Skip to content

Add Grafana dashboard for Prometheus monitoring #385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
muratugureminoglu wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Add Grafana dashboard for Prometheus monitoring #385

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8ea094a
Add Grafana dashboard for Prometheus monitoring
muratugureminoglu May 31, 2026
cab28de
Add Grafana alert rules for AntMedia monitoring
muratugureminoglu May 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
312 changes: 312 additions & 0 deletions monitor/grafana-prometheus-alert-rules.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,312 @@
apiVersion: 1
groups:
- orgId: 1
name: AntMedia Multitenant
folder: AntMedia Alerts
interval: 1m
rules:
- uid: antmedia-db-query-gt-20s
title: AntMedia DB Average Query Time > 20s
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: cflfl4jfwlpfkd
model:
datasource:
type: prometheus
uid: cflfl4jfwlpfkd
editorMode: code
expr: max by (job, instance, user) (ams_dbaveragequerytimems{job=~".+",instance=~".+",user=~".+"}) / 1000
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: A
intervalMs: 1000
maxDataPoints: 43200
reducer: last
refId: B
settings:
mode: dropNN
type: reduce
- refId: C
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: $B > 20
intervalMs: 1000
maxDataPoints: 43200
refId: C
type: math
dashboardUid: antmedia-multitenant-pushgateway
panelId: 7
noDataState: NoData
execErrState: Error
for: 2m
annotations:
__dashboardUid__: antmedia-multitenant-pushgateway
__panelId__: "7"
description: Tenant {{ $labels.user }} on {{ $labels.instance }} exceeded 20s DB query time.
summary: DB average query time is above 20 seconds
labels:
service: antmedia
severity: critical
source: prometheus-pushgateway
isPaused: false
- uid: antmedia-cpu-load-gt-50
title: AntMedia CPU Load > 50
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: cflfl4jfwlpfkd
model:
datasource:
type: prometheus
uid: cflfl4jfwlpfkd
editorMode: code
expr: max by (job, instance, user) (ams_cpuusage_processcpuload{job=~".+",instance=~".+",user=~".+"})
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: A
intervalMs: 1000
maxDataPoints: 43200
reducer: last
refId: B
settings:
mode: dropNN
type: reduce
- refId: C
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: $B > 50
intervalMs: 1000
maxDataPoints: 43200
refId: C
type: math
dashboardUid: antmedia-multitenant-pushgateway
panelId: 5
noDataState: NoData
execErrState: Error
for: 2m
annotations:
__dashboardUid__: antmedia-multitenant-pushgateway
__panelId__: "5"
description: Tenant {{ $labels.user }} on {{ $labels.instance }} exceeded CPU load 50.
summary: CPU load is above 50
labels:
service: antmedia
severity: warning
source: prometheus-pushgateway
isPaused: false
- uid: antmedia-system-load-gt-20
title: AntMedia System Load Average (1m) > 20
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: cflfl4jfwlpfkd
model:
datasource:
type: prometheus
uid: cflfl4jfwlpfkd
editorMode: code
expr: max by (job, instance, user) (ams_cpuusage_systemloadaveragelastminute{job=~".+",instance=~".+",user=~".+"})
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: A
intervalMs: 1000
maxDataPoints: 43200
reducer: last
refId: B
settings:
mode: dropNN
type: reduce
- refId: C
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: $B > 20
intervalMs: 1000
maxDataPoints: 43200
refId: C
type: math
dashboardUid: antmedia-multitenant-pushgateway
panelId: 6
noDataState: NoData
execErrState: Error
for: 2m
annotations:
__dashboardUid__: antmedia-multitenant-pushgateway
__panelId__: "6"
description: Tenant {{ $labels.user }} on {{ $labels.instance }} exceeded load average 20.
summary: System load average is above 20
labels:
service: antmedia
severity: warning
source: prometheus-pushgateway
isPaused: false
- uid: antmedia-memory-free-lt-20
title: AntMedia System Memory Free < 20%
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: cflfl4jfwlpfkd
model:
datasource:
type: prometheus
uid: cflfl4jfwlpfkd
editorMode: code
expr: 100 * max by (job, instance, user) (ams_systemmemoryinfo_availablememory{job=~".+",instance=~".+",user=~".+"}) / max by (job, instance, user) (ams_systemmemoryinfo_totalmemory{job=~".+",instance=~".+",user=~".+"})
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: A
intervalMs: 1000
maxDataPoints: 43200
reducer: last
refId: B
settings:
mode: dropNN
type: reduce
- refId: C
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: $B < 20
intervalMs: 1000
maxDataPoints: 43200
refId: C
type: math
dashboardUid: antmedia-multitenant-pushgateway
panelId: 12
noDataState: NoData
execErrState: Error
for: 2m
annotations:
__dashboardUid__: antmedia-multitenant-pushgateway
__panelId__: "12"
description: Tenant {{ $labels.user }} on {{ $labels.instance }} dropped below 20% free memory.
summary: System memory free percentage is below 20%
labels:
service: antmedia
severity: critical
source: prometheus-pushgateway
isPaused: false
- uid: antmedia-disk-free-lt-20
title: AntMedia Disk Free < 20%
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: cflfl4jfwlpfkd
model:
datasource:
type: prometheus
uid: cflfl4jfwlpfkd
editorMode: code
expr: 100 * max by (job, instance, user) (ams_filesysteminfo_freespace{job=~".+",instance=~".+",user=~".+"}) / max by (job, instance, user) (ams_filesysteminfo_totalspace{job=~".+",instance=~".+",user=~".+"})
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: A
intervalMs: 1000
maxDataPoints: 43200
reducer: last
refId: B
settings:
mode: dropNN
type: reduce
- refId: C
datasourceUid: __expr__
model:
datasource:
type: __expr__
uid: __expr__
expression: $B < 20
intervalMs: 1000
maxDataPoints: 43200
refId: C
type: math
dashboardUid: antmedia-multitenant-pushgateway
panelId: 13
noDataState: NoData
execErrState: Error
for: 2m
annotations:
__dashboardUid__: antmedia-multitenant-pushgateway
__panelId__: "13"
description: Tenant {{ $labels.user }} on {{ $labels.instance }} dropped below 20% free disk.
summary: Disk free percentage is below 20%
labels:
service: antmedia
severity: critical
source: prometheus-pushgateway
isPaused: false
Loading
Loading