eal_hpet_init() API call should be called at application initialization. This API

call will ensure that the HPET is accessible, returning an error to the application if it is not, for

example, if HPET_MMAP is not enabled in the kernel. The application can then determine what

action to take, if any, if the HPET is not available at run-time.

Note: For applications that require timing APIs, but not the HPET timer speciﬁcally, it is recom-

mended that the rte_get_timer_cycles() and rte_get_timer_hz() API calls be used

instead of the HPET-speciﬁc APIs. 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(),

if any, and on what is available on the system at runtime.

Running DPDK Applications Without Root Privileges

Although applications using the DPDK use network ports and other hardware resources di-

rectly, with a number of small permission adjustments it is possible to run these applications

as a user other than “root”. To do so, the ownership, or permissions, on the following Linux ﬁle

system objects should be adjusted to ensure that the Linux user account being used to run the

DPDK application has access to them:

• All directories which serve as hugepage mount points, for example, /mnt/huge

• The userspace-io device ﬁles in /dev, for example, /dev/uio0, /dev/uio1, and so on

• The userspace-io sysfs conﬁg and resource ﬁles, for example for uio0:

/sys/class/uio/uio0/device/config

/sys/class/uio/uio0/device/resource

1.5. Enabling Additional Functionality 14

DPDK documentation, Release 17.05.0-rc0

• If the HPET is to be used, /dev/hpet

Note: On some Linux installations, /dev/hugepages is also a hugepage mount point cre-

ated by default.

Power Management and Power Saving Functionality

Enhanced Intel SpeedStep® Technology must be enabled in the platform BIOS if the

power management feature of DPDK is to be used. Otherwise, the sys ﬁle folder

/sys/devices/system/cpu/cpu0/cpufreq will not exist, and the CPU frequency- based

power management cannot be used. Consult the relevant BIOS documentation to determine

how these settings can be accessed.

For example, on some Intel reference platform BIOS variants, the path to Enhanced Intel

SpeedStep® Technology is:

Advanced

-> Processor Configuration

-> Enhanced Intel SpeedStep® Tech

In addition, C3 and C6 should be enabled as well for power management. The path of C3 and

C6 on the same platform BIOS is:

Advanced

-> Processor Configuration

-> Processor C3 Advanced

-> Processor Configuration

-> Processor C6

Using Linux Core Isolation to Reduce Context Switches

While the threads used by an DPDK application are pinned to logical cores on the system,

it is possible for the Linux scheduler to run other tasks on those cores also. To help prevent

additional workloads from running on those cores, it is possible to use the isolcpus Linux

kernel parameter to isolate them from the general Linux scheduler.

For example, if DPDK applications are to run on logical cores 2, 4 and 6, the following should

be added to the kernel parameter list:

isolcpus=2,4,6

Loading the DPDK KNI Kernel Module

To run the DPDK Kernel NIC Interface (KNI) sample application, an extra kernel module (the

kni module) must be loaded into the running kernel. The module is found in the kmod sub-

directory of the DPDK target directory. Similar to the loading of the igb_uio module, this

module should be loaded using the insmod command as shown below (assuming that the

current directory is the DPDK target directory):

insmod kmod/rte_kni.ko

1.5. Enabling Additional Functionality 15

DPDK documentation, Release 17.05.0-rc0

Note: See the “Kernel NIC Interface Sample Application” chapter in the DPDK Sample Appli-

cations User Guide for more details.

Using Linux IOMMU Pass-Through to Run DPDK with Intel® VT-d

To enable Intel® VT-d in a Linux kernel, a number of kernel conﬁguration options must be set.

These include:

• IOMMU_SUPPORT

• IOMMU_API

• INTEL_IOMMU

In addition, to run the DPDK with Intel® VT-d, the iommu=pt kernel parameter must be

used when using igb_uio driver. This results in pass-through of the DMAR (DMA Remap-

ping) lookup in the host. Also, if INTEL_IOMMU_DEFAULT_ON is not set in the kernel, the

intel_iommu=on kernel parameter must be used too. This ensures that the Intel IOMMU is

being initialized as expected.

Please 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.

High Performance of Small Packets on 40G NIC

As there might be ﬁrmware ﬁxes for performance enhancement in latest version of ﬁrmware

image, the ﬁrmware update might be needed for getting high performance. Check with the

local Intel’s Network Division application engineers for ﬁrmware updates. Users should consult

the release notes speciﬁc to a DPDK release to identify the validated ﬁrmware version for a

NIC using the i40e driver.

Use 16 Bytes RX Descriptor Size

As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes

size can provide helps to high performance of small packets. Conﬁguration of

CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC in conﬁg ﬁles can be changed to use 16

bytes size RX descriptors.

High Performance and per Packet Latency Tradeoff

Due to the hardware design, the interrupt signal inside NIC is needed for per packet de-

scriptor write-back. The minimum interval of interrupts could be set at compile time by

CONFIG_RTE_LIBRTE_I40E_ITR_INTERVAL in conﬁguration ﬁles. Though there is a default

conﬁguration, the interval could be tuned by the users with that conﬁguration item depends on

what the user cares about more, performance or per packet latency.

1.5. Enabling Additional Functionality 16

DPDK documentation, Release 17.05.0-rc0

Quick Start Setup Script

The dpdk-setup.sh script, found in the usertools subdirectory, allows the user to perform the

following tasks:

• Build the DPDK libraries

• Insert and remove the DPDK IGB_UIO kernel module

• Insert and remove VFIO kernel modules

• Insert and remove the DPDK KNI kernel module

• Create and delete hugepages for NUMA and non-NUMA cases

• View network port status and reserve ports for DPDK application use

• Set up permissions for using VFIO as a non-privileged user

• Run the test and testpmd applications

• Look at hugepages in the meminfo

• List hugepages in /mnt/huge

• Remove built DPDK libraries

Once these steps have been completed for one of the EAL targets, the user may compile their

own application that links in the EAL libraries to create the DPDK image.

Script Organization

The dpdk-setup.sh script is logically organized into a series of steps that a user performs in

sequence. Each step provides a number of options that guide the user to completing the

desired task. The following is a brief synopsis of each step.

Step 1: Build DPDK Libraries

Initially, the user must select a DPDK target to choose the correct target type and compiler

options to use when building the libraries.

The user must have all libraries, modules, updates and compilers installed in the system prior

to this, as described in the earlier chapters in this Getting Started Guide.

Step 2: Setup Environment

The user conﬁgures the Linux* environment to support the running of DPDK applications.

Hugepages can be set up for NUMA or non-NUMA systems. Any existing hugepages will

be removed. The DPDK kernel module that is needed can also be inserted in this step, and

network ports may be bound to this module for DPDK application use.

Step 3: Run an Application

The user may run the test application once the other steps have been performed. The test

application allows the user to run a series of functional tests for the DPDK. The testpmd appli-

cation, which supports the receiving and sending of packets, can also be run.

Step 4: Examining the System

This step provides some tools for examining the status of hugepage mappings.

1.6. Quick Start Setup Script 17

剩余807页未读，继续阅读

dangdanding

粉丝: 107
资源: 30

DPDK 17.05文档概述：快速入门与关键组件指南

dpdk-17.05.1.zip安装包

dpdk-17.05.2.tar.xz

dpdk vswitch

DPDK Cookbook

intel dpdk

Understanding DPDK

dpdk-app:appstools和dpdk框架

rust-dpdk:Rust绑定到DPDK

DPDK工具指南：dpdk-devbind, dpdk-pdump等命令详解

dpdk libnids

最新资源