forked from the-distro/infra
feat(alerts): add some basic "host & hardware" alerts
Signed-off-by: Raito Bezarius <masterancpp@gmail.com>
This commit is contained in:
parent
f8cad42b5c
commit
7388de79c4
|
|
@ -1,5 +0,0 @@
|
||||||
groups:
|
|
||||||
- name: Demo alerts
|
|
||||||
rules:
|
|
||||||
- alert: Demo alert
|
|
||||||
expr: 1
|
|
||||||
76
services/monitoring/lgtm/alerts/resources.yaml
Normal file
76
services/monitoring/lgtm/alerts/resources.yaml
Normal file
|
|
@ -0,0 +1,76 @@
|
||||||
|
groups:
|
||||||
|
- name: Host & hardware
|
||||||
|
rules:
|
||||||
|
- alert: HostOutOfMemory
|
||||||
|
expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host out of memory (instance {{ $labels.instance }})
|
||||||
|
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
|
||||||
|
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 }}"
|
||||||
|
- 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=~".+"}
|
||||||
|
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 }}"
|
||||||
|
- 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=~".+"}
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
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=~".+"}
|
||||||
|
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 }}"
|
||||||
|
- alert: HostCpuIsUnderutilized
|
||||||
|
expr: (100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * 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 }}"
|
||||||
|
- 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=~".+"}
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
|
||||||
|
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\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
|
||||||
|
annotations:
|
||||||
|
summary: Host OOM kill detected (instance {{ $labels.instance }})
|
||||||
|
description: "OOM kill detected\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 }}"
|
||||||
|
|
||||||
Loading…
Reference in a new issue