QEMU/KVM libvirt X710 PCI passthrough & DPDK 网络性能测试

QEMU/KVM libvirt X710 PCI passthrough & DPDK 网络性能测试

注:

  • 确认BIOS已启用 VT-dAMD-Vi;
  • 确认kernel开启 iommu=pt intel_iommu=on 后初始化正确;
  • 确认设备绑定 vfio-pciDMAR 初始化正确;

宿主机(Host) 配置

QEMU/KVM

$ sudo dnf install qemu-kvm libvirt-daemon-driver-qemu libvirt-daemon-kvm libvirt virt-install libguestfs-tools-c kernel-tools dpdk dpdk-tools
$ sudo systemctl start libvirtd
$ sudo /usr/libexec/qemu-kvm -version
QEMU emulator version 4.2.0 (qemu-kvm-4.2.0-48.module_el8.4.0+885+5e18b468.3)
Copyright (c) 2003-2019 Fabrice Bellard and the QEMU Project developers

CPU

$ sudo lscpu 
Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              24
On-line CPU(s) list: 0-23
Thread(s) per core:  1
Core(s) per socket:  12
Socket(s):           2
NUMA node(s):        2
Vendor ID:           GenuineIntel
BIOS Vendor ID:      Intel
CPU family:          6
Model:               79
Model name:          Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
BIOS Model name:     Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz
Stepping:            1
CPU MHz:             1614.949
CPU max MHz:         2200.0000
CPU min MHz:         1200.0000
BogoMIPS:            4399.60
Virtualization:      VT-x
L1d cache:           32K
L1i cache:           32K
L2 cache:            256K
L3 cache:            30720K
NUMA node0 CPU(s):   0-11
NUMA node1 CPU(s):   12-23
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single intel_ppin ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap intel_pt xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm arat pln pts
# 

$ sudo cpu_layout.py 
======================================================================
Core and Socket Information (as reported by '/sys/devices/system/cpu')
======================================================================

cores =  [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 12, 13]
sockets =  [0, 1]

        Socket 0    Socket 1   
        --------    --------   
Core 0  [0]         [12]       
Core 1  [1]         [13]       
Core 2  [2]         [14]       
Core 3  [3]         [15]       
Core 4  [4]         [16]       
Core 5  [5]         [17]       
Core 8  [6]         [18]       
Core 9  [7]         [19]       
Core 10 [8]         [20]       
Core 11 [9]         [21]       
Core 12 [10]        [22]       
Core 13 [11]        [23]       

Ethernet NIC

$ sudo lshw -C network -businfo
Bus info          Device      Class          Description
========================================================
pci@0000:06:00.0  ens1f0      network        MT27800 Family [ConnectX-5]
pci@0000:06:00.1  ens1f1      network        MT27800 Family [ConnectX-5]
pci@0000:0a:00.0  enp10s0     network        I210 Gigabit Network Connection
pci@0000:0b:00.0  enp11s0     network        I210 Gigabit Network Connection
pci@0000:86:00.0  enp134s0f0  network        I350 Gigabit Network Connection
pci@0000:86:00.1  enp134s0f1  network        I350 Gigabit Network Connection
pci@0000:86:00.2  enp134s0f2  network        I350 Gigabit Network Connection
pci@0000:86:00.3  enp134s0f3  network        I350 Gigabit Network Connection
pci@0000:88:00.0  enp136s0f0  network        I350 Gigabit Fiber Network Connection
pci@0000:88:00.1  enp136s0f1  network        I350 Gigabit Fiber Network Connection
pci@0000:88:00.2  enp136s0f2  network        I350 Gigabit Fiber Network Connection
pci@0000:88:00.3  enp136s0f3  network        I350 Gigabit Fiber Network Connection
pci@0000:8a:00.0  ens7f0      network        Ethernet Controller X710 for 10GbE SFP+
pci@0000:8a:00.1  ens7f1      network        Ethernet Controller X710 for 10GbE SFP+
pci@0000:8a:00.2  ens7f2      network        Ethernet Controller X710 for 10GbE SFP+
pci@0000:8a:00.3  ens7f3      network        Ethernet Controller X710 for 10GbE SFP+
pci@0000:8c:00.0  ens3f0      network        MT27800 Family [ConnectX-5]
pci@0000:8c:00.1  ens3f1      network        MT27800 Family [ConnectX-5]
$ sudo ethtool  -i ens7f0
driver: i40e
version: 4.18.0-305.17.1.el8_4.x86_64
firmware-version: 6.80 0x80004355 0.0.0
expansion-rom-version: 
bus-info: 0000:8a:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: yes

Kernel

$ sudo grubby --update-kernel=ALL --args="iommu=pt intel_iommu=on default_hugepagesz=1G intel_idle.max_cstate=0 processor.max_cstate=0 nohz=on rcu_nocb_poll audit=0 nosoftlockup nospectre_v1 nospectre_v2 spectre_v2=off nospec_store_bypass_disable no_stf_barrier nopti ssbd=off l1tf=off tsx=off tsx_async_abort=off mds=off srbds=off isolcpus=4-23"

$ sudo uname -a
Linux localhost.localdomain 4.18.0-305.17.1.el8_4.x86_64 #1 SMP Wed Sep 8 14:00:07 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux

Hugepages

echo 48 > /sys/devices/system/node/node1/hugepages/hugepages-1048576kB/nr_hugepages 
echo 48 > /sys/devices/system/node/node0/hugepages/hugepages-1048576kB/nr_hugepages 

$ sudo dpdk-hugepages.py -s
Node Pages Size Total
0    48    1Gb    48Gb
1    48    1Gb    48Gb

Hugepages mounted on /dev/hugepages

vfio-pci

绑定 X710 网卡到 vfio-pci (使用libvirt 这一步可以省略, 配置hostdev 会自动操作):

$ sudo modprobe vfio-pci
$ sudo dpdk-devbind.py -b vfio-pci 8a:00.0 8a:00.1 8a:00.2 8a:00.3
$ sudo dpdk-devbind.py  -s 

Network devices using DPDK-compatible driver
============================================
0000:8a:00.0 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:8a:00.1 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:8a:00.2 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:8a:00.3 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e

虚拟机(guest) 配置

Download CentOS-8 Cloud Image

镜像制作

sudo wget https://cloud.centos.org/centos/8-stream/x86_64/images/CentOS-Stream-GenericCloud-8-20210603.0.x86_64.qcow2 
/usr/bin/qemu-img create -f qcow2 -b CentOS-8-GenericCloud-8.4.2105-20210603.0.x86_64.qcow2 CentOS-Cloud-8-20210603.qcow2 50G

初始化, 重置密码&安装dpdk等工具

virt-sysprep --root-password password:123456 --uninstall cloud-init --selinux-relabel -a CentOS-Cloud-8-20210603.qcow2 --network --install "pciutils,ethtool,net-tools,dpdk,dpdk-tools,bridge-utils,iptables,dnsmasq"

安装

使用 48G 内存 & 12 虚拟CPU:

$ sudo virt-install --import  --name centos8 --ram=49152 --vcpus=12 \
		--nographics --accelerate \
		--network network:default,model=virtio --mac 00:16:3e:6f:b6:de \
		--wait 0 --console pty \
		--disk $1,bus=virtio --os-variant centos8

$ sudo vrish shutdown centos8 

优化

EDITOR=vim virsh edit centos8
Hugepages
  <memory unit='KiB'>50331648</memory>
  <currentMemory unit='KiB'>50331648</currentMemory>
  <memoryBacking>
    <hugepages>
      <page size='1048576' unit='KiB' nodeset='0'/>
    </hugepages>
    <locked/>
  </memoryBacking>
虚拟CPU (vcpu)
$ sudo cat /sys/bus/pci/devices/0000\:8a\:00.0/numa_node 
1

当前使用X710在NUMA-1, 将所有vcpu都绑定到NUMA-1:

  <vcpu placement='static'>12</vcpu>
  <cputune>
    <vcpupin vcpu='0' cpuset='12'/>
    <vcpupin vcpu='1' cpuset='13'/>
    <vcpupin vcpu='2' cpuset='14'/>
    <vcpupin vcpu='3' cpuset='15'/>
    <vcpupin vcpu='4' cpuset='16'/>
    <vcpupin vcpu='5' cpuset='17'/>
    <vcpupin vcpu='6' cpuset='18'/>
    <vcpupin vcpu='7' cpuset='19'/>
    <vcpupin vcpu='8' cpuset='20'/>
    <vcpupin vcpu='9' cpuset='21'/>
    <vcpupin vcpu='10' cpuset='22'/>
    <vcpupin vcpu='11' cpuset='23'/>
  </cputune>
hostdev

libvirt 通过配置 hostdev 自动绑定设备到 vfio-pci
注意 <rom bar='on/off'/> 配置,与当前PCIe设备有关,不是所有PCIe设备都包含Expansion ROM. 可通过 lspci -s xx.xx.x -vvv | grep -i "Expansion ROM 确认.

# lspci -s 8a:00.0  -vv |grep Lnk
		LnkCap:	Port #0, Speed 8GT/s, Width x8, ASPM L1, Exit Latency L1 <16us
		LnkCtl:	ASPM L1 Enabled; RCB 64 bytes, Disabled- CommClk+
		LnkSta:	Speed 8GT/s (ok), Width x8 (ok)
		LnkCap2: Supported Link Speeds: 2.5-8GT/s, Crosslink- Retimer- 2Retimers- DRS-
		LnkCtl2: Target Link Speed: 8GT/s, EnterCompliance- SpeedDis-
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete+ EqualizationPhase1+
		LnkCtl3: LnkEquIntrruptEn- PerformEqu-
# lspci -s 8a:00.0  -vvv | grep -i "Expansion ROM "
	Expansion ROM at fbc80000 [disabled] [size=512K]
    <hostdev mode='subsystem' type='pci' managed='yes'>
      <source>
        <address domain='0x0000' bus='0x8a' slot='0x00' function='0x0'/>
      </source>
      <rom bar='off'/>
      <address type='pci' domain='0x0000' bus='0x07' slot='0x00' function='0x0'/>
    </hostdev>
    <hostdev mode='subsystem' type='pci' managed='yes'>
      <source>
        <address domain='0x0000' bus='0x8a' slot='0x00' function='0x1'/>
      </source>
      <rom bar='off'/>
      <address type='pci' domain='0x0000' bus='0x07' slot='0x00' function='0x1'/>
    </hostdev>
    <hostdev mode='subsystem' type='pci' managed='yes'>
      <source>
        <address domain='0x0000' bus='0x8a' slot='0x00' function='0x2'/>
      </source>
      <rom bar='off'/>
      <address type='pci' domain='0x0000' bus='0x07' slot='0x00' function='0x2'/>
    </hostdev>
    <hostdev mode='subsystem' type='pci' managed='yes'>
      <source>
        <address domain='0x0000' bus='0x8a' slot='0x00' function='0x3'/>
      </source>
      <rom bar='off'/>
      <address type='pci' domain='0x0000' bus='0x07' slot='0x00' function='0x3'/>
    </hostdev>

虚拟机(guest) PCI passthrought 网络性能

[root@centos-guest ~]# lscpu 
Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              12
On-line CPU(s) list: 0-11
Thread(s) per core:  1
Core(s) per socket:  1
Socket(s):           12
NUMA node(s):        1
Vendor ID:           GenuineIntel
BIOS Vendor ID:      Red Hat
CPU family:          6
Model:               61
Model name:          Intel Core Processor (Broadwell, IBRS)
BIOS Model name:     RHEL-8.2.0 PC (Q35 + ICH9, 2009)
Stepping:            2
CPU MHz:             2199.970
BogoMIPS:            4399.94
Virtualization:      VT-x
Hypervisor vendor:   KVM
Virtualization type: full
L1d cache:           32K
L1i cache:           32K
L2 cache:            4096K
L3 cache:            16384K
NUMA node0 CPU(s):   0-11
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt arat umip arch_capabilities
[root@centos-guest ~]# 

$ sudo uname -a
Linux centos-guest 4.18.0-305.3.1.el8.x86_64 #1 SMP Tue Jun 1 16:14:33 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux

$ sudo cat /proc/cmdline 
BOOT_IMAGE=(hd0,msdos1)/boot/vmlinuz-4.18.0-305.3.1.el8.x86_64 root=UUID=3c13065b-5b99-49df-a909-6fde11725263 ro console=ttyS0,115200n8 no_timer_check net.ifnames=0 crashkernel=auto default_hugepagesz=1G intel_idle.max_cstate=0 processor.max_cstate=0 intel_pstate=disable nohz=on rcu_nocb_poll audit=0 nosoftlockup nospectre_v1 nospectre_v2 spectre_v2=off nospec_store_bypass_disable no_stf_barrier nopti ssbd=off l1tf=off tsx=off tsx_async_abort=off mds=off srbds=off isolcpus=1-11 iommu=pt intel_iommu=on

虚拟机重新绑定 X710vfio-pci 并初始化 hugepages:

[root@centos-guest ~]# cat dpdk-init.sh 
$ sudo!/bin/sh
echo 16 > /proc/sys/vm/nr_hugepages
modprobe vfio enable_unsafe_noiommu_mode=1
modprobe vfio-pci
dpdk-devbind.py -b vfio-pci 07:00.0 08:00.0 09:00.0 0a:00.0

[root@centos-guest ~]# dpdk-hugepages.py -s
Node Pages Size Total
0    16    1Gb    16Gb

Hugepages mounted on /dev/hugepages
[root@centos-guest ~]# dpdk-devbind.py -s

Network devices using DPDK-compatible driver
============================================
0000:07:00.0 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:08:00.0 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:09:00.0 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e
0000:0a:00.0 'Ethernet Controller X710 for 10GbE SFP+ 1572' drv=vfio-pci unused=i40e

Network devices using kernel driver
===================================
0000:01:00.0 'Virtio network device 1041' if=eth0 drv=virtio-pci unused=vfio-pci *Active*

dpdk testpmd

ALLOW_DEVS+=" -a 8a:00.0 -a 8a:00.1 "
ARGS_EXTRA=" --iova-mode=pa -l 0,12-23 --socket-mem=48,48 -n 4 "

dpdk-testpmd ${ALLOW_DEVS} $ARGS_EXTRA  \
	-- -i --rxd=2048 --txd=2048 \
	--rxq=1 --txq=1 --nb-cores=8 \
	--forward-mode=rxonly \
	--rss-ip --rss-udp \
	--numa  --rx-offloads=0 --mbcache=512 --burst=64 \
	--mlockall -a --huge-unlink

testpmd rxony 2 ports

testpmd> show port stats  all

  ######################## NIC statistics for port 0  ########################
  RX-packets: 285296238  RX-missed: 0          RX-bytes:  17117773320
  RX-errors: 2
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     14881153          Rx-bps:   7142953792
  Tx-pps:            0          Tx-bps:            0
  ############################################################################

  ######################## NIC statistics for port 1  ########################
  RX-packets: 284435334  RX-missed: 0          RX-bytes:  17066119016
  RX-errors: 2
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     14881153          Rx-bps:   7142953784
  Tx-pps:            0          Tx-bps:            0
  ############################################################################
testpmd> 

testpmd rxony 4 ports

testpmd> show port stats  all

  ######################## NIC statistics for port 0  ########################
  RX-packets: 65458721   RX-missed: 26401075   RX-bytes:  3927522428
  RX-errors: 2
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     10533178          Rx-bps:   5055924928
  Tx-pps:            0          Tx-bps:            0
  ############################################################################

  ######################## NIC statistics for port 1  ########################
  RX-packets: 63840530   RX-missed: 25252259   RX-bytes:  3830430776
  RX-errors: 2
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     10533140          Rx-bps:   5055904104
  Tx-pps:            0          Tx-bps:            0
  ############################################################################

  ######################## NIC statistics for port 2  ########################
  RX-packets: 62966569   RX-missed: 23313249   RX-bytes:  3777993436
  RX-errors: 0
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     10392311          Rx-bps:   4988307000
  Tx-pps:            0          Tx-bps:            0
  ############################################################################

  ######################## NIC statistics for port 3  ########################
  RX-packets: 63841766   RX-missed: 26310381   RX-bytes:  3830505128
  RX-errors: 1
  RX-nombuf:  0         
  TX-packets: 0          TX-errors: 0          TX-bytes:  0

  Throughput (since last show)
  Rx-pps:     10533129          Rx-bps:   5055903056
  Tx-pps:            0          Tx-bps:            0
  ############################################################################
testpmd> 
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值