mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-22 01:17:19 +08:00
Publish
This commit is contained in:
Samuel Berthe
parent
0adc449e1e
commit
ccf24bcf03
56 changed files with 3970 additions and 0 deletions
32
dist/rules/apache/lusitaniae-apache-exporter.yml
vendored
Normal file
32
dist/rules/apache/lusitaniae-apache-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: LusitaniaeApacheExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: ApacheDown
|
||||
expr: 'apache_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Apache down (instance {{ $labels.instance }})
|
||||
description: "Apache down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ApacheWorkersLoad
|
||||
expr: '(sum by (instance) (apache_workers{state="busy"}) / sum by (instance) (apache_scoreboard) ) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Apache workers load (instance {{ $labels.instance }})
|
||||
description: "Apache workers in busy state approach the max workers count 80% workers busy on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ApacheRestart
|
||||
expr: 'apache_uptime_seconds_total / 60 < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Apache restart (instance {{ $labels.instance }})
|
||||
description: "Apache has just been restarted.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
77
dist/rules/blackbox/blackbox-exporter.yml
vendored
Normal file
77
dist/rules/blackbox/blackbox-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
groups:
|
||||
|
||||
- name: BlackboxExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: BlackboxProbeFailed
|
||||
expr: 'probe_success == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Blackbox probe failed (instance {{ $labels.instance }})
|
||||
description: "Probe failed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxSlowProbe
|
||||
expr: 'avg_over_time(probe_duration_seconds[1m]) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Blackbox slow probe (instance {{ $labels.instance }})
|
||||
description: "Blackbox probe took more than 1s to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxProbeHttpFailure
|
||||
expr: 'probe_http_status_code <= 199 OR probe_http_status_code >= 400'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Blackbox probe HTTP failure (instance {{ $labels.instance }})
|
||||
description: "HTTP status code is not 200-399\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxSslCertificateWillExpireSoon
|
||||
expr: 'probe_ssl_earliest_cert_expiry - time() < 86400 * 30'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }})
|
||||
description: "SSL certificate expires in 30 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxSslCertificateWillExpireSoon
|
||||
expr: 'probe_ssl_earliest_cert_expiry - time() < 86400 * 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Blackbox SSL certificate will expire soon (instance {{ $labels.instance }})
|
||||
description: "SSL certificate expires in 3 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxSslCertificateExpired
|
||||
expr: 'probe_ssl_earliest_cert_expiry - time() <= 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Blackbox SSL certificate expired (instance {{ $labels.instance }})
|
||||
description: "SSL certificate has expired already\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxProbeSlowHttp
|
||||
expr: 'avg_over_time(probe_http_duration_seconds[1m]) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Blackbox probe slow HTTP (instance {{ $labels.instance }})
|
||||
description: "HTTP request took more than 1s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: BlackboxProbeSlowPing
|
||||
expr: 'avg_over_time(probe_icmp_duration_seconds[1m]) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Blackbox probe slow ping (instance {{ $labels.instance }})
|
||||
description: "Blackbox ping took more than 1s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
167
dist/rules/cassandra/criteo-cassandra-exporter.yml
vendored
Normal file
167
dist/rules/cassandra/criteo-cassandra-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,167 @@
|
|||
groups:
|
||||
|
||||
- name: CriteoCassandraExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: CassandraHintsCount
|
||||
expr: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:storage:totalhints:count"}[1m]) > 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra hints count (instance {{ $labels.instance }})
|
||||
description: "Cassandra hints count has changed on {{ $labels.instance }} some nodes may go down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCompactionTaskPending
|
||||
expr: 'avg_over_time(cassandra_stats{name="org:apache:cassandra:metrics:compaction:pendingtasks:value"}[1m]) > 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra compaction task pending (instance {{ $labels.instance }})
|
||||
description: "Many Cassandra compaction tasks are pending. You might need to increase I/O capacity by adding nodes to the cluster.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraViewwriteLatency
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:viewwrite:viewwritelatency:99thpercentile",service="cas"} > 100000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra viewwrite latency (instance {{ $labels.instance }})
|
||||
description: "High viewwrite latency on {{ $labels.instance }} cassandra node\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraBadHacker
|
||||
expr: 'rate(cassandra_stats{name="org:apache:cassandra:metrics:client:authfailure:count"}[1m]) > 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra bad hacker (instance {{ $labels.instance }})
|
||||
description: "Increase of Cassandra authentication failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraNodeDown
|
||||
expr: 'sum(cassandra_stats{name="org:apache:cassandra:net:failuredetector:downendpointcount"}) by (service,group,cluster,env) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra node down (instance {{ $labels.instance }})
|
||||
description: "Cassandra node down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCommitlogPendingTasks
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:commitlog:pendingtasks:value"} > 15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra commitlog pending tasks (instance {{ $labels.instance }})
|
||||
description: "Unexpected number of Cassandra commitlog pending tasks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCompactionExecutorBlockedTasks
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:compactionexecutor:currentlyblockedtasks:count"} > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra compaction executor blocked tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra compaction executor tasks are blocked\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraFlushWriterBlockedTasks
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:memtableflushwriter:currentlyblockedtasks:count"} > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra flush writer blocked tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra flush writer tasks are blocked\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraRepairPendingTasks
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:antientropystage:pendingtasks:value"} > 2'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra repair pending tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra repair tasks are pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraRepairBlockedTasks
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:threadpools:internal:antientropystage:currentlyblockedtasks:count"} > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra repair blocked tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra repair tasks are blocked\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraConnectionTimeoutsTotal
|
||||
expr: 'rate(cassandra_stats{name="org:apache:cassandra:metrics:connection:totaltimeouts:count"}[1m]) > 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra connection timeouts total (instance {{ $labels.instance }})
|
||||
description: "Some connection between nodes are ending in timeout\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraStorageExceptions
|
||||
expr: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:storage:exceptions:count"}[1m]) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra storage exceptions (instance {{ $labels.instance }})
|
||||
description: "Something is going wrong with cassandra storage\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraTombstoneDump
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:table:tombstonescannedhistogram:99thpercentile"} > 1000'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra tombstone dump (instance {{ $labels.instance }})
|
||||
description: "Too much tombstones scanned in queries\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestUnvailableWrite
|
||||
expr: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:write:unavailables:count"}[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request unvailable write (instance {{ $labels.instance }})
|
||||
description: "Write failures have occurred because too many nodes are unavailable\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestUnvailableRead
|
||||
expr: 'changes(cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:read:unavailables:count"}[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request unvailable read (instance {{ $labels.instance }})
|
||||
description: "Read failures have occurred because too many nodes are unavailable\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestWriteFailure
|
||||
expr: 'increase(cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:write:failures:oneminuterate"}[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request write failure (instance {{ $labels.instance }})
|
||||
description: "A lot of write failures encountered. A write failure is a non-timeout exception encountered during a write request. Examine the reason map to find to the root cause. The most common cause for this type of error is when batch sizes are too large.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestReadFailure
|
||||
expr: 'increase(cassandra_stats{name="org:apache:cassandra:metrics:clientrequest:read:failures:oneminuterate"}[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request read failure (instance {{ $labels.instance }})
|
||||
description: "A lot of read failures encountered. A read failure is a non-timeout exception encountered during a read request. Examine the reason map to find to the root cause. The most common cause for this type of error is when batch sizes are too large.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCacheHitRateKeyCache
|
||||
expr: 'cassandra_stats{name="org:apache:cassandra:metrics:cache:keycache:hitrate:value"} < .85'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra cache hit rate key cache (instance {{ $labels.instance }})
|
||||
description: "Key cache hit rate is below 85%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
113
dist/rules/cassandra/instaclustr-cassandra-exporter.yml
vendored
Normal file
113
dist/rules/cassandra/instaclustr-cassandra-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,113 @@
|
|||
groups:
|
||||
|
||||
- name: InstaclustrCassandraExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: CassandraNodeIsUnavailable
|
||||
expr: 'sum(cassandra_endpoint_active) by (cassandra_cluster,instance,exported_endpoint) < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra Node is unavailable (instance {{ $labels.instance }})
|
||||
description: "Cassandra Node is unavailable - {{ $labels.cassandra_cluster }} {{ $labels.exported_endpoint }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraManyCompactionTasksArePending
|
||||
expr: 'cassandra_table_estimated_pending_compactions > 100'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra many compaction tasks are pending (instance {{ $labels.instance }})
|
||||
description: "Many Cassandra compaction tasks are pending - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCommitlogPendingTasks
|
||||
expr: 'cassandra_commit_log_pending_tasks > 15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra commitlog pending tasks (instance {{ $labels.instance }})
|
||||
description: "Cassandra commitlog pending tasks - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraCompactionExecutorBlockedTasks
|
||||
expr: 'cassandra_thread_pool_blocked_tasks{pool="CompactionExecutor"} > 15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra compaction executor blocked tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra compaction executor tasks are blocked - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraFlushWriterBlockedTasks
|
||||
expr: 'cassandra_thread_pool_blocked_tasks{pool="MemtableFlushWriter"} > 15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cassandra flush writer blocked tasks (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra flush writer tasks are blocked - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraConnectionTimeoutsTotal
|
||||
expr: 'avg(cassandra_client_request_timeouts_total) by (cassandra_cluster,instance) > 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra connection timeouts total (instance {{ $labels.instance }})
|
||||
description: "Some connection between nodes are ending in timeout - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraStorageExceptions
|
||||
expr: 'changes(cassandra_storage_exceptions_total[1m]) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra storage exceptions (instance {{ $labels.instance }})
|
||||
description: "Something is going wrong with cassandra storage - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraTombstoneDump
|
||||
expr: 'avg(cassandra_table_tombstones_scanned{quantile="0.99"}) by (instance,cassandra_cluster,keyspace) > 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra tombstone dump (instance {{ $labels.instance }})
|
||||
description: "Cassandra tombstone dump - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestUnvailableWrite
|
||||
expr: 'changes(cassandra_client_request_unavailable_exceptions_total{operation="write"}[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request unvailable write (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra client requests are unvailable to write - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestUnvailableRead
|
||||
expr: 'changes(cassandra_client_request_unavailable_exceptions_total{operation="read"}[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request unvailable read (instance {{ $labels.instance }})
|
||||
description: "Some Cassandra client requests are unvailable to read - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestWriteFailure
|
||||
expr: 'increase(cassandra_client_request_failures_total{operation="write"}[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request write failure (instance {{ $labels.instance }})
|
||||
description: "Read failures have occurred, ensure there are not too many unavailable nodes - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CassandraClientRequestReadFailure
|
||||
expr: 'increase(cassandra_client_request_failures_total{operation="read"}[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cassandra client request read failure (instance {{ $labels.instance }})
|
||||
description: "Read failures have occurred, ensure there are not too many unavailable nodes - {{ $labels.cassandra_cluster }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
122
dist/rules/ceph/embedded-exporter.yml
vendored
Normal file
122
dist/rules/ceph/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,122 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: CephState
|
||||
expr: 'ceph_health_status != 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Ceph State (instance {{ $labels.instance }})
|
||||
description: "Ceph instance unhealthy\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephMonitorClockSkew
|
||||
expr: 'abs(ceph_monitor_clock_skew_seconds) > 0.2'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph monitor clock skew (instance {{ $labels.instance }})
|
||||
description: "Ceph monitor clock skew detected. Please check ntp and hardware clock settings\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephMonitorLowSpace
|
||||
expr: 'ceph_monitor_avail_percent < 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph monitor low space (instance {{ $labels.instance }})
|
||||
description: "Ceph monitor storage is low.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephOsdDown
|
||||
expr: 'ceph_osd_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Ceph OSD Down (instance {{ $labels.instance }})
|
||||
description: "Ceph Object Storage Daemon Down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephHighOsdLatency
|
||||
expr: 'ceph_osd_perf_apply_latency_seconds > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph high OSD latency (instance {{ $labels.instance }})
|
||||
description: "Ceph Object Storage Daemon latency is high. Please check if it doesn't stuck in weird state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephOsdLowSpace
|
||||
expr: 'ceph_osd_utilization > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph OSD low space (instance {{ $labels.instance }})
|
||||
description: "Ceph Object Storage Daemon is going out of space. Please add more disks.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephOsdReweighted
|
||||
expr: 'ceph_osd_weight < 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph OSD reweighted (instance {{ $labels.instance }})
|
||||
description: "Ceph Object Storage Daemon takes too much time to resize.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgDown
|
||||
expr: 'ceph_pg_down > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Ceph PG down (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are down. Please ensure that all the data are available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgIncomplete
|
||||
expr: 'ceph_pg_incomplete > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Ceph PG incomplete (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are incomplete. Please ensure that all the data are available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgInconsistent
|
||||
expr: 'ceph_pg_inconsistent > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph PG inconsistent (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are inconsistent. Data is available but inconsistent across nodes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgActivationLong
|
||||
expr: 'ceph_pg_activating > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph PG activation long (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are too long to activate.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgBackfillFull
|
||||
expr: 'ceph_pg_backfill_toofull > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Ceph PG backfill full (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are located on full Object Storage Daemon on cluster. Those PGs can be unavailable shortly. Please check OSDs, change weight or reconfigure CRUSH rules.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CephPgUnavailable
|
||||
expr: 'ceph_pg_total - ceph_pg_active > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Ceph PG unavailable (instance {{ $labels.instance }})
|
||||
description: "Some Ceph placement groups are unavailable.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/consul/consul-exporter.yml
vendored
Normal file
32
dist/rules/consul/consul-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: ConsulExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: ConsulServiceHealthcheckFailed
|
||||
expr: 'consul_catalog_service_node_healthy == 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Consul service healthcheck failed (instance {{ $labels.instance }})
|
||||
description: "Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ConsulMissingMasterNode
|
||||
expr: 'consul_raft_peers < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Consul missing master node (instance {{ $labels.instance }})
|
||||
description: "Numbers of consul raft peers should be 3, in order to preserve quorum.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ConsulAgentUnhealthy
|
||||
expr: 'consul_health_node_status{status="critical"} == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Consul agent unhealthy (instance {{ $labels.instance }})
|
||||
description: "A Consul agent is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/coredns/embedded-exporter.yml
vendored
Normal file
14
dist/rules/coredns/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: CorednsPanicCount
|
||||
expr: 'increase(coredns_panics_total[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: CoreDNS Panic Count (instance {{ $labels.instance }})
|
||||
description: "Number of CoreDNS panics encountered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
59
dist/rules/cortex/embedded-exporter.yml
vendored
Normal file
59
dist/rules/cortex/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,59 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: CortexRulerConfigurationReloadFailure
|
||||
expr: 'cortex_ruler_config_last_reload_successful != 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Cortex ruler configuration reload failure (instance {{ $labels.instance }})
|
||||
description: "Cortex ruler configuration reload failure (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CortexNotConnectedToAlertmanager
|
||||
expr: 'cortex_prometheus_notifications_alertmanagers_discovered < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cortex not connected to Alertmanager (instance {{ $labels.instance }})
|
||||
description: "Cortex not connected to Alertmanager (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CortexNotificationAreBeingDropped
|
||||
expr: 'rate(cortex_prometheus_notifications_dropped_total[5m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cortex notification are being dropped (instance {{ $labels.instance }})
|
||||
description: "Cortex notification are being dropped due to errors (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CortexNotificationError
|
||||
expr: 'rate(cortex_prometheus_notifications_errors_total[5m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cortex notification error (instance {{ $labels.instance }})
|
||||
description: "Cortex is failing when sending alert notifications (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CortexIngesterUnhealthy
|
||||
expr: 'cortex_ring_members{state="Unhealthy", name="ingester"} > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cortex ingester unhealthy (instance {{ $labels.instance }})
|
||||
description: "Cortex has an unhealthy ingester\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: CortexFrontendQueriesStuck
|
||||
expr: 'sum by (job) (cortex_query_frontend_queue_length) > 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Cortex frontend queries stuck (instance {{ $labels.instance }})
|
||||
description: "There are queued up queries in query-frontend.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
59
dist/rules/docker-containers/google-cadvisor.yml
vendored
Normal file
59
dist/rules/docker-containers/google-cadvisor.yml
vendored
Normal file
|
|
@ -0,0 +1,59 @@
|
|||
groups:
|
||||
|
||||
- name: GoogleCadvisor
|
||||
|
||||
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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ContainerCpuUsage
|
||||
expr: '(sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Container CPU usage (instance {{ $labels.instance }})
|
||||
description: "Container CPU usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ContainerMemoryUsage
|
||||
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 Memory usage (instance {{ $labels.instance }})
|
||||
description: "Container Memory usage is above 80%\n VALUE = {{ $value }}\n 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%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ContainerHighThrottleRate
|
||||
expr: 'rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Container high throttle rate (instance {{ $labels.instance }})
|
||||
description: "Container is being throttled\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
140
dist/rules/elasticsearch/justwatchcom-elasticsearch-exporter.yml
vendored
Normal file
140
dist/rules/elasticsearch/justwatchcom-elasticsearch-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,140 @@
|
|||
groups:
|
||||
|
||||
- name: JustwatchcomElasticsearchExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: ElasticsearchHeapUsageTooHigh
|
||||
expr: '(elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch Heap Usage Too High (instance {{ $labels.instance }})
|
||||
description: "The heap usage is over 90%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchHeapUsageWarning
|
||||
expr: '(elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch Heap Usage warning (instance {{ $labels.instance }})
|
||||
description: "The heap usage is over 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchDiskOutOfSpace
|
||||
expr: 'elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch disk out of space (instance {{ $labels.instance }})
|
||||
description: "The disk usage is over 90%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchDiskSpaceLow
|
||||
expr: 'elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 20'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch disk space low (instance {{ $labels.instance }})
|
||||
description: "The disk usage is over 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchClusterRed
|
||||
expr: 'elasticsearch_cluster_health_status{color="red"} == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch Cluster Red (instance {{ $labels.instance }})
|
||||
description: "Elastic Cluster Red status\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchClusterYellow
|
||||
expr: 'elasticsearch_cluster_health_status{color="yellow"} == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch Cluster Yellow (instance {{ $labels.instance }})
|
||||
description: "Elastic Cluster Yellow status\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchHealthyNodes
|
||||
expr: 'elasticsearch_cluster_health_number_of_nodes < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch Healthy Nodes (instance {{ $labels.instance }})
|
||||
description: "Missing node in Elasticsearch cluster\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchHealthyDataNodes
|
||||
expr: 'elasticsearch_cluster_health_number_of_data_nodes < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch Healthy Data Nodes (instance {{ $labels.instance }})
|
||||
description: "Missing data node in Elasticsearch cluster\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchRelocatingShards
|
||||
expr: 'elasticsearch_cluster_health_relocating_shards > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Elasticsearch relocating shards (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch is relocating shards\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchRelocatingShardsTooLong
|
||||
expr: 'elasticsearch_cluster_health_relocating_shards > 0'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch relocating shards too long (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch has been relocating shards for 15min\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchInitializingShards
|
||||
expr: 'elasticsearch_cluster_health_initializing_shards > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Elasticsearch initializing shards (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch is initializing shards\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchInitializingShardsTooLong
|
||||
expr: 'elasticsearch_cluster_health_initializing_shards > 0'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch initializing shards too long (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch has been initializing shards for 15 min\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchUnassignedShards
|
||||
expr: 'elasticsearch_cluster_health_unassigned_shards > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Elasticsearch unassigned shards (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch has unassigned shards\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchPendingTasks
|
||||
expr: 'elasticsearch_cluster_health_number_of_pending_tasks > 0'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch pending tasks (instance {{ $labels.instance }})
|
||||
description: "Elasticsearch has pending tasks. Cluster works slowly.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ElasticsearchNoNewDocuments
|
||||
expr: 'increase(elasticsearch_indices_docs{es_data_node="true"}[10m]) < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Elasticsearch no new documents (instance {{ $labels.instance }})
|
||||
description: "No new documents for 10 min!\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
122
dist/rules/etcd/embedded-exporter.yml
vendored
Normal file
122
dist/rules/etcd/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,122 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: EtcdInsufficientMembers
|
||||
expr: 'count(etcd_server_id) % 2 == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Etcd insufficient Members (instance {{ $labels.instance }})
|
||||
description: "Etcd cluster should have an odd number of members\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdNoLeader
|
||||
expr: 'etcd_server_has_leader == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Etcd no Leader (instance {{ $labels.instance }})
|
||||
description: "Etcd cluster have no leader\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfLeaderChanges
|
||||
expr: 'increase(etcd_server_leader_changes_seen_total[10m]) > 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high number of leader changes (instance {{ $labels.instance }})
|
||||
description: "Etcd leader changed more than 2 times during 10 minutes\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfFailedGrpcRequests
|
||||
expr: 'sum(rate(grpc_server_handled_total{grpc_code!="OK"}[1m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total[1m])) BY (grpc_service, grpc_method) > 0.01'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high number of failed GRPC requests (instance {{ $labels.instance }})
|
||||
description: "More than 1% GRPC request failure detected in Etcd\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfFailedGrpcRequests
|
||||
expr: 'sum(rate(grpc_server_handled_total{grpc_code!="OK"}[1m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total[1m])) BY (grpc_service, grpc_method) > 0.05'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Etcd high number of failed GRPC requests (instance {{ $labels.instance }})
|
||||
description: "More than 5% GRPC request failure detected in Etcd\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdGrpcRequestsSlow
|
||||
expr: 'histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{grpc_type="unary"}[1m])) by (grpc_service, grpc_method, le)) > 0.15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd GRPC requests slow (instance {{ $labels.instance }})
|
||||
description: "GRPC requests slowing down, 99th percentile is over 0.15s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfFailedHttpRequests
|
||||
expr: 'sum(rate(etcd_http_failed_total[1m])) BY (method) / sum(rate(etcd_http_received_total[1m])) BY (method) > 0.01'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high number of failed HTTP requests (instance {{ $labels.instance }})
|
||||
description: "More than 1% HTTP failure detected in Etcd\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfFailedHttpRequests
|
||||
expr: 'sum(rate(etcd_http_failed_total[1m])) BY (method) / sum(rate(etcd_http_received_total[1m])) BY (method) > 0.05'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Etcd high number of failed HTTP requests (instance {{ $labels.instance }})
|
||||
description: "More than 5% HTTP failure detected in Etcd\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHttpRequestsSlow
|
||||
expr: 'histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[1m])) > 0.15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd HTTP requests slow (instance {{ $labels.instance }})
|
||||
description: "HTTP requests slowing down, 99th percentile is over 0.15s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdMemberCommunicationSlow
|
||||
expr: 'histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[1m])) > 0.15'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd member communication slow (instance {{ $labels.instance }})
|
||||
description: "Etcd member communication slowing down, 99th percentile is over 0.15s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighNumberOfFailedProposals
|
||||
expr: 'increase(etcd_server_proposals_failed_total[1h]) > 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high number of failed proposals (instance {{ $labels.instance }})
|
||||
description: "Etcd server got more than 5 failed proposals past hour\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighFsyncDurations
|
||||
expr: 'histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[1m])) > 0.5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high fsync durations (instance {{ $labels.instance }})
|
||||
description: "Etcd WAL fsync duration increasing, 99th percentile is over 0.5s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: EtcdHighCommitDurations
|
||||
expr: 'histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[1m])) > 0.25'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Etcd high commit durations (instance {{ $labels.instance }})
|
||||
description: "Etcd commit duration increasing, 99th percentile is over 0.25s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/freeswitch/znerol-freeswitch-exporter.yml
vendored
Normal file
32
dist/rules/freeswitch/znerol-freeswitch-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: ZnerolFreeswitchExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: FreeswitchDown
|
||||
expr: 'freeswitch_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Freeswitch down (instance {{ $labels.instance }})
|
||||
description: "Freeswitch is unresponsive\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: FreeswitchSessionsWarning
|
||||
expr: '(freeswitch_session_active * 100 / freeswitch_session_limit) > 80'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Freeswitch Sessions Warning (instance {{ $labels.instance }})
|
||||
description: "High sessions usage on {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: FreeswitchSessionsCritical
|
||||
expr: '(freeswitch_session_active * 100 / freeswitch_session_limit) > 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Freeswitch Sessions Critical (instance {{ $labels.instance }})
|
||||
description: "High sessions usage on {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
131
dist/rules/haproxy/embedded-exporter-v2.yml
vendored
Normal file
131
dist/rules/haproxy/embedded-exporter-v2.yml
vendored
Normal file
|
|
@ -0,0 +1,131 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporterV2
|
||||
|
||||
rules:
|
||||
|
||||
- alert: HaproxyHighHttp4xxErrorRateBackend
|
||||
expr: '((sum by (proxy) (rate(haproxy_server_http_responses_total{code="4xx"}[1m])) / sum by (proxy) (rate(haproxy_server_http_responses_total[1m]))) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 4xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 4xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp5xxErrorRateBackend
|
||||
expr: '((sum by (proxy) (rate(haproxy_server_http_responses_total{code="5xx"}[1m])) / sum by (proxy) (rate(haproxy_server_http_responses_total[1m]))) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 5xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 5xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp4xxErrorRateServer
|
||||
expr: '((sum by (server) (rate(haproxy_server_http_responses_total{code="4xx"}[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]))) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 4xx error rate server (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 4xx (> 5%) on server {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp5xxErrorRateServer
|
||||
expr: '((sum by (server) (rate(haproxy_server_http_responses_total{code="5xx"}[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]))) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 5xx error rate server (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 5xx (> 5%) on server {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerResponseErrors
|
||||
expr: '(sum by (server) (rate(haproxy_server_response_errors_total[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]))) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy server response errors (instance {{ $labels.instance }})
|
||||
description: "Too many response errors to {{ $labels.server }} server (> 5%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyBackendConnectionErrors
|
||||
expr: '(sum by (proxy) (rate(haproxy_backend_connection_errors_total[1m]))) > 100'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy backend connection errors (instance {{ $labels.instance }})
|
||||
description: "Too many connection errors to {{ $labels.fqdn }}/{{ $labels.backend }} backend (> 100 req/s). Request throughput may be too high.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerConnectionErrors
|
||||
expr: '(sum by (proxy) (rate(haproxy_server_connection_errors_total[1m]))) > 100'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy server connection errors (instance {{ $labels.instance }})
|
||||
description: "Too many connection errors to {{ $labels.server }} server (> 100 req/s). Request throughput may be too high.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyBackendMaxActiveSession>80%
|
||||
expr: '((haproxy_server_max_sessions >0) * 100) / (haproxy_server_limit_sessions > 0) > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy backend max active session > 80% (instance {{ $labels.instance }})
|
||||
description: "Session limit from backend {{ $labels.proxy }} to server {{ $labels.server }} reached 80% of limit - {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyPendingRequests
|
||||
expr: 'sum by (proxy) (rate(haproxy_backend_current_queue[2m])) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy pending requests (instance {{ $labels.instance }})
|
||||
description: "Some HAProxy requests are pending on {{ $labels.proxy }} - {{ $value | printf \"%.2f\"}}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHttpSlowingDown
|
||||
expr: 'avg by (instance, proxy) (haproxy_backend_max_total_time_seconds) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy HTTP slowing down (instance {{ $labels.instance }})
|
||||
description: "Average request time is increasing - {{ $value | printf \"%.2f\"}}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyRetryHigh
|
||||
expr: 'sum by (proxy) (rate(haproxy_backend_retry_warnings_total[1m])) > 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy retry high (instance {{ $labels.instance }})
|
||||
description: "High rate of retry on {{ $labels.proxy }} - {{ $value | printf \"%.2f\"}}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHasNoAliveBackends
|
||||
expr: 'haproxy_backend_active_servers + haproxy_backend_backup_servers == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAproxy has no alive backends (instance {{ $labels.instance }})
|
||||
description: "HAProxy has no alive active or backup backends for {{ $labels.proxy }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyFrontendSecurityBlockedRequests
|
||||
expr: 'sum by (proxy) (rate(haproxy_frontend_denied_connections_total[2m])) > 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy frontend security blocked requests (instance {{ $labels.instance }})
|
||||
description: "HAProxy is blocking requests for security reason\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerHealthcheckFailure
|
||||
expr: 'increase(haproxy_server_check_failures_total[1m]) > 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy server healthcheck failure (instance {{ $labels.instance }})
|
||||
description: "Some server healthcheck are failing on {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
149
dist/rules/haproxy/haproxy-exporter-v1.yml
vendored
Normal file
149
dist/rules/haproxy/haproxy-exporter-v1.yml
vendored
Normal file
|
|
@ -0,0 +1,149 @@
|
|||
groups:
|
||||
|
||||
- name: HaproxyExporterV1
|
||||
|
||||
rules:
|
||||
|
||||
- alert: HaproxyDown
|
||||
expr: 'haproxy_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy down (instance {{ $labels.instance }})
|
||||
description: "HAProxy down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp4xxErrorRateBackend
|
||||
expr: 'sum by (backend) (rate(haproxy_server_http_responses_total{code="4xx"}[1m])) / sum by (backend) (rate(haproxy_server_http_responses_total[1m]) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 4xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 4xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp5xxErrorRateBackend
|
||||
expr: 'sum by (backend) (rate(haproxy_server_http_responses_total{code="5xx"}[1m])) / sum by (backend) (rate(haproxy_server_http_responses_total[1m]) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 5xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 5xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp4xxErrorRateServer
|
||||
expr: 'sum by (server) (rate(haproxy_server_http_responses_total{code="4xx"}[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 4xx error rate server (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 4xx (> 5%) on server {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHighHttp5xxErrorRateServer
|
||||
expr: 'sum by (server) (rate(haproxy_server_http_responses_total{code="5xx"}[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy high HTTP 5xx error rate server (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 5xx (> 5%) on server {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerResponseErrors
|
||||
expr: 'sum by (server) (rate(haproxy_server_response_errors_total[1m])) / sum by (server) (rate(haproxy_server_http_responses_total[1m]) * 100) > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy server response errors (instance {{ $labels.instance }})
|
||||
description: "Too many response errors to {{ $labels.server }} server (> 5%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyBackendConnectionErrors
|
||||
expr: 'sum by (backend) (rate(haproxy_backend_connection_errors_total[1m])) > 100'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy backend connection errors (instance {{ $labels.instance }})
|
||||
description: "Too many connection errors to {{ $labels.fqdn }}/{{ $labels.backend }} backend (> 100 req/s). Request throughput may be too high.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerConnectionErrors
|
||||
expr: 'sum by (server) (rate(haproxy_server_connection_errors_total[1m])) > 100'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy server connection errors (instance {{ $labels.instance }})
|
||||
description: "Too many connection errors to {{ $labels.server }} server (> 100 req/s). Request throughput may be too high.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyBackendMaxActiveSession
|
||||
expr: '((sum by (backend) (avg_over_time(haproxy_backend_max_sessions[2m])) / sum by (backend) (avg_over_time(haproxy_backend_limit_sessions[2m]))) * 100) > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy backend max active session (instance {{ $labels.instance }})
|
||||
description: "HAproxy backend {{ $labels.fqdn }}/{{ $labels.backend }} is reaching session limit (> 80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyPendingRequests
|
||||
expr: 'sum by (backend) (haproxy_backend_current_queue) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy pending requests (instance {{ $labels.instance }})
|
||||
description: "Some HAProxy requests are pending on {{ $labels.fqdn }}/{{ $labels.backend }} backend\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyHttpSlowingDown
|
||||
expr: 'avg by (backend) (haproxy_backend_http_total_time_average_seconds) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy HTTP slowing down (instance {{ $labels.instance }})
|
||||
description: "Average request time is increasing\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyRetryHigh
|
||||
expr: 'sum by (backend) (rate(haproxy_backend_retry_warnings_total[1m])) > 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy retry high (instance {{ $labels.instance }})
|
||||
description: "High rate of retry on {{ $labels.fqdn }}/{{ $labels.backend }} backend\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyBackendDown
|
||||
expr: 'haproxy_backend_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy backend down (instance {{ $labels.instance }})
|
||||
description: "HAProxy backend is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerDown
|
||||
expr: 'haproxy_server_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: HAProxy server down (instance {{ $labels.instance }})
|
||||
description: "HAProxy server is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyFrontendSecurityBlockedRequests
|
||||
expr: 'sum by (frontend) (rate(haproxy_frontend_requests_denied_total[2m])) > 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy frontend security blocked requests (instance {{ $labels.instance }})
|
||||
description: "HAProxy is blocking requests for security reason\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HaproxyServerHealthcheckFailure
|
||||
expr: 'increase(haproxy_server_check_failures_total[1m]) > 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: HAProxy server healthcheck failure (instance {{ $labels.instance }})
|
||||
description: "Some server healthcheck are failing on {{ $labels.server }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/hashicorp-vault/embedded-exporter.yml
vendored
Normal file
32
dist/rules/hashicorp-vault/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: VaultSealed
|
||||
expr: 'vault_core_unsealed == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Vault sealed (instance {{ $labels.instance }})
|
||||
description: "Vault instance is sealed on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: VaultTooManyPendingTokens
|
||||
expr: 'avg(vault_token_create_count - vault_token_store_count) > 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Vault too many pending tokens (instance {{ $labels.instance }})
|
||||
description: "Too many pending tokens {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: VaultTooManyInfinityTokens
|
||||
expr: 'vault_token_count_by_ttl{creation_ttl="+Inf"} > 3'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Vault too many infinity tokens (instance {{ $labels.instance }})
|
||||
description: "Too many infinity tokens {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
311
dist/rules/host-and-hardware/node-exporter.yml
vendored
Normal file
311
dist/rules/host-and-hardware/node-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,311 @@
|
|||
groups:
|
||||
|
||||
- name: NodeExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: HostOutOfMemory
|
||||
expr: 'node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host out of memory (instance {{ $labels.instance }})
|
||||
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostMemoryUnderMemoryPressure
|
||||
expr: 'rate(node_vmstat_pgmajfault[1m]) > 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host memory under memory pressure (instance {{ $labels.instance }})
|
||||
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualNetworkThroughputIn
|
||||
expr: 'sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual network throughput in (instance {{ $labels.instance }})
|
||||
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualNetworkThroughputOut
|
||||
expr: 'sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual network throughput out (instance {{ $labels.instance }})
|
||||
description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualDiskReadRate
|
||||
expr: 'sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual disk read rate (instance {{ $labels.instance }})
|
||||
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualDiskWriteRate
|
||||
expr: 'sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual disk write rate (instance {{ $labels.instance }})
|
||||
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostOutOfDiskSpace
|
||||
expr: '(node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host out of disk space (instance {{ $labels.instance }})
|
||||
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostDiskWillFillIn24Hours
|
||||
expr: '(node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
|
||||
description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostOutOfInodes
|
||||
expr: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host out of inodes (instance {{ $labels.instance }})
|
||||
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostInodesWillFillIn24Hours
|
||||
expr: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
|
||||
description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualDiskReadLatency
|
||||
expr: 'rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual disk read latency (instance {{ $labels.instance }})
|
||||
description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostUnusualDiskWriteLatency
|
||||
expr: 'rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host unusual disk write latency (instance {{ $labels.instance }})
|
||||
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostHighCpuLoad
|
||||
expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host high CPU load (instance {{ $labels.instance }})
|
||||
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostCpuStealNoisyNeighbor
|
||||
expr: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
|
||||
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostCpuHighIowait
|
||||
expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 5'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host CPU high iowait (instance {{ $labels.instance }})
|
||||
description: "CPU iowait > 5%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostContextSwitching
|
||||
expr: '(rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 1000'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host context switching (instance {{ $labels.instance }})
|
||||
description: "Context switching is growing on node (> 1000 / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostSwapIsFillingUp
|
||||
expr: '(1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host swap is filling up (instance {{ $labels.instance }})
|
||||
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostSystemdServiceCrashed
|
||||
expr: 'node_systemd_unit_state{state="failed"} == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host systemd service crashed (instance {{ $labels.instance }})
|
||||
description: "systemd service crashed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostPhysicalComponentTooHot
|
||||
expr: 'node_hwmon_temp_celsius > 75'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host physical component too hot (instance {{ $labels.instance }})
|
||||
description: "Physical hardware component too hot\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostNodeOvertemperatureAlarm
|
||||
expr: 'node_hwmon_temp_crit_alarm_celsius == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Host node overtemperature alarm (instance {{ $labels.instance }})
|
||||
description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostRaidArrayGotInactive
|
||||
expr: 'node_md_state{state="inactive"} > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Host RAID array got inactive (instance {{ $labels.instance }})
|
||||
description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostRaidDiskFailure
|
||||
expr: 'node_md_disks{state="failed"} > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host RAID disk failure (instance {{ $labels.instance }})
|
||||
description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostKernelVersionDeviations
|
||||
expr: 'count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1'
|
||||
for: 6h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host kernel version deviations (instance {{ $labels.instance }})
|
||||
description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostOomKillDetected
|
||||
expr: 'increase(node_vmstat_oom_kill[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host OOM kill detected (instance {{ $labels.instance }})
|
||||
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostEdacCorrectableErrorsDetected
|
||||
expr: 'increase(node_edac_correctable_errors_total[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }})
|
||||
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostEdacUncorrectableErrorsDetected
|
||||
expr: 'node_edac_uncorrectable_errors_total > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})
|
||||
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostNetworkReceiveErrors
|
||||
expr: 'rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host Network Receive Errors (instance {{ $labels.instance }})
|
||||
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostNetworkTransmitErrors
|
||||
expr: 'rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host Network Transmit Errors (instance {{ $labels.instance }})
|
||||
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostNetworkInterfaceSaturated
|
||||
expr: '(rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host Network Interface Saturated (instance {{ $labels.instance }})
|
||||
description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostNetworkBondDegraded
|
||||
expr: '(node_bonding_active - node_bonding_slaves) != 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host Network Bond Degraded (instance {{ $labels.instance }})
|
||||
description: "Bond \"{{ $labels.device }}\" degraded on \"{{ $labels.instance }}\".\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostConntrackLimit
|
||||
expr: 'node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host conntrack limit (instance {{ $labels.instance }})
|
||||
description: "The number of conntrack is approaching limit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostClockSkew
|
||||
expr: '(node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host clock skew (instance {{ $labels.instance }})
|
||||
description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostClockNotSynchronising
|
||||
expr: 'min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host clock not synchronising (instance {{ $labels.instance }})
|
||||
description: "Clock not synchronising. Ensure NTP is configured on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostRequiresReboot
|
||||
expr: 'node_reboot_required > 0'
|
||||
for: 4h
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Host requires reboot (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.instance }} requires a reboot.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
95
dist/rules/istio/embedded-exporter.yml
vendored
Normal file
95
dist/rules/istio/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,95 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: IstioKubernetesGatewayAvailabilityDrop
|
||||
expr: 'min(kube_deployment_status_replicas_available{deployment="istio-ingressgateway", namespace="istio-system"}) without (instance, pod) < 2'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio Kubernetes gateway availability drop (instance {{ $labels.instance }})
|
||||
description: "Gateway pods have dropped. Inbound traffic will likely be affected.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioPilotHighTotalRequestRate
|
||||
expr: 'sum(rate(pilot_xds_push_errors[1m])) / sum(rate(pilot_xds_pushes[1m])) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio Pilot high total request rate (instance {{ $labels.instance }})
|
||||
description: "Number of Istio Pilot push errors is too high (> 5%). Envoy sidecars might have outdated configuration.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioMixerPrometheusDispatchesLow
|
||||
expr: 'sum(rate(mixer_runtime_dispatches_total{adapter=~"prometheus"}[1m])) < 180'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio Mixer Prometheus dispatches low (instance {{ $labels.instance }})
|
||||
description: "Number of Mixer dispatches to Prometheus is too low. Istio metrics might not be being exported properly.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioHighTotalRequestRate
|
||||
expr: 'sum(rate(istio_requests_total{reporter="destination"}[5m])) > 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio high total request rate (instance {{ $labels.instance }})
|
||||
description: "Global request rate in the service mesh is unusually high.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioLowTotalRequestRate
|
||||
expr: 'sum(rate(istio_requests_total{reporter="destination"}[5m])) < 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio low total request rate (instance {{ $labels.instance }})
|
||||
description: "Global request rate in the service mesh is unusually low.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioHigh4xxErrorRate
|
||||
expr: 'sum(rate(istio_requests_total{reporter="destination", response_code=~"4.*"}[5m])) / sum(rate(istio_requests_total{reporter="destination"}[5m])) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio high 4xx error rate (instance {{ $labels.instance }})
|
||||
description: "High percentage of HTTP 5xx responses in Istio (> 5%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioHigh5xxErrorRate
|
||||
expr: 'sum(rate(istio_requests_total{reporter="destination", response_code=~"5.*"}[5m])) / sum(rate(istio_requests_total{reporter="destination"}[5m])) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio high 5xx error rate (instance {{ $labels.instance }})
|
||||
description: "High percentage of HTTP 5xx responses in Istio (> 5%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioHighRequestLatency
|
||||
expr: 'rate(istio_request_duration_milliseconds_sum{reporter="destination"}[1m]) / rate(istio_request_duration_milliseconds_count{reporter="destination"}[1m]) > 100'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio high request latency (instance {{ $labels.instance }})
|
||||
description: "Istio average requests execution is longer than 100ms.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioLatency99Percentile
|
||||
expr: 'histogram_quantile(0.99, rate(istio_request_duration_milliseconds_bucket[1m])) > 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Istio latency 99 percentile (instance {{ $labels.instance }})
|
||||
description: "Istio 1% slowest requests are longer than 1s.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IstioPilotDuplicateEntry
|
||||
expr: 'sum(rate(pilot_duplicate_envoy_clusters{}[5m])) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Istio Pilot Duplicate Entry (instance {{ $labels.instance }})
|
||||
description: "Istio pilot duplicate entry error.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
68
dist/rules/jenkins/metric-plugin.yml
vendored
Normal file
68
dist/rules/jenkins/metric-plugin.yml
vendored
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
groups:
|
||||
|
||||
- name: MetricPlugin
|
||||
|
||||
rules:
|
||||
|
||||
- alert: JenkinsOffline
|
||||
expr: 'jenkins_node_offline_value > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Jenkins offline (instance {{ $labels.instance }})
|
||||
description: "Jenkins offline: `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsHealthcheck
|
||||
expr: 'jenkins_health_check_score < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Jenkins healthcheck (instance {{ $labels.instance }})
|
||||
description: "Jenkins healthcheck score: {{$value}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsOutdatedPlugins
|
||||
expr: 'sum(jenkins_plugins_withUpdate) by (instance) > 3'
|
||||
for: 1d
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Jenkins outdated plugins (instance {{ $labels.instance }})
|
||||
description: "{{ $value }} plugins need update\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsBuildsHealthScore
|
||||
expr: 'default_jenkins_builds_health_score < 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Jenkins builds health score (instance {{ $labels.instance }})
|
||||
description: "Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsRunFailureTotal
|
||||
expr: 'delta(jenkins_runs_failure_total[1h]) > 100'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Jenkins run failure total (instance {{ $labels.instance }})
|
||||
description: "Job run failures: ({{$value}}) {{$labels.jenkins_job}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsBuildTestsFailing
|
||||
expr: 'default_jenkins_builds_last_build_tests_failing > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Jenkins build tests failing (instance {{ $labels.instance }})
|
||||
description: "Last build tests failed: {{$labels.jenkins_job}}. Failed build Tests for job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JenkinsLastBuildFailed
|
||||
expr: 'default_jenkins_builds_last_build_result_ordinal == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Jenkins last build failed (instance {{ $labels.instance }})
|
||||
description: "Last build failed: {{$labels.jenkins_job}}. Failed build for job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/juniper/czerwonk-junos-exporter.yml
vendored
Normal file
32
dist/rules/juniper/czerwonk-junos-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: CzerwonkJunosExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: JuniperSwitchDown
|
||||
expr: 'junos_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Juniper switch down (instance {{ $labels.instance }})
|
||||
description: "The switch appears to be down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JuniperHighBandwidthUsage1gib
|
||||
expr: 'rate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.90'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Juniper high Bandwidth Usage 1GiB (instance {{ $labels.instance }})
|
||||
description: "Interface is highly saturated. (> 0.90GiB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: JuniperHighBandwidthUsage1gib
|
||||
expr: 'rate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.80'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Juniper high Bandwidth Usage 1GiB (instance {{ $labels.instance }})
|
||||
description: "Interface is getting saturated. (> 0.80GiB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/jvm/jvm-exporter.yml
vendored
Normal file
14
dist/rules/jvm/jvm-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: JvmExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: JvmMemoryFillingUp
|
||||
expr: '(sum by (instance)(jvm_memory_used_bytes{area="heap"}) / sum by (instance)(jvm_memory_max_bytes{area="heap"})) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: JVM memory filling up (instance {{ $labels.instance }})
|
||||
description: "JVM memory is filling up (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/kafka/danielqsj-kafka-exporter.yml
vendored
Normal file
23
dist/rules/kafka/danielqsj-kafka-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: DanielqsjKafkaExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: KafkaTopicsReplicas
|
||||
expr: 'sum(kafka_topic_partition_in_sync_replica) by (topic) < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kafka topics replicas (instance {{ $labels.instance }})
|
||||
description: "Kafka topic in-sync partition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KafkaConsumersGroup
|
||||
expr: 'sum(kafka_consumergroup_lag) by (consumergroup) > 50'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kafka consumers group (instance {{ $labels.instance }})
|
||||
description: "Kafka consumers group\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/kafka/linkedin-kafka-exporter.yml
vendored
Normal file
23
dist/rules/kafka/linkedin-kafka-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: LinkedinKafkaExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: KafkaTopicOffsetDecreased
|
||||
expr: 'delta(kafka_burrow_partition_current_offset[1m]) < 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kafka topic offset decreased (instance {{ $labels.instance }})
|
||||
description: "Kafka topic offset has decreased\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KafkaConsumerLag
|
||||
expr: 'kafka_burrow_topic_partition_offset - on(partition, cluster, topic) group_right() kafka_burrow_partition_current_offset >= (kafka_burrow_topic_partition_offset offset 15m - on(partition, cluster, topic) group_right() kafka_burrow_partition_current_offset offset 15m) AND kafka_burrow_topic_partition_offset - on(partition, cluster, topic) group_right() kafka_burrow_partition_current_offset > 0'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kafka consumer lag (instance {{ $labels.instance }})
|
||||
description: "Kafka consumer has a 30 minutes and increasing lag\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
302
dist/rules/kubernetes/kubestate-exporter.yml
vendored
Normal file
302
dist/rules/kubernetes/kubestate-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,302 @@
|
|||
groups:
|
||||
|
||||
- name: KubestateExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: KubernetesNodeReady
|
||||
expr: 'kube_node_status_condition{condition="Ready",status="true"} == 0'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Node ready (instance {{ $labels.instance }})
|
||||
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesMemoryPressure
|
||||
expr: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes memory pressure (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDiskPressure
|
||||
expr: 'kube_node_status_condition{condition="DiskPressure",status="true"} == 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes disk pressure (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesOutOfDisk
|
||||
expr: 'kube_node_status_condition{condition="OutOfDisk",status="true"} == 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes out of disk (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.node }} has OutOfDisk condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesOutOfCapacity
|
||||
expr: 'sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes out of capacity (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.node }} is out of capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesContainerOomKiller
|
||||
expr: '(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes container oom killer (instance {{ $labels.instance }})
|
||||
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesJobFailed
|
||||
expr: 'kube_job_status_failed > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Job failed (instance {{ $labels.instance }})
|
||||
description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesCronjobSuspended
|
||||
expr: 'kube_cronjob_spec_suspend != 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
|
||||
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPersistentvolumeclaimPending
|
||||
expr: 'kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
|
||||
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesVolumeOutOfDiskSpace
|
||||
expr: 'kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
|
||||
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesVolumeFullInFourDays
|
||||
expr: 'predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Volume full in four days (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPersistentvolumeError
|
||||
expr: 'kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
|
||||
description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetDown
|
||||
expr: '(kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
|
||||
description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesHpaScalingAbility
|
||||
expr: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes HPA scaling ability (instance {{ $labels.instance }})
|
||||
description: "Pod is unable to scale\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesHpaMetricAvailability
|
||||
expr: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes HPA metric availability (instance {{ $labels.instance }})
|
||||
description: "HPA is not able to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesHpaScaleCapability
|
||||
expr: 'kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Kubernetes HPA scale capability (instance {{ $labels.instance }})
|
||||
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPodNotHealthy
|
||||
expr: 'min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
|
||||
description: "Pod has been in a non-ready state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPodCrashLooping
|
||||
expr: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
|
||||
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesReplicassetMismatch
|
||||
expr: 'kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes ReplicasSet mismatch (instance {{ $labels.instance }})
|
||||
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDeploymentReplicasMismatch
|
||||
expr: 'kube_deployment_spec_replicas != kube_deployment_status_replicas_available'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
|
||||
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetReplicasMismatch
|
||||
expr: 'kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
|
||||
description: "A StatefulSet does not match the expected number of replicas.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDeploymentGenerationMismatch
|
||||
expr: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
|
||||
description: "A Deployment has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetGenerationMismatch
|
||||
expr: 'kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
|
||||
description: "A StatefulSet has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetUpdateNotRolledOut
|
||||
expr: 'max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
|
||||
description: "StatefulSet update has not been rolled out.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDaemonsetRolloutStuck
|
||||
expr: 'kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
|
||||
description: "Some Pods of DaemonSet are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDaemonsetMisscheduled
|
||||
expr: 'kube_daemonset_status_number_misscheduled > 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
|
||||
description: "Some DaemonSet Pods are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesCronjobTooLong
|
||||
expr: 'time() - kube_cronjob_next_schedule_time > 3600'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes CronJob too long (instance {{ $labels.instance }})
|
||||
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesJobSlowCompletion
|
||||
expr: 'kube_job_spec_completions - kube_job_status_succeeded > 0'
|
||||
for: 12h
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes job slow completion (instance {{ $labels.instance }})
|
||||
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesApiServerErrors
|
||||
expr: 'sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes API server errors (instance {{ $labels.instance }})
|
||||
description: "Kubernetes API server is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesApiClientErrors
|
||||
expr: '(sum(rate(rest_client_requests_total{code=~"(4|5).."}[1m])) by (instance, job) / sum(rate(rest_client_requests_total[1m])) by (instance, job)) * 100 > 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes API client errors (instance {{ $labels.instance }})
|
||||
description: "Kubernetes API client is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesClientCertificateExpiresNextWeek
|
||||
expr: 'apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 7*24*60*60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes client certificate expires next week (instance {{ $labels.instance }})
|
||||
description: "A client certificate used to authenticate to the apiserver is expiring next week.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesClientCertificateExpiresSoon
|
||||
expr: 'apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes client certificate expires soon (instance {{ $labels.instance }})
|
||||
description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesApiServerLatency
|
||||
expr: 'histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) / 1e+06 > 1'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes API server latency (instance {{ $labels.instance }})
|
||||
description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/linkerd/embedded-exporter.yml
vendored
Normal file
14
dist/rules/linkerd/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: LinkerdHighErrorRate
|
||||
expr: 'sum(rate(request_errors_total[1m])) by (deployment, statefulset, daemonset) / sum(rate(request_total[1m])) by (deployment, statefulset, daemonset) * 100 > 10'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Linkerd high error rate (instance {{ $labels.instance }})
|
||||
description: "Linkerd error rate for {{ $labels.deployment | $labels.statefulset | $labels.daemonset }} is over 10%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
41
dist/rules/loki/embedded-exporter.yml
vendored
Normal file
41
dist/rules/loki/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: LokiProcessTooManyRestarts
|
||||
expr: 'changes(process_start_time_seconds{job=~"loki"}[15m]) > 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Loki process too many restarts (instance {{ $labels.instance }})
|
||||
description: "A loki process had too many restarts (target {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: LokiRequestErrors
|
||||
expr: '100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) > 10'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Loki request errors (instance {{ $labels.instance }})
|
||||
description: "The {{ $labels.job }} and {{ $labels.route }} are experiencing errors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: LokiRequestPanic
|
||||
expr: 'sum(increase(loki_panic_total[10m])) by (namespace, job) > 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Loki request panic (instance {{ $labels.instance }})
|
||||
description: "The {{ $labels.job }} is experiencing {{ printf \"%.2f\" $value }}% increase of panics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: LokiRequestLatency
|
||||
expr: '(histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{route!~"(?i).*tail.*"}[5m])) by (le))) > 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Loki request latency (instance {{ $labels.instance }})
|
||||
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/minio/embedded-exporter.yml
vendored
Normal file
23
dist/rules/minio/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: MinioDiskOffline
|
||||
expr: 'minio_disks_offline > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Minio disk offline (instance {{ $labels.instance }})
|
||||
description: "Minio disk is offline\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MinioDiskSpaceUsage
|
||||
expr: 'disk_storage_available / disk_storage_total * 100 < 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Minio disk space usage (instance {{ $labels.instance }})
|
||||
description: "Minio available free space is low (< 10%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
95
dist/rules/mongodb/dcu-mongodb-exporter.yml
vendored
Normal file
95
dist/rules/mongodb/dcu-mongodb-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,95 @@
|
|||
groups:
|
||||
|
||||
- name: DcuMongodbExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: MongodbReplicationLag
|
||||
expr: 'avg(mongodb_replset_member_optime_date{state="PRIMARY"}) - avg(mongodb_replset_member_optime_date{state="SECONDARY"}) > 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication lag (instance {{ $labels.instance }})
|
||||
description: "Mongodb replication lag is more than 10s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationStatus3
|
||||
expr: 'mongodb_replset_member_state == 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication Status 3 (instance {{ $labels.instance }})
|
||||
description: "MongoDB Replication set member either perform startup self-checks, or transition from completing a rollback or resync\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationStatus6
|
||||
expr: 'mongodb_replset_member_state == 6'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication Status 6 (instance {{ $labels.instance }})
|
||||
description: "MongoDB Replication set member as seen from another member of the set, is not yet known\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationStatus8
|
||||
expr: 'mongodb_replset_member_state == 8'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication Status 8 (instance {{ $labels.instance }})
|
||||
description: "MongoDB Replication set member as seen from another member of the set, is unreachable\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationStatus9
|
||||
expr: 'mongodb_replset_member_state == 9'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication Status 9 (instance {{ $labels.instance }})
|
||||
description: "MongoDB Replication set member is actively performing a rollback. Data is not available for reads\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationStatus10
|
||||
expr: 'mongodb_replset_member_state == 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication Status 10 (instance {{ $labels.instance }})
|
||||
description: "MongoDB Replication set member was once in a replica set but was subsequently removed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbNumberCursorsOpen
|
||||
expr: 'mongodb_metrics_cursor_open{state="total_open"} > 10000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB number cursors open (instance {{ $labels.instance }})
|
||||
description: "Too many cursors opened by MongoDB for clients (> 10k)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbCursorsTimeouts
|
||||
expr: 'increase(mongodb_metrics_cursor_timed_out_total[1m]) > 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB cursors timeouts (instance {{ $labels.instance }})
|
||||
description: "Too many cursors are timing out\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbTooManyConnections
|
||||
expr: 'avg by(instance) (rate(mongodb_connections{state="current"}[1m])) / avg by(instance) (sum (mongodb_connections) by (instance)) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB too many connections (instance {{ $labels.instance }})
|
||||
description: "Too many connections (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbVirtualMemoryUsage
|
||||
expr: '(sum(mongodb_memory{type="virtual"}) BY (instance) / sum(mongodb_memory{type="mapped"}) BY (instance)) > 3'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB virtual memory usage (instance {{ $labels.instance }})
|
||||
description: "High memory usage\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
68
dist/rules/mongodb/percona-mongodb-exporter.yml
vendored
Normal file
68
dist/rules/mongodb/percona-mongodb-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
groups:
|
||||
|
||||
- name: PerconaMongodbExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: MongodbDown
|
||||
expr: 'mongodb_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB Down (instance {{ $labels.instance }})
|
||||
description: "MongoDB instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationLag
|
||||
expr: 'mongodb_mongod_replset_member_optime_date{state="PRIMARY"} - ON (set) mongodb_mongod_replset_member_optime_date{state="SECONDARY"} > 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication lag (instance {{ $labels.instance }})
|
||||
description: "Mongodb replication lag is more than 10s\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbReplicationHeadroom
|
||||
expr: '(avg(mongodb_mongod_replset_oplog_head_timestamp - mongodb_mongod_replset_oplog_tail_timestamp) - (avg(mongodb_mongod_replset_member_optime_date{state="PRIMARY"}) - avg(mongodb_mongod_replset_member_optime_date{state="SECONDARY"}))) <= 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MongoDB replication headroom (instance {{ $labels.instance }})
|
||||
description: "MongoDB replication headroom is <= 0\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbNumberCursorsOpen
|
||||
expr: 'mongodb_mongod_metrics_cursor_open{state="total"} > 10 * 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB number cursors open (instance {{ $labels.instance }})
|
||||
description: "Too many cursors opened by MongoDB for clients (> 10k)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbCursorsTimeouts
|
||||
expr: 'increase(mongodb_mongod_metrics_cursor_timed_out_total[1m]) > 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB cursors timeouts (instance {{ $labels.instance }})
|
||||
description: "Too many cursors are timing out\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbTooManyConnections
|
||||
expr: 'avg by(instance) (rate(mongodb_connections{state="current"}[1m])) / avg by(instance) (sum (mongodb_connections) by (instance)) * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB too many connections (instance {{ $labels.instance }})
|
||||
description: "Too many connections (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MongodbVirtualMemoryUsage
|
||||
expr: '(sum(mongodb_memory{type="virtual"}) BY (instance) / sum(mongodb_memory{type="mapped"}) BY (instance)) > 3'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MongoDB virtual memory usage (instance {{ $labels.instance }})
|
||||
description: "High memory usage\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/mongodb/stefanprodan-mgob-exporter.yml
vendored
Normal file
14
dist/rules/mongodb/stefanprodan-mgob-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: StefanprodanMgobExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: MgobBackupFailed
|
||||
expr: 'changes(mgob_scheduler_backup_total{status="500"}[1h]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Mgob backup failed (instance {{ $labels.instance }})
|
||||
description: "MongoDB backup has failed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
86
dist/rules/mysql/mysqld-exporter.yml
vendored
Normal file
86
dist/rules/mysql/mysqld-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
groups:
|
||||
|
||||
- name: MysqldExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: MysqlDown
|
||||
expr: 'mysql_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MySQL down (instance {{ $labels.instance }})
|
||||
description: "MySQL instance is down on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlTooManyConnections(>80%)
|
||||
expr: 'max_over_time(mysql_global_status_threads_connected[1m]) / mysql_global_variables_max_connections * 100 > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MySQL too many connections (> 80%) (instance {{ $labels.instance }})
|
||||
description: "More than 80% of MySQL connections are in use on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlHighThreadsRunning
|
||||
expr: 'max_over_time(mysql_global_status_threads_running[1m]) / mysql_global_variables_max_connections * 100 > 60'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MySQL high threads running (instance {{ $labels.instance }})
|
||||
description: "More than 60% of MySQL connections are in running state on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlSlaveIoThreadNotRunning
|
||||
expr: 'mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_io_running == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MySQL Slave IO thread not running (instance {{ $labels.instance }})
|
||||
description: "MySQL Slave IO thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlSlaveSqlThreadNotRunning
|
||||
expr: 'mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_sql_running == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MySQL Slave SQL thread not running (instance {{ $labels.instance }})
|
||||
description: "MySQL Slave SQL thread not running on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlSlaveReplicationLag
|
||||
expr: 'mysql_slave_status_master_server_id > 0 and ON (instance) (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) > 30'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: MySQL Slave replication lag (instance {{ $labels.instance }})
|
||||
description: "MySQL replication lag on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlSlowQueries
|
||||
expr: 'increase(mysql_global_status_slow_queries[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MySQL slow queries (instance {{ $labels.instance }})
|
||||
description: "MySQL server mysql has some new slow query.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlInnodbLogWaits
|
||||
expr: 'rate(mysql_global_status_innodb_log_waits[15m]) > 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: MySQL InnoDB log waits (instance {{ $labels.instance }})
|
||||
description: "MySQL innodb log writes stalling\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: MysqlRestarted
|
||||
expr: 'mysql_global_status_uptime < 60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: MySQL restarted (instance {{ $labels.instance }})
|
||||
description: "MySQL has just been restarted, less than one minute ago on {{ $labels.instance }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
86
dist/rules/netdata/embedded-exporter.yml
vendored
Normal file
86
dist/rules/netdata/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: NetdataHighCpuUsage
|
||||
expr: 'rate(netdata_cpu_cpu_percentage_average{dimension="idle"}[1m]) > 80'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata high cpu usage (instance {{ $labels.instance }})
|
||||
description: "Netdata high CPU usage (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HostCpuStealNoisyNeighbor
|
||||
expr: 'rate(netdata_cpu_cpu_percentage_average{dimension="steal"}[1m]) > 10'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
|
||||
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataHighMemoryUsage
|
||||
expr: '100 / netdata_system_ram_MB_average * netdata_system_ram_MB_average{dimension=~"free|cached"} < 20'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata high memory usage (instance {{ $labels.instance }})
|
||||
description: "Netdata high memory usage (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataLowDiskSpace
|
||||
expr: '100 / netdata_disk_space_GB_average * netdata_disk_space_GB_average{dimension=~"avail|cached"} < 20'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata low disk space (instance {{ $labels.instance }})
|
||||
description: "Netdata low disk space (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataPredictedDiskFull
|
||||
expr: 'predict_linear(netdata_disk_space_GB_average{dimension=~"avail|cached"}[3h], 24 * 3600) < 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata predicted disk full (instance {{ $labels.instance }})
|
||||
description: "Netdata predicted disk full in 24 hours\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataMdMismatchCntUnsynchronizedBlocks
|
||||
expr: 'netdata_md_mismatch_cnt_unsynchronized_blocks_average > 1024'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata MD mismatch cnt unsynchronized blocks (instance {{ $labels.instance }})
|
||||
description: "RAID Array have unsynchronized blocks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataDiskReallocatedSectors
|
||||
expr: 'increase(netdata_smartd_log_reallocated_sectors_count_sectors_average[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Netdata disk reallocated sectors (instance {{ $labels.instance }})
|
||||
description: "Reallocated sectors on disk\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataDiskCurrentPendingSector
|
||||
expr: 'netdata_smartd_log_current_pending_sector_count_sectors_average > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata disk current pending sector (instance {{ $labels.instance }})
|
||||
description: "Disk current pending sector\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NetdataReportedUncorrectableDiskSectors
|
||||
expr: 'increase(netdata_smartd_log_offline_uncorrectable_sector_count_sectors_average[2m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Netdata reported uncorrectable disk sectors (instance {{ $labels.instance }})
|
||||
description: "Reported uncorrectable disk sectors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/nginx/knyar-nginx-exporter.yml
vendored
Normal file
32
dist/rules/nginx/knyar-nginx-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: KnyarNginxExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: NginxHighHttp4xxErrorRate
|
||||
expr: 'sum(rate(nginx_http_requests_total{status=~"^4.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Nginx high HTTP 4xx error rate (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 4xx (> 5%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NginxHighHttp5xxErrorRate
|
||||
expr: 'sum(rate(nginx_http_requests_total{status=~"^5.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Nginx high HTTP 5xx error rate (instance {{ $labels.instance }})
|
||||
description: "Too many HTTP requests with status 5xx (> 5%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NginxLatencyHigh
|
||||
expr: 'histogram_quantile(0.99, sum(rate(nginx_http_request_duration_seconds_bucket[2m])) by (host, node)) > 3'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Nginx latency high (instance {{ $labels.instance }})
|
||||
description: "Nginx p99 latency is higher than 3 seconds\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
41
dist/rules/nomad/embedded-exporter.yml
vendored
Normal file
41
dist/rules/nomad/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: NomadJobFailed
|
||||
expr: 'nomad_nomad_job_summary_failed > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Nomad job failed (instance {{ $labels.instance }})
|
||||
description: "Nomad job failed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NomadJobLost
|
||||
expr: 'nomad_nomad_job_summary_lost > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Nomad job lost (instance {{ $labels.instance }})
|
||||
description: "Nomad job lost\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NomadJobQueued
|
||||
expr: 'nomad_nomad_job_summary_queued > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Nomad job queued (instance {{ $labels.instance }})
|
||||
description: "Nomad job queued\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: NomadBlockedEvaluation
|
||||
expr: 'nomad_nomad_blocked_evals_total_blocked > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Nomad blocked evaluation (instance {{ $labels.instance }})
|
||||
description: "Nomad blocked evaluation\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/openebs/embedded-exporter.yml
vendored
Normal file
14
dist/rules/openebs/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: OpenebsUsedPoolCapacity
|
||||
expr: 'openebs_used_pool_capacity_percent > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: OpenEBS used pool capacity (instance {{ $labels.instance }})
|
||||
description: "OpenEBS Pool use more than 80% of his capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/pgbouncer/spreaker-pgbouncer-exporter.yml
vendored
Normal file
32
dist/rules/pgbouncer/spreaker-pgbouncer-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: SpreakerPgbouncerExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: PgbouncerActiveConnections
|
||||
expr: 'pgbouncer_pools_server_active_connections > 200'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: PGBouncer active connections (instance {{ $labels.instance }})
|
||||
description: "PGBouncer pools are filling up\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PgbouncerErrors
|
||||
expr: 'increase(pgbouncer_errors_count{errmsg!="server conn crashed?"}[1m]) > 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: PGBouncer errors (instance {{ $labels.instance }})
|
||||
description: "PGBouncer is logging errors. This may be due to a a server restart or an admin typing commands at the pgbouncer console.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PgbouncerMaxConnections
|
||||
expr: 'increase(pgbouncer_errors_count{errmsg="no more connections allowed (max_client_conn)"}[30s]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: PGBouncer max connections (instance {{ $labels.instance }})
|
||||
description: "The number of PGBouncer client connections has reached max_client_conn.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
14
dist/rules/php-fpm/bakins-fpm-exporter.yml
vendored
Normal file
14
dist/rules/php-fpm/bakins-fpm-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
groups:
|
||||
|
||||
- name: BakinsFpmExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: Php-fpmMax-childrenReached
|
||||
expr: 'sum(phpfpm_max_children_reached_total) by (instance) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: PHP-FPM max-children reached (instance {{ $labels.instance }})
|
||||
description: "PHP-FPM reached max children - {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
212
dist/rules/postgresql/postgres-exporter.yml
vendored
Normal file
212
dist/rules/postgresql/postgres-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,212 @@
|
|||
groups:
|
||||
|
||||
- name: PostgresExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: PostgresqlDown
|
||||
expr: 'pg_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql down (instance {{ $labels.instance }})
|
||||
description: "Postgresql instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlRestarted
|
||||
expr: 'time() - pg_postmaster_start_time_seconds < 60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql restarted (instance {{ $labels.instance }})
|
||||
description: "Postgresql restarted\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlExporterError
|
||||
expr: 'pg_exporter_last_scrape_error > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql exporter error (instance {{ $labels.instance }})
|
||||
description: "Postgresql exporter is showing errors. A query may be buggy in query.yaml\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlReplicationLag
|
||||
expr: 'pg_replication_lag > 30 and ON(instance) pg_replication_is_replica == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql replication lag (instance {{ $labels.instance }})
|
||||
description: "PostgreSQL replication lag is going up (> 30s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlTableNotAutoVacuumed
|
||||
expr: '(pg_stat_user_tables_last_autovacuum > 0) and (time() - pg_stat_user_tables_last_autovacuum) > 60 * 60 * 24 * 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql table not auto vacuumed (instance {{ $labels.instance }})
|
||||
description: "Table {{ $labels.relname }} has not been auto vacuumed for 10 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlTableNotAutoAnalyzed
|
||||
expr: '(pg_stat_user_tables_last_autoanalyze > 0) and (time() - pg_stat_user_tables_last_autoanalyze) > 24 * 60 * 60 * 10'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql table not auto analyzed (instance {{ $labels.instance }})
|
||||
description: "Table {{ $labels.relname }} has not been auto analyzed for 10 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlTooManyConnections
|
||||
expr: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) > pg_settings_max_connections * 0.8'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql too many connections (instance {{ $labels.instance }})
|
||||
description: "PostgreSQL instance has too many connections (> 80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlNotEnoughConnections
|
||||
expr: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql not enough connections (instance {{ $labels.instance }})
|
||||
description: "PostgreSQL instance should have more connections (> 5)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlDeadLocks
|
||||
expr: 'increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql dead locks (instance {{ $labels.instance }})
|
||||
description: "PostgreSQL has dead-locks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlHighRollbackRate
|
||||
expr: 'rate(pg_stat_database_xact_rollback{datname!~"template.*"}[3m]) / rate(pg_stat_database_xact_commit{datname!~"template.*"}[3m]) > 0.02'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql high rollback rate (instance {{ $labels.instance }})
|
||||
description: "Ratio of transactions being aborted compared to committed is > 2 %\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlCommitRateLow
|
||||
expr: 'rate(pg_stat_database_xact_commit[1m]) < 10'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql commit rate low (instance {{ $labels.instance }})
|
||||
description: "Postgresql seems to be processing very few transactions\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlLowXidConsumption
|
||||
expr: 'rate(pg_txid_current[1m]) < 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql low XID consumption (instance {{ $labels.instance }})
|
||||
description: "Postgresql seems to be consuming transaction IDs very slowly\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlHighRateStatementTimeout
|
||||
expr: 'rate(postgresql_errors_total{type="statement_timeout"}[1m]) > 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql high rate statement timeout (instance {{ $labels.instance }})
|
||||
description: "Postgres transactions showing high rate of statement timeouts\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlHighRateDeadlock
|
||||
expr: 'increase(postgresql_errors_total{type="deadlock_detected"}[1m]) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql high rate deadlock (instance {{ $labels.instance }})
|
||||
description: "Postgres detected deadlocks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlUnusedReplicationSlot
|
||||
expr: 'pg_replication_slots_active == 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql unused replication slot (instance {{ $labels.instance }})
|
||||
description: "Unused Replication Slots\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlTooManyDeadTuples
|
||||
expr: '((pg_stat_user_tables_n_dead_tup > 10000) / (pg_stat_user_tables_n_live_tup + pg_stat_user_tables_n_dead_tup)) >= 0.1 unless ON(instance) (pg_replication_is_replica == 1)'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql too many dead tuples (instance {{ $labels.instance }})
|
||||
description: "PostgreSQL dead tuples is too large\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlSplitBrain
|
||||
expr: 'count(pg_replication_is_replica == 0) != 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql split brain (instance {{ $labels.instance }})
|
||||
description: "Split Brain, too many primary Postgresql databases in read-write mode\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlPromotedNode
|
||||
expr: 'pg_replication_is_replica and changes(pg_replication_is_replica[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql promoted node (instance {{ $labels.instance }})
|
||||
description: "Postgresql standby server has been promoted as primary node\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlConfigurationChanged
|
||||
expr: '{__name__=~"pg_settings_.*"} != ON(__name__) {__name__=~"pg_settings_([^t]|t[^r]|tr[^a]|tra[^n]|tran[^s]|trans[^a]|transa[^c]|transac[^t]|transact[^i]|transacti[^o]|transactio[^n]|transaction[^_]|transaction_[^r]|transaction_r[^e]|transaction_re[^a]|transaction_rea[^d]|transaction_read[^_]|transaction_read_[^o]|transaction_read_o[^n]|transaction_read_on[^l]|transaction_read_onl[^y]).*"} OFFSET 5m'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: info
|
||||
annotations:
|
||||
summary: Postgresql configuration changed (instance {{ $labels.instance }})
|
||||
description: "Postgres Database configuration change has occurred\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlSslCompressionActive
|
||||
expr: 'sum(pg_stat_ssl_compression) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql SSL compression active (instance {{ $labels.instance }})
|
||||
description: "Database connections with SSL compression enabled. This may add significant jitter in replication delay. Replicas should turn off SSL compression via `sslcompression=0` in `recovery.conf`.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlTooManyLocksAcquired
|
||||
expr: '((sum (pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.20'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Postgresql too many locks acquired (instance {{ $labels.instance }})
|
||||
description: "Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlBloatIndexHigh(>80%)
|
||||
expr: 'pg_bloat_btree_bloat_pct > 80 and on (idxname) (pg_bloat_btree_real_size > 100000000)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql bloat index high (> 80%) (instance {{ $labels.instance }})
|
||||
description: "The index {{ $labels.idxname }} is bloated. You should execute `REINDEX INDEX CONCURRENTLY {{ $labels.idxname }};`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PostgresqlBloatTableHigh(>80%)
|
||||
expr: 'pg_bloat_table_bloat_pct > 80 and on (relname) (pg_bloat_table_real_size > 200000000)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Postgresql bloat table high (> 80%) (instance {{ $labels.instance }})
|
||||
description: "The table {{ $labels.relname }} is bloated. You should execute `VACUUM {{ $labels.relname }};`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
239
dist/rules/prometheus-self-monitoring/embedded-exporter.yml
vendored
Normal file
239
dist/rules/prometheus-self-monitoring/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,239 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/promtail/embedded-exporter.yml
vendored
Normal file
23
dist/rules/promtail/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: PromtailRequestErrors
|
||||
expr: '100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Promtail request errors (instance {{ $labels.instance }})
|
||||
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PromtailRequestLatency
|
||||
expr: 'histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Promtail request latency (instance {{ $labels.instance }})
|
||||
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
95
dist/rules/pulsar/embedded-exporter.yml
vendored
Normal file
95
dist/rules/pulsar/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,95 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: PulsarSubscriptionHighNumberOfBacklogEntries
|
||||
expr: 'sum(pulsar_subscription_back_log) by (subscription) > 5000'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Pulsar subscription high number of backlog entries (instance {{ $labels.instance }})
|
||||
description: "The number of subscription backlog entries is over 5k\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarSubscriptionVeryHighNumberOfBacklogEntries
|
||||
expr: 'sum(pulsar_subscription_back_log) by (subscription) > 100000'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar subscription very high number of backlog entries (instance {{ $labels.instance }})
|
||||
description: "The number of subscription backlog entries is over 100k\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarTopicLargeBacklogStorageSize
|
||||
expr: 'sum(pulsar_storage_size > 5*1024*1024*1024) by (topic)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Pulsar topic large backlog storage size (instance {{ $labels.instance }})
|
||||
description: "The topic backlog storage size is over 5 GB\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarTopicVeryLargeBacklogStorageSize
|
||||
expr: 'sum(pulsar_storage_size > 20*1024*1024*1024) by (topic)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar topic very large backlog storage size (instance {{ $labels.instance }})
|
||||
description: "The topic backlog storage size is over 20 GB\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarHighWriteLatency
|
||||
expr: 'sum(pulsar_storage_write_latency_overflow > 0) by (topic)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar high write latency (instance {{ $labels.instance }})
|
||||
description: "Messages cannot be written in a timely fashion\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarLargeMessagePayload
|
||||
expr: 'sum(pulsar_entry_size_overflow > 0) by (topic)'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Pulsar large message payload (instance {{ $labels.instance }})
|
||||
description: "Observing large message payload (> 1MB)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarHighLedgerDiskUsage
|
||||
expr: 'sum(bookie_ledger_dir__pulsar_data_bookkeeper_ledgers_usage) by (kubernetes_pod_name) > 75'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar high ledger disk usage (instance {{ $labels.instance }})
|
||||
description: "Observing Ledger Disk Usage (> 75%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarReadOnlyBookies
|
||||
expr: 'count(bookie_SERVER_STATUS{} == 0) by (pod)'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar read only bookies (instance {{ $labels.instance }})
|
||||
description: "Observing Readonly Bookies\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarHighNumberOfFunctionErrors
|
||||
expr: 'sum((rate(pulsar_function_user_exceptions_total{}[1m]) + rate(pulsar_function_system_exceptions_total{}[1m])) > 10) by (name)'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar high number of function errors (instance {{ $labels.instance }})
|
||||
description: "Observing more than 10 Function errors per minute\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: PulsarHighNumberOfSinkErrors
|
||||
expr: 'sum(rate(pulsar_sink_sink_exceptions_total{}[1m]) > 10) by (name)'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Pulsar high number of sink errors (instance {{ $labels.instance }})
|
||||
description: "Observing more than 10 Sink errors per minute\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
104
dist/rules/rabbitmq/kbudde-rabbitmq-exporter.yml
vendored
Normal file
104
dist/rules/rabbitmq/kbudde-rabbitmq-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
groups:
|
||||
|
||||
- name: KbuddeRabbitmqExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: RabbitmqDown
|
||||
expr: 'rabbitmq_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq down (instance {{ $labels.instance }})
|
||||
description: "RabbitMQ node down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqClusterDown
|
||||
expr: 'sum(rabbitmq_running) < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq cluster down (instance {{ $labels.instance }})
|
||||
description: "Less than 3 nodes running in RabbitMQ cluster\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqClusterPartition
|
||||
expr: 'rabbitmq_partitions > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq cluster partition (instance {{ $labels.instance }})
|
||||
description: "Cluster partition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqOutOfMemory
|
||||
expr: 'rabbitmq_node_mem_used / rabbitmq_node_mem_limit * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq out of memory (instance {{ $labels.instance }})
|
||||
description: "Memory available for RabbmitMQ is low (< 10%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqTooManyConnections
|
||||
expr: 'rabbitmq_connectionsTotal > 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq too many connections (instance {{ $labels.instance }})
|
||||
description: "RabbitMQ instance has too many connections (> 1000)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqDeadLetterQueueFillingUp
|
||||
expr: 'rabbitmq_queue_messages{queue="my-dead-letter-queue"} > 10'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq dead letter queue filling up (instance {{ $labels.instance }})
|
||||
description: "Dead letter queue is filling up (> 10 msgs)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqTooManyMessagesInQueue
|
||||
expr: 'rabbitmq_queue_messages_ready{queue="my-queue"} > 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq too many messages in queue (instance {{ $labels.instance }})
|
||||
description: "Queue is filling up (> 1000 msgs)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqSlowQueueConsuming
|
||||
expr: 'time() - rabbitmq_queue_head_message_timestamp{queue="my-queue"} > 60'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq slow queue consuming (instance {{ $labels.instance }})
|
||||
description: "Queue messages are consumed slowly (> 60s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqNoConsumer
|
||||
expr: 'rabbitmq_queue_consumers == 0'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq no consumer (instance {{ $labels.instance }})
|
||||
description: "Queue has no consumer\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqTooManyConsumers
|
||||
expr: 'rabbitmq_queue_consumers{queue="my-queue"} > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq too many consumers (instance {{ $labels.instance }})
|
||||
description: "Queue should have only 1 consumer\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqUnactiveExchange
|
||||
expr: 'rate(rabbitmq_exchange_messages_published_in_total{exchange="my-exchange"}[1m]) < 5'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq unactive exchange (instance {{ $labels.instance }})
|
||||
description: "Exchange receive less than 5 msgs per second\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
86
dist/rules/rabbitmq/rabbitmq-exporter.yml
vendored
Normal file
86
dist/rules/rabbitmq/rabbitmq-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
groups:
|
||||
|
||||
- name: RabbitmqExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: RabbitmqNodeDown
|
||||
expr: 'sum(rabbitmq_build_info) < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq node down (instance {{ $labels.instance }})
|
||||
description: "Less than 3 nodes running in RabbitMQ cluster\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqNodeNotDistributed
|
||||
expr: 'erlang_vm_dist_node_state < 3'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Rabbitmq node not distributed (instance {{ $labels.instance }})
|
||||
description: "Distribution link state is not 'up'\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqInstancesDifferentVersions
|
||||
expr: 'count(count(rabbitmq_build_info) by (rabbitmq_version)) > 1'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq instances different versions (instance {{ $labels.instance }})
|
||||
description: "Running different version of Rabbitmq in the same cluster, can lead to failure.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqMemoryHigh
|
||||
expr: 'rabbitmq_process_resident_memory_bytes / rabbitmq_resident_memory_limit_bytes * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq memory high (instance {{ $labels.instance }})
|
||||
description: "A node use more than 90% of allocated RAM\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqFileDescriptorsUsage
|
||||
expr: 'rabbitmq_process_open_fds / rabbitmq_process_max_fds * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq file descriptors usage (instance {{ $labels.instance }})
|
||||
description: "A node use more than 90% of file descriptors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqTooManyUnackMessages
|
||||
expr: 'sum(rabbitmq_queue_messages_unacked) BY (queue) > 1000'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq too many unack messages (instance {{ $labels.instance }})
|
||||
description: "Too many unacknowledged messages\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqTooManyConnections
|
||||
expr: 'rabbitmq_connections > 1000'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq too many connections (instance {{ $labels.instance }})
|
||||
description: "The total connections of a node is too high\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqNoQueueConsumer
|
||||
expr: 'rabbitmq_queue_consumers < 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq no queue consumer (instance {{ $labels.instance }})
|
||||
description: "A queue has less than 1 consumer\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RabbitmqUnroutableMessages
|
||||
expr: 'increase(rabbitmq_channel_messages_unroutable_returned_total[1m]) > 0 or increase(rabbitmq_channel_messages_unroutable_dropped_total[1m]) > 0'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Rabbitmq unroutable messages (instance {{ $labels.instance }})
|
||||
description: "A queue has unroutable messages\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
113
dist/rules/redis/oliver006-redis-exporter.yml
vendored
Normal file
113
dist/rules/redis/oliver006-redis-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,113 @@
|
|||
groups:
|
||||
|
||||
- name: Oliver006RedisExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: RedisDown
|
||||
expr: 'redis_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Redis down (instance {{ $labels.instance }})
|
||||
description: "Redis instance is down\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n 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.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RedisDisconnectedSlaves
|
||||
expr: 'count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 1'
|
||||
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.\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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).\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n 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%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RedisOutOfConfiguredMaxmemory
|
||||
expr: 'redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
|
||||
description: "Redis is running out of configured maxmemory (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: RedisTooManyConnections
|
||||
expr: 'redis_connected_clients > 100'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Redis too many connections (instance {{ $labels.instance }})
|
||||
description: "Redis instance has too many connections\n VALUE = {{ $value }}\n 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)\n VALUE = {{ $value }}\n 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\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/sidekiq/strech-sidekiq-exporter.yml
vendored
Normal file
23
dist/rules/sidekiq/strech-sidekiq-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: StrechSidekiqExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: SidekiqQueueSize
|
||||
expr: 'sidekiq_queue_size > 100'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Sidekiq queue size (instance {{ $labels.instance }})
|
||||
description: "Sidekiq queue {{ $labels.name }} is growing\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SidekiqSchedulingLatencyTooHigh
|
||||
expr: 'max(sidekiq_queue_latency) > 60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Sidekiq scheduling latency too high (instance {{ $labels.instance }})
|
||||
description: "Sidekiq jobs are taking more than 1min to be picked up. Users may be seeing delays in background processing.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
41
dist/rules/solr/embedded-exporter.yml
vendored
Normal file
41
dist/rules/solr/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: SolrUpdateErrors
|
||||
expr: 'increase(solr_metrics_core_update_handler_errors_total[1m]) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Solr update errors (instance {{ $labels.instance }})
|
||||
description: "Solr collection {{ $labels.collection }} has failed updates for replica {{ $labels.replica }} on {{ $labels.base_url }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SolrQueryErrors
|
||||
expr: 'increase(solr_metrics_core_errors_total{category="QUERY"}[1m]) > 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Solr query errors (instance {{ $labels.instance }})
|
||||
description: "Solr has increased query errors in collection {{ $labels.collection }} for replica {{ $labels.replica }} on {{ $labels.base_url }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SolrReplicationErrors
|
||||
expr: 'increase(solr_metrics_core_errors_total{category="REPLICATION"}[1m]) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Solr replication errors (instance {{ $labels.instance }})
|
||||
description: "Solr collection {{ $labels.collection }} has failed updates for replica {{ $labels.replica }} on {{ $labels.base_url }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SolrLowLiveNodeCount
|
||||
expr: 'solr_collections_live_nodes < 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Solr low live node count (instance {{ $labels.instance }})
|
||||
description: "Solr collection {{ $labels.collection }} has less than two live nodes for replica {{ $labels.replica }} on {{ $labels.base_url }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/speedtest/nlamirault-speedtest-exporter.yml
vendored
Normal file
23
dist/rules/speedtest/nlamirault-speedtest-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: NlamiraultSpeedtestExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: SpeedtestSlowInternetDownload
|
||||
expr: 'avg_over_time(speedtest_download[10m]) < 100'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: SpeedTest Slow Internet Download (instance {{ $labels.instance }})
|
||||
description: "Internet download speed is currently {{humanize $value}} Mbps.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SpeedtestSlowInternetUpload
|
||||
expr: 'avg_over_time(speedtest_upload[10m]) < 20'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: SpeedTest Slow Internet Upload (instance {{ $labels.instance }})
|
||||
description: "Internet upload speed is currently {{humanize $value}} Mbps.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
23
dist/rules/sql-server/ozarklake-mssql-exporter.yml
vendored
Normal file
23
dist/rules/sql-server/ozarklake-mssql-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
groups:
|
||||
|
||||
- name: OzarklakeMssqlExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: SqlServerDown
|
||||
expr: 'mssql_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SQL Server down (instance {{ $labels.instance }})
|
||||
description: "SQL server instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SqlServerDeadlock
|
||||
expr: 'increase(mssql_deadlocks[1m]) > 5'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: SQL Server deadlock (instance {{ $labels.instance }})
|
||||
description: "SQL Server is having some deadlock.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
41
dist/rules/ssl/tls/ribbybibby-ssl-exporter.yml
vendored
Normal file
41
dist/rules/ssl/tls/ribbybibby-ssl-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: RibbybibbySslExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: SslCertificateProbeFailed
|
||||
expr: 'ssl_probe_success == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SSL certificate probe failed (instance {{ $labels.instance }})
|
||||
description: "Failed to fetch SSL information {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SslCertificateOscpStatusUnknown
|
||||
expr: 'ssl_ocsp_response_status == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: SSL certificate OSCP status unknown (instance {{ $labels.instance }})
|
||||
description: "Failed to get the OSCP status {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SslCertificateRevoked
|
||||
expr: 'ssl_ocsp_response_status == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SSL certificate revoked (instance {{ $labels.instance }})
|
||||
description: "SSL certificate revoked {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: SslCertificateExpiry(<7Days)
|
||||
expr: 'ssl_verified_cert_not_after{chain_no="0"} - time() < 86400 * 7'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: SSL certificate expiry (< 7 days) (instance {{ $labels.instance }})
|
||||
description: "{{ $labels.instance }} Certificate is expiring in 7 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/thanos/embedded-exporter.yml
vendored
Normal file
32
dist/rules/thanos/embedded-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: ThanosCompactionHalted
|
||||
expr: 'thanos_compact_halted == 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Thanos compaction halted (instance {{ $labels.instance }})
|
||||
description: "Thanos compaction has failed to run and is now halted.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ThanosCompactBucketOperationFailure
|
||||
expr: 'rate(thanos_objstore_bucket_operation_failures_total[1m]) > 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Thanos compact bucket operation failure (instance {{ $labels.instance }})
|
||||
description: "Thanos compaction has failing storage operations\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ThanosCompactNotRun
|
||||
expr: '(time() - thanos_objstore_bucket_last_successful_upload_time) > 24*60*60'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Thanos compact not run (instance {{ $labels.instance }})
|
||||
description: "Thanos compaction has not run in 24 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/traefik/embedded-exporter-v1.yml
vendored
Normal file
32
dist/rules/traefik/embedded-exporter-v1.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporterV1
|
||||
|
||||
rules:
|
||||
|
||||
- alert: TraefikBackendDown
|
||||
expr: 'count(traefik_backend_server_up) by (backend) == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Traefik backend down (instance {{ $labels.instance }})
|
||||
description: "All Traefik backends are down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: TraefikHighHttp4xxErrorRateBackend
|
||||
expr: 'sum(rate(traefik_backend_requests_total{code=~"4.*"}[3m])) by (backend) / sum(rate(traefik_backend_requests_total[3m])) by (backend) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Traefik high HTTP 4xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Traefik backend 4xx error rate is above 5%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: TraefikHighHttp5xxErrorRateBackend
|
||||
expr: 'sum(rate(traefik_backend_requests_total{code=~"5.*"}[3m])) by (backend) / sum(rate(traefik_backend_requests_total[3m])) by (backend) * 100 > 5'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Traefik high HTTP 5xx error rate backend (instance {{ $labels.instance }})
|
||||
description: "Traefik backend 5xx error rate is above 5%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
32
dist/rules/traefik/embedded-exporter-v2.yml
vendored
Normal file
32
dist/rules/traefik/embedded-exporter-v2.yml
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
groups:
|
||||
|
||||
- name: EmbeddedExporterV2
|
||||
|
||||
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\n VALUE = {{ $value }}\n 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%\n VALUE = {{ $value }}\n 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%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
41
dist/rules/vmware/pryorda-vmware-exporter.yml
vendored
Normal file
41
dist/rules/vmware/pryorda-vmware-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: PryordaVmwareExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: VirtualMachineMemoryWarning
|
||||
expr: 'vmware_vm_mem_usage_average / 100 >= 80 and vmware_vm_mem_usage_average / 100 < 90'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Virtual Machine Memory Warning (instance {{ $labels.instance }})
|
||||
description: "High memory usage on {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: VirtualMachineMemoryCritical
|
||||
expr: 'vmware_vm_mem_usage_average / 100 >= 90'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Virtual Machine Memory Critical (instance {{ $labels.instance }})
|
||||
description: "High memory usage on {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: HighNumberOfSnapshots
|
||||
expr: 'vmware_vm_snapshots > 3'
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: High Number of Snapshots (instance {{ $labels.instance }})
|
||||
description: "High snapshots number on {{ $labels.instance }}: {{ $value }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: OutdatedSnapshots
|
||||
expr: '(time() - vmware_vm_snapshot_timestamp_seconds) / (60 * 60 * 24) >= 3'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Outdated Snapshots (instance {{ $labels.instance }})
|
||||
description: "Outdated snapshots on {{ $labels.instance }}: {{ $value | printf \"%.0f\"}} days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
50
dist/rules/windows-server/windows-exporter.yml
vendored
Normal file
50
dist/rules/windows-server/windows-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,50 @@
|
|||
groups:
|
||||
|
||||
- name: WindowsExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: WindowsServerCollectorError
|
||||
expr: 'windows_exporter_collector_success == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Windows Server collector Error (instance {{ $labels.instance }})
|
||||
description: "Collector {{ $labels.collector }} was not successful\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: WindowsServerServiceStatus
|
||||
expr: 'windows_service_status{status="ok"} != 1'
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Windows Server service Status (instance {{ $labels.instance }})
|
||||
description: "Windows Service state is not OK\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: WindowsServerCpuUsage
|
||||
expr: '100 - (avg by (instance) (rate(windows_cpu_time_total{mode="idle"}[2m])) * 100) > 80'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Windows Server CPU Usage (instance {{ $labels.instance }})
|
||||
description: "CPU Usage is more than 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: WindowsServerMemoryUsage
|
||||
expr: '100 - ((windows_os_physical_memory_free_bytes / windows_cs_physical_memory_bytes) * 100) > 90'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Windows Server memory Usage (instance {{ $labels.instance }})
|
||||
description: "Memory usage is more than 90%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: WindowsServerDiskSpaceUsage
|
||||
expr: '100.0 - 100 * ((windows_logical_disk_free_bytes / 1024 / 1024 ) / (windows_logical_disk_size_bytes / 1024 / 1024)) > 80'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Windows Server disk Space Usage (instance {{ $labels.instance }})
|
||||
description: "Disk usage is more than 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
5
dist/rules/zfs/node-exporter.yml
vendored
Normal file
5
dist/rules/zfs/node-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
groups:
|
||||
|
||||
- name: NodeExporter
|
||||
|
||||
rules:
|
||||
5
dist/rules/zookeeper/cloudflare-kafka-zookeeper-exporter.yml
vendored
Normal file
5
dist/rules/zookeeper/cloudflare-kafka-zookeeper-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
groups:
|
||||
|
||||
- name: CloudflareKafkaZookeeperExporter
|
||||
|
||||
rules:
|
||||
41
dist/rules/zookeeper/dabealu-zookeeper-exporter.yml
vendored
Normal file
41
dist/rules/zookeeper/dabealu-zookeeper-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
groups:
|
||||
|
||||
- name: DabealuZookeeperExporter
|
||||
|
||||
rules:
|
||||
|
||||
- alert: ZookeeperDown
|
||||
expr: 'zk_up == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Zookeeper Down (instance {{ $labels.instance }})
|
||||
description: "Zookeeper down on instance {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ZookeeperMissingLeader
|
||||
expr: 'sum(zk_server_leader) == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Zookeeper missing leader (instance {{ $labels.instance }})
|
||||
description: "Zookeeper cluster has no node marked as leader\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ZookeeperTooManyLeaders
|
||||
expr: 'sum(zk_server_leader) > 1'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Zookeeper Too Many Leaders (instance {{ $labels.instance }})
|
||||
description: "Zookeeper cluster has too many nodes marked as leader\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: ZookeeperNotOk
|
||||
expr: 'zk_ruok == 0'
|
||||
for: 3m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Zookeeper Not Ok (instance {{ $labels.instance }})
|
||||
description: "Zookeeper instance is not ok\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
Loading…
Reference in a new issue