summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRebeccah Hunter <rhunter@redhat.com>2022-10-12 20:08:17 +0200
committerGitHub <noreply@github.com>2022-10-12 20:08:17 +0200
commit50614b961ea4868ba4c437f69ba511302f46acfd (patch)
treeefa615c5592070e7e0231515f13bacf7cc665aff
parentMerge pull request #12974 from kialam/new-health-check-started (diff)
parentUpdates to Grafana Dashboard and example alerts (diff)
downloadawx-50614b961ea4868ba4c437f69ba511302f46acfd.tar.xz
awx-50614b961ea4868ba4c437f69ba511302f46acfd.zip
Merge pull request #13001 from kdelee/moooore-dashboard
Moooore 🐮 dashboard
Diffstat
-rw-r--r--tools/docker-compose/ansible/roles/sources/templates/docker-compose.yml.j22
-rw-r--r--tools/grafana/README.md11
-rw-r--r--tools/grafana/alerting/alerts.yml301
-rw-r--r--tools/grafana/dashboards/demo_dashboard.json2114
4 files changed, 1463 insertions, 965 deletions
diff --git a/tools/docker-compose/ansible/roles/sources/templates/docker-compose.yml.j2 b/tools/docker-compose/ansible/roles/sources/templates/docker-compose.yml.j2
index db4988b207..ee2e79f990 100644
--- a/tools/docker-compose/ansible/roles/sources/templates/docker-compose.yml.j2
+++ b/tools/docker-compose/ansible/roles/sources/templates/docker-compose.yml.j2
@@ -180,7 +180,7 @@ services:
image: postgres:12
container_name: tools_postgres_1
# additional logging settings for postgres can be found https://www.postgresql.org/docs/current/runtime-config-logging.html
- command: postgres -c log_destination=stderr -c log_min_messages=info -c log_min_duration_statement={{ pg_log_min_duration_statement|default(1000) }}
+ command: postgres -c log_destination=stderr -c log_min_messages=info -c log_min_duration_statement={{ pg_log_min_duration_statement|default(1000) }} -c max_connections={{ pg_max_connections|default(1024) }}
environment:
POSTGRES_HOST_AUTH_METHOD: trust
POSTGRES_USER: {{ pg_username }}
diff --git a/tools/grafana/README.md b/tools/grafana/README.md
index f6e17c256b..a2fc38e69c 100644
--- a/tools/grafana/README.md
+++ b/tools/grafana/README.md
@@ -36,9 +36,18 @@ GRAFANA=true PROMETHEUS=true EXTRA_SOURCES_ANSIBLE_OPTS="-e scrape_interval=1 ad
We are configuring alerts in grafana using the provisioning files method. This feature is new in Grafana as of August, 2022. Documentation can be found: https://grafana.com/docs/grafana/latest/administration/provisioning/#alerting however it does not fully show all parameters to the config.
-One way to understand how to build rules is to build them in the UI and use chrometools to inspect the payload as you save the rules. It appears that the "data" portion of the payload for each rule is the same syntax as needed in the provisioning file config. To reload the alerts without restarting the container, from within the container you can send a POST with `curl -X POST http://admin:admin@localhost:3000/api/admin/provisioning/alerting/reload`. Keep in mind the grafana container does not contain `curl`. You can install it with the command `apk add curl`.
+One way to understand how to build rules is to build them in the UI and use chrometools to inspect the payload as you save the rules. It appears that the "data" portion of the payload for each rule is the same syntax as needed in the provisioning file config. To reload the alerts without restarting the container, from your terminal you can send a POST with `curl -X POST http://admin:admin@localhost:3001/api/admin/provisioning/alerting/reload`.
Another way to export rules is explore the api.
1. Get all the folders: `GET` to `/api/folders`
2. Get the rules `GET` to `/api/ruler/grafana/api/v1/rules/{{ Folder }}`
+You can do this via curl or in the web browser.
+
+### Included Alerts
+
+#### Alert if remaining capacity low and pending jobs exist
+
+We want to know if jobs are in pending but we lack capacity in the cluster to run them. Our approach is to sum all remaining capacity in the cluster and compare it to the total capacity of the cluster. If less than 10% of our capacity is remaining and we have pending jobs, and this is true for more than 180s, we will fire the alert.
+
+This alert is named "capacity_below_10_percent" and can be found in this directory in https://github.com/ansible/awx/blob/devel/tools/grafana/alerting/alerts.yml
diff --git a/tools/grafana/alerting/alerts.yml b/tools/grafana/alerting/alerts.yml
index a6679e2989..d3e0f32189 100644
--- a/tools/grafana/alerting/alerts.yml
+++ b/tools/grafana/alerting/alerts.yml
@@ -2,15 +2,21 @@
apiVersion: 1
groups:
- folder: awx
- interval: 60s
+ interval: 10s
name: awx_rules
orgId: 1
+ exec_err_state: Alerting
+ no_data_state: NoData
rules:
- - condition: if_failures_too_high
- dashboardUid: awx
+ - for: 5m
+ noDataState: OK
+ panelId: 2
+ title: failure_rate_exceeded_20_percent
+ uid: failure_rate_exceeded_20_percent
+ condition: compare
data:
- refId: total_errors
- queryType: ''
+ queryType: ""
relativeTimeRange:
from: 600
to: 0
@@ -19,7 +25,7 @@ groups:
editorMode: code
expr: >-
max(delta(awx_instance_status_total{instance="awx1:8013",
- status="failed|error"}[30m]))
+ status=~"failed|error"}[30m]))
hide: false
intervalMs: 1000
legendFormat: __auto
@@ -27,11 +33,11 @@ groups:
range: true
refId: total_errors
- refId: max_errors
- queryType: ''
+ queryType: ""
relativeTimeRange:
from: 0
to: 0
- datasourceUid: '-100'
+ datasourceUid: "-100"
model:
conditions:
- evaluator:
@@ -60,7 +66,7 @@ groups:
refId: max_errors
type: reduce
- refId: total_success
- queryType: ''
+ queryType: ""
relativeTimeRange:
from: 600
to: 0
@@ -80,11 +86,11 @@ groups:
range: true
refId: total_success
- refId: max_success
- queryType: ''
+ queryType: ""
relativeTimeRange:
from: 0
to: 0
- datasourceUid: '-100'
+ datasourceUid: "-100"
model:
conditions:
- evaluator:
@@ -113,11 +119,11 @@ groups:
refId: max_success
type: reduce
- refId: compare
- queryType: ''
+ queryType: ""
relativeTimeRange:
from: 0
to: 0
- datasourceUid: '-100'
+ datasourceUid: "-100"
model:
conditions:
- evaluator:
@@ -158,15 +164,19 @@ groups:
maxDataPoints: 43200
refId: compare
type: math
- for: 30m
+ - for: 60s
noDataState: OK
- panelId: 2
- title: failure_rate_exceeded_20_percent
- uid: failure_rate_exceeded_20_percent
- - condition: if_redis_queue_too_large
+ panelId: 1
+ title: redis_queue_too_large_to_clear_in_2_min
+ uid: redis_queue_too_large_to_clear_in_2_min
+ condition: redis_queue_growing_faster_than_insertion_rate
dashboardUid: awx
data:
- - datasourceUid: awx_prometheus
+ - refId: events_insertion_rate_per_second
+ relativeTimeRange:
+ from: 300
+ to: 0
+ datasourceUid: awx_prometheus
model:
editorMode: code
expr: irate(callback_receiver_events_insert_db{node='awx_1'}[1m])
@@ -177,11 +187,11 @@ groups:
range: true
refId: events_insertion_rate_per_second
queryType: ""
- refId: events_insertion_rate_per_second
+ - refId: mean_event_insertion_rate
relativeTimeRange:
- from: 300
+ from: 0
to: 0
- - datasourceUid: -100
+ datasourceUid: -100
model:
conditions:
- evaluator:
@@ -208,11 +218,11 @@ groups:
refId: mean_event_insertion_rate
type: reduce
queryType: ""
- refId: mean_event_insertion_rate
+ - refId: redis_queue_size
relativeTimeRange:
- from: 0
+ from: 300
to: 0
- - datasourceUid: awx_prometheus
+ datasourceUid: awx_prometheus
model:
datasource:
type: prometheus
@@ -226,11 +236,11 @@ groups:
range: true
refId: redis_queue_size
queryType: ""
- refId: redis_queue_size
+ - refId: last_redis_queue_size
relativeTimeRange:
- from: 300
- to: 0
- - datasourceUid: -100
+ from: 0
+ to: 0
+ datasourceUid: -100
model:
conditions:
- evaluator:
@@ -257,11 +267,12 @@ groups:
refId: last_redis_queue_size
type: reduce
queryType: ""
- refId: last_redis_queue_size
+ - refId: redis_queue_growing_faster_than_insertion_rate
+ queryType: ""
relativeTimeRange:
from: 0
to: 0
- - datasourceUid: -100
+ datasourceUid: -100
model:
conditions:
- evaluator:
@@ -282,44 +293,167 @@ groups:
name: Expression
type: __expr__
uid: __expr__
- expression: '($last_redis_queue_size > ($mean_event_insertion_rate * 120))'
+ expression: "($last_redis_queue_size > ($mean_event_insertion_rate * 120))"
hide: false
intervalMs: 1000
maxDataPoints: 43200
- refId: redis_queue_growing_faster_than_insertion_rate
type: math
+ - for: 60s
+ noDataState: OK
+ panelId: 3
+ uid: capacity_below_10_percent
+ title: capacity_below_10_percent
+ condition: pending_jobs_and_capacity_compare
+ data:
+ - refId: remaining_capacity
+ queryType: ""
+ relativeTimeRange:
+ from: 300
+ to: 0
+ datasourceUid: awx_prometheus
+ model:
+ editorMode: code
+ expr: sum(awx_instance_remaining_capacity)
+ hide: false
+ intervalMs: 1000
+ legendFormat: __auto
+ maxDataPoints: 43200
+ range: true
+ refId: remaining_capacity
+ - refId: last_remaining_capacity
queryType: ""
- refId: redis_queue_growing_faster_than_insertion_rate
relativeTimeRange:
from: 0
to: 0
- for: 60s
- noDataState: OK
- panelId: 1
- title: redis_queue_too_large_to_clear_in_2_min
- uid: redis_queue_too_large_to_clear_in_2_min
- - condition: if_capacity_is_too_low
- dashboardUid: awx
- no_data_state: OK
- exec_err_state: Error
- data:
- - refId: remaining_capacity
- queryType: ''
+ datasourceUid: "-100"
+ model:
+ conditions:
+ - evaluator:
+ params:
+ - 3
+ type: outside_range
+ operator:
+ type: and
+ query:
+ params:
+ - total_capacity
+ reducer:
+ params: []
+ type: percent_diff
+ type: query
+ datasource:
+ type: __expr__
+ uid: "-100"
+ expression: remaining_capacity
+ hide: false
+ intervalMs: 1000
+ maxDataPoints: 43200
+ reducer: last
+ refId: last_remaining_capacity
+ type: reduce
+ - refId: total_capacity
+ queryType: ""
+ relativeTimeRange:
+ from: 600
+ to: 0
+ datasourceUid: awx_prometheus
+ model:
+ datasource:
+ type: prometheus
+ uid: awx_prometheus
+ editorMode: code
+ expr: sum(awx_instance_capacity{instance="awx1:8013"})
+ hide: false
+ intervalMs: 1000
+ legendFormat: __auto
+ maxDataPoints: 43200
+ range: true
+ refId: total_capacity
+ - refId: last_total_capacity
+ queryType: ""
+ relativeTimeRange:
+ from: 0
+ to: 0
+ datasourceUid: "-100"
+ model:
+ conditions:
+ - evaluator:
+ params:
+ - 0
+ - 0
+ type: gt
+ operator:
+ type: and
+ query:
+ params:
+ - capacity_below_10%
+ reducer:
+ params: []
+ type: avg
+ type: query
+ datasource:
+ name: Expression
+ type: __expr__
+ uid: __expr__
+ expression: total_capacity
+ hide: false
+ intervalMs: 1000
+ maxDataPoints: 43200
+ reducer: last
+ refId: last_total_capacity
+ type: reduce
+ - refId: 10_percent_total_capacity
+ queryType: ""
relativeTimeRange:
- from: 1800
+ from: 0
+ to: 0
+ datasourceUid: "-100"
+ model:
+ conditions:
+ - evaluator:
+ params:
+ - 0
+ - 0
+ type: gt
+ operator:
+ type: and
+ query:
+ params:
+ - last_total_capacity
+ reducer:
+ params: []
+ type: avg
+ type: query
+ datasource:
+ name: Expression
+ type: __expr__
+ uid: __expr__
+ expression: "$last_total_capacity*.10"
+ hide: false
+ intervalMs: 1000
+ maxDataPoints: 43200
+ refId: 10_percent_total_capacity
+ type: math
+ - refId: pending_jobs
+ queryType: ""
+ relativeTimeRange:
+ from: 600
to: 0
datasourceUid: awx_prometheus
model:
+ datasource:
+ type: prometheus
+ uid: awx_prometheus
editorMode: builder
- expr: awx_instance_remaining_capacity{instance="awx1:8013"}
+ expr: awx_pending_jobs_total{instance="awx1:8013"}
hide: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
- refId: remaining_capacity
- - refId: if_capacity_is_too_low
- queryType: ''
+ refId: pending_jobs
+ - refId: last_pending_jobs
+ queryType: ""
relativeTimeRange:
from: 0
to: 0
@@ -328,14 +462,14 @@ groups:
conditions:
- evaluator:
params:
- - 20
- 0
- type: lt
+ - 0
+ type: gt
operator:
- type: when
+ type: and
query:
params:
- - remaining_capacity
+ - pending_jobs_and_capacity_compare
reducer:
params: []
type: avg
@@ -344,12 +478,59 @@ groups:
name: Expression
type: __expr__
uid: __expr__
- expression: remaining_capacity
+ expression: pending_jobs
+ hide: false
+ intervalMs: 1000
+ maxDataPoints: 43200
+ reducer: last
+ refId: last_pending_jobs
+ type: reduce
+ - refId: pending_jobs_and_capacity_compare
+ queryType: ""
+ relativeTimeRange:
+ from: 0
+ to: 0
+ datasourceUid: "-100"
+ model:
+ conditions:
+ - evaluator:
+ params:
+ - 0
+ - 0
+ type: gt
+ operator:
+ type: and
+ query:
+ params:
+ - 10_percent_total_capacity
+ reducer:
+ params: []
+ type: last
+ type: query
+ - evaluator:
+ params:
+ - 0
+ - 0
+ type: gt
+ operator:
+ type: and
+ query:
+ params:
+ - pending_jobs
+ reducer:
+ params: []
+ type: last
+ type: query
+ datasource:
+ name: Expression
+ type: __expr__
+ uid: __expr__
+ expression:
+ "($10_percent_total_capacity > $last_remaining_capacity) && $last_pending_jobs
+ > 1"
hide: false
intervalMs: 1000
maxDataPoints: 43200
- refId: if_capacity_is_too_low
- type: classic_conditions
- for: 30m
- title: if_capacity_is_too_low
- uid: if_capacity_is_too_low
+ reducer: mean
+ refId: pending_jobs_and_capacity_compare
+ type: math
diff --git a/tools/grafana/dashboards/demo_dashboard.json b/tools/grafana/dashboards/demo_dashboard.json
index 3589794499..f654bc8e6f 100644
--- a/tools/grafana/dashboards/demo_dashboard.json
+++ b/tools/grafana/dashboards/demo_dashboard.json
@@ -29,6 +29,19 @@
"liveNow": false,
"panels": [
{
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 37,
+ "panels": [],
+ "title": "System",
+ "type": "row"
+ },
+ {
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
@@ -73,7 +86,8 @@
"mode": "absolute",
"steps": [
{
- "color": "green"
+ "color": "green",
+ "value": null
},
{
"color": "red",
@@ -82,61 +96,15 @@
]
}
},
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "failed"
- },
- "properties": [
- {
- "id": "color",
- "value": {
- "fixedColor": "semi-dark-red",
- "mode": "fixed"
- }
- }
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "running"
- },
- "properties": [
- {
- "id": "color",
- "value": {
- "fixedColor": "dark-green",
- "mode": "fixed"
- }
- }
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "canceled"
- },
- "properties": [
- {
- "id": "color",
- "value": {
- "fixedColor": "super-light-yellow",
- "mode": "fixed"
- }
- }
- ]
- }
- ]
+ "overrides": []
},
"gridPos": {
- "h": 6,
+ "h": 8,
"w": 12,
"x": 0,
- "y": 0
+ "y": 1
},
- "id": 8,
+ "id": 14,
"options": {
"legend": {
"calcs": [],
@@ -155,106 +123,90 @@
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "code",
- "expr": "awx_status_total",
- "legendFormat": "{{status}}",
+ "editorMode": "builder",
+ "expr": "awx_database_connections_total",
+ "legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
- "title": "job status",
+ "title": "Database",
"type": "timeseries"
},
{
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
+ "datasource": {},
"fieldConfig": {
"defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
}
- },
- "mappings": [],
+ ],
"thresholds": {
"mode": "absolute",
"steps": [
{
- "color": "green"
+ "color": "light-blue",
+ "value": null
},
{
"color": "red",
"value": 80
}
]
- }
+ },
+ "unit": "short"
},
"overrides": []
},
"gridPos": {
- "h": 6,
- "w": 12,
+ "h": 4,
+ "w": 5,
"x": 12,
- "y": 0
+ "y": 1
},
- "id": 27,
+ "id": 25,
+ "links": [],
+ "maxDataPoints": 100,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
+ "colorMode": "background",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "/^tower_version$/",
+ "values": false
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
+ "textMode": "auto"
},
+ "pluginVersion": "9.1.6",
"targets": [
{
"datasource": {
"type": "prometheus",
- "uid": "awx_prometheus"
+ "uid": "000000021"
},
- "editorMode": "builder",
- "expr": "awx_instance_remaining_capacity",
- "legendFormat": "remaining_capacity_{{hostname}}",
- "range": true,
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "awx_system_info",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
"refId": "A"
}
],
- "title": "Remaining Instance Capacity",
- "type": "timeseries"
+ "title": "Controller Version",
+ "type": "stat"
},
{
"datasource": {
@@ -263,49 +215,14 @@
},
"fieldConfig": {
"defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
- },
+ "displayName": "Instances",
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
- "color": "green"
- },
- {
- "color": "red",
- "value": 80
+ "color": "light-blue",
+ "value": null
}
]
}
@@ -313,886 +230,1277 @@
"overrides": []
},
"gridPos": {
- "h": 8,
- "w": 12,
- "x": 0,
- "y": 6
+ "h": 4,
+ "w": 5,
+ "x": 12,
+ "y": 5
},
- "id": 20,
+ "id": 13,
"options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
+ "colorMode": "background",
+ "graphMode": "none",
+ "justifyMode": "center",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
+ "textMode": "auto"
},
+ "pluginVersion": "9.1.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "awx_instance_consumed_capacity",
- "legendFormat": "__auto",
+ "editorMode": "code",
+ "expr": "count(awx_instance_info)",
+ "interval": "",
+ "legendFormat": " ",
"range": true,
"refId": "A"
}
],
- "title": "Consumed Instance Capacity",
- "type": "timeseries"
+ "title": "Controller Node Count",
+ "type": "stat"
},
{
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 9
},
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 32,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
- },
- "thresholdsStyle": {
- "mode": "off"
- }
+ "id": 35,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
- }
- ]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}"
- },
- "properties": [
- {
- "id": "color",
- "value": {
- "fixedColor": "blue",
- "mode": "fixed"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
}
},
- {
- "id": "displayName",
- "value": "Job Events Processed/Minute"
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
}
- ]
- },
- {
- "matcher": {
- "id": "byName",
- "options": "{__name__=\"callback_receiver_events_queue_size_redis\", instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}"
},
- "properties": [
+ "overrides": [
{
- "id": "color",
- "value": {
- "fixedColor": "semi-dark-red",
- "mode": "fixed"
- }
+ "matcher": {
+ "id": "byName",
+ "options": "failed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "semi-dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "running"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-green",
+ "mode": "fixed"
+ }
+ }
+ ]
},
{
- "id": "displayName",
- "value": "Redis Queue Size"
+ "matcher": {
+ "id": "byName",
+ "options": "canceled"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "super-light-yellow",
+ "mode": "fixed"
+ }
+ }
+ ]
}
]
- }
- ]
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 6
- },
- "id": 24,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "callback_receiver_events_queue_size_redis",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 10
+ },
+ "id": 8,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "code",
+ "expr": "awx_status_total",
+ "legendFormat": "{{status}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "job status",
+ "type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "code",
- "expr": "irate(callback_receiver_events_insert_db[1m])*60",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "B"
- }
- ],
- "title": "Redis Queue Size vs. Job Events Processed/Minute",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
- },
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "thresholdsStyle": {
- "mode": "off"
- }
- },
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
+ "overrides": [
{
- "color": "green"
+ "matcher": {
+ "id": "byName",
+ "options": "awx_1-error"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
},
{
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": [
- {
- "__systemRef": "hideSeriesFrom",
- "matcher": {
- "id": "byNames",
- "options": {
- "mode": "exclude",
- "names": [
- "task_manager_pending_processed{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}",
- "task_manager_running_processed{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}",
- "task_manager_tasks_started{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}"
- ],
- "prefix": "All except:",
- "readOnly": true
- }
- },
- "properties": [
+ "matcher": {
+ "id": "byName",
+ "options": "awx_1-successful"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "light-purple",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
{
- "id": "custom.hideFrom",
- "value": {
- "legend": false,
- "tooltip": false,
- "viz": true
- }
+ "matcher": {
+ "id": "byName",
+ "options": "awx_3-failed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "light-orange",
+ "mode": "fixed"
+ }
+ }
+ ]
}
]
- }
- ]
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 0,
- "y": 14
- },
- "id": 12,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
},
- "expr": "task_manager_running_processed",
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 10
},
- "expr": "task_manager_pending_processed",
- "hide": false,
- "refId": "B"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "id": 29,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
},
- "expr": "task_manager_tasks_blocked",
- "hide": false,
- "refId": "D"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "awx_instance_status_total",
+ "legendFormat": "{{node}}-{{status}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Job Status per Instance",
+ "type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "expr": "task_manager_tasks_started",
- "hide": false,
- "refId": "C"
- }
- ],
- "title": "Task manager workload",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 18,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "smooth",
- "lineStyle": {
- "fill": "solid"
- },
- "lineWidth": 1,
- "pointSize": 6,
- "scaleDistribution": {
- "type": "linear"
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 18
+ },
+ "id": 16,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- "thresholdsStyle": {
- "mode": "off"
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": [
- {
- "matcher": {
- "id": "byName",
- "options": "{__name__=\"callback_receiver_event_processing_avg_seconds\", instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}"
+ "editorMode": "builder",
+ "expr": "dependency_manager__schedule_seconds",
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
},
- "properties": [
- {
- "id": "color",
- "value": {
- "fixedColor": "orange",
- "mode": "fixed"
- }
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "id": "displayName",
- "value": "Avg Job Event Processing Lag Time"
- }
- ]
- }
- ]
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 14
- },
- "id": 26,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
+ "editorMode": "builder",
+ "expr": "dependency_manager_generate_dependencies_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "dependency_manager_get_tasks_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "hide": false,
+ "refId": "D"
+ }
+ ],
+ "title": "Dependency Manager Timings",
+ "type": "timeseries"
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "callback_receiver_event_processing_avg_seconds",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
- }
- ],
- "title": "Avg Job Event Processing Lag Time",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 18
+ },
+ "id": 18,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- "thresholdsStyle": {
- "mode": "off"
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": []
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 0,
- "y": 22
- },
- "id": 10,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
+ "editorMode": "builder",
+ "expr": "workflow_manager__schedule_seconds",
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "hide": false,
+ "refId": "B"
+ }
+ ],
+ "title": "Workflow Manager Timings",
+ "type": "timeseries"
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "task_manager_process_pending_tasks_seconds",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
},
- "editorMode": "builder",
- "expr": "task_manager_process_running_tasks_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "B"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "gridPos": {
+ "h": 6,
+ "w": 12,
+ "x": 0,
+ "y": 26
},
- "editorMode": "builder",
- "expr": "task_manager_get_tasks_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "D"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "id": 27,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
},
- "editorMode": "builder",
- "expr": "task_manager_commit_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "C"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "awx_instance_remaining_capacity",
+ "legendFormat": "remaining_capacity_{{hostname}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Remaining Instance Capacity",
+ "type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "task_manager__schedule_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "E"
- }
- ],
- "title": "Task manager timings",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "description": "",
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 26
+ },
+ "id": 20,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- "thresholdsStyle": {
- "mode": "off"
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": []
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 22
- },
- "id": 16,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
+ "editorMode": "builder",
+ "expr": "awx_instance_consumed_capacity",
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Consumed Instance Capacity",
+ "type": "timeseries"
}
+ ],
+ "title": "Jobs and Capacity",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 10
},
- "targets": [
+ "id": 33,
+ "panels": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "dependency_manager__schedule_seconds",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": [
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "task_manager_pending_processed{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}",
+ "task_manager_running_processed{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}",
+ "task_manager_tasks_started{instance=\"awx1:8013\", job=\"awx\", node=\"awx_1\"}"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": false,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
},
- "editorMode": "builder",
- "expr": "dependency_manager_generate_dependencies_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "B"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 2
},
- "editorMode": "builder",
- "expr": "dependency_manager_get_tasks_seconds",
- "hide": false,
- "legendFormat": "__auto",
- "range": true,
- "refId": "C"
+ "id": 12,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "expr": "task_manager_running_processed",
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "expr": "task_manager_pending_processed",
+ "hide": false,
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "expr": "task_manager_tasks_blocked",
+ "hide": false,
+ "refId": "D"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "expr": "task_manager_tasks_started",
+ "hide": false,
+ "refId": "C"
+ }
+ ],
+ "title": "Task manager workload",
+ "type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "hide": false,
- "refId": "D"
- }
- ],
- "title": "Dependency Manager Timings",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 2
+ },
+ "id": 10,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- "thresholdsStyle": {
- "mode": "off"
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": []
- },
+ "editorMode": "builder",
+ "expr": "task_manager_process_pending_tasks_seconds",
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "task_manager_process_running_tasks_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "task_manager_get_tasks_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "D"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "task_manager_commit_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "task_manager__schedule_seconds",
+ "hide": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "E"
+ }
+ ],
+ "title": "Task manager timings",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Task Manager",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
"gridPos": {
- "h": 8,
- "w": 12,
+ "h": 1,
+ "w": 24,
"x": 0,
- "y": 30
- },
- "id": 14,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
- },
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
+ "y": 11
},
- "targets": [
+ "id": 31,
+ "panels": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "awx_database_connections_total",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
- }
- ],
- "title": "Database",
- "type": "timeseries"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
- },
- "fieldConfig": {
- "defaults": {
- "color": {
- "mode": "palette-classic"
- },
- "custom": {
- "axisCenteredZero": false,
- "axisColorMode": "text",
- "axisLabel": "",
- "axisPlacement": "auto",
- "barAlignment": 0,
- "drawStyle": "line",
- "fillOpacity": 0,
- "gradientMode": "none",
- "hideFrom": {
- "legend": false,
- "tooltip": false,
- "viz": false
- },
- "lineInterpolation": "linear",
- "lineWidth": 1,
- "pointSize": 5,
- "scaleDistribution": {
- "type": "linear"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 18,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "smooth",
+ "lineStyle": {
+ "fill": "solid"
+ },
+ "lineWidth": 1,
+ "pointSize": 6,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
- "showPoints": "auto",
- "spanNulls": false,
- "stacking": {
- "group": "A",
- "mode": "none"
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 36
+ },
+ "id": 26,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- "thresholdsStyle": {
- "mode": "off"
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
},
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
},
- {
- "color": "red",
- "value": 80
- }
- ]
- }
- },
- "overrides": []
- },
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 30
- },
- "id": 18,
- "options": {
- "legend": {
- "calcs": [],
- "displayMode": "list",
- "placement": "bottom",
- "showLegend": true
+ "editorMode": "builder",
+ "expr": "callback_receiver_event_processing_avg_seconds",
+ "legendFormat": "{{node}}-processing-avg-seconds",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Avg Job Event Processing Lag Time",
+ "type": "timeseries"
},
- "tooltip": {
- "mode": "single",
- "sort": "none"
- }
- },
- "targets": [
{
"datasource": {
"type": "prometheus",
"uid": "awx_prometheus"
},
- "editorMode": "builder",
- "expr": "workflow_manager__schedule_seconds",
- "legendFormat": "__auto",
- "range": true,
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "awx_prometheus"
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 31,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 1,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ }
+ ]
+ }
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "awx_2-job-event-processing-rate"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "light-green",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "awx_1-redis-queue"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "semi-dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 36
+ },
+ "id": 24,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
},
- "hide": false,
- "refId": "B"
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "builder",
+ "expr": "callback_receiver_events_queue_size_redis",
+ "legendFormat": "{{node}}-redis-queue",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "awx_prometheus"
+ },
+ "editorMode": "code",
+ "expr": "irate(callback_receiver_events_insert_db[1m])*60",
+ "hide": false,
+ "legendFormat": "{{node}}-job-event-processing-rate",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Redis Queue Size vs. Job Events Processed/Minute",
+ "type": "timeseries"
}
],
- "title": "Workflow Manager Timings",
- "type": "timeseries"
+ "title": "Job Event Processing",
+ "type": "row"
}
],
"refresh": "5s",
@@ -1210,6 +1518,6 @@
"timezone": "",
"title": "awx-demo",
"uid": "GISWZOXnk",
- "version": 2,
+ "version": 12,
"weekStart": ""
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-30 06:49:34 +0100