chore: upd alerts

conf/prometheus/alerts/embedded-exporter.yml

@@ -32,7 +32,7 @@ groups:
         description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: PrometheusTargetMissingWithWarmupTime
-      expr: 'sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))'
+      expr: 'sum by (instance, job) ((up == 0) * on (instance) group_left (__name__) (node_time_seconds - node_boot_time_seconds > 600))'
       for: 0m
       labels:
         severity: critical
@@ -248,7 +248,7 @@ groups:
         description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: PrometheusTimeseriesCardinality
-      expr: 'label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000'
+      expr: '(label_replace(count by (__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") unless on (__name__) ({__name__=~"node_cpu.*|node_systemd_unit_state"})) > 10000'
       for: 0m
       labels:
         severity: warning

conf/prometheus/alerts/kubestate-exporter.yml

@@ -257,7 +257,7 @@ groups:
         description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} 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'
+      expr: 'time() - kube_cronjob_next_schedule_time > 604800'
       for: 0m
       labels:
         severity: warning

conf/prometheus/alerts/node-exporter.yml

@@ -5,7 +5,7 @@ groups:
   rules:
 
     - alert: HostOutOfMemory
-      expr: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 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
@@ -14,97 +14,88 @@ groups:
         description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostMemoryUnderMemoryPressure
-      expr: '(rate(node_vmstat_pgmajfault[1m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '(rate(node_vmstat_pgmajfault[5m]) > 1000)'
-      for: 2m
+      for: 0m
       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 }}"
+        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: '(100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: 'min_over_time(node_memory_MemFree_bytes[1w]) > node_memory_MemTotal_bytes * .8'
-      for: 1w
+      for: 0m
       labels:
         severity: info
       annotations:
         summary: Host Memory is underutilized (instance {{ $labels.instance }})
-        description: "Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        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: '(sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * 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: 5m
+      for: 0m
       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 }}"
+        description: "Host receive bandwidth is high (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostUnusualNetworkThroughputOut
-      expr: '(sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100) * 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: 5m
+      for: 0m
       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 }}"
+        description: "Host transmit bandwidth is high (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostUnusualDiskReadRate
-      expr: '(sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '(rate(node_disk_io_time_seconds_total[5m]) > .80)'
-      for: 5m
+      for: 0m
       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 }}"
+        description: "Disk is too busy (IO wait > 80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
-
-    - alert: HostUnusualDiskWriteRate
-      expr: '(sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
-      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) * 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: warning
+        severity: critical
       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
+    - alert: HostDiskMayFillIn24Hours
-      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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: 'predict_linear(node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"}[1h], 86400) <= 0 and node_filesystem_avail_bytes > 0'
       for: 2m
       labels:
         severity: warning
       annotations:
-        summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
+        summary: Host disk may 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 }}"
+        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"} * 100 < 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: warning
+        severity: critical
       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: HostFilesystemDeviceError
-      expr: 'node_filesystem_device_error == 1'
+      expr: 'node_filesystem_device_error{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} == 1'
       for: 2m
       labels:
         severity: critical
       annotations:
         summary: Host filesystem device error (instance {{ $labels.instance }})
-        description: "{{ $labels.instance }}: Device error with the {{ $labels.mountpoint }} filesystem\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        description: "Error stat-ing the {{ $labels.mountpoint }} filesystem\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostInodesWillFillIn24Hours
-      expr: '(node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{fstype!="msdosfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!="msdosfs"} == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: 'predict_linear(node_filesystem_files_free{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"}[1h], 86400) <= 0 and node_filesystem_files_free > 0'
       for: 2m
       labels:
         severity: warning
@@ -113,7 +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
@@ -122,7 +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
@@ -131,7 +122,7 @@ groups:
         description: "Disk latency is growing (write operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostHighCpuLoad
-      expr: '(sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8) * 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
@@ -140,16 +131,16 @@ groups:
         description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostCpuIsUnderutilized
-      expr: '(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
       for: 1w
       labels:
         severity: info
       annotations:
         summary: Host CPU is underutilized (instance {{ $labels.instance }})
-        description: "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        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
@@ -158,28 +149,25 @@ 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])) * 100 > 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
       annotations:
         summary: Host CPU high iowait (instance {{ $labels.instance }})
-        description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        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[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: 'rate(node_disk_io_time_seconds_total[5m]) > 0.8'
       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.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostContextSwitchingHigh
-      expr: '(rate(node_context_switches_total[15m])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"}))
+      expr: '(rate(node_context_switches_total[15m])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"}))/(rate(node_context_switches_total[1d])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) > 2'
-/
-(rate(node_context_switches_total[1d])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) > 2
-'
       for: 0m
       labels:
         severity: warning
@@ -188,7 +176,7 @@ groups:
         description: "Context switching is growing on the node (twice the daily average during the last 15m)\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
@@ -197,7 +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
@@ -206,7 +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 > node_hwmon_temp_max_celsius'
       for: 5m
       labels:
         severity: warning
@@ -223,44 +211,44 @@ groups:
         summary: Host node overtemperature alarm (instance {{ $labels.instance }})
         description: "Physical node temperature alarm triggered\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
-    - alert: HostRaidArrayGotInactive
+    - alert: HostSoftwareRaidInsufficientDrives
-      expr: '(node_md_state{state="inactive"} > 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
       annotations:
-        summary: Host RAID array got inactive (instance {{ $labels.instance }})
+        summary: Host Software RAID insufficient drives (instance {{ $labels.instance }})
-        description: "RAID array {{ $labels.device }} is in a degraded state due to one or more disk failures. The number of spare drives is insufficient to fix the issue automatically.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} has insufficient drives remaining.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
-    - alert: HostRaidDiskFailure
+    - 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
       annotations:
-        summary: Host RAID disk failure (instance {{ $labels.instance }})
+        summary: Host Software 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 }}"
+        description: "MD RAID array {{ $labels.device }} on {{ $labels.instance }} needs attention.\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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: 'changes(node_uname_info[1h]) > 0'
-      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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
       for: 0m
       labels:
-        severity: warning
+        severity: info
+      annotations:
+        summary: Host kernel version deviations (instance {{ $labels.instance }})
+        description: "Kernel version for {{ $labels.instance }} has changed\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: HostOomKillDetected
+      expr: '(increase(node_vmstat_oom_kill[1m]) > 0)'
+      for: 0m
+      labels:
+        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
@@ -269,7 +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
@@ -278,7 +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
@@ -287,7 +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
@@ -295,17 +283,8 @@ groups:
         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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
-      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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
+      expr: '((node_bonding_active - node_bonding_slaves) != 0)'
       for: 2m
       labels:
         severity: warning
@@ -314,7 +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
@@ -323,7 +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
@@ -332,7 +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
@@ -341,7 +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

conf/prometheus/alerts/postgres-exporter.yml

@@ -32,7 +32,7 @@ groups:
         description: "Postgresql exporter is showing errors. A query may be buggy in query.yaml\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'
+      expr: '((pg_stat_user_tables_n_tup_del + pg_stat_user_tables_n_tup_upd + pg_stat_user_tables_n_tup_hot_upd) > pg_settings_autovacuum_vacuum_threshold) and (time() - pg_stat_user_tables_last_autovacuum) > 864000'
       for: 0m
       labels:
         severity: warning
@@ -41,7 +41,7 @@ groups:
         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'
+      expr: '((pg_stat_user_tables_n_tup_del + pg_stat_user_tables_n_tup_upd + pg_stat_user_tables_n_tup_hot_upd) > pg_settings_autovacuum_analyze_threshold) and (time() - pg_stat_user_tables_last_autoanalyze) > 864000'
       for: 0m
       labels:
         severity: warning
@@ -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'
+      expr: 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[5m]) < 5'
-      for: 2m
+      for: 5m
       labels:
         severity: critical
       annotations:
@@ -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'

conf/prometheus/alerts/smartctl-exporter.yml

@@ -0,0 +1,77 @@
+groups:
+
+- name: SmartctlExporter
+
+  rules:
+
+    - alert: SmartDeviceTemperatureWarning
+      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 }} over 60°C\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: SmartDeviceTemperatureCritical
+      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 }} over 70°C\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - 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 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
+      labels:
+        severity: critical
+      annotations:
+        summary: SMART status (instance {{ $labels.instance }})
+        description: "Device has a SMART status failure on {{ $labels.instance }} drive {{ $labels.device }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: SmartCriticalWarning
+      expr: 'smartctl_device_critical_warning > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: SMART critical warning (instance {{ $labels.instance }})
+        description: "Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: SmartMediaErrors
+      expr: 'smartctl_device_media_errors > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: SMART media errors (instance {{ $labels.instance }})
+        description: "Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: SmartWearoutIndicator
+      expr: 'smartctl_device_available_spare < smartctl_device_available_spare_threshold'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: SMART Wearout Indicator (instance {{ $labels.instance }})
+        description: "Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"