From b660fafe4c5b7005c07729225f89ee983c379eee Mon Sep 17 00:00:00 2001 From: samber Date: Sun, 25 Feb 2024 00:10:19 +0000 Subject: [PATCH] Publish --- .../rules/host-and-hardware/node-exporter.yml | 106 ++++++++---------- .../smartctl-exporter.yml | 16 +-- 2 files changed, 52 insertions(+), 70 deletions(-) diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index de48231..e5fa55c 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 * 100 < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + expr: '(node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' 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=~".+"}' - for: 2m + expr: '(rate(node_vmstat_pgmajfault[5m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 1w 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=~".+"}' - for: 5m + 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=~".+"}' + 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=~".+"}' - for: 5m + 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=~".+"}' + 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=~".+"}' - for: 5m + expr: '(rate(node_disk_io_time_seconds_total[5m]) > .80) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' + 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 }}" - - - 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 }}" + description: "Disk is too busy (IO wait > 80%)\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) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}' 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 - 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=~".+"}' + - alert: HostDiskMayFillIn24Hours + 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 }}) - description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Host disk may fill in 24 hours (instance {{ $labels.instance }}) + 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' 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: 0m 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 @@ -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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 10m labels: severity: warning @@ -140,13 +131,13 @@ 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: '((avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' 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=~".+"}' @@ -158,22 +149,22 @@ 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) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' 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=~".+"}' - for: 5m + expr: '(rate(node_disk_io_time_seconds_total[5m]) > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + for: 0m 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: 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=~".+"}' @@ -220,32 +211,32 @@ groups: summary: Host node overtemperature alarm (instance {{ $labels.instance }}) description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: HostRaidArrayGotInactive - expr: '(node_md_state{state="inactive"} > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' + - alert: HostSoftwareRaidIsNotActive + expr: '(node_md_disks_required - on(device, instance) node_md_disks{state="active"}) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 0m labels: severity: critical annotations: - summary: Host RAID array got inactive (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 }}" + summary: Host Software RAID is not active (instance {{ $labels.instance }}) + 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=~".+"}' 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\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Host Software RAID disk failure (instance {{ $labels.instance }}) + 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 + severity: info annotations: summary: Host kernel version deviations (instance {{ $labels.instance }}) - description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + 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=~".+"}' @@ -292,15 +283,6 @@ 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=~".+"}' for: 2m 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 4334bf0..9b82a6f 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 @@ -5,13 +5,13 @@ groups: rules: - alert: SmartDeviceTemperatureWarning - expr: 'avg_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) > 60' + expr: 'avg_over_time(smartctl_device_temperature{temperature_type="current"} [5m]) > 60' for: 0m labels: severity: warning annotations: summary: SMART device temperature warning (instance {{ $labels.instance }}) - description: "Device temperature warning (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device temperature warning on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: SmartDeviceTemperatureCritical expr: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= 70' @@ -20,7 +20,7 @@ groups: severity: critical annotations: summary: SMART device temperature critical (instance {{ $labels.instance }}) - description: "Device temperature critical (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device temperature critical on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: SmartDeviceTemperatureWasOverTripValue expr: 'max_over_time(smartctl_device_temperature{temperature_type="current"} [10m]) >= on(device, instance) smartctl_device_temperature{temperature_type="drive_trip"}' @@ -29,7 +29,7 @@ groups: severity: critical annotations: summary: SMART device temperature was over trip value (instance {{ $labels.instance }}) - description: "Device temperature over trip value (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device temperature over trip value on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: SmartStatus expr: 'smartctl_device_smart_status != 1' @@ -38,7 +38,7 @@ groups: severity: critical annotations: summary: SMART status (instance {{ $labels.instance }}) - description: "Device has a SMART status failure (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + 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' @@ -47,7 +47,7 @@ groups: severity: critical annotations: summary: SMART critical warning (instance {{ $labels.instance }}) - description: "Disk controller has critical warning (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + 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' @@ -56,7 +56,7 @@ groups: severity: critical annotations: summary: SMART media errors (instance {{ $labels.instance }}) - description: "Disk controller detected media errors (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + 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' @@ -65,4 +65,4 @@ groups: severity: critical annotations: summary: SMART Wearout Indicator (instance {{ $labels.instance }}) - description: "Device is wearing out (instance {{ $labels.instance }}, drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"