assets,site/content: daily assets regeneration

monitoring-mixins · Dec 12, 2024 · 2355980 · 2355980
1 parent 82075a7
commit 2355980
Show file tree

Hide file tree

Showing 19 changed files with 262 additions and 262 deletions.
diff --git a/assets/jvm/alerts.yaml b/assets/jvm/alerts.yaml
@@ -6,8 +6,8 @@ groups:
       description: JVM heap memory usage is at {{ printf "%.0f" $value }}% over the
         last 5 minutes on {{$labels.instance}}, which is above the threshold of 80%.
       summary: JVM heap memory filling up.
-    expr: ((sum without (id) (jvm_memory_used_bytes{area="heap", job!=""}))/(sum without
-      (id) (jvm_memory_max_bytes{area="heap", job!=""} != -1))) * 100 > 80
+    expr: ((sum without (id) (jvm_memory_used_bytes{area="heap", }))/(sum without
+      (id) (jvm_memory_max_bytes{area="heap", } != -1))) * 100 > 80
     for: 5m
     keep_firing_for: 5m
     labels:
@@ -18,7 +18,7 @@ groups:
         are in a cyclic dependency with each other. The restart is required to resolve
         the deadlock.'
       summary: JVM deadlock detected.
-    expr: (jvm_threads_deadlocked{job!=""}) > 0
+    expr: (jvm_threads_deadlocked{}) > 0
     for: 2m
     keep_firing_for: 5m
     labels:

diff --git a/assets/jvm/dashboards/jvm-dashboard.json b/assets/jvm/dashboards/jvm-dashboard.json
diff --git a/assets/kafka/alerts.yaml b/assets/kafka/alerts.yaml
@@ -6,7 +6,7 @@ groups:
       description: 'Kafka lag keeps increasing over the last 15 minutes for consumer
         group: {{$labels.consumergroup}}, topic: {{$labels.topic}}.'
       summary: Kafka lag keeps increasing.
-    expr: sum by (job,kafka_cluster, topic, consumergroup) (delta(kafka_consumergroup_uncommitted_offsets{job="integrations/kafka",topic!="__consumer_offsets",consumergroup!=""}[5m]))
+    expr: sum by (job,kafka_cluster, topic, consumergroup) (delta(kafka_consumergroup_uncommitted_offsets{topic!="__consumer_offsets",consumergroup!="",job="integrations/kafka"}[5m]))
       > 0
     for: 15m
     keep_firing_for: 10m
@@ -17,7 +17,7 @@ groups:
       description: 'Total kafka lag across all partitions is too high ({{ printf "%.0f"
         $value }}) for consumer group: {{$labels.consumergroup}}, topic: {{$labels.topic}}.'
       summary: Kafka lag is too high.
-    expr: sum by (job,kafka_cluster, topic, consumergroup) (kafka_consumergroup_uncommitted_offsets{job="integrations/kafka",topic!="__consumer_offsets",consumergroup!=""})
+    expr: sum by (job,kafka_cluster, topic, consumergroup) (kafka_consumergroup_uncommitted_offsets{topic!="__consumer_offsets",consumergroup!="",job="integrations/kafka"})
       > 100
     for: 15m
     keep_firing_for: 5m
@@ -118,8 +118,8 @@ groups:
       description: Kafka broker {{ $labels.instance }} in cluster {{ $labels.kafka_cluster
         }} has disconected from Zookeeper.
       summary: Kafka Zookeeper sync disconected.
-    expr: avg by(job,kafka_cluster,instance) (rate(kafka_server_sessionexpirelistener_zookeepersyncconnectspersec{job="integrations/kafka",
-      quantile="0.95"}[5m])) < 0
+    expr: avg by(job,kafka_cluster,instance) (rate(kafka_server_sessionexpirelistener_zookeepersyncconnectspersec{quantile="0.95",job="integrations/kafka"}[5m]))
+      < 0
     for: 5m
     labels:
       severity: critical

diff --git a/assets/kafka/dashboards/kafka-overview-dashboard.json b/assets/kafka/dashboards/kafka-overview-dashboard.json
diff --git a/assets/kafka/dashboards/kafka-topic-dashboard.json b/assets/kafka/dashboards/kafka-topic-dashboard.json
@@ -95,7 +95,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_logstartoffset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
+               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_logstartoffset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -106,7 +106,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_logendoffset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
+               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_logendoffset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -117,7 +117,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,topic,partition) (\n  rate(kafka_topic_partition_current_offset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
+               "expr": "sum by (job,kafka_cluster,topic,partition) (\n  rate(kafka_topic_partition_current_offset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -128,7 +128,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_size{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
+               "expr": "max by (job,kafka_cluster,topic,partition) (\n  kafka_log_log_size{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -223,7 +223,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_topic_partition_current_offset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
+               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_topic_partition_current_offset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -289,7 +289,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_server_brokertopicmetrics_bytesinpersec{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
+               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_server_brokertopicmetrics_bytesinpersec{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -355,7 +355,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_server_brokertopicmetrics_bytesoutpersec{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
+               "expr": "sum by (job,kafka_cluster,topic) (\n  rate(kafka_server_brokertopicmetrics_bytesoutpersec{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ topic }}",
@@ -435,7 +435,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  rate(kafka_consumergroup_current_offset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}[$__rate_interval])\n)",
+               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  rate(kafka_consumergroup_current_offset{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -446,7 +446,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumergroup_uncommitted_offsets{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
+               "expr": "sum by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumergroup_uncommitted_offsets{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -457,7 +457,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumer_lag_millis{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
+               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumer_lag_millis{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -552,7 +552,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  rate(kafka_consumergroup_current_offset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}[$__rate_interval])\n)",
+               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  rate(kafka_consumergroup_current_offset{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}[$__rate_interval])\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -616,7 +616,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "sum by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumergroup_uncommitted_offsets{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
+               "expr": "sum by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumergroup_uncommitted_offsets{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -680,7 +680,7 @@
                   "type": "prometheus",
                   "uid": "${datasource}"
                },
-               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumer_lag_millis{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
+               "expr": "avg by (job,kafka_cluster,consumergroup,topic) (\n  kafka_consumer_lag_millis{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\",consumergroup=~\"$consumergroup\"}\n)",
                "format": "time_series",
                "instant": false,
                "legendFormat": "{{ consumergroup }} ({{ topic }})",
@@ -714,7 +714,7 @@
             "label": "Job",
             "multi": true,
             "name": "job",
-            "query": "label_values(kafka_log_log_logstartoffset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\"}, job)",
+            "query": "label_values(kafka_log_log_logstartoffset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\"}, job)",
             "refresh": 2,
             "sort": 1,
             "type": "query"
@@ -729,7 +729,7 @@
             "label": "Kafka_cluster",
             "multi": true,
             "name": "kafka_cluster",
-            "query": "label_values(kafka_log_log_logstartoffset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\"}, kafka_cluster)",
+            "query": "label_values(kafka_log_log_logstartoffset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\"}, kafka_cluster)",
             "refresh": 2,
             "sort": 1,
             "type": "query"
@@ -744,7 +744,7 @@
             "label": "Topic",
             "multi": true,
             "name": "topic",
-            "query": "label_values(kafka_log_log_logstartoffset{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\"}, topic)",
+            "query": "label_values(kafka_log_log_logstartoffset{topic!=\"__consumer_offsets\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\"}, topic)",
             "refresh": 2,
             "sort": 1,
             "type": "query"
@@ -759,7 +759,7 @@
             "label": "Consumergroup",
             "multi": true,
             "name": "consumergroup",
-            "query": "label_values(kafka_consumergroup_uncommitted_offsets{job=\"integrations/kafka\",topic!=\"__consumer_offsets\",consumergroup!=\"\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}, consumergroup)",
+            "query": "label_values(kafka_consumergroup_uncommitted_offsets{topic!=\"__consumer_offsets\",consumergroup!=\"\",job=\"integrations/kafka\",job=~\"$job\",kafka_cluster=~\"$kafka_cluster\",topic=~\"$topic\"}, consumergroup)",
             "refresh": 2,
             "sort": 1,
             "type": "query"

diff --git a/assets/openstack/dashboards/overview b/assets/openstack/dashboards/overview
@@ -573,8 +573,8 @@
          },
          "fieldConfig": {
             "defaults": {
-               "max": "150",
-               "min": "0",
+               "max": 150,
+               "min": 0,
                "thresholds": {
                   "steps": [
                      {
@@ -617,8 +617,8 @@
          },
          "fieldConfig": {
             "defaults": {
-               "max": "150",
-               "min": "0",
+               "max": 150,
+               "min": 0,
                "thresholds": {
                   "steps": [
                      {

diff --git a/assets/windows-active-directory/alerts.yaml b/assets/windows-active-directory/alerts.yaml
@@ -7,7 +7,7 @@ groups:
         CPU usage on host {{ $labels.instance }} is above 90%. The current value is {{ $value | printf "%.2f" }}%.
       summary: High CPU usage on Windows host.
     expr: |
-      100 - (avg without (mode, core) (rate(windows_cpu_time_total{job=~".*windows.*", mode="idle"}[2m])) * 100) > 90
+      100 - (avg without (mode, core) (rate(windows_cpu_time_total{mode="idle", }[2m])) * 100) > 90
     for: 15m
     keep_firing_for: 5m
     labels:
@@ -18,9 +18,9 @@ groups:
         Memory usage on host {{ $labels.instance }} is above 90%. The current value is {{ $value | printf "%.2f" }}%.
       summary: High memory usage on Windows host.
     expr: |
-      100 - ((windows_os_physical_memory_free_bytes{job=~".*windows.*"}
+      100 - ((windows_os_physical_memory_free_bytes{}
       /
-      windows_cs_physical_memory_bytes{job=~".*windows.*"}) * 100) > 90
+      windows_cs_physical_memory_bytes{}) * 100) > 90
     for: 15m
     keep_firing_for: 5m
     labels:
@@ -31,7 +31,7 @@ groups:
         Volume {{ $labels.volume }} is almost full on host {{ $labels.instance }}, more than 90% of space is used. The current volume utilization is {{ $value | printf "%.2f" }}%.
       summary: Disk is almost full on Windows host.
     expr: |
-      100 - ((windows_logical_disk_free_bytes{job=~".*windows.*"} ) / (windows_logical_disk_size_bytes{job=~".*windows.*"})) * 100  > 90
+      100 - ((windows_logical_disk_free_bytes{} ) / (windows_logical_disk_size_bytes{})) * 100  > 90
     for: 15m
     keep_firing_for: 5m
     labels:
@@ -42,7 +42,7 @@ groups:
         Windows service {{ $labels.name }} is not in healthy state, currently in '{{ $labels.status }}'.
       summary: Windows service is not healthy.
     expr: |
-      windows_service_status{job=~".*windows.*", status!~"starting|stopping|ok"} > 0
+      windows_service_status{status!~"starting|stopping|ok", } > 0
     for: 5m
     labels:
       severity: critical
@@ -52,7 +52,7 @@ groups:
         Windows disk {{ $labels.name }} is not in healthy state, currently in '{{ $labels.status }}' status.
       summary: Windows physical disk is not healthy.
     expr: |
-      windows_disk_drive_status{job=~".*windows.*", status="OK"} != 1
+      windows_disk_drive_status{status="OK", } != 1
     for: 5m
     labels:
       severity: critical
@@ -62,7 +62,7 @@ groups:
         Round-trip time of NTP client on instance {{ $labels.instance }} is greater than 1 second. Delay is {{ $value }} sec.
       summary: NTP client delay.
     expr: |
-      windows_time_ntp_round_trip_delay_seconds{job=~".*windows.*"} > 1
+      windows_time_ntp_round_trip_delay_seconds{} > 1
     for: 5m
     keep_firing_for: 5m
     labels:
@@ -73,7 +73,7 @@ groups:
         NTP time offset for instance {{ $labels.instance }} is greater than 1 second. Offset is {{ $value }} sec.
       summary: NTP time offset is too large.
     expr: |
-      windows_time_computed_time_offset_seconds{job=~".*windows.*"} > 1
+      windows_time_computed_time_offset_seconds{} > 1
     for: 5m
     keep_firing_for: 5m
     labels:
@@ -85,7 +85,7 @@ groups:
       summary: There is a high number of pending replication operations in Active
         Directory. A high number of pending operations sustained over a period of
         time can indicate a problem with replication.
-    expr: "windows_ad_replication_pending_operations{job=~\".*windows.*\"} >= 50 \n"
+    expr: "windows_ad_replication_pending_operations{} >= 50 \n"
     for: 10m
     keep_firing_for: 5m
     labels:
@@ -97,7 +97,7 @@ groups:
       summary: There are a number of replication synchronization request failures.
         These can cause authentication failures, outdated information being propagated
         across domain controllers, and potentially data loss or inconsistencies.
-    expr: "increase(windows_ad_replication_sync_requests_schema_mismatch_failure_total{job=~\".*windows.*\"}[5m])
+    expr: "increase(windows_ad_replication_sync_requests_schema_mismatch_failure_total{}[5m])
       > 0 \n"
     for: 5m
     keep_firing_for: 5m
@@ -111,7 +111,7 @@ groups:
       summary: There is a high number of password changes. This may indicate unauthorized
         changes or attacks.
     expr: |
-      increase(windows_ad_sam_password_changes_total{job=~".*windows.*"}[5m]) > 25
+      increase(windows_ad_sam_password_changes_total{}[5m]) > 25
     for: 5m
     labels:
       keep_firing_for: 24h