cerc-io/stack-orchestrator
17
1
Fork 3
Code Issues 113 Pull Requests 18 Actions Packages Projects Releases 480 Wiki Activity

Setup basic alerting for watchers in monitoring stack #698

Merged
prathamesh0 merged 5 commits from pm-grafana-alerts into main 2024-01-08 11:55:30 +00:00
Conversation 0 Commits 5 Files Changed 5 +971
1 changed files with 971 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 3b5a363483 - Show all commits

971
stack_orchestrator/data/config/monitoring/watcher-alert-rules.yml Normal file
View File

@ -0,0 +1,971 @@
apiVersion: 1
groups:
- orgId: 1
name: watcher
folder: WatcherAlerts
interval: 30s
rules:
# Azimuth
- uid: azimuth_diff_external
title: azimuth_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="azimuth", instance="azimuth", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: censures_diff_external
title: censures_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="azimuth", instance="censures", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: claims_diff_external
title: claims_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="azimuth", instance="claims", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: conditional_star_release_diff_external
title: conditional_star_release_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="azimuth", instance="conditional_star_release", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: delegated_sending_diff_external
title: delegated_sending_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="azimuth", instance="delegated_sending", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: ecliptic_diff_external
title: ecliptic_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="azimuth", instance="ecliptic", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: linear_star_release_diff_external
title: linear_star_release_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="azimuth", instance="linear_star_release", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: polls_diff_external
title: polls_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="azimuth", instance="polls", 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="ethereum"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_external
- refId: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
# Sushi
- uid: sushiswap_diff_external
title: sushiswap_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="sushi", instance="sushiswap", 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: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false
- uid: merkl_sushiswap_diff_external
title: merkl_sushiswap_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="sushi", instance="merkl_sushiswap", 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: latest_indexed
relativeTimeRange:
from: 600
to: 0
datasourceUid: PBFA97CFB590B2093
model:
datasource:
type: prometheus
uid: PBFA97CFB590B2093
editorMode: code
expr: sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
hide: false
instant: true
legendFormat: __auto
range: false
refId: latest_indexed
- 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
dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
panelId: 24
noDataState: Alerting
execErrState: Alerting
for: 15m
annotations:
__dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
__panelId__: "24"
summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
isPaused: false