From f6e36a699ae2d073e340e0a5844b8e111ed3de37 Mon Sep 17 00:00:00 2001 From: Azat Bahawi Date: Thu, 23 Mar 2023 16:59:15 +0300 Subject: 2023-03-23 --- modules/nixos/monitoring/rules/nginx.yaml | 52 +++ modules/nixos/monitoring/rules/node.yaml | 552 +++++++++++++++++++++++++++ modules/nixos/monitoring/rules/postgres.yaml | 310 +++++++++++++++ modules/nixos/monitoring/rules/redis.yaml | 189 +++++++++ 4 files changed, 1103 insertions(+) create mode 100644 modules/nixos/monitoring/rules/nginx.yaml create mode 100644 modules/nixos/monitoring/rules/node.yaml create mode 100644 modules/nixos/monitoring/rules/postgres.yaml create mode 100644 modules/nixos/monitoring/rules/redis.yaml (limited to 'modules/nixos/monitoring/rules') diff --git a/modules/nixos/monitoring/rules/nginx.yaml b/modules/nixos/monitoring/rules/nginx.yaml new file mode 100644 index 0000000..59229a8 --- /dev/null +++ b/modules/nixos/monitoring/rules/nginx.yaml @@ -0,0 +1,52 @@ +--- +groups: + - name: Nginx + + 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%). + + VALUE = {{ $value }} + 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%). + + VALUE = {{ $value }} + 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 high latency (instance {{ $labels.instance }}) + description: |- + NGINX 99% latency is higher than 3 seconds. + + VALUE = {{ $value }} + LABELS = {{ $labels }} diff --git a/modules/nixos/monitoring/rules/node.yaml b/modules/nixos/monitoring/rules/node.yaml new file mode 100644 index 0000000..81d7810 --- /dev/null +++ b/modules/nixos/monitoring/rules/node.yaml @@ -0,0 +1,552 @@ +--- +groups: + - name: Node + + 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). + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostOutOfInodes + expr: >- + node_filesystem_files_free + / node_filesystem_files * 100 + < 10 + and + ON (instance, device, mountpoint) node_filesystem_readonly + == 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). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostInodesWillFillIn24Hours + expr: >- + node_filesystem_files_free + / node_filesystem_files + * 100 + < 10 + and + predict_linear(node_filesystem_files_free[1h], 24 * 3600) + < 0 + and ON (instance, device, mountpoint) node_filesystem_readonly + == 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. + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + 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). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostHighCpuLoad + expr: >- + sum by (instance) + (avg by (mode, instance) + (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) + > 0.8 + for: 0m + labels: + severity: warning + annotations: + summary: Host high CPU load (instance {{ $labels.instance }}) + description: |- + CPU load is > 80%. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostCpuHighIowait + expr: |- + avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) + * 100 + > 10 + for: 0m + labels: + severity: warning + annotations: + summary: Host CPU high iowait (instance {{ $labels.instance }}) + description: |- + CPU iowait > 10%. A high iowait means that you are disk or network + bound. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostUnusualDiskIo + expr: >- + rate(node_disk_io_time_seconds_total[1m]) > 0.5 + for: 5m + labels: + severity: warning + annotations: + summary: Host unusual disk IO (instance {{ $labels.instance }}) + description: |- + Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues. + + VALUE = {{ $value }} + 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%). + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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 }}". + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: HostRequiresReboot + expr: >- + node_reboot_required > 0 + for: 4h + labels: + severity: info + annotations: + summary: Host requires reboot (instance {{ $labels.instance }}) + description: |- + Instance {{ $labels.instance }} requires a reboot. + + VALUE = {{ $value }} + LABELS = {{ $labels }} diff --git a/modules/nixos/monitoring/rules/postgres.yaml b/modules/nixos/monitoring/rules/postgres.yaml new file mode 100644 index 0000000..5d360fa --- /dev/null +++ b/modules/nixos/monitoring/rules/postgres.yaml @@ -0,0 +1,310 @@ +--- +groups: + - name: Postgres + + rules: + - alert: PostgresqlDown + expr: >- + pg_up == 0 + for: 0m + labels: + severity: critical + annotations: + summary: PostgreSQL is down (instance {{ $labels.instance }}) + description: |- + Postgresql instance is down. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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%). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: PostgresqlNotEnoughConnections + expr: >- + sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) + < 1 + for: 2m + labels: + severity: warning + annotations: + summary: Postgresql not enough connections (instance {{ $labels.instance }}) + description: |- + PostgreSQL instance should have more connections (> 1). + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: PostgresqlHighRollbackRate + expr: >- + sum by (namespace,datname) + ( + (rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) + / + ( + (rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) + + + (rate(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[3m])) + ) + ) + > 0.02 + for: 0m + labels: + severity: warning + annotations: + summary: PostgreSQL is at a high rollback rate (instance {{ $labels.instance }}) + description: |- + Ratio of transactions being aborted compared to committed is > 2%. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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: |- + PostgreSQL transactions showing high rate of statement timeouts. + + VALUE = {{ $value }} + 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: |- + PostgreSQL detected deadlocks. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + 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 + for: 2m + labels: + severity: warning + annotations: + summary: PostgreSQL too many dead tuples (instance {{ $labels.instance }}) + description: |- + PostgreSQL number of dead tuples is too large. + + VALUE = {{ $value }} + 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 is enabled. This may add a + significant jitter in the replication delay. + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: PostgresqlBloatIndexHigh + 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 }};` + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: PostgresqlBloatTableHigh + 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 }};` + + VALUE = {{ $value }} + LABELS = {{ $labels }} diff --git a/modules/nixos/monitoring/rules/redis.yaml b/modules/nixos/monitoring/rules/redis.yaml new file mode 100644 index 0000000..f6d1fe1 --- /dev/null +++ b/modules/nixos/monitoring/rules/redis.yaml @@ -0,0 +1,189 @@ +--- +groups: + - name: Redis + + rules: + - alert: RedisDown + expr: >- + redis_up == 0 + for: 0m + labels: + severity: critical + annotations: + summary: Redis down (instance {{ $labels.instance }}) + description: |- + Redis instance is down. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisMissingMaster + expr: >- + (count(redis_instance_info{role="master"}) or vector(0)) + < 1 + for: 0m + labels: + severity: critical + annotations: + summary: Redis missing master (instance {{ $labels.instance }}) + description: |- + Redis cluster has no node marked as master. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisTooManyMasters + expr: >- + count(redis_instance_info{role="master"}) > 1 + for: 0m + labels: + severity: critical + annotations: + summary: Redis too many masters (instance {{ $labels.instance }}) + description: |- + Redis cluster has too many nodes marked as master. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisDisconnectedSlaves + expr: >- + count without (instance, job) (redis_connected_slaves) + - sum without (instance, job) (redis_connected_slaves) + - 1 + > 1 + for: 0m + labels: + severity: critical + annotations: + summary: Redis disconnected slaves (instance {{ $labels.instance }}) + description: |- + Redis is not replicating for all slaves. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisReplicationBroken + expr: >- + delta(redis_connected_slaves[1m]) < 0 + for: 0m + labels: + severity: critical + annotations: + summary: Redis replication broken (instance {{ $labels.instance }}) + description: |- + Redis instance lost a slave. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisClusterFlapping + expr: >- + changes(redis_connected_slaves[1m]) > 1 + for: 2m + labels: + severity: critical + annotations: + summary: Redis cluster flapping (instance {{ $labels.instance }}) + description: |- + Changes have been detected in the Redis replica connection. This can + occur when replica nodes lose connection to the master and reconnect + (a.k.a flapping). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisMissingBackup + expr: >- + time() - redis_rdb_last_save_timestamp_seconds + > 60 * 60 * 24 + for: 0m + labels: + severity: critical + annotations: + summary: Redis missing backup (instance {{ $labels.instance }}) + description: |- + Redis has not been backed up for 24 hours. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisOutOfSystemMemory + expr: >- + redis_memory_used_bytes + / + redis_total_system_memory_bytes * 100 + > 90 + for: 2m + labels: + severity: warning + annotations: + summary: Redis out of system memory (instance {{ $labels.instance }}) + description: |- + Redis is running out of system memory (> 90%). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisOutOfConfiguredMaxmemory + expr: >- + redis_memory_max_bytes != 0 + and + ( + 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%). + + VALUE = {{ $value }} + 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. + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisNotEnoughConnections + expr: >- + redis_connected_clients < 1 + for: 2m + labels: + severity: warning + annotations: + summary: Redis not enough connections (instance {{ $labels.instance }}) + description: |- + Redis instance should have more connections (> 1). + + VALUE = {{ $value }} + LABELS = {{ $labels }} + + - alert: RedisRejectedConnections + expr: >- + increase(redis_rejected_connections_total[1m]) > 0 + for: 0m + labels: + severity: critical + annotations: + summary: Redis rejected connections (instance {{ $labels.instance }}) + description: |- + Some connections to Redis have been rejected. + + VALUE = {{ $value }} + LABELS = {{ $labels }} -- cgit v1.2.3