修复 kubelet 超限与旧 Docker 采集目标 (#148)

Co-authored-by: panxiao81 <[email protected]>

platform/observability/metrics/scrapes/docker-hosts.yaml

@@ -1,6 +1,6 @@
-# Pull metrics from Docker hosts running ../../docker-hosts/compose.yaml.
-# vmagent scrapes each host's node-exporter (:9100) and cAdvisor (:8080) over the LAN.
-# Add one target block per host; keep the `host` label in sync with its HOST_LABEL.
+# 仅抓取已存在的宿主机 node-exporter。旧 :8080 目标实际返回 nginx 404，
+# 独立 Docker cAdvisor 尚未部署；部署并确认端口后再添加其目标。
+# Kubernetes 容器指标由 kubelet.yaml 的 /metrics/cadvisor 独立采集。
 apiVersion: operator.victoriametrics.com/v1beta1
 kind: VMStaticScrape
 metadata:
@@ -17,13 +17,6 @@ spec:
       labels:
         job: node-exporter
         host: docker-01
-    - targets:
-        - "192.168.10.127:8080"
-      labels:
-        job: cadvisor
-        host: docker-01
-    # --- add more hosts below, mirroring the two blocks above ---
+    # --- 新增主机前确认 exporter 已部署且 /metrics 返回成功 ---
     # - targets: ["192.168.10.x:9100"]
     #   labels: { job: node-exporter, host: docker-02 }
-    # - targets: ["192.168.10.x:8080"]
-    #   labels: { job: cadvisor, host: docker-02 }

platform/observability/metrics/scrapes/kubelet.yaml

@@ -13,6 +13,9 @@ spec:
   honorLabels: true
   honorTimestamps: false
   interval: 30s
+  # k3s 此端点包含 apiserver/etcd 指标，响应已超过默认 16 MiB。
+  # 仅放宽 kubelet 任务，其他采集目标保留默认限制。
+  max_scrape_size: "32MiB"
   tlsConfig:
     insecureSkipVerify: true
     caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt