完成a6000测试系统构建、部署、测试整合 (#35)

测试方案：

- lm2机器端口映射到本机：18080, 18081, 8082-8085
- 访问URL: http://localhost:18080/dashboard

![image.png](/attachments/30ed6e20-697a-4d3b-a6d3-6acccd2e9922)

![image.png](/attachments/38ef1751-0f3b-49c6-9100-f70d15617acc)

![image.png](/attachments/3be45005-9b9e-4165-8ef6-1d27405800f1)

![image.png](/attachments/eb916192-edc1-4096-8f9f-9769ab6d9039)

![image.png](/attachments/620e6efc-bd02-45ae-bba1-99a95a1b4c02)

![image.png](/attachments/986e77e7-c687-405f-a760-93282249f72f)

端到端测试通过：

![image.png](/attachments/c6e29875-4a16-4718-8b2f-368f64eb545e)

Co-authored-by: sundapeng.sdp <sundapeng@hashdata.cn>
Reviewed-on: #35
Reviewed-by: xuxt <xuxt@zgclab.edu.cn>
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>
Reviewed-by: huhy <husteryezi@163.com>

src/sys/tests/scripts/13_metric_verify_dataplane.sh

@@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+TMP_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+# 载入端口变量（由 .env 提供）
+TEST_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)"
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  set -a; source "$TEST_ROOT/.env"; set +a
+fi
+
+PROM_BASE="http://localhost:${PROMETHEUS_PORT:-9090}/api/v1"
+INSTANCE="${METRIC_TEST_INSTANCE:-172.31.0.50:9100}"
+IP_ONLY="${INSTANCE%%:*}"
+
+echo "[VERIFY:DATA] node exporter metrics present in container"
+docker exec argus-metric-test-node bash -lc "curl -fsS --max-time 5 http://localhost:9100/metrics | head -n 5" > "$TMP_DIR/node_metrics_head.txt" || { echo "[ERR] cannot fetch node exporter metrics" >&2; exit 1; }
+if ! grep -E "node_(exporter_build_info|time_seconds)" -q "$TMP_DIR/node_metrics_head.txt"; then
+  echo "[WARN] head did not show expected lines; continuing (exporter may output later lines)"
+fi
+echo "[OK] node exporter endpoint reachable"
+
+echo "[VERIFY:DATA] Prometheus has recent sample for build_info"
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_1.json"
+
+python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
+import json,sys,time
+j=json.load(open(sys.argv[1]))
+res=j.get('data',{}).get('result',[])
+assert res, 'no result for node_exporter_build_info'
+ts=float(res[0]['value'][0])
+now=time.time()
+assert now-ts<180, f"sample too old: now={now} ts={ts}"
+print(int(ts))
+PY
+T1=$?
+sleep 30
+curl -fsS --max-time 5 --get "$PROM_BASE/query" --data-urlencode "query=node_exporter_build_info{job=\"node\",ip=\"$IP_ONLY\"}" > "$TMP_DIR/prom_ne_build_info_2.json"
+
+TS1=$(python3 - "$TMP_DIR/prom_ne_build_info_1.json" <<'PY'
+import json,sys
+print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
+PY
+)
+TS2=$(python3 - "$TMP_DIR/prom_ne_build_info_2.json" <<'PY'
+import json,sys
+print(float(json.load(open(sys.argv[1]))['data']['result'][0]['value'][0]))
+PY
+)
+awk -v a="$TS1" -v b="$TS2" 'BEGIN{ if (b>=a) exit 0; else exit 1 }' || { echo "[ERR] sample timestamp did not advance" >&2; exit 1; }
+echo "[OK] sample timestamp advanced"
+echo "[DONE] dataplane verify"
+
+# 追加：GPU 节点端点连通性检查（启用 GPU 时）
+if [[ "${ENABLE_GPU:-false}" == "true" ]]; then
+  echo
+  echo "[VERIFY:DATA][GPU] curl endpoints on gpu node"
+  if ! docker exec argus-metric-test-gpu-node bash -lc 'curl -fsS --max-time 5 http://localhost:9100/metrics >/dev/null'; then
+    echo "[ERR] gpu node 9100 not reachable" >&2; exit 1
+  fi
+  if ! docker exec argus-metric-test-gpu-node bash -lc 'curl -fsS --max-time 5 http://localhost:9400/metrics >/dev/null'; then
+    echo "[ERR] gpu node 9400 not reachable" >&2; exit 1
+  fi
+  echo "[OK] gpu node endpoints reachable"
+fi