debug

domain-api/deploy/multi-region/check_temp_topology.sh

@@ -0,0 +1,126 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+MAINLAND_BASE_URL="${1:-http://127.0.0.1:8100}"
+OVERSEAS_BASE_URL="${2:-http://152.53.37.118:8100}"
+PYTHON_BIN="${PYTHON_BIN:-python3}"
+
+echo "[1/5] mainland runtime cluster"
+MAINLAND_CLUSTER="$(curl -fsS "${MAINLAND_BASE_URL}/api/v1/runtime/cluster")"
+echo "${MAINLAND_CLUSTER}"
+echo
+echo
+
+echo "[2/5] mainland runtime readiness"
+MAINLAND_READINESS="$(curl -fsS "${MAINLAND_BASE_URL}/api/v1/runtime/readiness")"
+echo "${MAINLAND_READINESS}"
+echo
+echo
+
+echo "[3/5] mainland worker participation"
+PARTICIPATION_JSON="$(/www/server/pgsql/bin/psql -U postgres -d domain -At <<'SQL'
+with latest_job as (
+  select id, job_code, status
+  from detect_jobs
+  where status in ('pending','running')
+  order by id desc
+  limit 1
+),
+node_stats as (
+  select
+    node_code,
+    role,
+    status,
+    coalesce(metadata_json->>'worker_online', '') as worker_online,
+    coalesce(metadata_json->>'detect_participating', '') as detect_participating
+  from detect_worker_nodes
+),
+item_stats as (
+  select
+    coalesce(claimed_by, '') as claimed_by,
+    status,
+    count(*) as cnt
+  from detect_job_items
+  where job_id = (select id from latest_job)
+  group by claimed_by, status
+)
+select json_build_object(
+  'job', (
+    select json_build_object(
+      'job_code', coalesce(job_code, ''),
+      'status', coalesce(status, '')
+    )
+    from latest_job
+  ),
+  'online_nodes', (
+    select coalesce(json_agg(json_build_object(
+      'node_code', node_code,
+      'role', role,
+      'status', status,
+      'worker_online', worker_online,
+      'detect_participating', detect_participating
+    ) order by node_code), '[]'::json)
+    from node_stats
+    where status in ('online', 'busy')
+  ),
+  'claimed_distribution', (
+    select coalesce(json_agg(json_build_object(
+      'claimed_by', claimed_by,
+      'status', status,
+      'count', cnt
+    ) order by claimed_by, status), '[]'::json)
+    from item_stats
+  )
+);
+SQL
+)"
+echo "${PARTICIPATION_JSON}"
+echo
+echo
+
+echo "[4/5] overseas runtime cluster"
+OVERSEAS_CLUSTER="$(curl -fsS "${OVERSEAS_BASE_URL}/api/v1/runtime/cluster")"
+echo "${OVERSEAS_CLUSTER}"
+echo
+echo
+
+echo "[5/5] condensed summary"
+"${PYTHON_BIN}" - <<'PY' "$MAINLAND_CLUSTER" "$MAINLAND_READINESS" "$PARTICIPATION_JSON" "$OVERSEAS_CLUSTER"
+import json
+import sys
+
+mainland_cluster = json.loads(sys.argv[1]).get("data", {})
+mainland_readiness = json.loads(sys.argv[2]).get("data", {})
+participation = json.loads(sys.argv[3])
+overseas_cluster = json.loads(sys.argv[4]).get("data", {})
+
+mainland_summary = mainland_cluster.get("summary") or {}
+overseas_summary = overseas_cluster.get("summary") or {}
+
+def node_codes(cluster):
+    return [str(item.get("node_code") or "") for item in (cluster.get("nodes") or [])]
+
+print(
+    json.dumps(
+        {
+            "mainland": {
+                "readiness_status": mainland_readiness.get("status", ""),
+                "readiness_summary": mainland_readiness.get("summary", ""),
+                "online_worker_nodes": mainland_summary.get("online_worker_nodes", 0),
+                "dedicated_online_worker_nodes": mainland_summary.get("dedicated_online_worker_nodes", 0),
+                "online_control_nodes": mainland_summary.get("online_control_nodes", 0),
+                "node_codes": node_codes(mainland_cluster),
+            },
+            "participation": participation,
+            "overseas": {
+                "online_worker_nodes": overseas_summary.get("online_worker_nodes", 0),
+                "dedicated_online_worker_nodes": overseas_summary.get("dedicated_online_worker_nodes", 0),
+                "online_control_nodes": overseas_summary.get("online_control_nodes", 0),
+                "node_codes": node_codes(overseas_cluster),
+            },
+        },
+        ensure_ascii=False,
+        indent=2,
+    )
+)
+PY