diff options
Diffstat (limited to '')
| -rw-r--r-- | modules/nixos/monitoring/rules/node.yaml | 304 |
1 files changed, 153 insertions, 151 deletions
diff --git a/modules/nixos/monitoring/rules/node.yaml b/modules/nixos/monitoring/rules/node.yaml index 81d7810..98217b3 100644 --- a/modules/nixos/monitoring/rules/node.yaml +++ b/modules/nixos/monitoring/rules/node.yaml @@ -13,12 +13,12 @@ groups: labels: severity: warning annotations: - summary: Host out of memory (instance {{ $labels.instance }}) + summary: Host out of memory at {{ $labels.instance }}. description: |- - Node memory is filling up (< 10% left). + Node memory is filling up. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostMemoryUnderMemoryPressure expr: >- @@ -27,13 +27,12 @@ groups: labels: severity: warning annotations: - summary: Host memory under memory pressure (instance {{ $labels.instance }}) + summary: Host memory under memory pressure at {{ $labels.instance }}. description: |- - The node is under heavy memory pressure. High rate of major page - faults. + The node is under heavy memory pressure. High rate of major page faults. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualNetworkThroughputIn expr: >- @@ -47,10 +46,10 @@ groups: annotations: summary: Host unusual network throughput in (instance {{ $labels.instance }}) description: |- - Host network interfaces are probably receiving too much data (> 100 MB/s). + Host network interfaces are probably receiving too much data. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualNetworkThroughputOut expr: >- @@ -62,12 +61,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual network throughput out (instance {{ $labels.instance }}) + summary: Host unusual network throughput out at {{ $labels.instance }}. description: |- - Host network interfaces are probably sending too much data (> 100 MB/s). + Host network interfaces are probably sending too much data. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualDiskReadRate expr: >- @@ -79,12 +78,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual disk read rate (instance {{ $labels.instance }}) + summary: Host unusual disk read rate at {{ $labels.instance }}. description: |- - Disk is probably reading too much data (> 50 MB/s). + Disk is probably reading too much data. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualDiskWriteRate expr: >- @@ -96,12 +95,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual disk write rate (instance {{ $labels.instance }}) + summary: Host unusual disk write rate at {{ $labels.instance }}. description: |- - Disk is probably writing too much data (> 50 MB/s). + Disk is probably writing too much data. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostOutOfDiskSpace expr: >- @@ -109,18 +108,18 @@ groups: / node_filesystem_size_bytes < 10 and - ON (instance, device, mountpoint) node_filesystem_readonly + on (instance, device, mountpoint) node_filesystem_readonly == 0 for: 2m labels: severity: warning annotations: - summary: Host out of disk space (instance {{ $labels.instance }}) + summary: Host out of disk space at {{ $labels.instance }}. description: |- - Disk is almost full (< 10% left). + Disk is almost full. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostDiskWillFillIn24Hours expr: >- @@ -136,13 +135,12 @@ groups: labels: severity: warning annotations: - summary: Host disk will fill in 24 hours (instance {{ $labels.instance }}) + summary: Host disk will fill in 24 hours at {{ $labels.instance }}. description: |- - Filesystem is predicted to run out of space within the next 24 hours - at current write rate. + Filesystem is predicted to run out of space within the next 24 hours at current write rate. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostOutOfInodes expr: >- @@ -156,12 +154,12 @@ groups: labels: severity: warning annotations: - summary: Host out of inodes (instance {{ $labels.instance }}) + summary: Host out of inodes at {{ $labels.instance }}. description: |- - Disk is almost running out of available inodes (< 10% left). + Disk is almost running out of available inodes. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostInodesWillFillIn24Hours expr: >- @@ -178,13 +176,12 @@ groups: labels: severity: warning annotations: - summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }}) + summary: Host inodes will fill in 24 hours at {{ $labels.instance }}. description: |- - Filesystem is predicted to run out of inodes within the next 24 - hours at current write rate. + Filesystem is predicted to run out of inodes within the next 24 hours at current write rate. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualDiskReadLatency expr: >- @@ -198,12 +195,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual disk read latency (instance {{ $labels.instance }}) + summary: Host unusual disk read latency at {{ $labels.instance }}. description: |- - Disk latency is growing (read operations > 100ms). + Disk latency is growing. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualDiskWriteLatency expr: >- @@ -217,12 +214,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual disk write latency (instance {{ $labels.instance }}) + summary: Host unusual disk write latency at {{ $labels.instance }}. description: |- - Disk latency is growing (write operations > 100ms). + Disk latency is growing. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostHighCpuLoad expr: >- @@ -234,23 +231,23 @@ groups: labels: severity: warning annotations: - summary: Host high CPU load (instance {{ $labels.instance }}) + summary: Host high CPU load at {{ $labels.instance }}. description: |- - CPU load is > 80%. + CPU load is high. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostCpuStealNoisyNeighbor expr: >- avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 - > 10 + > 15 for: 0m labels: severity: warning annotations: - summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }}) + summary: Host CPU steal noisy neighbor at {{ $labels.instance }}. description: |- CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit. @@ -262,18 +259,17 @@ groups: expr: |- avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 - > 10 + > 15 for: 0m labels: severity: warning annotations: - summary: Host CPU high iowait (instance {{ $labels.instance }}) + summary: Host CPU high I/O wait at {{ $labels.instance }}. description: |- - CPU iowait > 10%. A high iowait means that you are disk or network - bound. + CPU I/O wait is high. A high I/O wait means that you are disk or network bound. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostUnusualDiskIo expr: >- @@ -282,12 +278,12 @@ groups: labels: severity: warning annotations: - summary: Host unusual disk IO (instance {{ $labels.instance }}) + summary: Host unusual disk I/O at {{ $labels.instance }}. description: |- - Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues. + Time spent over I/O is too high. Check storage for issues. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostSwapIsFillingUp expr: >- @@ -298,12 +294,12 @@ groups: labels: severity: warning annotations: - summary: Host swap is filling up (instance {{ $labels.instance }}) + summary: Host swap is filling up at {{ $labels.instance }}. description: |- - Swap is filling up (> 80%). + Swap is filling up. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostSystemdServiceCrashed expr: >- @@ -312,12 +308,12 @@ groups: labels: severity: warning annotations: - summary: Host systemd service crashed (instance {{ $labels.instance }}) + summary: Host systemd service crashed at {{ $labels.instance }}. description: |- Systemd service crashed. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostPhysicalComponentTooHot expr: >- @@ -326,12 +322,12 @@ groups: labels: severity: warning annotations: - summary: Host physical component too hot (instance {{ $labels.instance }}) + summary: Host physical component too hot at {{ $labels.instance }}. description: |- Physical hardware component too hot. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostNodeOvertemperatureAlarm expr: >- @@ -340,12 +336,12 @@ groups: labels: severity: critical annotations: - summary: Host node overtemperature alarm (instance {{ $labels.instance }}) + summary: Host node overtemperature alarm at {{ $labels.instance }}. description: |- Physical node temperature alarm triggered. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostRaidArrayGotInactive expr: >- @@ -354,14 +350,12 @@ groups: labels: severity: critical annotations: - summary: Host RAID array got inactive (instance {{ $labels.instance }}) + summary: Host RAID array got inactive at {{ $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. + RAID array is in a degraded state due to one or more disks failures. Number of spare drives is insufficient to fix the issue automatically. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostRaidDiskFailure expr: >- @@ -370,14 +364,12 @@ groups: labels: severity: warning annotations: - summary: Host RAID disk failure (instance {{ $labels.instance }}) + summary: Host RAID disk failure at {{ $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. + At least one device in RAID array is failed. Possibly, a disk swap is required. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostOomKillDetected expr: >- @@ -386,12 +378,12 @@ groups: labels: severity: warning annotations: - summary: Host OOM kill detected (instance {{ $labels.instance }}) + summary: Host OOM kill detected at {{ $labels.instance }}. description: |- OOM kill detected. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostEdacCorrectableErrorsDetected expr: >- @@ -400,13 +392,12 @@ groups: labels: severity: info annotations: - summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }}) + summary: Host EDAC correctable errors detected at {{ $labels.instance }}. description: |- - Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} - correctable memory errors reported by EDAC in the last 5 minutes. + Host has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostEdacUncorrectableErrorsDetected expr: >- @@ -415,66 +406,67 @@ groups: labels: severity: warning annotations: - summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }}) + summary: Host EDAC uncorrectable errors detected at {{ $labels.instance }}. description: |- - Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} - uncorrectable memory errors reported by EDAC in the last 5 - minutes. + Host has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostNetworkReceiveErrors - expr: "rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01" + expr: >- + rate(node_network_receive_errs_total{device!~"^wg.*"}[2m]) + / + rate(node_network_receive_packets_total{device!~"^wg.*"}[2m]) + > 0.01 for: 2m labels: severity: warning annotations: - summary: Host Network Receive Errors (instance {{ $labels.instance }}) + summary: Host Network Receive Errors at {{ $labels.instance }}. description: |- - Host {{ $labels.instance }} interface {{ $labels.device }} has - encountered {{ printf "%.0f" $value }} receive errors in the last - two minutes. + Host interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostNetworkTransmitErrors - expr: "rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01" + expr: >- + rate(node_network_transmit_errs_total{device!~"^wg.*"}[2m]) + / + rate(node_network_transmit_packets_total{device!~"^wg.*"}[2m]) + > 0.1 for: 2m labels: severity: warning annotations: - summary: Host Network Transmit Errors (instance {{ $labels.instance }}) + summary: Host network transmit errors at {{ $labels.instance }}. description: |- - Host {{ $labels.instance }} interface {{ $labels.device }} has - encountered {{ printf "%.0f" $value }} transmit errors in the last - two minutes. + Host interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostNetworkInterfaceSaturated expr: >- ( - rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_receive_bytes_total{device!~"^wg.*"}[1m]) + - rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^wg.*"}[1m]) ) - / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} + / node_network_speed_bytes{device!~"^wg.*"} > 0.8 < 10000 for: 1m labels: severity: warning annotations: - summary: Host Network Interface Saturated (instance {{ $labels.instance }}) + summary: Host network interface saturated at {{ $labels.instance }}. description: |- - The network interface "{{ $labels.device }}" on "{{ $labels.instance }}" - is getting overloaded. + The network interface {{ $labels.device }} is getting overloaded. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostNetworkBondDegraded expr: >- @@ -483,43 +475,53 @@ groups: labels: severity: warning annotations: - summary: Host Network Bond Degraded (instance {{ $labels.instance }}) + summary: Host network bond degraded at {{ $labels.instance }}. description: |- - Bond "{{ $labels.device }}" degraded on "{{ $labels.instance }}". + Bond {{ $labels.device }} degraded. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostConntrackLimit expr: >- - node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8 + node_nf_conntrack_entries + / + node_nf_conntrack_entries_limit + > 0.8 for: 5m labels: severity: warning annotations: - summary: Host conntrack limit (instance {{ $labels.instance }}) + summary: Host conntrack limit at {{ $labels.instance }}. description: |- The number of conntrack is approaching limit. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostClockSkew expr: >- - (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) + ( + 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) + ( + 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 }}) + summary: Host clock skew at {{ $labels.instance }}. description: |- - Clock skew detected. Clock is out of sync. Ensure NTP is configured - correctly on this host. + Clock skew is detected and the clock is out of sync. Ensure that NTP is configured correctly on this host. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostClockNotSynchronising expr: >- @@ -530,12 +532,12 @@ groups: labels: severity: warning annotations: - summary: Host clock not synchronising (instance {{ $labels.instance }}) + summary: Host clock not synchronising at {{ $labels.instance }}. description: |- - Clock not synchronising. Ensure NTP is configured on this host. + Clock is not synchronising. Ensure that NTP is configured correctly on this host. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} - alert: HostRequiresReboot expr: >- @@ -544,9 +546,9 @@ groups: labels: severity: info annotations: - summary: Host requires reboot (instance {{ $labels.instance }}) + summary: Host requires reboot at {{ $labels.instance }}. description: |- - Instance {{ $labels.instance }} requires a reboot. + Instance requires a reboot. - VALUE = {{ $value }} - LABELS = {{ $labels }} + VALUE = {{ $value }} + LABELS = {{ $labels }} |