Skip to content

Commit

Permalink
Alertmanager dashboard: allow using cortex_request_duration_seconds n…
Browse files Browse the repository at this point in the history
…ative histogram

Signed-off-by: Yuri Nikolic <durica.nikolic@grafana.com>
  • Loading branch information
duricanikolic committed Jul 22, 2024
1 parent dd70068 commit 946786f
Show file tree
Hide file tree
Showing 7 changed files with 191 additions and 25 deletions.
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,7 @@
* Writes dashboard: `cortex_request_duration_seconds` metric. #8757 #8791
* Reads dashboard: `cortex_request_duration_seconds` metric. #8752
* Rollout progress dashboard. #8779
* Alertmanager dashboard.
* [ENHANCEMENT] Alerts: `MimirRunningIngesterReceiveDelayTooHigh` alert has been tuned to be more reactive to high receive delay. #8538
* [ENHANCEMENT] Dashboards: improve end-to-end latency and strong read consistency panels when experimental ingest storage is enabled. #8543
* [ENHANCEMENT] Dashboards: Add panels for monitoring ingester autoscaling when not using ingest-storage. These panels are disabled by default, but can be enabled using the `autoscaling.ingester.enabled: true` config option. #8484
Expand Down
1 change: 1 addition & 0 deletions operations/helm/charts/mimir-distributed/CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ Entries should include a reference to the Pull Request that introduced the chang
* Writes dashboard: `cortex_request_duration_seconds` metric. #8757
* Reads dashboard: `cortex_request_duration_seconds` metric. #8752
* Rollout progress dashboard. #8779
* Alertmanager dashboard.
* [ENHANCEMENT] Memcached: Update to Memcached 1.6.28 and memcached-exporter 0.14.4. #8557
* [ENHANCEMENT] Add missing fields in multiple topology spread constraints. #8533
* [ENHANCEMENT] Add support for setting the image pull secrets, node selectors, tolerations and topology spread constraints for the Grafana Agent pods used for metamonitoring. #8670
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1175,7 +1175,13 @@ data:
"span": 6,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A_classic"
},
{
"expr": "sum by (status) (\n label_replace(label_replace(histogram_count(rate(cortex_request_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval])),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
Expand Down Expand Up @@ -1224,22 +1230,40 @@ data:
"span": 6,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A"
"refId": "A_classic"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A_native"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B"
"refId": "B_classic"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})",
"expr": "histogram_quantile(0.50, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B_native"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) /\nsum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})\n < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C"
"refId": "C_classic"
},
{
"expr": "1e3 * sum(histogram_sum(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) /\nsum(histogram_count(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}))\n < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C_native"
}
],
"title": "Latency",
Expand Down Expand Up @@ -3134,6 +3158,35 @@ data:
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"current": {
"selected": true,
"text": "classic",
"value": "1"
},
"description": "Choose between showing latencies based on low precision classic or high precision native histogram metrics.",
"hide": 0,
"includeAll": false,
"label": "Latency metrics",
"multi": false,
"name": "latency_metrics",
"options": [
{
"selected": false,
"text": "native",
"value": "-1"
},
{
"selected": true,
"text": "classic",
"value": "1"
}
],
"query": "native : -1,classic : 1",
"skipUrlSync": false,
"type": "custom",
"useTags": false
}
]
},
Expand Down

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading

0 comments on commit 946786f

Please sign in to comment.