iklim.co/Environment_Monitoring
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(health-agent): rename monitor keys to Title Case With Space

Browse Source 
Update all hardcoded push monitor names in check files to match the new Title Case With Space format in monitors.yml. The uk_tokens.yml keys are derived from monitor names so the push() calls must match exactly.
This commit is contained in:
Murat ÖZDEMİR 2026-06-26 20:52:35 +03:00
parent bc8b3d0934
commit 3c2e872bf4
7 changed files with 37 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
health-agent/src/health_agent/checks/filesystem.py
View File

@ -18,7 +18,7 @@ def check_storagebox_mount():
if not os.path.exists(storagebox_path): if not os.path.exists(storagebox_path):
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
push("STORAGEBOX-MOUNT", "down", f"{storagebox_path} not found", ping_ms) push("Storagebox Mount", "down", f"{storagebox_path} not found", ping_ms)
return return
for rel_path in expected_files: for rel_path in expected_files:
@ -30,7 +30,7 @@ def check_storagebox_mount():
if missing_files: if missing_files:
msg = f"mount exists but missing: {', '.join(missing_files)}" msg = f"mount exists but missing: {', '.join(missing_files)}"
push("STORAGEBOX-MOUNT", "down", msg, ping_ms) push("Storagebox Mount", "down", msg, ping_ms)
else: else:
msg = f"{storagebox_path} OK | all critical files present" msg = f"{storagebox_path} OK | all critical files present"
push("STORAGEBOX-MOUNT", "up", msg, ping_ms) push("Storagebox Mount", "up", msg, ping_ms)

38
health-agent/src/health_agent/checks/http.py
View File

@ -54,7 +54,7 @@ def check_patroni_cluster():
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
if not cluster_data: if not cluster_data:
push("PATRONI-CLUSTER", "down", error_msg, ping_ms) push("Patroni Cluster", "down", error_msg, ping_ms)
return return
members = cluster_data.get("members", []) members = cluster_data.get("members", [])
@ -73,7 +73,7 @@ def check_patroni_cluster():
if not leader: if not leader:
down_nodes = [f"{r[0]} state: {r[2]}" for r in replicas if r[2] not in ("running", "streaming")] down_nodes = [f"{r[0]} state: {r[2]}" for r in replicas if r[2] not in ("running", "streaming")]
msg = f"no leader detected | " + " ".join(down_nodes) msg = f"no leader detected | " + " ".join(down_nodes)
push("PATRONI-CLUSTER", "down", msg, ping_ms) push("Patroni Cluster", "down", msg, ping_ms)
else: else:
lag_strs = [] lag_strs = []
for name, lag, state in replicas: for name, lag, state in replicas:
@ -81,7 +81,7 @@ def check_patroni_cluster():
lag_strs.append(f"{name} (lag:{lag_mb:.0f}MB)") lag_strs.append(f"{name} (lag:{lag_mb:.0f}MB)")
msg = f"leader: {leader} | replicas: " + " ".join(lag_strs) msg = f"leader: {leader} | replicas: " + " ".join(lag_strs)
push("PATRONI-CLUSTER", "up", msg, ping_ms) push("Patroni Cluster", "up", msg, ping_ms)
def check_rabbitmq_cluster(): def check_rabbitmq_cluster():
url = "http://rabbitmq:15672/api/healthchecks/node" url = "http://rabbitmq:15672/api/healthchecks/node"
@ -104,14 +104,14 @@ def check_rabbitmq_cluster():
alarms = [n.get("name") for n in data if n.get("mem_alarm") or n.get("disk_free_alarm")] alarms = [n.get("name") for n in data if n.get("mem_alarm") or n.get("disk_free_alarm")]
if alarms: if alarms:
msg = f"disk/mem alarm active on {','.join(alarms)}" msg = f"disk/mem alarm active on {','.join(alarms)}"
push("RABBITMQ-CLUSTER", "down", msg, ping_ms) push("Rabbitmq Cluster", "down", msg, ping_ms)
return return
msg = f"{nodes_running}/{total_nodes} nodes running" msg = f"{nodes_running}/{total_nodes} nodes running"
push("RABBITMQ-CLUSTER", "up", msg, ping_ms) push("Rabbitmq Cluster", "up", msg, ping_ms)
else: else:
msg = err or f"HTTP {resp.status_code if resp else 'Unknown'}" msg = err or f"HTTP {resp.status_code if resp else 'Unknown'}"
push("RABBITMQ-CLUSTER", "down", msg, ping_ms) push("Rabbitmq Cluster", "down", msg, ping_ms)
def check_apisix(): def check_apisix():
url = "http://apisix:9180/apisix/admin/routes" url = "http://apisix:9180/apisix/admin/routes"
@ -120,9 +120,9 @@ def check_apisix():
ok, resp, ping_ms, err = http_check(url, headers=headers) ok, resp, ping_ms, err = http_check(url, headers=headers)
if ok: if ok:
push("APISIX-GATEWAY", "up", "admin API reachable", ping_ms) push("Apisix Gateway", "up", "admin API reachable", ping_ms)
else: else:
push("APISIX-GATEWAY", "down", f"admin API unreachable: {err or resp.status_code}", ping_ms) push("Apisix Gateway", "down", f"admin API unreachable: {err or resp.status_code}", ping_ms)
def check_vault(): def check_vault():
hosts_env = os.getenv("VAULT_HOSTS", "vault") hosts_env = os.getenv("VAULT_HOSTS", "vault")
@ -152,18 +152,18 @@ def check_vault():
if unsealed_count == total: if unsealed_count == total:
msg = f"{unsealed_count}/{total} unsealed" msg = f"{unsealed_count}/{total} unsealed"
push("VAULT-CLUSTER", "up", msg, ping_ms) push("Vault Cluster", "up", msg, ping_ms)
else: else:
msg = " | ".join(errors) if errors else "Vault checks failed" msg = " | ".join(errors) if errors else "Vault checks failed"
push("VAULT-CLUSTER", "down", msg, ping_ms) push("Vault Cluster", "down", msg, ping_ms)
def check_prometheus(): def check_prometheus():
url = "http://prometheus:9090/-/healthy" url = "http://prometheus:9090/-/healthy"
ok, resp, ping_ms, err = http_check(url) ok, resp, ping_ms, err = http_check(url)
if ok: if ok:
push("PROMETHEUS", "up", "healthy", ping_ms) push("Prometheus", "up", "healthy", ping_ms)
else: else:
push("PROMETHEUS", "down", f"prometheus unreachable: {err}", ping_ms) push("Prometheus", "down", f"prometheus unreachable: {err}", ping_ms)
def check_grafana(): def check_grafana():
url = "http://grafana:3000/api/health" url = "http://grafana:3000/api/health"
@ -172,27 +172,27 @@ def check_grafana():
data = resp.json() data = resp.json()
db_status = data.get("database", "unknown") db_status = data.get("database", "unknown")
if db_status == "ok": if db_status == "ok":
push("GRAFANA", "up", f"ok | db: {db_status}", ping_ms) push("Grafana", "up", f"ok | db: {db_status}", ping_ms)
else: else:
push("GRAFANA", "down", f"db not ok: {db_status}", ping_ms) push("Grafana", "down", f"db not ok: {db_status}", ping_ms)
else: else:
push("GRAFANA", "down", f"grafana unreachable: {err}", ping_ms) push("Grafana", "down", f"grafana unreachable: {err}", ping_ms)
def check_portainer(): def check_portainer():
url = "http://portainer:9000/api/system/status" url = "http://portainer:9000/api/system/status"
ok, resp, ping_ms, err = http_check(url) ok, resp, ping_ms, err = http_check(url)
if ok: if ok:
push("PORTAINER", "up", "running", ping_ms) push("Portainer", "up", "running", ping_ms)
else: else:
push("PORTAINER", "down", f"portainer unreachable: {err}", ping_ms) push("Portainer", "down", f"portainer unreachable: {err}", ping_ms)
def check_loki(): def check_loki():
url = "http://loki:3100/ready" url = "http://loki:3100/ready"
ok, resp, ping_ms, err = http_check(url) ok, resp, ping_ms, err = http_check(url)
if ok: if ok:
push("LOKI", "up", "ready", ping_ms) push("Loki", "up", "ready", ping_ms)
else: else:
push("LOKI", "down", f"loki unreachable: {err}", ping_ms) push("Loki", "down", f"loki unreachable: {err}", ping_ms)
def run_all_http_checks(): def run_all_http_checks():
check_patroni_cluster() check_patroni_cluster()

10
health-agent/src/health_agent/checks/mongodb.py
View File

@ -35,7 +35,7 @@ def check_mongodb():
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
if cluster_size == 1: if cluster_size == 1:
push("MONGODB-REPLICASET", "up", "standalone mode OK", ping_ms) push("Mongodb Replicaset", "up", "standalone mode OK", ping_ms)
return return
if primary: if primary:
@ -45,13 +45,13 @@ def check_mongodb():
unhealthy_secs = [s for s in secondaries if s[1] not in ('SECONDARY', 'ARBITER')] unhealthy_secs = [s for s in secondaries if s[1] not in ('SECONDARY', 'ARBITER')]
if unhealthy_secs: if unhealthy_secs:
msg = f"PRIMARY: {primary} | unhealthy: {','.join([s[0] + ':' + s[1] for s in unhealthy_secs])}" msg = f"PRIMARY: {primary} | unhealthy: {','.join([s[0] + ':' + s[1] for s in unhealthy_secs])}"
push("MONGODB-REPLICASET", "down", msg, ping_ms) push("Mongodb Replicaset", "down", msg, ping_ms)
else: else:
push("MONGODB-REPLICASET", "up", msg, ping_ms) push("Mongodb Replicaset", "up", msg, ping_ms)
else: else:
msg = "no PRIMARY | quorum lost" msg = "no PRIMARY | quorum lost"
push("MONGODB-REPLICASET", "down", msg, ping_ms) push("Mongodb Replicaset", "down", msg, ping_ms)
except Exception as e: except Exception as e:
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
push("MONGODB-REPLICASET", "down", f"connection failed: {e}", ping_ms) push("Mongodb Replicaset", "down", f"connection failed: {e}", ping_ms)

6
health-agent/src/health_agent/checks/redis_sentinel.py
View File

@ -24,7 +24,7 @@ def check_redis_sentinel():
redis_mode = os.getenv("REDIS_MODE", "sentinel") redis_mode = os.getenv("REDIS_MODE", "sentinel")
if redis_mode != "sentinel": if redis_mode != "sentinel":
push("REDIS-SENTINEL", "up", "standalone mode (skipped)", int((time.time() - start_t) * 1000)) push("Redis Sentinel", "up", "standalone mode (skipped)", int((time.time() - start_t) * 1000))
return return
try: try:
@ -43,8 +43,8 @@ def check_redis_sentinel():
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
msg = f"master: {master_ip}:{master_port} | replicas: {replicas_count} | sentinels quorum OK" msg = f"master: {master_ip}:{master_port} | replicas: {replicas_count} | sentinels quorum OK"
push("REDIS-SENTINEL", "up", msg, ping_ms) push("Redis Sentinel", "up", msg, ping_ms)
except Exception as e: except Exception as e:
ping_ms = int((time.time() - start_t) * 1000) ping_ms = int((time.time() - start_t) * 1000)
push("REDIS-SENTINEL", "down", f"quorum FAIL or master unreachable: {e}", ping_ms) push("Redis Sentinel", "down", f"quorum FAIL or master unreachable: {e}", ping_ms)

6
health-agent/src/health_agent/checks/swarm.py
View File

@ -38,12 +38,12 @@ def check_swarm_cluster():
if ready_count == total_nodes: if ready_count == total_nodes:
msg = f"{ready_count}/{total_nodes} nodes Ready (managers: {', '.join(managers)})" msg = f"{ready_count}/{total_nodes} nodes Ready (managers: {', '.join(managers)})"
push("SWARM-CLUSTER", "up", msg, ping_ms) push("Swarm Cluster", "up", msg, ping_ms)
else: else:
msg = f"{ready_count}/{total_nodes} nodes Ready | Managers reachable: {len(managers)}" msg = f"{ready_count}/{total_nodes} nodes Ready | Managers reachable: {len(managers)}"
push("SWARM-CLUSTER", "down", msg, ping_ms) push("Swarm Cluster", "down", msg, ping_ms)
except Exception as e: except Exception as e:
ping_ms = int((time.time() - start_time) * 1000) ping_ms = int((time.time() - start_time) * 1000)
logger.error(f"Swarm check failed: {e}") logger.error(f"Swarm check failed: {e}")
push("SWARM-CLUSTER", "down", str(e), ping_ms) push("Swarm Cluster", "down", str(e), ping_ms)

4
health-agent/src/health_agent/checks/tcp.py
View File

@ -70,8 +70,8 @@ def check_etcd_cluster():
if healthy_count == len(nodes): if healthy_count == len(nodes):
leader_info = f" | leader: {leader}" if leader else "" leader_info = f" | leader: {leader}" if leader else ""
msg = f"{healthy_count}/{len(nodes)} healthy{leader_info}" msg = f"{healthy_count}/{len(nodes)} healthy{leader_info}"
push("ETCD-CLUSTER", "up", msg, ping_ms) push("Etcd Cluster", "up", msg, ping_ms)
else: else:
quorum_msg = f" | quorum at risk ({healthy_count}/{len(nodes)})" if healthy_count < 3 else "" quorum_msg = f" | quorum at risk ({healthy_count}/{len(nodes)})" if healthy_count < 3 else ""
msg = " | ".join(errors) + quorum_msg msg = " | ".join(errors) + quorum_msg
push("ETCD-CLUSTER", "down", msg, ping_ms) push("Etcd Cluster", "down", msg, ping_ms)

4
health-agent/src/health_agent/checks/tls.py
View File

@ -57,6 +57,6 @@ def check_swag_tls():
msg = " | ".join(msg_parts) msg = " | ".join(msg_parts)
if is_down: if is_down:
push("SWAG-TLS", "down", msg, ping_ms) push("Swag Tls", "down", msg, ping_ms)
else: else:
push("SWAG-TLS", "up", msg, ping_ms) push("Swag Tls", "up", msg, ping_ms)