fix(topology): add more logs to process task (#1531)

keephq · Aug 4, 2024 · cee3757 · cee3757
1 parent f3effde
commit cee3757
Show file tree

Hide file tree

Showing 2 changed files with 67 additions and 9 deletions.
diff --git a/keep/api/tasks/process_topology_task.py b/keep/api/tasks/process_topology_task.py
@@ -16,19 +16,21 @@
 def process_topology(
     tenant_id: str, topology_data: list[TopologyServiceInDto], provider_id: str
 ):
+    extra = {"provider_id": provider_id, "tenant_id": tenant_id}
     if not topology_data:
         logger.info(
             "No topology data to process",
-            extra={"provider_id": provider_id, "tenant_id": tenant_id},
+            extra=extra,
         )
         return
 
+    logger.info("Processing topology data", extra=extra)
     session = get_session_sync()
 
     try:
         logger.info(
             "Deleting existing topology data",
-            extra={"provider_id": provider_id, "tenant_id": tenant_id},
+            extra=extra,
         )
         session.query(TopologyService).filter(
             TopologyService.source_provider_id == provider_id,
@@ -37,14 +39,14 @@ def process_topology(
         session.commit()
         logger.info(
             "Deleted existing topology data",
-            extra={"provider_id": provider_id, "tenant_id": tenant_id},
+            extra=extra,
         )
-    except Exception as e:
+    except Exception:
         logger.exception(
-            "Failed to delete TopologyService",
-            extra={"provider_id": provider_id, "error": str(e)},
+            "Failed to delete existing topology data",
+            extra=extra,
         )
-        return
+        raise
 
     logger.info(
         "Creating new topology data",
@@ -72,11 +74,19 @@ def process_topology(
             )
 
     session.commit()
+
+    try:
+        session.close()
+    except Exception as e:
+        logger.warning(
+            "Failed to close session",
+            extra={**extra, "error": str(e)},
+        )
+
     logger.info(
         "Created new topology data",
-        extra={"provider_id": provider_id, "tenant_id": tenant_id},
+        extra=extra,
     )
-    return True
 
 
 async def async_process_topology(*args, **kwargs):

diff --git a/keep/providers/grafana_provider/alerts_mock.py b/keep/providers/grafana_provider/alerts_mock.py
@@ -1,4 +1,52 @@
 ALERTS = {
+    "database_connection_failure": {
+        "severity": "critical",
+        "title": "Database Connection Failure",
+        "alerts": [
+            {
+                "condition": "A",
+                "data": [
+                    {
+                        "datasourceUid": "datasource1",
+                        "model": {
+                            "conditions": [
+                                {
+                                    "evaluator": {"params": [1], "type": "gt"},
+                                    "operator": {"type": "and"},
+                                    "query": {"params": ["A", "5m", "now"]},
+                                    "reducer": {"params": [], "type": "last"},
+                                    "type": "query",
+                                }
+                            ],
+                            "datasource": {"type": "grafana", "uid": "datasource1"},
+                            "expression": "",
+                            "hide": False,
+                            "intervalMs": 1000,
+                            "maxDataPoints": 100,
+                            "refId": "A",
+                            "type": "classic_conditions",
+                        },
+                        "queryType": "",
+                        "refId": "A",
+                        "relativeTimeRange": {"from": 300, "to": 0},
+                    }
+                ],
+                "execErrState": "Alerting",
+                "folderUID": "keep_alerts",
+                "for_": "5m",
+                "isPaused": False,
+                "labels": {"severity": "critical", "monitor": "database"},
+                "noDataState": "NoData",
+                "orgID": 1,
+                "ruleGroup": "keep_group_1",
+                "title": "Database Connection Failure",
+                "parameters": {
+                    "labels.monitor": ["database1", "database2", "database3"],
+                    "for_": ["5m", "10m", "15m"],
+                },
+            },
+        ],
+    },
     "high_memory_usage": {
         "payload": {
             "condition": "B",