Alert thresholds depend on the nature of your applications. Some queries may have arbitrary tolerance thresholds. Building an efficient monitoring platform takes time. 😉
12 Prometheus alerting rules for Redis. Exported via oliver006/redis_exporter. These rules cover critical and warning conditions — copy and paste the YAML into your Prometheus configuration.
groups:
- name: Oliver006RedisExporter
rules:
# 1m delay allows a restart without triggering an alert.
- alert: RedisDown
expr: redis_up == 0
for: 1m
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 }}"
# 1m delay allows a restart without triggering an alert.
- alert: RedisTooManyMasters
expr: count(redis_instance_info{role="master"}) > 1
for: 1m
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 > 0
for: 0m
labels:
severity: critical
annotations:
summary: Redis disconnected slaves (instance {{ $labels.instance }})
description: "Redis not replicating for all slaves. Consider reviewing the redis replication status.\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 * 48
for: 0m
labels:
severity: critical
annotations:
summary: Redis missing backup (instance {{ $labels.instance }})
description: "Redis has not been backed up for 48 hours\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# The exporter must be started with --include-system-metrics flag or REDIS_EXPORTER_INCL_SYSTEM_METRICS=true environment variable.
- alert: RedisOutOfSystemMemory
expr: redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90 and redis_total_system_memory_bytes > 0
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 and on(instance) redis_memory_max_bytes > 0
for: 2m
labels:
severity: warning
annotations:
summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
description: "Redis is running out of configured maxmemory (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: RedisTooManyConnections
expr: redis_connected_clients / redis_config_maxclients * 100 > 90 and redis_config_maxclients > 0
for: 2m
labels:
severity: warning
annotations:
summary: Redis too many connections (instance {{ $labels.instance }})
description: "Redis is running out of connections (> 90% used)\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]) > 5
for: 0m
labels:
severity: warning
annotations:
summary: Redis rejected connections (instance {{ $labels.instance }})
description: "Some connections to Redis has been rejected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" wget https://raw.githubusercontent.com/samber/awesome-prometheus-alerts/refs/heads/master/dist/rules/redis/oliver006-redis-exporter.yml
Redis instance is down
# 1m delay allows a restart without triggering an alert.
- alert: RedisDown
expr: redis_up == 0
for: 1m
labels:
severity: critical
annotations:
summary: Redis down (instance {{ $labels.instance }})
description: "Redis instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" Redis cluster has no node marked as master.
- 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 }}" Redis cluster has too many nodes marked as master.
# 1m delay allows a restart without triggering an alert.
- alert: RedisTooManyMasters
expr: count(redis_instance_info{role="master"}) > 1
for: 1m
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 }}" Redis not replicating for all slaves. Consider reviewing the redis replication status.
- alert: RedisDisconnectedSlaves
expr: count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 0
for: 0m
labels:
severity: critical
annotations:
summary: Redis disconnected slaves (instance {{ $labels.instance }})
description: "Redis not replicating for all slaves. Consider reviewing the redis replication status.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" Redis instance lost a slave
- 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 }}" 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).
- 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 }}" Redis has not been backed up for 48 hours
- alert: RedisMissingBackup
expr: time() - redis_rdb_last_save_timestamp_seconds > 60 * 60 * 48
for: 0m
labels:
severity: critical
annotations:
summary: Redis missing backup (instance {{ $labels.instance }})
description: "Redis has not been backed up for 48 hours\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" Redis is running out of system memory (> 90%)
# The exporter must be started with --include-system-metrics flag or REDIS_EXPORTER_INCL_SYSTEM_METRICS=true environment variable.
- alert: RedisOutOfSystemMemory
expr: redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90 and redis_total_system_memory_bytes > 0
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 }}" Redis is running out of configured maxmemory (> 90%)
- alert: RedisOutOfConfiguredMaxmemory
expr: redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90 and on(instance) redis_memory_max_bytes > 0
for: 2m
labels:
severity: warning
annotations:
summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
description: "Redis is running out of configured maxmemory (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" Redis is running out of connections (> 90% used)
- alert: RedisTooManyConnections
expr: redis_connected_clients / redis_config_maxclients * 100 > 90 and redis_config_maxclients > 0
for: 2m
labels:
severity: warning
annotations:
summary: Redis too many connections (instance {{ $labels.instance }})
description: "Redis is running out of connections (> 90% used)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" Redis instance should have more connections (> 5)
- 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 }}" Some connections to Redis has been rejected
- alert: RedisRejectedConnections
expr: increase(redis_rejected_connections_total[1m]) > 5
for: 0m
labels:
severity: warning
annotations:
summary: Redis rejected connections (instance {{ $labels.instance }})
description: "Some connections to Redis has been rejected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"