feat: support slow query alert settings

Chart.yaml

@@ -2,5 +2,5 @@ apiVersion: v2
 name: pgdog-control
 description: PgDog Control
 type: application
-version: 0.2.15
-appVersion: "29a6513b"
+version: 0.2.16
+appVersion: "84c7c56a"

README.md

@@ -662,7 +662,7 @@ control:
 
 ### Alerting
 
-`control.config.alerts` enables outbound alert integrations. Leave `incident_io` unset to disable incident.io. Thresholds are optional and only configured metrics create alerts.
+`control.config.alerts` enables outbound alert integrations. Leave `incident_io` unset to disable incident.io. Alert conditions are optional; only configured metric thresholds and explicitly enabled query alerts create incidents.
 
 ```yaml
 control:
@@ -674,6 +674,7 @@ control:
         cpu: 90.0
         memory: 2048
         server_connections: 100
+        slow_queries: true
       incident_io:
         api_key: inc_live_xxx
 ```
@@ -685,6 +686,7 @@ control:
 | `thresholds.cpu` | CPU usage percentage. Must be between `0.0` and `100.0`, inclusive (float, optional). |
 | `thresholds.memory` | Memory used, in megabytes (int, optional). |
 | `thresholds.server_connections` | Number of open server connections (int, optional). |
+| `thresholds.slow_queries` | Create incidents for queries whose duration reaches `store.slow_queries_threshold` (bool, default `false`). |
 | `incident_io.api_key` | incident.io API key with permission to create incidents. Missing `incident_io` disables the integration (string, optional). |
 
 ### State store
@@ -700,6 +702,7 @@ control:
       evict_after_secs: 60
       metrics_retention_secs: 300
       query_history_limit: 1000
+      slow_queries_threshold: 5000
       autoreload: immediately # or in_sync, or off
 ```
 
@@ -710,6 +713,7 @@ control:
 | `evict_after_secs` | Instance is dropped from the store entirely if its newest metric is older than this (int, default `60`). |
 | `metrics_retention_secs` | How much per-instance metric history is kept in memory. Older points are dropped as new ones arrive (int, default `300`). |
 | `query_history_limit` | Per-token historical query store capacity. Oldest deduped query entries are evicted first once the limit is reached (int, default `1000`). |
+| `slow_queries_threshold` | Minimum query duration, in milliseconds, for classifying a query as slow (int, default `5000`). |
 | `autoreload` | Automatically enqueue `reload_configuration` for instances that report config drift (enum, default `off`, available options: `off`, `immediately`, `in_sync`). |
 
 ### Slack Notifications

templates/configmap.yaml

@@ -93,6 +93,9 @@ data:
     {{- if hasKey . "query_history_limit" }}
     query_history_limit = {{ .query_history_limit }}
     {{- end }}
+    {{- if hasKey . "slow_queries_threshold" }}
+    slow_queries_threshold = {{ .slow_queries_threshold }}
+    {{- end }}
     {{- if hasKey . "autoreload" }}
     autoreload = {{ .autoreload | quote }}
     {{- end }}
@@ -207,6 +210,9 @@ data:
     {{- if hasKey . "server_connections" }}
     server_connections = {{ .server_connections }}
     {{- end }}
+    {{- if hasKey . "slow_queries" }}
+    slow_queries = {{ .slow_queries }}
+    {{- end }}
     {{- end }}
     {{- with .incident_io }}
 

test/test.sh

@@ -14,6 +14,12 @@ for values_file in "$TEST_DIR"/values-*.yaml; do
   helm template test-release "$CHART_DIR" -f "$values_file" > /dev/null
 done
 
+echo ""
+echo "==> Verifying query alert settings..."
+full_render=$(helm template test-release "$CHART_DIR" -f "$TEST_DIR/values-full.yaml")
+grep -q '^    slow_queries_threshold = 2500$' <<< "$full_render"
+grep -q '^    slow_queries = true$' <<< "$full_render"
+
 echo ""
 echo "==> Verifying external Redis rendering..."
 external_render=$(helm template test-release "$CHART_DIR" -f "$TEST_DIR/values-redis-external.yaml")

test/values-full.yaml

@@ -32,6 +32,7 @@ control:
       process_notify_interval_secs: 30
       metrics_retention_secs: 600
       query_history_limit: 500
+      slow_queries_threshold: 2500
       autoreload: "immediately"
     autoscaling:
       pool_size: true
@@ -68,6 +69,7 @@ control:
         cpu: 90.0
         memory: 2048
         server_connections: 100
+        slow_queries: true
       incident_io:
         api_key: incident-token
     slack:

values.yaml

@@ -104,6 +104,7 @@ control:
       # process_notify_interval_secs: 60
       # metrics_retention_secs: 300
       # query_history_limit: 1000
+      # slow_queries_threshold: 5000   # Minimum query duration in milliseconds.
       # autoreload: off
     autoscaling: {}
       # pool_size: false
@@ -155,6 +156,7 @@ control:
       #   cpu: 90.0
       #   memory: 2048
       #   server_connections: 100
+      #   slow_queries: false
       # incident_io:
       #   api_key: ""
     slack: {}