add docker compose
This commit is contained in:
shooter-dev committed
1 parent
88db93b07f
commit
f22f0f2ccc
14 files changed
+33251
No files matched your search
@@ -0,0 +1,145 @@
|
||||
groups:
|
||||
|
||||
- name: Alertes monitoring
|
||||
rules:
|
||||
- alert: NodeHasSwapIn
|
||||
expr: irate(node_vmstat_pswpin{job="prod"}[5m]) > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Node has swap in (instance {{ $labels.instance }})"
|
||||
description: "<!channel> La VM SWAP (in) LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: NodeHasSwapOut
|
||||
expr: irate(node_vmstat_pswpin{job="prod"}[5m]) > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Node has swap out (instance {{ $labels.instance }})"
|
||||
description: "<!channel> La VM SWAP (out) LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: OutOfInodes
|
||||
expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint ="/rootfs"} * 100 < 10
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Out of inodes (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Le disque n'a presque plus d'inode (< 10% restant) VALUE = {{ humanize $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
|
||||
- alert: OutOfMemory
|
||||
expr: (node_memory_MemFree_bytes + node_memory_Cached_bytes + node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 < 10
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Out of memory (instance {{ $labels.instance }})"
|
||||
description: "<!channel> L'hôte n'a presque plus de RAM (< 10% restant) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
|
||||
- alert: UnusualNetworkThroughputIn
|
||||
expr: sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Unusual network throughput in (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Les interfaces réseau reçoivent sans doute trop de données (> 100 MB/s) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: UnusualNetworkThroughputOut
|
||||
expr: sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Unusual network throughput out (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Les interfaces réseau envoient sans doute trop de données (> 100 MB/s) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: UnusualDiskReadRate
|
||||
expr: sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Unusual disk read rate (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Le disque lit sans doute trop de données (> 50 MB/s) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: UnusualDiskWriteRate
|
||||
expr: sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Unusual disk write rate (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Le disque écrit sans doute trop de données (> 50 MB/s) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: OutOfDiskSpace
|
||||
expr: node_filesystem_free_bytes{mountpoint ="/"} / node_filesystem_size_bytes{mountpoint ="/"} * 100 < 20
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Out of disk space (instance {{ $labels.instance }})"
|
||||
description: "<!channel> L'espace disque est presque complet (< 20% restant) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: UnusualDiskReadLatency
|
||||
expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Unusual disk read latency (instance {{ $labels.instance }})"
|
||||
description: "<!channel> La latence du disque augmente (read operations > 100ms) VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: CpuLoad
|
||||
expr: node_load15 / (count without (cpu, mode) (node_cpu_seconds_total{mode="system"})) > 2
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "CPU load (instance {{ $labels.instance }})"
|
||||
description: "<!channel> La charge CPU (15m) est élevée VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: ContextSwitching
|
||||
expr: rate(node_context_switches_total[5m]) > ((count without (cpu, mode) (node_cpu_seconds_total{mode="system"})) * 1500)
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Context switching (instance {{ $labels.instance }})"
|
||||
description: "<!channel> Le contexte switch augement sur l'hôte VALUE = {{ $value }} LABELS: {{ $labels.job }} : {{ $labels.instance }}"
|
||||
|
||||
- alert: Health endpoint down
|
||||
expr: probe_success == 0
|
||||
for: 10s
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "Health endpoint is down"
|
||||
description: "<!channel> L'URL ne répond pas : {{ $labels.addresse }}"
|
||||
|
||||
- alert: Certificate exprire
|
||||
expr: probe_ssl_earliest_cert_expiry{job="blackbox"} - time() < 86400 * 30
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critique
|
||||
annotations:
|
||||
identifier: "{{ $labels.instance }}"
|
||||
summary: "SSL certificate expire"
|
||||
description: "<!channel> Le certificat SSL exprire dans 3 mois {{ $labels.addresse }}"
|
||||
Reference in new issue
Block a user