diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index 32a3d71..79506c5 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -5,7 +5,7 @@ groups: rules: - alert: HostOutOfMemory - expr: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10)' for: 2m labels: severity: warning @@ -14,7 +14,7 @@ groups: description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostMemoryUnderMemoryPressure - expr: '(rate(node_vmstat_pgmajfault[5m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(rate(node_vmstat_pgmajfault[5m]) > 1000)' for: 0m labels: severity: warning @@ -23,7 +23,7 @@ groups: description: "The node is under heavy memory pressure. High rate of loading memory pages from disk.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostMemoryIsUnderutilized - expr: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80)' for: 1w labels: severity: info @@ -32,7 +32,7 @@ groups: description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualNetworkThroughputIn - expr: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' for: 0m labels: severity: warning @@ -41,7 +41,7 @@ groups: description: "Host receive bandwidth is high (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualNetworkThroughputOut - expr: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)' for: 0m labels: severity: warning @@ -50,7 +50,7 @@ groups: description: "Host transmit bandwidth is high (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualDiskReadRate - expr: '(rate(node_disk_io_time_seconds_total[5m]) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(rate(node_disk_io_time_seconds_total[5m]) > .80)' for: 0m labels: severity: warning @@ -59,7 +59,7 @@ groups: description: "Disk is too busy (IO wait > 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostOutOfDiskSpace - expr: '(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} / node_filesystem_size_bytes < .10 and on (instance, device, mountpoint) node_filesystem_readonly == 0) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} / node_filesystem_size_bytes < .10 and on (instance, device, mountpoint) node_filesystem_readonly == 0)' for: 2m labels: severity: critical @@ -77,7 +77,7 @@ groups: description: "Filesystem will likely run out of space within the next 24 hours\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostOutOfInodes - expr: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0)' for: 2m labels: severity: critical @@ -104,7 +104,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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 @@ -113,7 +113,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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 @@ -122,7 +122,7 @@ groups: description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostHighCpuLoad - expr: '((avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80)' for: 10m labels: severity: warning @@ -131,7 +131,7 @@ groups: description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostCpuIsUnderutilized - expr: '((avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80' for: 1w labels: severity: info @@ -140,7 +140,7 @@ groups: description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostCpuStealNoisyNeighbor - expr: '(avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10' for: 0m labels: severity: warning @@ -149,7 +149,7 @@ groups: 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])) > .10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10' for: 0m labels: severity: warning @@ -158,7 +158,7 @@ groups: description: "CPU iowait > 10%. Your CPU is idling waiting for storage to respond.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualDiskIo - expr: '(rate(node_disk_io_time_seconds_total[5m]) > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: 'rate(node_disk_io_time_seconds_total[5m]) > 0.8' for: 0m labels: severity: warning @@ -167,7 +167,7 @@ groups: description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities.\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"})) > 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000' for: 0m labels: severity: warning @@ -176,7 +176,7 @@ groups: description: "Context switching is growing on the node (> 10000 / CPU / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostSwapIsFillingUp - expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80)' for: 2m labels: severity: warning @@ -185,7 +185,7 @@ groups: description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostSystemdServiceCrashed - expr: '(node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_systemd_unit_state{state="failed"} == 1)' for: 0m labels: severity: warning @@ -194,7 +194,7 @@ groups: description: "systemd service crashed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostPhysicalComponentTooHot - expr: '((node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: 'node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75' for: 5m labels: severity: warning @@ -203,7 +203,7 @@ groups: description: "Physical hardware component too hot\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostNodeOvertemperatureAlarm - expr: '(node_hwmon_temp_crit_alarm_celsius == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_hwmon_temp_crit_alarm_celsius == 1)' for: 0m labels: severity: critical @@ -212,7 +212,7 @@ groups: description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostSoftwareRaidInsufficientDrives - expr: '((node_md_disks_required - on(device, instance) node_md_disks{state="active"}) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((node_md_disks_required - on(device, instance) node_md_disks{state="active"}) > 0)' for: 0m labels: severity: critical @@ -221,7 +221,7 @@ groups: description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostSoftwareRaidDiskFailure - expr: '(node_md_disks{state="failed"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_md_disks{state="failed"} > 0)' for: 2m labels: severity: warning @@ -231,7 +231,7 @@ groups: - alert: HostKernelVersionDeviations expr: 'changes(node_uname_info[1h]) > 0' - for: 6h + for: 0m labels: severity: info annotations: @@ -239,16 +239,16 @@ groups: description: "Kernel version for {{ $labels.instance }} has changed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostOomKillDetected - expr: '(increase(node_vmstat_oom_kill[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(increase(node_vmstat_oom_kill[1m]) > 0)' for: 0m labels: - severity: warning + severity: critical 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(increase(node_edac_correctable_errors_total[1m]) > 0)' for: 0m labels: severity: info @@ -257,7 +257,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_edac_uncorrectable_errors_total > 0)' for: 0m labels: severity: warning @@ -266,7 +266,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01)' for: 2m labels: severity: warning @@ -275,7 +275,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01)' for: 2m labels: severity: warning @@ -284,7 +284,7 @@ groups: 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: HostNetworkBondDegraded - expr: '((node_bonding_active - node_bonding_slaves) != 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '((node_bonding_active - node_bonding_slaves) != 0)' for: 2m labels: severity: warning @@ -293,7 +293,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8)' for: 5m labels: severity: warning @@ -302,7 +302,7 @@ groups: 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)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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: 10m labels: severity: warning @@ -311,7 +311,7 @@ groups: 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16)' for: 2m labels: severity: warning @@ -320,7 +320,7 @@ groups: description: "Clock not synchronising. Ensure NTP is configured on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostRequiresReboot - expr: '(node_reboot_required > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_reboot_required > 0)' for: 4h labels: severity: info diff --git a/dist/rules/postgresql/postgres-exporter.yml b/dist/rules/postgresql/postgres-exporter.yml index 0e1f473..c9a93b1 100644 --- a/dist/rules/postgresql/postgres-exporter.yml +++ b/dist/rules/postgresql/postgres-exporter.yml @@ -53,7 +53,7 @@ groups: expr: 'sum by (instance, job, server) (pg_stat_activity_count) > min by (instance, job, server) (pg_settings_max_connections * 0.8)' for: 2m labels: - severity: warning + severity: critical annotations: summary: Postgresql too many connections (instance {{ $labels.instance }}) description: "PostgreSQL instance has too many connections (> 80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" @@ -62,7 +62,7 @@ groups: expr: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5' for: 2m labels: - severity: warning + severity: critical annotations: summary: Postgresql not enough connections (instance {{ $labels.instance }}) description: "PostgreSQL instance should have more connections (> 5)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" @@ -86,8 +86,8 @@ groups: 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 + expr: 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[1m]) < 5' + for: 5m labels: severity: critical annotations: @@ -140,7 +140,7 @@ groups: description: "PostgreSQL dead tuples is too large\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' + expr: 'changes(label_replace({__name__=~"pg_settings_.*"},"name","$1","__name__", "(.+)")[1h:]) > 0' for: 0m labels: severity: info @@ -155,7 +155,7 @@ groups: 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 }}" + description: "Database allows connections with SSL compression enabled.\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' diff --git a/dist/rules/s.m.a.r.t-device-monitoring/smartctl-exporter.yml b/dist/rules/s.m.a.r.t-device-monitoring/smartctl-exporter.yml index 9b82a6f..866d715 100644 --- a/dist/rules/s.m.a.r.t-device-monitoring/smartctl-exporter.yml +++ b/dist/rules/s.m.a.r.t-device-monitoring/smartctl-exporter.yml @@ -5,32 +5,41 @@ groups: rules: - alert: SmartDeviceTemperatureWarning - expr: 'avg_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) > 60' + expr: '(avg_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) unless on (instance, device) smartctl_device_temperature{temperature_type="drive_trip"}) > 60' for: 0m labels: severity: warning annotations: summary: SMART device temperature warning (instance {{ $labels.instance }}) - description: "Device temperature warning on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device temperature warning on {{ $labels.instance }} drive {{ $labels.device }} over 60°C\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: SmartDeviceTemperatureCritical - expr: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= 70' + expr: '(max_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) unless on (instance, device) smartctl_device_temperature{temperature_type="drive_trip"}) > 70' for: 0m labels: severity: critical annotations: summary: SMART device temperature critical (instance {{ $labels.instance }}) - description: "Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }} over 70°C\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: SmartDeviceTemperatureWasOverTripValue + - alert: SmartDeviceTemperatureOverTripValue expr: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) smartctl_device_temperature{temperature_type="drive_trip"}' for: 0m labels: severity: critical annotations: - summary: SMART device temperature was over trip value (instance {{ $labels.instance }}) + summary: SMART device temperature over trip value (instance {{ $labels.instance }}) description: "Device temperature over trip value on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + - alert: SmartDeviceTemperatureNearingTripValue + expr: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) (smartctl_device_temperature{temperature_type="drive_trip"} * .80)' + for: 0m + labels: + severity: warning + annotations: + summary: SMART device temperature nearing trip value (instance {{ $labels.instance }}) + description: "Device temperature at 80% of trip value on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + - alert: SmartStatus expr: 'smartctl_device_smart_status != 1' for: 0m