Add alert rule for Ajna watcher
All checks were successful
Lint Checks / Run linter (pull_request) Successful in 46s
Webapp Test / Run webapp test suite (pull_request) Successful in 4m45s
Deploy Test / Run deploy test suite (pull_request) Successful in 6m5s
K8s Deploy Test / Run deploy test suite on kind/k8s (pull_request) Successful in 9m35s
Smoke Test / Run basic test suite (pull_request) Successful in 5m25s

This commit is contained in:
Prathamesh Musale 2024-04-10 16:03:49 +05:30
parent c4b05ac8a0
commit 6ee69623a3
2 changed files with 88 additions and 0 deletions

View File

@ -771,3 +771,81 @@ groups:
annotations: annotations:
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }} summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false isPaused: false
# Ajna
- uid: ajna_diff_external
title: ajna_watcher_head_tracking
condition: condition
data:
- refId: diff
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
disableTextWrap: false
editorMode: code
expr: latest_block_number - on(chain) group_right sync_status_block_number{job="ajna", instance="ajna", kind="latest_indexed"}
fullMetaSearch: false
includeNullMetadata: true
instant: true
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: false
refId: diff
useBackend: false
- refId: latest_external
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: latest_block_number{chain="filecoin"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: condition
relativeTimeRange:
from: 600
to: 0
datasourceUid: __expr__
model:
conditions:
- evaluator:
params:
- 0
- 0
type: gt
operator:
type: and
query:
params: []
reducer:
params: []
type: avg
type: query
datasource:
name: Expression
type: __expr__
uid: __expr__
expression: ${diff} >= 16
intervalMs: 1000
maxDataPoints: 43200
refId: condition
type: math
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false

View File

@ -103,6 +103,16 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
labels: labels:
instance: 'merkl_sushiswap' instance: 'merkl_sushiswap'
chain: 'filecoin' chain: 'filecoin'
- job_name: ajna
scrape_interval: 20s
metrics_path: /metrics
scheme: http
static_configs:
- targets: ['AJNA_WATCHER_HOST:AJNA_WATCHER_PORT']
labels:
instance: 'ajna'
chain: 'filecoin'
``` ```
Add scrape config as done above for any additional watcher to add it to the Watchers dashboard. Add scrape config as done above for any additional watcher to add it to the Watchers dashboard.