使用性能配置文件调整节点以实现低延迟

$ oc label node <node_name> node-role.kubernetes.io/worker-cnf="" (1)

$ oc adm must-gather

$ tar cvaf must-gather.tar.gz <must_gather_folder> (1)

$ oc get mcp

NAME         CONFIG                                                 UPDATED   UPDATING   DEGRADED   MACHINECOUNT   READYMACHINECOUNT   UPDATEDMACHINECOUNT   DEGRADEDMACHINECOUNT   AGE
master       rendered-master-58433c8c3c0b4ed5feef95434d455490       True      False      False      3              3                   3                     0                      8h
worker       rendered-worker-668f56a164f151e4a853229729b6adc4       True      False      False      2              2                   2                     0                      8h
worker-cnf   rendered-worker-cnf-668f56a164f151e4a853229729b6adc4   True      False      False      1              1                   1                     0                      79m

$ podman login registry.redhat.io

Username: <user_name>
Password: <password>

$ podman run --rm --entrypoint performance-profile-creator registry.redhat.io/openshift4/ose-cluster-node-tuning-rhel9-operator:v4.17 -h

A tool that automates creation of Performance Profiles

Usage:
  performance-profile-creator [flags]

Flags:
      --disable-ht                        Disable Hyperthreading
  -h, --help                              help for performance-profile-creator
      --info string                       Show cluster information; requires --must-gather-dir-path, ignore the other arguments. [Valid values: log, json] (default "log")
      --mcp-name string                   MCP name corresponding to the target machines (required)
      --must-gather-dir-path string       Must gather directory path (default "must-gather")
      --offlined-cpu-count int            Number of offlined CPUs
      --per-pod-power-management          Enable Per Pod Power Management
      --power-consumption-mode string     The power consumption mode.  [Valid values: default, low-latency, ultra-low-latency] (default "default")
      --profile-name string               Name of the performance profile to be created (default "performance")
      --reserved-cpu-count int            Number of reserved CPUs (required)
      --rt-kernel                         Enable Real Time Kernel (required)
      --split-reserved-cpus-across-numa   Split the Reserved CPUs across NUMA nodes
      --topology-manager-policy string    Kubelet Topology Manager Policy of the performance profile to be created. [Valid values: single-numa-node, best-effort, restricted] (default "restricted")
      --user-level-networking             Run with User level Networking(DPDK) enabled

$ podman run --entrypoint performance-profile-creator -v <path_to_must_gather>:/must-gather:z registry.redhat.io/openshift4/ose-cluster-node-tuning-rhel9-operator:v4.17 --info log --must-gather-dir-path /must-gather

$ podman run --entrypoint performance-profile-creator -v <path_to_must_gather>:/must-gather:z registry.redhat.io/openshift4/ose-cluster-node-tuning-rhel9-operator:v4.17 --mcp-name=worker-cnf --reserved-cpu-count=1 --rt-kernel=true --split-reserved-cpus-across-numa=false --must-gather-dir-path /must-gather --power-consumption-mode=ultra-low-latency --offlined-cpu-count=1 > my-performance-profile.yaml

$ cat my-performance-profile.yaml

---
apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: performance
spec:
  cpu:
    isolated: 2-3
    offlined: "1"
    reserved: "0"
  machineConfigPoolSelector:
    machineconfiguration.openshift.io/role: worker-cnf
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""
  numa:
    topologyPolicy: restricted
  realTimeKernel:
    enabled: true
  workloadHints:
    highPowerConsumption: true
    perPodPowerManagement: false
    realTime: true

$ oc apply -f my-performance-profile.yaml

performanceprofile.performance.openshift.io/performance created

$ vi run-perf-profile-creator.sh

#!/bin/bash

readonly CONTAINER_RUNTIME=${CONTAINER_RUNTIME:-podman}
readonly CURRENT_SCRIPT=$(basename "$0")
readonly CMD="${CONTAINER_RUNTIME} run --entrypoint performance-profile-creator"
readonly IMG_EXISTS_CMD="${CONTAINER_RUNTIME} image exists"
readonly IMG_PULL_CMD="${CONTAINER_RUNTIME} image pull"
readonly MUST_GATHER_VOL="/must-gather"

NTO_IMG="registry.redhat.io/openshift4/ose-cluster-node-tuning-rhel9-operator:v4.17"
MG_TARBALL=""
DATA_DIR=""

usage() {
  print "Wrapper usage:"
  print "  ${CURRENT_SCRIPT} [-h] [-p image][-t path] -- [performance-profile-creator flags]"
  print ""
  print "Options:"
  print "   -h                 help for ${CURRENT_SCRIPT}"
  print "   -p                 Node Tuning Operator image"
  print "   -t                 path to a must-gather tarball"

  ${IMG_EXISTS_CMD} "${NTO_IMG}" && ${CMD} "${NTO_IMG}" -h
}

function cleanup {
  [ -d "${DATA_DIR}" ] && rm -rf "${DATA_DIR}"
}
trap cleanup EXIT

exit_error() {
  print "error: $*"
  usage
  exit 1
}

print() {
  echo  "$*" >&2
}

check_requirements() {
  ${IMG_EXISTS_CMD} "${NTO_IMG}" || ${IMG_PULL_CMD} "${NTO_IMG}" || \
      exit_error "Node Tuning Operator image not found"

  [ -n "${MG_TARBALL}" ] || exit_error "Must-gather tarball file path is mandatory"
  [ -f "${MG_TARBALL}" ] || exit_error "Must-gather tarball file not found"

  DATA_DIR=$(mktemp -d -t "${CURRENT_SCRIPT}XXXX") || exit_error "Cannot create the data directory"
  tar -zxf "${MG_TARBALL}" --directory "${DATA_DIR}" || exit_error "Cannot decompress the must-gather tarball"
  chmod a+rx "${DATA_DIR}"

  return 0
}

main() {
  while getopts ':hp:t:' OPT; do
    case "${OPT}" in
      h)
        usage
        exit 0
        ;;
      p)
        NTO_IMG="${OPTARG}"
        ;;
      t)
        MG_TARBALL="${OPTARG}"
        ;;
      ?)
        exit_error "invalid argument: ${OPTARG}"
        ;;
    esac
  done
  shift $((OPTIND - 1))

  check_requirements || exit 1

  ${CMD} -v "${DATA_DIR}:${MUST_GATHER_VOL}:z" "${NTO_IMG}" "$@" --must-gather-dir-path "${MUST_GATHER_VOL}"
  echo "" 1>&2
}

main "$@"

$ chmod a+x run-perf-profile-creator.sh

$ podman login registry.redhat.io

Username: <user_name>
Password: <password>

$ ./run-perf-profile-creator.sh -h

Wrapper usage:
  run-perf-profile-creator.sh [-h] [-p image][-t path] -- [performance-profile-creator flags]

Options:
   -h                 help for run-perf-profile-creator.sh
   -p                 Node Tuning Operator image
   -t                 path to a must-gather tarball
A tool that automates creation of Performance Profiles

Usage:
  performance-profile-creator [flags]

Flags:
      --disable-ht                        Disable Hyperthreading
  -h, --help                              help for performance-profile-creator
      --info string                       Show cluster information; requires --must-gather-dir-path, ignore the other arguments. [Valid values: log, json] (default "log")
      --mcp-name string                   MCP name corresponding to the target machines (required)
      --must-gather-dir-path string       Must gather directory path (default "must-gather")
      --offlined-cpu-count int            Number of offlined CPUs
      --per-pod-power-management          Enable Per Pod Power Management
      --power-consumption-mode string     The power consumption mode.  [Valid values: default, low-latency, ultra-low-latency] (default "default")
      --profile-name string               Name of the performance profile to be created (default "performance")
      --reserved-cpu-count int            Number of reserved CPUs (required)
      --rt-kernel                         Enable Real Time Kernel (required)
      --split-reserved-cpus-across-numa   Split the Reserved CPUs across NUMA nodes
      --topology-manager-policy string    Kubelet Topology Manager Policy of the performance profile to be created. [Valid values: single-numa-node, best-effort, restricted] (default "restricted")
      --user-level-networking             Run with User level Networking(DPDK) enabled
      --enable-hardware-tuning            Enable setting maximum CPU frequencies

$ ./run-perf-profile-creator.sh -t /<path_to_must_gather_dir>/must-gather.tar.gz -- --info=log

$ ./run-perf-profile-creator.sh -t /path-to-must-gather/must-gather.tar.gz -- --mcp-name=worker-cnf --reserved-cpu-count=1 --rt-kernel=true --split-reserved-cpus-across-numa=false --power-consumption-mode=ultra-low-latency --offlined-cpu-count=1 > my-performance-profile.yaml

$ cat my-performance-profile.yaml

---
apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: performance
spec:
  cpu:
    isolated: 2-3
    offlined: "1"
    reserved: "0"
  machineConfigPoolSelector:
    machineconfiguration.openshift.io/role: worker-cnf
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""
  numa:
    topologyPolicy: restricted
  realTimeKernel:
    enabled: true
  workloadHints:
    highPowerConsumption: true
    perPodPowerManagement: false
    realTime: true

$ oc apply -f my-performance-profile.yaml

performanceprofile.performance.openshift.io/performance created

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: example-performanceprofile
spec:
  additionalKernelArgs:
    - nmi_watchdog=0
    - audit=0
    - mce=off
    - processor.max_cstate=1
    - idle=poll
    - intel_idle.max_cstate=0
    - nosmt
  cpu:
    isolated: 2-3
    reserved: 0-1
  hugepages:
    defaultHugepagesSize: 1G
    pages:
      - count: 2
        node: 0
        size: 1G
  nodeSelector:
    node-role.kubernetes.io/performance: ''
  realTimeKernel:
    enabled: true

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: dynamic-irq-profile
spec:
  cpu:
    isolated: 2-5
    reserved: 0-1
...

$ oc edit -f <your_profile_name>.yaml

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: manual
spec:
  cpu:
    isolated: 3-51,55-103
    reserved: 0-2,52-54
  net:
    userLevelNetworking: true
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: manual
spec:
  cpu:
    isolated: 3-51,55-103
    reserved: 0-2,52-54
  net:
    userLevelNetworking: true
    devices:
    - interfaceName: "eth0"
    - interfaceName: "eth1"
    - vendorID: "0x1af4"
      deviceID: "0x1000"
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: manual
spec:
  cpu:
    isolated: 3-51,55-103
    reserved: 0-2,52-54
  net:
    userLevelNetworking: true
    devices:
    - interfaceName: "eth*"
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: manual
spec:
  cpu:
    isolated: 3-51,55-103
    reserved: 0-2,52-54
  net:
    userLevelNetworking: true
    devices:
    - interfaceName: "!eno1"
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""

apiVersion: performance.openshift.io/v2
kind: PerformanceProfile
metadata:
  name: manual
spec:
  cpu:
    isolated: 3-51,55-103
    reserved: 0-2,52-54
  net:
    userLevelNetworking: true
    devices:
    - interfaceName: "eth0"
    - vendorID: "0x1af4"
      deviceID: "0x1000"
  nodeSelector:
    node-role.kubernetes.io/worker-cnf: ""

$ oc apply -f <your_profile_name>.yaml