Files
easyai-ai-gateway/scripts/cluster/common.sh
T
wangbo 7623449e33 fix(acceptance): 复用集群 SSH 控制连接
线上验收在宁波 SSH 建连超时时于负载前失败。为集群脚本增加受限 ControlMaster 复用和仅建连阶段的 ConnectionAttempts,避免重放远程命令。\n\n生产快照导出增加三次只读重试、原子落盘和空 Pod 清理防护。已通过 bash -n、ShellCheck、production acceptance 脚本测试、人工发布脚本测试,并验证宁波真实 SSH 控制连接可复用。
2026-08-01 15:59:00 +08:00

154 lines
5.1 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
cluster_root=$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)
cluster_env_file=${AI_GATEWAY_CLUSTER_ENV_FILE:-"$cluster_root/.env.local"}
cluster_ssh_key=${AI_GATEWAY_CLUSTER_SSH_KEY:-"$HOME/.ssh/id_ed25519_easyai_gateway_cluster"}
cluster_ssh_control_dir=${AI_GATEWAY_CLUSTER_SSH_CONTROL_DIR:-"/tmp/easyai-gateway-ssh-${UID:-$(id -u)}-$$"}
prepare_cluster_ssh_control_dir() {
(umask 077 && mkdir -p -- "$cluster_ssh_control_dir")
chmod 0700 "$cluster_ssh_control_dir"
}
load_cluster_env() {
[[ -f $cluster_env_file && ! -L $cluster_env_file ]] || {
echo "missing local cluster environment file: $cluster_env_file" >&2
return 1
}
set -a
# shellcheck source=/dev/null
source "$cluster_env_file"
set +a
cluster_ssh_key=${AI_GATEWAY_CLUSTER_SSH_KEY:-$cluster_ssh_key}
: "${AI_GATEWAY_DEPLOY_HOST:?}"
: "${AI_GATEWAY_DEPLOY_HOST_2:?}"
: "${AI_GATEWAY_DEPLOY_HOST_3:?}"
: "${ALI_KEY:?}"
: "${ALI_SECRET:?}"
: "${ALI_REGION:?}"
: "${ALI_BUCKET:?}"
CLUSTER_NINGBO_HOST=${AI_GATEWAY_NINGBO_HOST:-$AI_GATEWAY_DEPLOY_HOST}
CLUSTER_LOS_ANGELES_HOST=${AI_GATEWAY_LOS_ANGELES_HOST:-$AI_GATEWAY_DEPLOY_HOST_2}
CLUSTER_HONGKONG_HOST=${AI_GATEWAY_HONGKONG_HOST:-$AI_GATEWAY_DEPLOY_HOST_3}
CLUSTER_WORKER_NODE_4_HOST=${AI_GATEWAY_WORKER_NODE_4_HOST:-}
CLUSTER_WORKER_NODE_4_NAME=${AI_GATEWAY_WORKER_NODE_4_NAME:-}
CLUSTER_WORKER_NODE_4_SITE=${AI_GATEWAY_WORKER_NODE_4_SITE:-}
CLUSTER_WORKER_NODE_4_WIREGUARD_PORT=${AI_GATEWAY_WORKER_NODE_4_WIREGUARD_PORT:-51820}
CLUSTER_WORKER_NODE_4_NETWORK_APPROVED=${AI_GATEWAY_WORKER_NODE_4_NETWORK_APPROVED:-false}
CLUSTER_WORKER_NODE_4_ENABLED=${AI_GATEWAY_WORKER_NODE_4_ENABLED:-false}
export CLUSTER_NINGBO_HOST CLUSTER_LOS_ANGELES_HOST CLUSTER_HONGKONG_HOST
export CLUSTER_WORKER_NODE_4_HOST CLUSTER_WORKER_NODE_4_NAME CLUSTER_WORKER_NODE_4_SITE
export CLUSTER_WORKER_NODE_4_WIREGUARD_PORT CLUSTER_WORKER_NODE_4_NETWORK_APPROVED
export CLUSTER_WORKER_NODE_4_ENABLED
for host in "$CLUSTER_NINGBO_HOST" "$CLUSTER_HONGKONG_HOST" "$CLUSTER_LOS_ANGELES_HOST"; do
[[ $host =~ ^root@[A-Za-z0-9.-]+$ ]] || {
echo "cluster hosts must use root@host syntax" >&2
return 1
}
done
if [[ -n $CLUSTER_WORKER_NODE_4_HOST ]]; then
[[ $CLUSTER_WORKER_NODE_4_HOST =~ ^root@[A-Za-z0-9.-]+$ ]] || {
echo "dedicated Worker node 4 host must use root@host syntax" >&2
return 1
}
[[ ${#CLUSTER_WORKER_NODE_4_NAME} -le 63 &&
$CLUSTER_WORKER_NODE_4_NAME =~ ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ ]] || {
echo "dedicated Worker node 4 name must be a Kubernetes DNS label" >&2
return 1
}
[[ $CLUSTER_WORKER_NODE_4_SITE == ningbo || $CLUSTER_WORKER_NODE_4_SITE == hongkong ]] || {
echo "dedicated Worker node 4 site must be ningbo or hongkong" >&2
return 1
}
[[ $CLUSTER_WORKER_NODE_4_WIREGUARD_PORT =~ ^[0-9]+$ &&
$CLUSTER_WORKER_NODE_4_WIREGUARD_PORT -ge 1 &&
$CLUSTER_WORKER_NODE_4_WIREGUARD_PORT -le 65535 ]] || {
echo "dedicated Worker node 4 WireGuard port is invalid" >&2
return 1
}
[[ $CLUSTER_WORKER_NODE_4_NETWORK_APPROVED == true ||
$CLUSTER_WORKER_NODE_4_NETWORK_APPROVED == false ]] || {
echo "dedicated Worker node 4 network approval must be true or false" >&2
return 1
}
[[ $CLUSTER_WORKER_NODE_4_ENABLED == true || $CLUSTER_WORKER_NODE_4_ENABLED == false ]] || {
echo "dedicated Worker node 4 enabled flag must be true or false" >&2
return 1
}
elif [[ -n $CLUSTER_WORKER_NODE_4_NAME || -n $CLUSTER_WORKER_NODE_4_SITE ]]; then
echo "dedicated Worker node 4 metadata requires AI_GATEWAY_WORKER_NODE_4_HOST" >&2
return 1
fi
[[ $ALI_REGION =~ ^[a-z0-9-]+$ && $ALI_BUCKET =~ ^[A-Za-z0-9.-]+$ ]] || {
echo 'invalid OSS region or bucket' >&2
return 1
}
[[ -f $cluster_ssh_key && ! -L $cluster_ssh_key ]] || {
echo "missing cluster SSH key: $cluster_ssh_key" >&2
return 1
}
}
cluster_ssh() {
local host=$1
shift
prepare_cluster_ssh_control_dir
ssh \
-i "$cluster_ssh_key" \
-o BatchMode=yes \
-o ConnectionAttempts=3 \
-o ConnectTimeout=10 \
-o ControlMaster=auto \
-o ControlPersist=120 \
-o "ControlPath=$cluster_ssh_control_dir/%C" \
-o ServerAliveInterval=15 \
-o ServerAliveCountMax=3 \
"$host" "$@"
}
cluster_scp() {
prepare_cluster_ssh_control_dir
scp \
-i "$cluster_ssh_key" \
-o BatchMode=yes \
-o ConnectionAttempts=3 \
-o ConnectTimeout=10 \
-o ControlMaster=auto \
-o ControlPersist=120 \
-o "ControlPath=$cluster_ssh_control_dir/%C" \
"$@"
}
require_commands() {
local command
for command in "$@"; do
command -v "$command" >/dev/null 2>&1 || {
echo "$command is required" >&2
return 1
}
done
}
assert_private_file() {
local path=$1
local mode
[[ -f $path && ! -L $path ]] || {
echo "missing private file: $path" >&2
return 1
}
if [[ $(uname -s) == Darwin ]]; then
mode=$(stat -f '%Lp' "$path")
else
mode=$(stat -c '%a' "$path")
fi
[[ $mode == 600 ]] || {
echo "private file must have mode 0600: $path" >&2
return 1
}
}