docker-compose: move TooManyLogs into vm-health alerts set (#3199)

deployment/docker/alerts-cluster.yml

@@ -89,17 +89,6 @@ groups:
           description: "The limit of concurrent flushes on instance {{ $labels.instance }} is equal to number of CPUs.\n
             When vmstorage constantly hits the limit it means that storage is overloaded and requires more CPU."
 
-      - alert: TooManyLogs
-        expr: sum(increase(vm_log_messages_total{level="error"}[5m])) by (job, instance) > 0
-        for: 15m
-        labels:
-          severity: warning
-        annotations:
-          dashboard: "http://localhost:3000/d/oS7Bi_0Wz?viewPanel=104&var-instance={{ $labels.instance }}"
-          summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
-          description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
-           Worth to check logs for specific error messages."
-
       - alert: RowsRejectedOnIngestion
         expr: sum(rate(vm_rows_ignored_total[5m])) by (instance, reason) > 0
         for: 15m

deployment/docker/alerts-health.yml

@@ -51,4 +51,14 @@ groups:
         annotations:
           summary: "More than 90% of CPU is used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
           description: "Too high CPU usage may be a sign of insufficient resources and make process unstable.
-               Consider to either increase available CPU resources or decrease the load on the process."
+               Consider to either increase available CPU resources or decrease the load on the process."
+
+      - alert: TooManyLogs
+        expr: sum(increase(vm_log_messages_total{level="error"}[5m])) by (job, instance) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
+          description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
+         Worth to check logs for specific error messages."

deployment/docker/alerts.yml

@@ -71,17 +71,6 @@ groups:
           description: "The limit of concurrent flushes on instance {{ $labels.instance }} is equal to number of CPUs.\n
             When VictoriaMetrics constantly hits the limit it means that storage is overloaded and requires more CPU."
 
-      - alert: TooManyLogs
-        expr: sum(increase(vm_log_messages_total{level="error"}[5m])) by (job, instance) > 0
-        for: 15m
-        labels:
-          severity: warning
-        annotations:
-          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=67&var-instance={{ $labels.instance }}"
-          summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
-          description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
-           Worth to check logs for specific error messages."
-
       - alert: RowsRejectedOnIngestion
         expr: sum(rate(vm_rows_ignored_total[5m])) by (instance, reason) > 0
         for: 15m
@@ -154,4 +143,4 @@ groups:
           summary: "Metrics ingested in ({{ $labels.instance }}) are exceeding labels limit"
           description: "VictoriaMetrics limits the number of labels per each metric with `-maxLabelsPerTimeseries` command-line flag.\n
            This prevents from ingesting metrics with too many labels. Please verify that `-maxLabelsPerTimeseries` is configured
-           correctly or that clients which send these metrics aren't misbehaving."
+           correctly or that clients which send these metrics aren't misbehaving."