refactor: 资源名 opsx-loki/opsxloki → lokistack(线上已迁移完成)

【已在线完成,零数据丢失】
K8s ns=log 资源全部改名:
  Deployment  opsx-loki          → lokistack
  Service     opsx-loki          → lokistack
  Service     opsx-loki-nodeport → lokistack-nodeport
  PVC         opsxloki-data      → lokistack-data
  Secret      opsxloki-secrets   → lokistack-secrets
  Label       app: opsx-loki     → app: lokistack
  Ingress     log.astx.club 后端  → lokistack-nodeport:8080
  镜像        lghost/opsxloki     → lghost/lokistack
  docker-compose 卷/容器名同步更名

【保留不变(改了会出事)】
  namespace: log
  数据文件名 opsxloki.json(代码硬编码)
  容器内路径 /app/data

【迁移过程】
  1. 备份 PVC 数据(32KB) + Secret 原值 + 旧 yaml → /root/lokistack-migration-backup-20261026-171141
  2. scale 旧 Deployment → 0,等 Pod 消失
  3. 复制 Secret(JWT sha256 校验一致)
  4. 新建 PVC lokistack-data(Bound 30Gi cbs)
  5. 临时 Pod 恢复数据(chown 1000:1000,opsxloki.json 保留 0600)
  6. apply 新 Deployment → 1/1 Running
  7. 修复 Ingress 后端(TKE qcloud 要求 NodePort)→ CLB 恢复 200
  8. 删除旧 Deployment / 失效 Service

【验证】
  lokistack 1/1,0 重启,镜像 lghost/lokistack:latest(statically linked)
  /api/v1/health → {"status":"ok","version":"2.0.0"}
  /app/data/opsxloki.json 610B 完整(admin 用户 + 配置)
  http://log.astx.club/ → HTTP 200
  镜像加固:admin123=0、/app/backend/=0、initial-admin-password.txt 存在

【回滚兜底(建议 7 天后删)】
  pvc/opsxloki-data、secret/opsxloki-secrets

【文档】
  README 新增「从 opsx-loki 升级」章节:
  K8s 七步迁移脚本 + docker-compose 卷迁移命令
This commit is contained in:
opsx committed 2026-10-26 17:16:15 +00:00
1 parent b65dcc9677
commit 3c9388658b
13 files changed
+230 -152

No files matched your search

+26 -26
View File
@@ -1,6 +1,6 @@
#!/usr/bin/env bash
# ============================================================================
# opsx-loki 一键部署
# lokistack 一键部署
#
# 自动适配:阿里云 ACK / 腾讯云 TKE / AWS EKS / 华为云 CCE / GCP GKE / 自建 K8s
# 命名空间固定:log
@@ -94,10 +94,10 @@ resolve_storage_class() {
#
# 代价:数据固定在一台节点,节点损毁需从备份恢复(README 有 CSI 备份说明)
# ============================================================================
LOCAL_SC_NAME="opsxloki-local"
LOCAL_PV_NAME="opsxloki-data-pv"
LOCAL_SC_NAME="lokistack-local"
LOCAL_PV_NAME="lokistack-data-pv"
LOCAL_PV_SIZE="${PV_SIZE:-30Gi}"
LOCAL_PV_PATH="${PV_PATH:-/var/lib/opsxloki-data}"
LOCAL_PV_PATH="${PV_PATH:-/var/lib/lokistack-data}"
pick_local_node() {
if [ -n "${NODE_NAME:-}" ]; then echo "${NODE_NAME}"; return 0; fi
@@ -129,7 +129,7 @@ kind: PersistentVolume
metadata:
name: ${LOCAL_PV_NAME}
labels:
app: opsx-loki
app: lokistack
spec:
capacity:
storage: ${LOCAL_PV_SIZE}
@@ -157,7 +157,7 @@ EOF
}
CLOUD="$(detect_cloud)"
info "opsx-loki 部署开始(namespace: ${NS})"
info "lokistack 部署开始(namespace: ${NS})"
info "集群: $(kubectl config current-context 2>/dev/null || echo unknown)"
info "平台: ${CLOUD}"
@@ -219,11 +219,11 @@ rand_hex() {
fi
}
if kubectl -n "${NS}" get secret opsxloki-secrets >/dev/null 2>&1; then
info "Secret opsxloki-secrets 已存在,跳过(不覆盖现有密钥)"
if kubectl -n "${NS}" get secret lokistack-secrets >/dev/null 2>&1; then
info "Secret lokistack-secrets 已存在,跳过(不覆盖现有密钥)"
else
info "生成随机密钥 JWT_SECRET / ENCRYPTION_KEY"
kubectl -n "${NS}" create secret generic opsxloki-secrets \
kubectl -n "${NS}" create secret generic lokistack-secrets \
--from-literal=JWT_SECRET="$(rand_hex)" \
--from-literal=ENCRYPTION_KEY="$(rand_hex)" >/dev/null
ok "Secret 已创建"
@@ -256,33 +256,33 @@ fi
# 5) 等待就绪(失败时给出按云定制的诊断)
# ============================================================================
info "等待 Deployment 就绪(最多 180 秒)..."
if ! kubectl -n "${NS}" rollout status deployment/opsx-loki --timeout=180s; then
if ! kubectl -n "${NS}" rollout status deployment/lokistack --timeout=180s; then
echo ""
warn "部署未在 180 秒内就绪,开始诊断:"
echo ""
kubectl -n "${NS}" get po -l app=opsx-loki -o wide 2>/dev/null | sed 's/^/ /'
kubectl -n "${NS}" get po -l app=lokistack -o wide 2>/dev/null | sed 's/^/ /'
REASON=$(kubectl -n "${NS}" get po -l app=opsx-loki -o jsonpath='{.items[0].status.containerStatuses[0].state.waiting.reason}' 2>/dev/null || true)
REASON=$(kubectl -n "${NS}" get po -l app=lokistack -o jsonpath='{.items[0].status.containerStatuses[0].state.waiting.reason}' 2>/dev/null || true)
echo ""
case "${REASON}" in
ImagePullBackOff|ErrImagePull)
warn "镜像拉取失败(${REASON})"
echo " → 当前镜像: $(grep -E '^\s+image:' "${DIR}/deployment.yaml" | head -1 | awk '{print $2}')"
echo " → 该节点拉不到 Docker Hub。请改为目标云可拉的仓库后重跑:"
echo " 腾讯云 TCR : ccr.ccs.tencentyun.com/<ns>/opsxloki:latest"
echo " 阿里云 ACR : registry.cn-hangzhou.aliyuncs.com/<ns>/opsxloki:latest"
echo " 华为云 SWR : swr.cn-north-4.myhuaweicloud.com/<ns>/opsxloki:latest"
echo " 自建 Harbor: harbor.your.domain/library/opsxloki:latest"
echo " 腾讯云 TCR : ccr.ccs.tencentyun.com/<ns>/lokistack:latest"
echo " 阿里云 ACR : registry.cn-hangzhou.aliyuncs.com/<ns>/lokistack:latest"
echo " 华为云 SWR : swr.cn-north-4.myhuaweicloud.com/<ns>/lokistack:latest"
echo " 自建 Harbor: harbor.your.domain/library/lokistack:latest"
;;
CreateContainerConfigError)
warn "容器配置缺失(通常是 Secret 不存在)"
echo " → 检查: kubectl -n ${NS} get secret opsxloki-secrets"
echo " → 检查: kubectl -n ${NS} get secret lokistack-secrets"
;;
"")
PVC_PHASE=$(kubectl -n "${NS}" get pvc opsxloki-data -o jsonpath='{.status.phase}' 2>/dev/null || echo unknown)
PVC_PHASE=$(kubectl -n "${NS}" get pvc lokistack-data -o jsonpath='{.status.phase}' 2>/dev/null || echo unknown)
if [ "${PVC_PHASE}" != "Bound" ]; then
warn "PVC 未绑定(phase=${PVC_PHASE})"
echo " → 检查 StorageClass: kubectl -n ${NS} describe pvc opsxloki-data"
echo " → 检查 StorageClass: kubectl -n ${NS} describe pvc lokistack-data"
echo " → ${CLOUD} 建议的 SC:"
case "${CLOUD}" in
腾讯云*) echo " cbs" ;;
@@ -296,7 +296,7 @@ if ! kubectl -n "${NS}" rollout status deployment/opsx-loki --timeout=180s; then
esac
echo ""
kubectl -n "${NS}" describe po -l app=opsx-loki 2>/dev/null | tail -15 | sed 's/^/ /'
kubectl -n "${NS}" describe po -l app=lokistack 2>/dev/null | tail -15 | sed 's/^/ /'
die "部署未完成,请按上面提示处理"
fi
ok "Deployment 已就绪"
@@ -304,24 +304,24 @@ ok "Deployment 已就绪"
# ============================================================================
# 6) 输出访问信息
# ============================================================================
POD=$(kubectl -n "${NS}" get po -l app=opsx-loki -o jsonpath='{.items[0].metadata.name}' 2>/dev/null || echo "-")
POD_IP=$(kubectl -n "${NS}" get po -l app=opsx-loki -o jsonpath='{.items[0].status.podIP}' 2>/dev/null || echo "-")
NODE=$(kubectl -n "${NS}" get po -l app=opsx-loki -o jsonpath='{.items[0].spec.nodeName}' 2>/dev/null || echo "-")
POD=$(kubectl -n "${NS}" get po -l app=lokistack -o jsonpath='{.items[0].metadata.name}' 2>/dev/null || echo "-")
POD_IP=$(kubectl -n "${NS}" get po -l app=lokistack -o jsonpath='{.items[0].status.podIP}' 2>/dev/null || echo "-")
NODE=$(kubectl -n "${NS}" get po -l app=lokistack -o jsonpath='{.items[0].spec.nodeName}' 2>/dev/null || echo "-")
echo ""
echo "════════════════════════════════════════════════════════"
ok "opsx-loki 部署完成"
ok "lokistack 部署完成"
echo "════════════════════════════════════════════════════════"
echo " 平台 : ${CLOUD}"
echo " Namespace : ${NS}"
echo " 存储类 : ${RESOLVED_SC}"
echo " Pod : ${POD} (node=${NODE} ip=${POD_IP})"
echo " Service : opsx-loki.${NS}.svc.cluster.local:8080"
echo " Service : lokistack.${NS}.svc.cluster.local:8080"
[ "${WITH_NODEPORT}" = "1" ] && echo " NodePort : <任意节点IP>:30080"
echo ""
echo " 初始账号 : admin / admin123 ← 首次登录请立即改密"
echo ""
echo " 本地访问 : kubectl -n ${NS} port-forward svc/opsx-loki 8080:8080"
echo " 本地访问 : kubectl -n ${NS} port-forward svc/lokistack 8080:8080"
echo " 浏览器打开 http://localhost:8080"
echo ""
echo " 配 Ingress(可选,先跑 WITH_NODEPORT=1 bash install.sh):"