XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 17:07:24 +08:00
Code Issues Projects Releases Packages Wiki Activity

Replace 'ip' by 'instance' in some rules

Browse source 
The metrics return 'instance', not 'ip'
This PR fixes the rules to use 'instance'
This commit is contained in:
Mahesh Paolini-Subramanya 2019-12-27 09:18:16 -05:00
parent 580366554d
commit 88b55f1dee
1 changed files with 122 additions and 124 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

246
_data/rules.yml
View file

@ -1,23 +1,22 @@
services:
- name: Prometheus
exporters:
- rules:
- name: Prometheus configuration reload
description: Prometheus configuration reload error
query: 'prometheus_config_last_reload_successful != 1'
query: "prometheus_config_last_reload_successful != 1"
severity: error
- name: Prometheus not connected to alertmanager
description: Prometheus cannot connect the alertmanager
query: 'prometheus_notifications_alertmanagers_discovered < 1'
description: Prometheus cannot connect the alertmanager
query: "prometheus_notifications_alertmanagers_discovered < 1"
severity: error
- name: AlertManager configuration reload
description: AlertManager configuration reload error
query: 'alertmanager_config_last_reload_successful != 1'
query: "alertmanager_config_last_reload_successful != 1"
severity: error
- name: Exporter down
description: Prometheus exporter down
query: 'up == 0'
query: "up == 0"
severity: warning
- name: Host
@ -27,23 +26,23 @@ services:
rules:
- name: Out of memory
description: Node memory is filling up (< 10% left)
query: 'node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10'
query: "node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10"
severity: warning
- name: Unusual network throughput in
description: Host network interfaces are probably receiving too much data (> 100 MB/s)
query: 'sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'
query: "sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100"
severity: warning
- name: Unusual network throughput out
description: Host network interfaces are probably sending too much data (> 100 MB/s)
query: 'sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'
query: "sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100"
severity: warning
- name: Unusual disk read rate
description: Disk is probably reading too much data (> 50 MB/s)
query: 'sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'
query: "sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50"
severity: warning
- name: Unusual disk write rate
description: Disk is probably writing too much data (> 50 MB/s)
query: 'sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'
query: "sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50"
severity: warning
- name: Out of disk space
description: Disk is almost full (< 10% left)
@ -51,7 +50,7 @@ services:
severity: warning
- name: Disk will fill in 4 hours
description: Disk will fill in 4 hours at current write rate
query: 'predict_linear(node_filesystem_free_bytes[1h], 4 * 3600) < 0'
query: "predict_linear(node_filesystem_free_bytes[1h], 4 * 3600) < 0"
severity: warning
- name: Out of inodes
description: Disk is almost running out of available inodes (< 10% left)
@ -59,11 +58,11 @@ services:
severity: warning
- name: Unusual disk read latency
description: Disk latency is growing (read operations > 100ms)
query: 'rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100'
query: "rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100"
severity: warning
- name: Unusual disk write latency
description: Disk latency is growing (write operations > 100ms)
query: 'rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 100'
query: "rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 100"
severity: warning
- name: High CPU load
description: CPU load is > 80%
@ -71,7 +70,7 @@ services:
severity: warning
- name: Context switching
description: Context switching is growing on node (> 1000 / s)
query: 'rate(node_context_switches_total[5m]) > 1000'
query: "rate(node_context_switches_total[5m]) > 1000"
severity: warning
comments: |
1000 context switches is an arbitrary number.
@ -79,22 +78,21 @@ services:
Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
- name: Swap is filling up
description: Swap is filling up (>80%)
query: '(1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80'
query: "(1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80"
severity: warning
- name: SystemD service crashed
description: 'SystemD service crashed'
description: "SystemD service crashed"
query: 'node_systemd_unit_state{state="failed"} == 1'
severity: warning
- name: Physical component too hot
description: 'Physical hardware component too hot'
query: 'node_hwmon_temp_celsius > 75'
description: "Physical hardware component too hot"
query: "node_hwmon_temp_celsius > 75"
severity: warning
- name: Node overtemperature alarm
description: 'Physical node temperature alarm triggered'
query: 'node_hwmon_temp_alarm == 1'
description: "Physical node temperature alarm triggered"
query: "node_hwmon_temp_alarm == 1"
severity: critical
- name: Docker containers
exporters:
- name: cAdvisor
@ -102,23 +100,23 @@ services:
rules:
- name: Container killed
description: A container has disappeared
query: 'time() - container_last_seen > 60'
query: "time() - container_last_seen > 60"
severity: warning
- name: Container CPU usage
description: Container CPU usage is above 80%
query: '(sum(rate(container_cpu_usage_seconds_total[3m])) BY (ip, name) * 100) > 80'
query: "(sum(rate(container_cpu_usage_seconds_total[3m])) BY (instance, name) * 100) > 80"
severity: warning
- name: Container Memory usage
description: Container Memory usage is above 80%
query: '(sum(container_memory_usage_bytes) BY (ip) / sum(container_memory_max_usage_bytes) BY (ip) * 100) > 80'
query: "(sum(container_memory_usage_bytes) BY (instance) / sum(container_memory_max_usage_bytes) BY (instance) * 100) > 80"
severity: warning
- name: Container Volume usage
description: Container Volume usage is above 80%
query: '(1 - (sum(container_fs_inodes_free) BY (ip) / sum(container_fs_inodes_total) BY (ip)) * 100) > 80'
query: "(1 - (sum(container_fs_inodes_free) BY (instance) / sum(container_fs_inodes_total) BY (instance)) * 100) > 80"
severity: warning
- name: Container Volume IO usage
description: Container Volume IO usage is above 80%
query: '(sum(container_fs_io_current) BY (ip, name) * 100) > 80'
query: "(sum(container_fs_io_current) BY (instance, name) * 100) > 80"
severity: warning
- name: Nginx
@ -142,23 +140,23 @@ services:
rules:
- name: Rabbitmq down
description: RabbitMQ node down
query: 'rabbitmq_up == 0'
query: "rabbitmq_up == 0"
severity: error
- name: Cluster down
description: Less than 3 nodes running in RabbitMQ cluster
query: 'sum(rabbitmq_running) < 3'
query: "sum(rabbitmq_running) < 3"
severity: error
- name: Cluster partition
description: Cluster partition
query: 'rabbitmq_partitions > 0'
query: "rabbitmq_partitions > 0"
severity: error
- name: Out of memory
description: Memory available for RabbmitMQ is low (< 10%)
query: 'rabbitmq_node_mem_used / rabbitmq_node_mem_limit * 100 > 90'
query: "rabbitmq_node_mem_used / rabbitmq_node_mem_limit * 100 > 90"
severity: warning
- name: Too many connections
description: RabbitMQ instance has too many connections (> 1000)
query: 'rabbitmq_connectionsTotal > 1000'
query: "rabbitmq_connectionsTotal > 1000"
severity: warning
- name: Dead letter queue filling up
description: Dead letter queue is filling up (> 10 msgs)
@ -174,11 +172,11 @@ services:
severity: warning
- name: No consumer
description: Queue has no consumer
query: 'rabbitmq_queue_consumers == 0'
query: "rabbitmq_queue_consumers == 0"
severity: error
- name: Too many consumers
description: Queue should have only 1 consumer
query: 'rabbitmq_queue_consumers > 1'
query: "rabbitmq_queue_consumers > 1"
severity: error
- name: Unactive exchange
description: Exchange receive less than 5 msgs per second
@ -198,19 +196,19 @@ services:
rules:
- name: PostgreSQL down
description: PostgreSQL instance is down
query: 'pg_up == 0'
query: "pg_up == 0"
severity: error
- name: Replication lag
description: PostgreSQL replication lag is going up (> 10s)
query: 'pg_replication_lag > 10'
query: "pg_replication_lag > 10"
severity: warning
- name: Table not vaccumed
description: Table has not been vaccum for 24 hours
query: 'time() - pg_stat_user_tables_last_autovacuum > 60 * 60 * 24'
query: "time() - pg_stat_user_tables_last_autovacuum > 60 * 60 * 24"
severity: warning
- name: Table not analyzed
description: Table has not been analyzed for 24 hours
query: 'time() - pg_stat_user_tables_last_autoanalyze > 60 * 60 * 24'
query: "time() - pg_stat_user_tables_last_autoanalyze > 60 * 60 * 24"
severity: warning
- name: Too many connections
description: PostgreSQL instance has too many connections
@ -240,31 +238,31 @@ services:
rules:
- name: Redis down
description: Redis instance is down
query: 'redis_up == 0'
query: "redis_up == 0"
severity: error
- name: Missing backup
description: Redis has not been backuped for 24 hours
query: 'time() - redis_rdb_last_save_timestamp_seconds > 60 * 60 * 24'
query: "time() - redis_rdb_last_save_timestamp_seconds > 60 * 60 * 24"
severity: error
- name: Out of memory
description: Redis is running out of memory (> 90%)
query: 'redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90'
query: "redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90"
severity: warning
- name: Replication broken
description: Redis instance lost a slave
query: 'delta(redis_connected_slaves[1m]) < 0'
query: "delta(redis_connected_slaves[1m]) < 0"
severity: error
- name: Too many connections
description: Redis instance has too many connections
query: 'redis_connected_clients > 100'
query: "redis_connected_clients > 100"
severity: warning
- name: Not enough connections
description: Redis instance should have more connections (> 5)
query: 'redis_connected_clients < 5'
query: "redis_connected_clients < 5"
severity: warning
- name: Rejected connections
description: Some connections to Redis has been rejected
query: 'increase(redis_rejected_connections_total[1m]) > 0'
query: "increase(redis_rejected_connections_total[1m]) > 0"
severity: error
- name: MongoDB
@ -282,23 +280,23 @@ services:
severity: error
- name: MongoDB replication Status 3
description: MongoDB Replication set member either perform startup self-checks, or transition from completing a rollback or resync
query: 'mongodb_replset_member_state == 3'
query: "mongodb_replset_member_state == 3"
severity: error
- name: MongoDB replication Status 6
description: MongoDB Replication set member as seen from another member of the set, is not yet known
query: 'mongodb_replset_member_state == 6'
query: "mongodb_replset_member_state == 6"
severity: error
- name: MongoDB replication Status 8
description: MongoDB Replication set member as seen from another member of the set, is unreachable
query: 'mongodb_replset_member_state == 8'
query: "mongodb_replset_member_state == 8"
severity: error
- name: MongoDB replication Status 9
description: MongoDB Replication set member is actively performing a rollback. Data is not available for reads
query: 'mongodb_replset_member_state == 9'
query: "mongodb_replset_member_state == 9"
severity: error
- name: MongoDB replication Status 10
description: MongoDB Replication set member was once in a replica set but was subsequently removed
query: 'mongodb_replset_member_state == 10'
query: "mongodb_replset_member_state == 10"
severity: error
- name: MongoDB number cursors open
description: Too many cursors opened by MongoDB for clients (> 10k)
@ -306,7 +304,7 @@ services:
severity: warning
- name: MongoDB cursors timeouts
description: Too many cursors are timing out
query: 'increase(mongodb_metrics_cursor_timed_out_total[10m]) > 100'
query: "increase(mongodb_metrics_cursor_timed_out_total[10m]) > 100"
severity: warning
- name: MongoDB too many connections
description: Too many connections
@ -323,11 +321,11 @@ services:
doc_url: https://github.com/justwatchcom/elasticsearch_exporter
rules:
- name: Elastic Heap Usage Too High
description: 'The heap usage is over 90% for 5m'
description: "The heap usage is over 90% for 5m"
query: '(elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 90'
severity: error
- name: Elastic Heap Usage warning
description: 'The heap usage is over 80% for 5m'
description: "The heap usage is over 80% for 5m"
query: '(elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"}) * 100 > 80'
severity: warning
- name: Elastic Cluster Red
@ -339,28 +337,28 @@ services:
query: 'elasticsearch_cluster_health_status{color="yellow"} == 1'
severity: warning
- name: Number of Elastic Healthy Nodes
description: 'Number Healthy Nodes less then number_of_nodes'
query: 'elasticsearch_cluster_health_number_of_nodes < number_of_nodes'
description: "Number Healthy Nodes less then number_of_nodes"
query: "elasticsearch_cluster_health_number_of_nodes < number_of_nodes"
severity: error
- name: Number of Elastic Healthy Data Nodes
description: 'Number Healthy Data Nodes less then number_of_data_nodes'
query: 'elasticsearch_cluster_health_number_of_data_nodes < number_of_data_nodes'
description: "Number Healthy Data Nodes less then number_of_data_nodes"
query: "elasticsearch_cluster_health_number_of_data_nodes < number_of_data_nodes"
severity: error
- name: Number of relocation shards
description: 'Number of relocation shards for 20 min'
query: 'elasticsearch_cluster_health_relocating_shards > 0'
description: "Number of relocation shards for 20 min"
query: "elasticsearch_cluster_health_relocating_shards > 0"
severity: error
- name: Number of initializing shards
description: 'Number of initializing shards for 10 min'
query: 'elasticsearch_cluster_health_initializing_shards > 0'
description: "Number of initializing shards for 10 min"
query: "elasticsearch_cluster_health_initializing_shards > 0"
severity: error
- name: Number of unassigned shards
description: 'Number of unassigned shards for 2 min'
query: 'elasticsearch_cluster_health_unassigned_shards > 0'
description: "Number of unassigned shards for 2 min"
query: "elasticsearch_cluster_health_unassigned_shards > 0"
severity: error
- name: Number of pending tasks
description: 'Number of pending tasks for 10 min. Cluster works slowly.'
query: 'elasticsearch_cluster_health_number_of_pending_tasks > 0'
description: "Number of pending tasks for 10 min. Cluster works slowly."
query: "elasticsearch_cluster_health_number_of_pending_tasks > 0"
severity: warning
- name: Elastic no new documents
description: No new documents for 10 min!
@ -388,14 +386,14 @@ services:
- name: Traefik v1.*
exporters:
- rules:
- name: Traefik backend down
description: All Traefik backends are down
query: 'count(traefik_backend_server_up) by (backend) == 0'
severity: error
- name: Traefik backend errors
description: Traefik backend error rate is above 10%
query: 'sum(rate(traefik_backend_requests_total{code=~"5.*"}[5m])) by (backend) / sum(rate(traefik_backend_requests_total[5m])) by (backend) > 0.1'
severity: error
- name: Traefik backend down
description: All Traefik backends are down
query: "count(traefik_backend_server_up) by (backend) == 0"
severity: error
- name: Traefik backend errors
description: Traefik backend error rate is above 10%
query: 'sum(rate(traefik_backend_requests_total{code=~"5.*"}[5m])) by (backend) / sum(rate(traefik_backend_requests_total[5m])) by (backend) > 0.1'
severity: error
- name: PHP-FPM
exporters:
@ -425,40 +423,40 @@ services:
doc_url: https://github.com/kubernetes/kube-state-metrics/tree/master/docs
rules:
- name: Kubernetes MemoryPressure
description: '{{ $labels.node }} has MemoryPressure condition'
description: "{{ $labels.node }} has MemoryPressure condition"
query: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1'
severity: error
- name: Kubernetes DiskPressure
description: '{{ $labels.node }} has DiskPressure condition'
description: "{{ $labels.node }} has DiskPressure condition"
query: 'kube_node_status_condition{condition="DiskPressure",status="true"} == 1'
severity: error
- name: Kubernetes OutOfDisk
description: '{{ $labels.node }} has OutOfDisk condition'
description: "{{ $labels.node }} has OutOfDisk condition"
query: 'kube_node_status_condition{condition="OutOfDisk",status="true"} == 1'
severity: error
- name: Kubernetes Job failed
description: 'Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete'
query: 'kube_job_status_failed > 0'
description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete"
query: "kube_job_status_failed > 0"
severity: warning
- name: Kubernetes CronJob suspended
description: 'CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended'
query: 'kube_cronjob_spec_suspend != 0'
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended"
query: "kube_cronjob_spec_suspend != 0"
severity: info
- name: Kubernetes PersistentVolumeClaim pending
description: 'PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending'
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending"
query: 'kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1'
severity: warning
- name: Volume out of disk space
description: Volume is almost full (< 10% left)
query: 'kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10'
query: "kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10"
severity: warning
- name: Volume full in four days
description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."
query: '100 * (kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes) < 15 and predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0'
query: "100 * (kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes) < 15 and predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0"
severity: error
- name: StatefulSet down
description: A StatefulSet went down
query: '(kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1'
query: "(kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1"
severity: error
- name: Nomad
@ -473,12 +471,12 @@ services:
doc_url: https://github.com/prometheus/consul_exporter
rules:
- name: Service healthcheck failed
description: 'Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`'
query: 'consul_catalog_service_node_healthy == 0'
description: "Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`"
query: "consul_catalog_service_node_healthy == 0"
severity: error
- name: Missing Consul master node
description: Numbers of consul raft peers less then expected <https://example.ru/ui/{{ $labels.dc }}/services/consul|Consul masters>
query: 'consul_raft_peers < number_of_consul_master'
query: "consul_raft_peers < number_of_consul_master"
severity: error
- name: Etcd
@ -486,15 +484,15 @@ services:
- rules:
- name: Insufficient Members
description: Etcd cluster should have an odd number of members
query: 'count(etcd_server_id) > (count(etcd_server_id) / 2 - 1)'
query: "count(etcd_server_id) > (count(etcd_server_id) / 2 - 1)"
severity: error
- name: No Leader
description: Etcd cluster have no leader
query: 'etcd_server_has_leader == 0'
query: "etcd_server_has_leader == 0"
severity: error
- name: High number of leader changes
description: Etcd leader changed more than 3 times during last hour
query: 'increase(etcd_server_leader_changes_seen_total[1h]) > 3'
query: "increase(etcd_server_leader_changes_seen_total[1h]) > 3"
severity: warning
- name: High number of failed GRPC requests
description: More than 1% GRPC request failure detected in Etcd for 5 minutes
@ -510,31 +508,31 @@ services:
severity: warning
- name: High number of failed HTTP requests
description: More than 1% HTTP failure detected in Etcd for 5 minutes
query: 'sum(rate(etcd_http_failed_total[5m])) BY (method) / sum(rate(etcd_http_received_total[5m])) BY (method) > 0.01'
query: "sum(rate(etcd_http_failed_total[5m])) BY (method) / sum(rate(etcd_http_received_total[5m])) BY (method) > 0.01"
severity: warning
- name: High number of failed HTTP requests
description: More than 5% HTTP failure detected in Etcd for 5 minutes
query: 'sum(rate(etcd_http_failed_total[5m])) BY (method) / sum(rate(etcd_http_received_total[5m])) BY (method) > 0.05'
query: "sum(rate(etcd_http_failed_total[5m])) BY (method) / sum(rate(etcd_http_received_total[5m])) BY (method) > 0.05"
severity: error
- name: HTTP requests slow
description: HTTP requests slowing down, 99th percentil is over 0.15s for 5 minutes
query: 'histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15'
query: "histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15"
severity: warning
- name: Etcd member communication slow
description: Etcd member communication slowing down, 99th percentil is over 0.15s for 5 minutes
query: 'histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m])) > 0.15'
query: "histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m])) > 0.15"
severity: warning
- name: High number of failed proposals
description: Etcd server got more than 5 failed proposals past hour
query: 'increase(etcd_server_proposals_failed_total[1h]) > 5'
query: "increase(etcd_server_proposals_failed_total[1h]) > 5"
severity: warning
- name: High fsync durations
description: Etcd WAL fsync duration increasing, 99th percentil is over 0.5s for 5 minutes
query: 'histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5'
query: "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5"
severity: warning
- name: High commit durations
description: Etcd commit duration increasing, 99th percentil is over 0.25s for 5 minutes
query: 'histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25'
query: "histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25"
severity: warning
- name: Zookeeper
@ -550,11 +548,11 @@ services:
rules:
- name: Kafka Topics
description: Kafka topic in-sync partition
query: 'sum(kafka_topic_partition_in_sync_replica) by (topic) < 3'
query: "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3"
severity: error
- name: Kafka consumers group
description: Kafka consumers group
query: 'sum(kafka_consumergroup_lag) by (consumergroup) > 50'
query: "sum(kafka_consumergroup_lag) by (consumergroup) > 50"
severity: error
- name: Linkerd
@ -576,27 +574,27 @@ services:
severity: error
- name: Slow probe
description: Blackbox probe took more than 1s to complete
query: 'avg_over_time(probe_duration_seconds[1m]) > 1'
query: "avg_over_time(probe_duration_seconds[1m]) > 1"
severity: warning
- name: HTTP Status Code
description: HTTP status code is not 200-399
query: 'probe_http_status_code <= 199 OR probe_http_status_code >= 400'
query: "probe_http_status_code <= 199 OR probe_http_status_code >= 400"
severity: error
- name: SSL certificate will expire soon
description: SSL certificate expires in 30 days
query: 'probe_ssl_earliest_cert_expiry - time() < 86400 * 30'
query: "probe_ssl_earliest_cert_expiry - time() < 86400 * 30"
severity: warning
- name: SSL certificate expired
description: SSL certificate has expired already
query: 'probe_ssl_earliest_cert_expiry - time() <= 0'
query: "probe_ssl_earliest_cert_expiry - time() <= 0"
severity: error
- name: HTTP slow requests
description: HTTP request took more than 1s
query: 'avg_over_time(probe_http_duration_seconds[1m]) > 1'
query: "avg_over_time(probe_http_duration_seconds[1m]) > 1"
severity: warning
- name: Slow ping
description: Blackbox ping took more than 1s
query: 'avg_over_time(probe_icmp_duration_seconds[1m]) > 1'
query: "avg_over_time(probe_icmp_duration_seconds[1m]) > 1"
severity: warning
- name: Windows Server
@ -605,8 +603,8 @@ services:
doc_url: https://github.com/martinlindhe/wmi_exporter
rules:
- name: Collector Error
description: 'Collector {{ $labels.collector }} was not successful'
query: 'wmi_exporter_collector_success == 0'
description: "Collector {{ $labels.collector }} was not successful"
query: "wmi_exporter_collector_success == 0"
severity: error
- name: Service Status
description: Windows Service state is not OK
@ -618,11 +616,11 @@ services:
severity: warning
- name: Memory Usage
description: Memory Usage is more than 90%
query: '100*(wmi_os_physical_memory_free_bytes) / wmi_cs_physical_memory_bytes > 90'
query: "100*(wmi_os_physical_memory_free_bytes) / wmi_cs_physical_memory_bytes > 90"
severity: warning
- name: Disk Space Usage
description: Disk Space on Drive is used more than 80%
query: '100.0 - 100 * ((wmi_logical_disk_free_bytes{} / 1024 / 1024 ) / (wmi_logical_disk_size_bytes{} / 1024 / 1024)) > 80'
query: "100.0 - 100 * ((wmi_logical_disk_free_bytes{} / 1024 / 1024 ) / (wmi_logical_disk_size_bytes{} / 1024 / 1024)) > 80"
severity: error
- name: OpenEBS
@ -630,7 +628,7 @@ services:
- rules:
- name: Used pool capacity
description: 'OpenEBS Pool use more than 80% of his capacity\n VALUE = {{ $value }}\n LABELS: {{ $labels }}'
query: '(openebs_used_pool_capacity_percent) > 80'
query: "(openebs_used_pool_capacity_percent) > 80"
severity: warning
- name: Minio
@ -638,7 +636,7 @@ services:
- rules:
- name: Disk down
description: 'Minio Disk is down\n VALUE = {{ $value }}\n LABELS: {{ $labels }}'
query: 'minio_offline_disks > 0'
query: "minio_offline_disks > 0"
severity: error
- name: Juniper
@ -646,23 +644,23 @@ services:
- name: czerwonk/junos_exporter
doc_url: https://github.com/czerwonk/junos_exporter
rules:
- name: Switch is down
description: The switch appears to be down
query: junos_up == 0
severity: error
- name: High Bandwith Usage 1GiB
description: Interface is highly saturated for at least 1 min. (> 0.90GiB/s)
query: 'irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.90'
severity: error
- name: High Bandwith Usage 1GiB
description: Interface is getting saturated for at least 1 min. (> 0.80GiB/s)
query: 'irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.80'
severity: warning
- name: Switch is down
description: The switch appears to be down
query: junos_up == 0
severity: error
- name: High Bandwith Usage 1GiB
description: Interface is highly saturated for at least 1 min. (> 0.90GiB/s)
query: "irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.90"
severity: error
- name: High Bandwith Usage 1GiB
description: Interface is getting saturated for at least 1 min. (> 0.80GiB/s)
query: "irate(junos_interface_transmit_bytes[1m]) * 8 > 1e+9 * 0.80"
severity: warning
- name: CoreDNS
exporters:
- rules:
- name: CoreDNS Panic Count
description: Number of CoreDNS panics encountered
query: 'increase(coredns_panic_count_total[10m]) > 0'
query: "increase(coredns_panic_count_total[10m]) > 0"
severity: error