@leverege/build-tools 2.66.0 → 2.66.1

package/src/helm-charts/prom-operator/rules/awesome-base/prometheus-rules.yaml

@@ -0,0 +1,318 @@
+# https://samber.github.io/awesome-prometheus-alerts/rules#prometheus-self-monitoring
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: embedded-exporter
+  namespace: prometheus
+spec:
+  groups:
+    - name: EmbeddedExporter-rules
+      rules:
+        - alert: PrometheusJobMissing
+          expr: absent(up{job="prometheus"})
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus job missing (instance {{ $labels.instance }})
+            description: |-
+              A Prometheus job has disappeared
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTargetMissing
+          expr: up == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus target missing (instance {{ $labels.instance }})
+            description: |-
+              A Prometheus target has disappeared. An exporter might be crashed.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAllTargetsMissing
+          expr: sum by (job) (up) == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus all targets missing (instance {{ $labels.instance }})
+            description: |-
+              A Prometheus job does not have living target anymore.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTargetMissingWithWarmupTime
+          expr: sum by (instance, job) ((up == 0) * on (instance) group_left(__name__) (node_time_seconds - node_boot_time_seconds > 600))
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus target missing with warmup time (instance {{ $labels.instance }})
+            description: |-
+              Allow a job time to start up (10 minutes) before alerting that it's down.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusConfigurationReloadFailure
+          expr: prometheus_config_last_reload_successful != 1
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
+            description: |-
+              Prometheus configuration reload error
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTooManyRestarts
+          expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus too many restarts (instance {{ $labels.instance }})
+            description: |-
+              Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAlertmanagerJobMissing
+          expr: absent(up{job="alertmanager"})
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
+            description: |-
+              A Prometheus AlertManager job has disappeared
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAlertmanagerConfigurationReloadFailure
+          expr: alertmanager_config_last_reload_successful != 1
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
+            description: |-
+              AlertManager configuration reload error
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAlertmanagerConfigNotSynced
+          expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
+            description: |-
+              Configurations of AlertManager cluster instances are out of sync
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAlertmanagerE2eDeadManSwitch
+          expr: vector(1)
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
+            description: |-
+              Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusNotConnectedToAlertmanager
+          expr: prometheus_notifications_alertmanagers_discovered < 1
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
+            description: |-
+              Prometheus cannot connect the alertmanager
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusRuleEvaluationFailures
+          expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTemplateTextExpansionFailures
+          expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} template text expansion failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusRuleEvaluationSlow
+          expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
+            description: |-
+              Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusNotificationsBacklog
+          expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus notifications backlog (instance {{ $labels.instance }})
+            description: |-
+              The Prometheus notification queue has not been empty for 10 minutes
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusAlertmanagerNotificationFailing
+          expr: rate(alertmanager_notifications_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
+            description: |-
+              Alertmanager is failing sending notifications
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTargetEmpty
+          expr: prometheus_sd_discovered_targets == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus target empty (instance {{ $labels.instance }})
+            description: |-
+              Prometheus has no target in service discovery
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTargetScrapingSlow
+          expr: prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus target scraping slow (instance {{ $labels.instance }})
+            description: |-
+              Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusLargeScrape
+          expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus large scrape (instance {{ $labels.instance }})
+            description: |-
+              Prometheus has many scrapes that exceed the sample limit
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTargetScrapeDuplicate
+          expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
+            description: |-
+              Prometheus has many samples rejected due to duplicate timestamps but different values
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbCheckpointCreationFailures
+          expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} checkpoint creation failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbCheckpointDeletionFailures
+          expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} checkpoint deletion failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbCompactionsFailed
+          expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} TSDB compactions failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbHeadTruncationsFailed
+          expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} TSDB head truncation failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbReloadFailures
+          expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} TSDB reload failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbWalCorruptions
+          expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} TSDB WAL corruptions
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTsdbWalTruncationsFailed
+          expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
+            description: |-
+              Prometheus encountered {{ $value }} TSDB WAL truncation failures
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: PrometheusTimeseriesCardinality
+          expr: label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Prometheus timeseries cardinality (instance {{ $labels.instance }})
+            description: |-
+              The "{{ $labels.name }}" timeseries cardinality is getting very high: {{ $value }}
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}

package/src/helm-charts/prom-operator/rules/awesome-base/redis-rules.yaml

@@ -0,0 +1,142 @@
+# https://samber.github.io/awesome-prometheus-alerts/rules#redis
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: oliver006-redis-exporter
+  namespace: prometheus
+spec:
+  groups:
+    - name: Oliver006RedisExporter-rules
+      rules:
+        - alert: RedisDown
+          expr: redis_up == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis down (instance {{ $labels.instance }})
+            description: |-
+              Redis instance is down
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisMissingMaster
+          expr: (count(redis_instance_info{role="master"}) or vector(0)) < 1
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis missing master (instance {{ $labels.instance }})
+            description: |-
+              Redis cluster has no node marked as master.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisTooManyMasters
+          expr: count(redis_instance_info{role="master"}) > 1
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis too many masters (instance {{ $labels.instance }})
+            description: |-
+              Redis cluster has too many nodes marked as master.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisDisconnectedSlaves
+          expr: count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis disconnected slaves (instance {{ $labels.instance }})
+            description: |-
+              Redis not replicating for all slaves. Consider reviewing the redis replication status.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisReplicationBroken
+          expr: delta(redis_connected_slaves[1m]) < 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis replication broken (instance {{ $labels.instance }})
+            description: |-
+              Redis instance lost a slave
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisClusterFlapping
+          expr: changes(redis_connected_slaves[1m]) > 1
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis cluster flapping (instance {{ $labels.instance }})
+            description: |-
+              Changes have been detected in Redis replica connection. This can occur when replica nodes lose connection to the master and reconnect (a.k.a flapping).
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisMissingBackup
+          expr: time() - redis_rdb_last_save_timestamp_seconds > 60 * 60 * 24
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis missing backup (instance {{ $labels.instance }})
+            description: |-
+              Redis has not been backuped for 24 hours
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisOutOfSystemMemory
+          expr: redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Redis out of system memory (instance {{ $labels.instance }})
+            description: |-
+              Redis is running out of system memory (> 90%)
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisOutOfConfiguredMaxmemory
+          expr: redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90 and on(instance) redis_memory_max_bytes > 0
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
+            description: |-
+              Redis is running out of configured maxmemory (> 90%)
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisTooManyConnections
+          expr: redis_connected_clients / redis_config_maxclients * 100 > 90
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Redis too many connections (instance {{ $labels.instance }})
+            description: |-
+              Redis is running out of connections (> 90% used)
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisNotEnoughConnections
+          expr: redis_connected_clients < 5
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Redis not enough connections (instance {{ $labels.instance }})
+            description: |-
+              Redis instance should have more connections (> 5)
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: RedisRejectedConnections
+          expr: increase(redis_rejected_connections_total[1m]) > 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Redis rejected connections (instance {{ $labels.instance }})
+            description: |-
+              Some connections to Redis has been rejected
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}

package/src/helm-charts/prom-operator/rules/awesome-base/traefik-rules.yaml

@@ -0,0 +1,43 @@
+# https://samber.github.io/awesome-prometheus-alerts/rules#traefik
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: embedded-exporter-v2
+  namespace: prometheus
+spec:
+  groups:
+    - name: EmbeddedExporterV2-rules
+      rules:
+        - alert: TraefikServiceDown
+          expr: count(traefik_service_server_up) by (service) == 0
+          for: 0m
+          labels:
+            severity: critical
+          annotations:
+            summary: Traefik service down (instance {{ $labels.instance }})
+            description: |-
+              All Traefik services are down
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: TraefikHighHttp4xxErrorRateService
+          expr: sum(rate(traefik_service_requests_total{code=~"4.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 5
+          for: 1m
+          labels:
+            severity: critical
+          annotations:
+            summary: Traefik high HTTP 4xx error rate service (instance {{ $labels.instance }})
+            description: |-
+              Traefik service 4xx error rate is above 5%
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: TraefikHighHttp5xxErrorRateService
+          expr: sum(rate(traefik_service_requests_total{code=~"5.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 5
+          for: 1m
+          labels:
+            severity: critical
+          annotations:
+            summary: Traefik high HTTP 5xx error rate service (instance {{ $labels.instance }})
+            description: |-
+              Traefik service 5xx error rate is above 5%
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}

package/src/helm-charts/prom-operator/rules/cadvisor-rules.yaml

@@ -0,0 +1,109 @@
+# https://samber.github.io/awesome-prometheus-alerts/rules#docker-containers
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: google-cadvisor
+  namespace: prometheus
+spec:
+  groups:
+    - name: Cadvisor (awesome) # GoogleCadvisor-rules
+      rules:
+        - alert: ContainerKilled
+          expr: time() - container_last_seen > 60
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container killed (instance {{ $labels.instance }})
+            description: |-
+              A container has disappeared
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerAbsent
+          expr: absent(container_last_seen)
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container absent (instance {{ $labels.instance }})
+            description: |-
+              A container is absent for 5 min
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerHighCpuUtilization
+          expr: (sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) > 80
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container High CPU utilization (instance {{ $labels.instance }})
+            description: |-
+              Container CPU utilization is above 80%
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerHighMemoryUsage
+          expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container High Memory usage (instance {{ $labels.instance }})
+            description: |-
+              Container Memory usage is above 80%
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerVolumeUsage
+          expr: (1 - (sum(container_fs_inodes_free{name!=""}) BY (instance) / sum(container_fs_inodes_total) BY (instance))) * 100 > 80
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container Volume usage (instance {{ $labels.instance }})
+            description: |-
+              Container Volume usage is above 80%
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerHighThrottleRate
+          expr: sum(increase(container_cpu_cfs_throttled_periods_total{container!=""}[5m])) by (container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total[5m])) by (container, pod, namespace) > ( 25 / 100 )
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Container high throttle rate (instance {{ $labels.instance }})
+            description: |-
+              Container is being throttled
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+#       - alert: ContainerHighLowChangeCpuUsage
+#         expr: (abs((sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m])) * 100) - (sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m] offset 1m)) * 100)) or abs((sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[1m])) * 100) - (sum by (instance, name) (rate(container_cpu_usage_seconds_total{name!=""}[5m] offset 1m)) * 100))) > 25
+#         for: 0m
+#         labels:
+#           severity: info
+#         annotations:
+#           summary: Container high low change CPU usage (instance {{ $labels.instance }})
+#           description: |-
+#             This alert rule monitors the absolute change in CPU usage within a time window and triggers an alert when the change exceeds 25%.
+#               VALUE = {{ $value }}
+#               LABELS = {{ $labels }}
+        - alert: ContainerLowCpuUtilization
+          expr: (sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) < 20
+          for: 7d
+          labels:
+            severity: info
+          annotations:
+            summary: Container Low CPU utilization (instance {{ $labels.instance }})
+            description: |-
+              Container CPU utilization is under 20% for 1 week. Consider reducing the allocated CPU.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}
+        - alert: ContainerLowMemoryUsage
+          expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) < 20
+          for: 7d
+          labels:
+            severity: info
+          annotations:
+            summary: Container Low Memory usage (instance {{ $labels.instance }})
+            description: |-
+              Container Memory usage is under 20% for 1 week. Consider reducing the allocated memory.
+                VALUE = {{ $value }}
+                LABELS = {{ $labels }}