wangbo
e20688bbe2
原因：香港虚拟磁盘在低吞吐下仍出现高同步写延迟，触发 etcd slow apply、Handler timeout 和 PostgreSQL API Server 连通性异常。\n\n影响：新增仅针对香港根块设备的 mq-deadline 配置脚本，应用时不重启 K3s，并提供显式 rollback 恢复 none；运行手册明确该项仅为缓解，不能替代高性能云盘。\n\n验证：新香港节点同步写探针从 13.28ms 降至 6.25ms；bash -n、ShellCheck、manual-release-test.sh 通过。
85 lines
2.6 KiB
Bash
Executable File
85 lines
2.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
|
|
# shellcheck source=scripts/cluster/common.sh
|
|
source "$script_dir/common.sh"
|
|
|
|
action=${1:-status}
|
|
[[ $action == status || $action == apply || $action == rollback ]] || {
|
|
echo 'usage: configure-control-plane-io.sh {status|apply|rollback}' >&2
|
|
exit 64
|
|
}
|
|
|
|
load_cluster_env
|
|
unit_name=easyai-k3s-io-scheduler.service
|
|
unit_path=/etc/systemd/system/$unit_name
|
|
|
|
cluster_ssh "$CLUSTER_HONGKONG_HOST" bash -s -- "$action" "$unit_name" "$unit_path" <<'REMOTE'
|
|
set -euo pipefail
|
|
action=$1
|
|
unit_name=$2
|
|
unit_path=$3
|
|
|
|
root_source=$(findmnt -n -o SOURCE /)
|
|
root_partition=${root_source#/dev/}
|
|
device=$(lsblk -no PKNAME "/dev/$root_partition" | head -n 1)
|
|
[[ $device =~ ^[a-zA-Z0-9._-]+$ && -f /sys/block/$device/queue/scheduler ]]
|
|
|
|
current_scheduler() {
|
|
sed -n 's/.*\[\([^]]*\)\].*/\1/p' "/sys/block/$device/queue/scheduler"
|
|
}
|
|
|
|
case $action in
|
|
status)
|
|
configured=false
|
|
systemctl is-enabled --quiet "$unit_name" 2>/dev/null && configured=true
|
|
printf 'control_plane_io=STATUS node=hongkong device=%s scheduler=%s configured=%s\n' \
|
|
"$device" "$(current_scheduler)" "$configured"
|
|
;;
|
|
apply)
|
|
grep -qw mq-deadline "/sys/block/$device/queue/scheduler" || {
|
|
echo 'mq-deadline is not supported by the Hong Kong root block device' >&2
|
|
exit 1
|
|
}
|
|
temporary=$(mktemp /etc/systemd/system/.easyai-k3s-io-scheduler.XXXXXX)
|
|
cleanup() {
|
|
[[ -f ${temporary:-} ]] && rm -f -- "$temporary" || true
|
|
}
|
|
trap cleanup EXIT
|
|
cat >"$temporary" <<EOF
|
|
[Unit]
|
|
Description=EasyAI K3s control-plane disk scheduler
|
|
After=local-fs.target
|
|
Before=k3s.service
|
|
|
|
[Service]
|
|
Type=oneshot
|
|
ExecStart=/bin/sh -c 'printf "%s\\n" mq-deadline > /sys/block/$device/queue/scheduler'
|
|
ExecStop=/bin/sh -c 'printf "%s\\n" none > /sys/block/$device/queue/scheduler'
|
|
RemainAfterExit=yes
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|
|
EOF
|
|
chmod 0644 "$temporary"
|
|
install -o root -g root -m 0644 "$temporary" "$unit_path"
|
|
systemctl daemon-reload
|
|
systemctl enable --now "$unit_name" >/dev/null
|
|
[[ $(current_scheduler) == mq-deadline ]]
|
|
printf 'control_plane_io=APPLIED node=hongkong device=%s scheduler=mq-deadline restart=false\n' "$device"
|
|
;;
|
|
rollback)
|
|
if [[ -f $unit_path ]]; then
|
|
systemctl disable --now "$unit_name" >/dev/null 2>&1 || true
|
|
rm -f -- "$unit_path"
|
|
systemctl daemon-reload
|
|
else
|
|
printf '%s\n' none >"/sys/block/$device/queue/scheduler"
|
|
fi
|
|
[[ $(current_scheduler) == none ]]
|
|
printf 'control_plane_io=ROLLED_BACK node=hongkong device=%s scheduler=none\n' "$device"
|
|
;;
|
|
esac
|
|
REMOTE
|