forked from RemoteSync/grafana-meta-monitoring-chart
Compare commits
9 Commits
add_tempo_
...
fix_mimir_
Author | SHA1 | Date | |
---|---|---|---|
|
15f96d9cc6 | ||
|
b9f22ba27e | ||
|
2f79e7ef14 | ||
|
6fb22ae671 | ||
|
d3878e1516 | ||
|
8ae136e0c4 | ||
|
ac3e4462f9 | ||
|
c95c0e2ca9 | ||
|
c288a80bd4 |
@@ -67,7 +67,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -143,7 +143,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -219,7 +219,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -315,7 +315,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"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\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$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-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -390,7 +390,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"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",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -398,7 +398,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"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(0.50, 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",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -406,7 +406,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"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": "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\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -497,14 +497,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
"expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -591,7 +591,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}",
|
"expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -681,14 +681,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -763,14 +763,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n",
|
"expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "success - {{ integration }}",
|
"legendFormat": "success - {{ integration }}",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)",
|
"expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed - {{ integration }}",
|
"legendFormat": "failed - {{ integration }}",
|
||||||
@@ -845,21 +845,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1613,7 +1613,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -1688,7 +1688,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -1763,7 +1763,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -1853,14 +1853,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1935,7 +1935,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{reason}}",
|
"legendFormat": "{{reason}}",
|
||||||
@@ -2010,7 +2010,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "errors",
|
"legendFormat": "errors",
|
||||||
@@ -2097,7 +2097,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2173,7 +2173,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2181,7 +2181,7 @@
|
|||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2189,7 +2189,7 @@
|
|||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2268,7 +2268,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2276,7 +2276,7 @@
|
|||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"interval": "1m",
|
"interval": "1m",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2367,14 +2367,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2452,14 +2452,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2537,14 +2537,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
|
@@ -71,21 +71,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "started",
|
"legendFormat": "started",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "completed",
|
"legendFormat": "completed",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -152,7 +152,7 @@
|
|||||||
"span": 3,
|
"span": 3,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n",
|
"expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -279,7 +279,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -505,7 +505,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
"expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -654,7 +654,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "compactions",
|
"legendFormat": "compactions",
|
||||||
@@ -730,21 +730,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -831,7 +831,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
"expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "avg",
|
"legendFormat": "avg",
|
||||||
@@ -907,7 +907,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
"expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{user}}",
|
"legendFormat": "{{user}}",
|
||||||
@@ -994,7 +994,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "blocks",
|
"legendFormat": "blocks",
|
||||||
@@ -1072,14 +1072,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1169,14 +1169,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1251,21 +1251,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2028,7 +2028,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -2103,21 +2103,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
|
@@ -81,7 +81,7 @@
|
|||||||
"uid": "$datasource"
|
"uid": "$datasource"
|
||||||
},
|
},
|
||||||
"exemplar": false,
|
"exemplar": false,
|
||||||
"expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
"expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"legendFormat": "Writes",
|
"legendFormat": "Writes",
|
||||||
"range": true
|
"range": true
|
||||||
@@ -91,7 +91,7 @@
|
|||||||
"uid": "$datasource"
|
"uid": "$datasource"
|
||||||
},
|
},
|
||||||
"exemplar": false,
|
"exemplar": false,
|
||||||
"expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
"expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"legendFormat": "Reads",
|
"legendFormat": "Reads",
|
||||||
"range": true
|
"range": true
|
||||||
@@ -101,7 +101,7 @@
|
|||||||
"uid": "$datasource"
|
"uid": "$datasource"
|
||||||
},
|
},
|
||||||
"exemplar": false,
|
"exemplar": false,
|
||||||
"expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"legendFormat": "Rule evaluations",
|
"legendFormat": "Rule evaluations",
|
||||||
"range": true
|
"range": true
|
||||||
@@ -111,7 +111,7 @@
|
|||||||
"uid": "$datasource"
|
"uid": "$datasource"
|
||||||
},
|
},
|
||||||
"exemplar": false,
|
"exemplar": false,
|
||||||
"expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n",
|
"expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n",
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"legendFormat": "Alerting notifications",
|
"legendFormat": "Alerting notifications",
|
||||||
"range": true
|
"range": true
|
||||||
@@ -214,7 +214,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -289,7 +289,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -297,7 +297,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -305,7 +305,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -381,14 +381,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "samples / sec",
|
"legendFormat": "samples / sec",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "exemplars / sec",
|
"legendFormat": "exemplars / sec",
|
||||||
@@ -495,7 +495,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -570,7 +570,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -578,7 +578,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -586,7 +586,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -699,63 +699,63 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "instant queries",
|
"legendFormat": "instant queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "range queries",
|
"legendFormat": "range queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "\"label names\" queries",
|
"legendFormat": "\"label names\" queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "\"label values\" queries",
|
"legendFormat": "\"label values\" queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "series queries",
|
"legendFormat": "series queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_read\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_read\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "remote read queries",
|
"legendFormat": "remote read queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_metadata\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_metadata\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "metadata queries",
|
"legendFormat": "metadata queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_exemplars\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_exemplars\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "exemplar queries",
|
"legendFormat": "exemplar queries",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\".*(query|query_range|label.*|series|read|metadata|query_exemplars)\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\".*(query|query_range|label.*|series|read|metadata|query_exemplars)\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "other",
|
"legendFormat": "other",
|
||||||
@@ -856,21 +856,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "success",
|
"legendFormat": "success",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "missed",
|
"legendFormat": "missed",
|
||||||
@@ -945,7 +945,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "average",
|
"legendFormat": "average",
|
||||||
@@ -1023,14 +1023,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1317,7 +1317,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))",
|
"expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "blocks",
|
"legendFormat": "blocks",
|
||||||
|
@@ -66,21 +66,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -155,21 +155,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -244,7 +244,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"})",
|
"expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -309,7 +309,7 @@
|
|||||||
"span": 3,
|
"span": 3,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0",
|
"expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{user}}",
|
"legendFormat": "{{user}}",
|
||||||
@@ -572,7 +572,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "splitting rate",
|
"legendFormat": "splitting rate",
|
||||||
@@ -647,7 +647,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after migration to new memcached backend.\n sum (\n rate(cortex_cache_hits{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(cortex_cache_fetched_keys{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n",
|
"expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after migration to new memcached backend.\n sum (\n rate(cortex_cache_hits{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(cortex_cache_fetched_keys{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{request_type}}",
|
"legendFormat": "{{request_type}}",
|
||||||
@@ -723,7 +723,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{reason}}",
|
"legendFormat": "{{reason}}",
|
||||||
@@ -811,7 +811,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "sharded queries ratio",
|
"legendFormat": "sharded queries ratio",
|
||||||
@@ -887,21 +887,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -988,7 +988,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -996,7 +996,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1004,7 +1004,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
"expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1080,7 +1080,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1088,7 +1088,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1096,7 +1096,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
"expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1172,7 +1172,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1180,7 +1180,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1188,7 +1188,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
"expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1276,21 +1276,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1365,21 +1365,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1456,7 +1456,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Failure Rate",
|
"legendFormat": "Failure Rate",
|
||||||
@@ -1532,7 +1532,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))",
|
"expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{reason}}",
|
"legendFormat": "{{reason}}",
|
||||||
@@ -1619,21 +1619,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
"expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Max",
|
"legendFormat": "Max",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
"expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Min",
|
"legendFormat": "Min",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})",
|
"expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1711,14 +1711,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1793,21 +1793,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1894,7 +1894,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "blocks",
|
"legendFormat": "blocks",
|
||||||
@@ -1969,7 +1969,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
"expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{data_type}}",
|
"legendFormat": "{{data_type}}",
|
||||||
@@ -2044,7 +2044,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
"expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{data_type}}",
|
"legendFormat": "{{data_type}}",
|
||||||
@@ -2131,7 +2131,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{stage}}",
|
"legendFormat": "{{stage}}",
|
||||||
@@ -2206,7 +2206,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n",
|
"expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{stage}}",
|
"legendFormat": "{{stage}}",
|
||||||
@@ -2282,7 +2282,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n",
|
"expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "% of time reduced by preloading",
|
"legendFormat": "% of time reduced by preloading",
|
||||||
@@ -2369,7 +2369,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
"expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -2447,14 +2447,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2532,14 +2532,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2626,7 +2626,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
"expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
@@ -2701,21 +2701,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2791,21 +2791,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2892,7 +2892,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "hit ratio",
|
"legendFormat": "hit ratio",
|
||||||
@@ -2967,7 +2967,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "hit ratio",
|
"legendFormat": "hit ratio",
|
||||||
@@ -3042,7 +3042,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "hit ratio",
|
"legendFormat": "hit ratio",
|
||||||
|
@@ -1571,7 +1571,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
|
@@ -91,7 +91,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
"expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -168,7 +168,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -245,7 +245,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -322,7 +322,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -399,7 +399,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -495,7 +495,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -570,7 +570,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -578,7 +578,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -586,7 +586,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -670,7 +670,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -920,7 +920,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n",
|
"expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Requests/s",
|
"legendFormat": "Requests/s",
|
||||||
@@ -995,7 +995,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1003,7 +1003,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1011,7 +1011,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1108,7 +1108,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1183,7 +1183,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1191,7 +1191,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1199,7 +1199,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1283,7 +1283,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -1346,7 +1346,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1421,7 +1421,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1429,7 +1429,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1437,7 +1437,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1521,7 +1521,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -1584,7 +1584,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1659,7 +1659,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -1667,7 +1667,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -1675,7 +1675,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1759,7 +1759,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -2084,7 +2084,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -2159,21 +2159,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2260,7 +2260,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{operation}}",
|
"legendFormat": "{{operation}}",
|
||||||
@@ -2335,7 +2335,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -2343,7 +2343,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -2351,7 +2351,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2428,7 +2428,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
"expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{item_type}}",
|
"legendFormat": "{{item_type}}",
|
||||||
@@ -2515,7 +2515,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{operation}}",
|
"legendFormat": "{{operation}}",
|
||||||
@@ -2590,7 +2590,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -2598,7 +2598,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -2606,7 +2606,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2682,7 +2682,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "items",
|
"legendFormat": "items",
|
||||||
@@ -2769,7 +2769,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{operation}}",
|
"legendFormat": "{{operation}}",
|
||||||
@@ -2844,7 +2844,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -2852,7 +2852,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -2860,7 +2860,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2936,7 +2936,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "items",
|
"legendFormat": "items",
|
||||||
@@ -3023,7 +3023,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{operation}}",
|
"legendFormat": "{{operation}}",
|
||||||
@@ -3098,7 +3098,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -3106,7 +3106,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
"expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -3114,7 +3114,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -3190,7 +3190,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
"expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((.*querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "items",
|
"legendFormat": "items",
|
||||||
|
@@ -242,7 +242,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -354,7 +354,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -462,7 +462,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -574,7 +574,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -678,7 +678,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -790,7 +790,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -898,7 +898,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -1010,7 +1010,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n",
|
||||||
"format": null,
|
"format": null,
|
||||||
"instant": false,
|
"instant": false,
|
||||||
"interval": "",
|
"interval": "",
|
||||||
@@ -1290,14 +1290,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n",
|
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "writes",
|
"legendFormat": "writes",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n",
|
"expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "reads",
|
"legendFormat": "reads",
|
||||||
|
@@ -67,7 +67,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -143,7 +143,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})",
|
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -220,7 +220,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -296,7 +296,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -386,21 +386,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "success",
|
"legendFormat": "success",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "missed",
|
"legendFormat": "missed",
|
||||||
@@ -475,7 +475,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "average",
|
"legendFormat": "average",
|
||||||
@@ -571,7 +571,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -646,21 +646,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -756,7 +756,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -831,21 +831,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -941,7 +941,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1016,21 +1016,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1117,21 +1117,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1206,21 +1206,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1297,7 +1297,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Failures / sec",
|
"legendFormat": "Failures / sec",
|
||||||
@@ -1374,7 +1374,7 @@
|
|||||||
"span": 4,
|
"span": 4,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n",
|
"expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -1422,7 +1422,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
"expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -1487,7 +1487,7 @@
|
|||||||
"span": 4,
|
"span": 4,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
"expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -1541,7 +1541,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
"expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -1616,7 +1616,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n",
|
"expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -1691,7 +1691,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
"expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ rule_group }}",
|
"legendFormat": "{{ rule_group }}",
|
||||||
@@ -1778,7 +1778,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
"expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
|
@@ -96,7 +96,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "in-memory",
|
"legendFormat": "in-memory",
|
||||||
@@ -110,14 +110,14 @@
|
|||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "active",
|
"legendFormat": "active",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
"expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "active ({{ name }})",
|
"legendFormat": "active ({{ name }})",
|
||||||
@@ -199,14 +199,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "active",
|
"legendFormat": "active",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "active ({{ name }})",
|
"legendFormat": "active ({{ name }})",
|
||||||
@@ -288,14 +288,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "buckets",
|
"legendFormat": "buckets",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
"expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "buckets ({{ name }})",
|
"legendFormat": "buckets ({{ name }})",
|
||||||
@@ -377,7 +377,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "series",
|
"legendFormat": "series",
|
||||||
@@ -447,7 +447,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
"expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "age",
|
"legendFormat": "age",
|
||||||
@@ -517,7 +517,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
"expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "age",
|
"legendFormat": "age",
|
||||||
@@ -599,7 +599,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -681,7 +681,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -764,7 +764,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ reason }}",
|
"legendFormat": "{{ reason }}",
|
||||||
@@ -846,7 +846,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -928,7 +928,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -1011,14 +1011,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "deduplicated",
|
"legendFormat": "deduplicated",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "non-HA",
|
"legendFormat": "non-HA",
|
||||||
@@ -1094,14 +1094,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ reason }} (distributor)",
|
"legendFormat": "{{ reason }} (distributor)",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ reason }} (ingester)",
|
"legendFormat": "{{ reason }} (ingester)",
|
||||||
@@ -1183,7 +1183,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -1253,7 +1253,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -1329,7 +1329,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ reason }}",
|
"legendFormat": "{{ reason }}",
|
||||||
@@ -1399,7 +1399,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -1487,7 +1487,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
"expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ job }}",
|
"legendFormat": "{{ job }}",
|
||||||
@@ -1563,7 +1563,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
"expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ job }}",
|
"legendFormat": "{{ job }}",
|
||||||
@@ -1657,7 +1657,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
"expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "groups",
|
"legendFormat": "groups",
|
||||||
@@ -1734,7 +1734,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})",
|
"expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rules",
|
"legendFormat": "rules",
|
||||||
@@ -1803,7 +1803,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -1878,7 +1878,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0",
|
"expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ rule_group }}",
|
"legendFormat": "{{ rule_group }}",
|
||||||
@@ -2003,7 +2003,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2118,7 +2118,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
"expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -2201,7 +2201,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -2272,7 +2272,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "rate",
|
"legendFormat": "rate",
|
||||||
@@ -2359,7 +2359,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Queries / Sec",
|
"legendFormat": "Queries / Sec",
|
||||||
|
@@ -127,7 +127,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -254,7 +254,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n)",
|
"expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} )\n)\n)",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -343,7 +343,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n",
|
"expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -468,7 +468,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -557,7 +557,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
"expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -682,7 +682,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
"expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -771,7 +771,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
"expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*|.*distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{ user }}",
|
"legendFormat": "{{ user }}",
|
||||||
@@ -896,7 +896,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
"expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -1023,7 +1023,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
"expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}[5m])))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -1150,7 +1150,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))",
|
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -1277,7 +1277,7 @@
|
|||||||
],
|
],
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))",
|
"expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((.*ruler|cortex|mimir|mimir-backend.*))\"}))",
|
||||||
"format": "table",
|
"format": "table",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
|
@@ -590,7 +590,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{pod}}",
|
"legendFormat": "{{pod}}",
|
||||||
|
@@ -90,7 +90,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -167,7 +167,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -244,7 +244,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
"expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -321,7 +321,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
"expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"}))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -397,7 +397,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}))",
|
"expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"instant": true,
|
"instant": true,
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
@@ -493,7 +493,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -568,7 +568,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -576,7 +576,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -584,7 +584,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -668,7 +668,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -731,7 +731,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -806,7 +806,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
@@ -814,7 +814,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
@@ -822,7 +822,7 @@
|
|||||||
"step": 10
|
"step": 10
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})",
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -906,7 +906,7 @@
|
|||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"exemplar": true,
|
"exemplar": true,
|
||||||
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))",
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "",
|
"legendFormat": "",
|
||||||
@@ -1302,7 +1302,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1377,21 +1377,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1487,7 +1487,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1562,21 +1562,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1672,7 +1672,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "{{status}}",
|
"legendFormat": "{{status}}",
|
||||||
@@ -1747,21 +1747,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -1852,14 +1852,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -1935,21 +1935,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))",
|
"expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2040,14 +2040,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2123,21 +2123,21 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "99th Percentile",
|
"legendFormat": "99th Percentile",
|
||||||
"refId": "A"
|
"refId": "A"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "50th Percentile",
|
"legendFormat": "50th Percentile",
|
||||||
"refId": "B"
|
"refId": "B"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "Average",
|
"legendFormat": "Average",
|
||||||
@@ -2228,14 +2228,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2314,14 +2314,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "successful",
|
"legendFormat": "successful",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "failed",
|
"legendFormat": "failed",
|
||||||
@@ -2387,7 +2387,7 @@
|
|||||||
"span": 3,
|
"span": 3,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n",
|
"expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "avg",
|
"legendFormat": "avg",
|
||||||
@@ -2432,14 +2432,14 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "WAL",
|
"legendFormat": "WAL",
|
||||||
"legendLink": null
|
"legendLink": null
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
"expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "mmap-ed chunks",
|
"legendFormat": "mmap-ed chunks",
|
||||||
@@ -2527,7 +2527,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "incoming exemplars",
|
"legendFormat": "incoming exemplars",
|
||||||
@@ -2603,7 +2603,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})",
|
"expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "received exemplars",
|
"legendFormat": "received exemplars",
|
||||||
@@ -2679,7 +2679,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "ingested exemplars",
|
"legendFormat": "ingested exemplars",
|
||||||
@@ -2755,7 +2755,7 @@
|
|||||||
"steppedLine": false,
|
"steppedLine": false,
|
||||||
"targets": [
|
"targets": [
|
||||||
{
|
{
|
||||||
"expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
"expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((.*ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((.*distributor|cortex|mimir|mimir-write.*))\"})\n)\n",
|
||||||
"format": "time_series",
|
"format": "time_series",
|
||||||
"intervalFactor": 2,
|
"intervalFactor": 2,
|
||||||
"legendFormat": "appended exemplars",
|
"legendFormat": "appended exemplars",
|
||||||
|
53
charts/meta-monitoring/src/rules/loki-rules.yaml
Normal file
53
charts/meta-monitoring/src/rules/loki-rules.yaml
Normal file
@@ -0,0 +1,53 @@
|
|||||||
|
groups:
|
||||||
|
- name: loki_rules
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:loki_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:loki_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m]))
|
||||||
|
by (cluster, job)
|
||||||
|
record: cluster_job:loki_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job)
|
||||||
|
record: cluster_job:loki_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:loki_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:loki_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
|
||||||
|
/ sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job,
|
||||||
|
route)
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:loki_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
|
||||||
|
job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate
|
571
charts/meta-monitoring/src/rules/mimir-rules.yaml
Normal file
571
charts/meta-monitoring/src/rules/mimir-rules.yaml
Normal file
@@ -0,0 +1,571 @@
|
|||||||
|
groups:
|
||||||
|
- name: mimir_api_1
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[1m]))
|
||||||
|
by (cluster, job)
|
||||||
|
record: cluster_job:cortex_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job)
|
||||||
|
record: cluster_job:cortex_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_api_2
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
|
||||||
|
/ sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job,
|
||||||
|
route)
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route)
|
||||||
|
record: cluster_job_route:cortex_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_api_3
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
|
||||||
|
job, route) / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace,
|
||||||
|
job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_querier_api
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_querier_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, route))
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by
|
||||||
|
(cluster, job, route)
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job, route)
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job, route)
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job, route)
|
||||||
|
record: cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m]))
|
||||||
|
by (cluster, namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_cache
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, method))
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_memcache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, method))
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job, method) / sum(rate(cortex_memcache_request_duration_seconds_count[1m]))
|
||||||
|
by (cluster, job, method)
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_memcache_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_memcache_request_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_memcache_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_memcache_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
/ sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_cache_request_duration_seconds_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, method))
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_cache_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job, method))
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
|
||||||
|
method) / sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_sum[1m])) by (cluster, job,
|
||||||
|
method)
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_cache_request_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job, method)
|
||||||
|
record: cluster_job_method:cortex_cache_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_storage
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
/ sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_kv_request_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_queries
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_query_frontend_retries:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_query_frontend_retries:50quantile
|
||||||
|
- expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[1m]))
|
||||||
|
by (cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_retries:avg
|
||||||
|
- expr: sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_retries_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_retries_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_retries_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by
|
||||||
|
(cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds:avg
|
||||||
|
- expr: sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le,
|
||||||
|
cluster, job)
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate
|
||||||
|
- name: mimir_ingester_queries
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_series:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_series:50quantile
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[1m]))
|
||||||
|
by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_series:avg
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_series_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_series_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_series_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples:50quantile
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[1m]))
|
||||||
|
by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples:avg
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_samples_count:sum_rate
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m]))
|
||||||
|
by (le, cluster, job))
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars:50quantile
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) /
|
||||||
|
sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars:avg
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster,
|
||||||
|
job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate
|
||||||
|
- expr: sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job)
|
||||||
|
record: cluster_job:cortex_ingester_queried_exemplars_count:sum_rate
|
||||||
|
- name: mimir_received_samples
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m]))
|
||||||
|
record: cluster_namespace_job:cortex_distributor_received_samples:rate5m
|
||||||
|
- name: mimir_exemplars_in
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m]))
|
||||||
|
record: cluster_namespace_job:cortex_distributor_exemplars_in:rate5m
|
||||||
|
- name: mimir_received_exemplars
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m]))
|
||||||
|
record: cluster_namespace_job:cortex_distributor_received_exemplars:rate5m
|
||||||
|
- name: mimir_exemplars_ingested
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m]))
|
||||||
|
record: cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m
|
||||||
|
- name: mimir_exemplars_appended
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m]))
|
||||||
|
record: cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m
|
||||||
|
- name: mimir_scaling_rules
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
# Convenience rule to get the number of replicas for both a deployment and a statefulset.
|
||||||
|
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
kube_deployment_spec_replicas,
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
or
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")
|
||||||
|
)
|
||||||
|
record: cluster_namespace_deployment:actual_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
quantile_over_time(0.99,
|
||||||
|
sum by (cluster, namespace) (
|
||||||
|
cluster_namespace_job:cortex_distributor_received_samples:rate5m
|
||||||
|
)[24h:]
|
||||||
|
)
|
||||||
|
/ 240000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: distributor
|
||||||
|
reason: sample_rate
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
|
||||||
|
* 0.59999999999999998 / 240000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: distributor
|
||||||
|
reason: sample_rate_limits
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
quantile_over_time(0.99,
|
||||||
|
sum by (cluster, namespace) (
|
||||||
|
cluster_namespace_job:cortex_distributor_received_samples:rate5m
|
||||||
|
)[24h:]
|
||||||
|
)
|
||||||
|
* 3 / 80000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: ingester
|
||||||
|
reason: sample_rate
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
quantile_over_time(0.99,
|
||||||
|
sum by(cluster, namespace) (
|
||||||
|
cortex_ingester_memory_series
|
||||||
|
)[24h:]
|
||||||
|
)
|
||||||
|
/ 1500000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: ingester
|
||||||
|
reason: active_series
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="max_global_series_per_user"})
|
||||||
|
* 3 * 0.59999999999999998 / 1500000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: ingester
|
||||||
|
reason: active_series_limits
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"})
|
||||||
|
* 0.59999999999999998 / 80000
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: ingester
|
||||||
|
reason: sample_rate_limits
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
ceil(
|
||||||
|
(sum by (cluster, namespace) (
|
||||||
|
cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"}
|
||||||
|
) / 4)
|
||||||
|
/
|
||||||
|
avg by (cluster, namespace) (
|
||||||
|
memcached_limit_bytes{job=~".+/memcached"}
|
||||||
|
)
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
deployment: memcached
|
||||||
|
reason: active_series
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[1m])),
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate
|
||||||
|
- expr: |
|
||||||
|
# Convenience rule to get the CPU request for both a deployment and a statefulset.
|
||||||
|
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
|
||||||
|
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
|
||||||
|
# that remove resource metrics, ref:
|
||||||
|
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
|
||||||
|
# - https://github.com/kubernetes/kube-state-metrics/pull/1004
|
||||||
|
#
|
||||||
|
# This is the old expression, compatible with kube-state-metrics < v2.0.0,
|
||||||
|
# where kube_pod_container_resource_requests_cpu_cores was removed:
|
||||||
|
(
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
kube_pod_container_resource_requests_cpu_cores,
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
)
|
||||||
|
or
|
||||||
|
# This expression is compatible with kube-state-metrics >= v1.4.0,
|
||||||
|
# where kube_pod_container_resource_requests was introduced.
|
||||||
|
(
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
kube_pod_container_resource_requests{resource="cpu"},
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
)
|
||||||
|
record: cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
|
||||||
|
- expr: |
|
||||||
|
# Jobs should be sized to their CPU usage.
|
||||||
|
# We do this by comparing 99th percentile usage over the last 24hrs to
|
||||||
|
# their current provisioned #replicas and resource requests.
|
||||||
|
ceil(
|
||||||
|
cluster_namespace_deployment:actual_replicas:count
|
||||||
|
*
|
||||||
|
quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h])
|
||||||
|
/
|
||||||
|
cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
reason: cpu_usage
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- expr: |
|
||||||
|
# Convenience rule to get the Memory utilization for both a deployment and a statefulset.
|
||||||
|
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
container_memory_usage_bytes{image!=""},
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
record: cluster_namespace_deployment:container_memory_usage_bytes:sum
|
||||||
|
- expr: |
|
||||||
|
# Convenience rule to get the Memory request for both a deployment and a statefulset.
|
||||||
|
# Multi-zone deployments are grouped together removing the "zone-X" suffix.
|
||||||
|
# This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2
|
||||||
|
# that remove resource metrics, ref:
|
||||||
|
# - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16
|
||||||
|
# - https://github.com/kubernetes/kube-state-metrics/pull/1004
|
||||||
|
#
|
||||||
|
# This is the old expression, compatible with kube-state-metrics < v2.0.0,
|
||||||
|
# where kube_pod_container_resource_requests_memory_bytes was removed:
|
||||||
|
(
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
kube_pod_container_resource_requests_memory_bytes,
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
)
|
||||||
|
or
|
||||||
|
# This expression is compatible with kube-state-metrics >= v1.4.0,
|
||||||
|
# where kube_pod_container_resource_requests was introduced.
|
||||||
|
(
|
||||||
|
sum by (cluster, namespace, deployment) (
|
||||||
|
label_replace(
|
||||||
|
label_replace(
|
||||||
|
kube_pod_container_resource_requests{resource="memory"},
|
||||||
|
"deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))"
|
||||||
|
),
|
||||||
|
# The question mark in "(.*?)" is used to make it non-greedy, otherwise it
|
||||||
|
# always matches everything and the (optional) zone is not removed.
|
||||||
|
"deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"
|
||||||
|
)
|
||||||
|
)
|
||||||
|
)
|
||||||
|
record: cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
|
||||||
|
- expr: |
|
||||||
|
# Jobs should be sized to their Memory usage.
|
||||||
|
# We do this by comparing 99th percentile usage over the last 24hrs to
|
||||||
|
# their current provisioned #replicas and resource requests.
|
||||||
|
ceil(
|
||||||
|
cluster_namespace_deployment:actual_replicas:count
|
||||||
|
*
|
||||||
|
quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h])
|
||||||
|
/
|
||||||
|
cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum
|
||||||
|
)
|
||||||
|
labels:
|
||||||
|
reason: memory_usage
|
||||||
|
record: cluster_namespace_deployment_reason:required_replicas:count
|
||||||
|
- name: mimir_alertmanager_rules
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job, pod) (cortex_alertmanager_alerts)
|
||||||
|
record: cluster_job_pod:cortex_alertmanager_alerts:sum
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job, pod) (cortex_alertmanager_silences)
|
||||||
|
record: cluster_job_pod:cortex_alertmanager_silences:sum
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_alerts_received_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m]))
|
||||||
|
record: cluster_job_integration:cortex_alertmanager_notifications_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m]))
|
||||||
|
record: cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_state_replication_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m
|
||||||
|
- expr: |
|
||||||
|
sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m]))
|
||||||
|
record: cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m
|
||||||
|
- name: mimir_ingester_rules
|
||||||
|
rules:
|
||||||
|
- expr: |
|
||||||
|
sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m]))
|
||||||
|
record: cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m
|
15
charts/meta-monitoring/src/rules/tempo-rules.yaml
Normal file
15
charts/meta-monitoring/src/rules/tempo-rules.yaml
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
groups:
|
||||||
|
- name: tempo_rules
|
||||||
|
rules:
|
||||||
|
- expr: histogram_quantile(0.99, sum(rate(tempo_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds:99quantile
|
||||||
|
- expr: histogram_quantile(0.50, sum(rate(tempo_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, job, route))
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds:50quantile
|
||||||
|
- expr: sum(rate(tempo_request_duration_seconds_sum[1m])) by (cluster, namespace, job, route) / sum(rate(tempo_request_duration_seconds_count[1m])) by (cluster, namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds:avg
|
||||||
|
- expr: sum(rate(tempo_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds_bucket:sum_rate
|
||||||
|
- expr: sum(rate(tempo_request_duration_seconds_sum[1m])) by (cluster, namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds_sum:sum_rate
|
||||||
|
- expr: sum(rate(tempo_request_duration_seconds_count[1m])) by (cluster, namespace, job, route)
|
||||||
|
record: cluster_namespace_job_route:tempo_request_duration_seconds_count:sum_rate
|
@@ -37,6 +37,8 @@ data:
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Logs
|
||||||
|
|
||||||
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
|
{{- if or .Values.local.logs.enabled .Values.cloud.logs.enabled }}
|
||||||
loki.source.kubernetes "pods" {
|
loki.source.kubernetes "pods" {
|
||||||
targets = discovery.relabel.rename_meta_labels.output
|
targets = discovery.relabel.rename_meta_labels.output
|
||||||
@@ -58,6 +60,8 @@ data:
|
|||||||
{{- end }}
|
{{- end }}
|
||||||
{{- end }}
|
{{- end }}
|
||||||
|
|
||||||
|
// Metrics
|
||||||
|
|
||||||
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
|
{{- if or .Values.local.metrics.enabled .Values.cloud.metrics.enabled }}
|
||||||
prometheus.scrape "pods" {
|
prometheus.scrape "pods" {
|
||||||
targets = discovery.relabel.rename_meta_labels.output
|
targets = discovery.relabel.rename_meta_labels.output
|
||||||
@@ -70,8 +74,117 @@ data:
|
|||||||
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||||
}
|
}
|
||||||
{{- end }}
|
{{- end }}
|
||||||
|
|
||||||
|
// cAdvisor and Kubelete metrics
|
||||||
|
// Based on https://github.com/Chewie/loutretelecom-manifests/blob/main/manifests/addons/monitoring/config.river
|
||||||
|
discovery.kubernetes "all_nodes" {
|
||||||
|
role = "node"
|
||||||
|
}
|
||||||
|
|
||||||
|
discovery.relabel "all_nodes" {
|
||||||
|
targets = discovery.kubernetes.all_nodes.targets
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_node_name"]
|
||||||
|
target_label = "node"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_namespace"]
|
||||||
|
target_label = "namespace"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_pod_name"]
|
||||||
|
target_label = "pod"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
|
||||||
|
separator = "/"
|
||||||
|
regex = "(.*)/(.*)/(.*)"
|
||||||
|
replacement = "${1}/${2}-${3}"
|
||||||
|
target_label = "job"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
target_label = "cluster"
|
||||||
|
replacement = "{{- .Values.clusterName -}}"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
prometheus.scrape "cadvisor" {
|
||||||
|
targets = discovery.relabel.all_nodes.output
|
||||||
|
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||||
|
|
||||||
|
scrape_interval = "15s"
|
||||||
|
metrics_path = "/metrics/cadvisor"
|
||||||
|
scheme = "https"
|
||||||
|
|
||||||
|
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
|
||||||
|
tls_config {
|
||||||
|
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
prometheus.scrape "kubelet" {
|
||||||
|
targets = discovery.relabel.all_nodes.output
|
||||||
|
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||||
|
|
||||||
|
scrape_interval = "15s"
|
||||||
|
metrics_path = "/metrics"
|
||||||
|
scheme = "https"
|
||||||
|
|
||||||
|
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
|
||||||
|
tls_config {
|
||||||
|
ca_file = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
prometheus.exporter.unix {}
|
||||||
|
|
||||||
|
prometheus.scrape "node_exporter" {
|
||||||
|
targets = prometheus.exporter.unix.targets
|
||||||
|
forward_to = [prometheus.relabel.node_exporter.receiver]
|
||||||
|
|
||||||
|
job_name = "node-exporter"
|
||||||
|
scrape_interval = "15s"
|
||||||
|
}
|
||||||
|
|
||||||
|
prometheus.relabel "node_exporter" {
|
||||||
|
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
|
||||||
|
|
||||||
|
rule {
|
||||||
|
replacement = env("HOSTNAME")
|
||||||
|
target_label = "nodename"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
replacement = "node-exporter"
|
||||||
|
target_label = "job"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_node_name"]
|
||||||
|
target_label = "node"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_namespace"]
|
||||||
|
target_label = "namespace"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_pod_name"]
|
||||||
|
target_label = "pod"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_label_app_kubernetes_io_name", "__meta_kubernetes_pod_label_app_kubernetes_io_component"]
|
||||||
|
separator = "/"
|
||||||
|
regex = "(.*)/(.*)/(.*)"
|
||||||
|
replacement = "${1}/${2}-${3}"
|
||||||
|
target_label = "job"
|
||||||
|
}
|
||||||
|
rule {
|
||||||
|
target_label = "cluster"
|
||||||
|
replacement = "{{- .Values.clusterName -}}"
|
||||||
|
}
|
||||||
|
}
|
||||||
{{- end }}
|
{{- end }}
|
||||||
|
|
||||||
|
// Traces
|
||||||
|
|
||||||
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
|
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}
|
||||||
// Shamelessly copied from https://github.com/grafana/intro-to-mlt/blob/main/agent/config.river
|
// Shamelessly copied from https://github.com/grafana/intro-to-mlt/blob/main/agent/config.river
|
||||||
otelcol.receiver.otlp "otlp_receiver" {
|
otelcol.receiver.otlp "otlp_receiver" {
|
||||||
|
126
charts/meta-monitoring/templates/ruler/ruler.yaml
Normal file
126
charts/meta-monitoring/templates/ruler/ruler.yaml
Normal file
@@ -0,0 +1,126 @@
|
|||||||
|
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||||
|
apiVersion: apps/v1
|
||||||
|
kind: Deployment
|
||||||
|
metadata:
|
||||||
|
name: meta-mimir-ruler-for-dashboards
|
||||||
|
namespace: meta
|
||||||
|
spec:
|
||||||
|
progressDeadlineSeconds: 600
|
||||||
|
replicas: 1
|
||||||
|
revisionHistoryLimit: 10
|
||||||
|
selector:
|
||||||
|
matchLabels:
|
||||||
|
app.kubernetes.io/component: ruler-for-dashboards
|
||||||
|
app.kubernetes.io/instance: meta
|
||||||
|
app.kubernetes.io/name: mimir
|
||||||
|
strategy:
|
||||||
|
rollingUpdate:
|
||||||
|
maxSurge: 50%
|
||||||
|
maxUnavailable: 0
|
||||||
|
type: RollingUpdate
|
||||||
|
template:
|
||||||
|
metadata:
|
||||||
|
labels:
|
||||||
|
app.kubernetes.io/component: ruler-for-dashboards
|
||||||
|
app.kubernetes.io/instance: meta
|
||||||
|
app.kubernetes.io/name: mimir
|
||||||
|
namespace: meta
|
||||||
|
spec:
|
||||||
|
containers:
|
||||||
|
- args:
|
||||||
|
- -target=ruler
|
||||||
|
- -log.level=debug
|
||||||
|
- -ruler-storage.backend=local
|
||||||
|
- -ruler-storage.local.directory=/etc/rules
|
||||||
|
- -ruler.ring.prefix=dashboards/
|
||||||
|
- -config.expand-env=true
|
||||||
|
- -config.file=/etc/mimir/mimir.yaml
|
||||||
|
image: grafana/mimir:2.8.0
|
||||||
|
imagePullPolicy: IfNotPresent
|
||||||
|
name: ruler
|
||||||
|
ports:
|
||||||
|
- containerPort: 8080
|
||||||
|
name: http-metrics
|
||||||
|
protocol: TCP
|
||||||
|
- containerPort: 9095
|
||||||
|
name: grpc
|
||||||
|
protocol: TCP
|
||||||
|
- containerPort: 7946
|
||||||
|
name: memberlist
|
||||||
|
protocol: TCP
|
||||||
|
readinessProbe:
|
||||||
|
failureThreshold: 3
|
||||||
|
httpGet:
|
||||||
|
path: /ready
|
||||||
|
port: http-metrics
|
||||||
|
scheme: HTTP
|
||||||
|
initialDelaySeconds: 45
|
||||||
|
periodSeconds: 10
|
||||||
|
successThreshold: 1
|
||||||
|
timeoutSeconds: 1
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
cpu: 100m
|
||||||
|
memory: 128Mi
|
||||||
|
securityContext:
|
||||||
|
allowPrivilegeEscalation: false
|
||||||
|
capabilities:
|
||||||
|
drop:
|
||||||
|
- ALL
|
||||||
|
readOnlyRootFilesystem: true
|
||||||
|
terminationMessagePath: /dev/termination-log
|
||||||
|
terminationMessagePolicy: File
|
||||||
|
volumeMounts:
|
||||||
|
- mountPath: /etc/mimir
|
||||||
|
name: config
|
||||||
|
- mountPath: /var/mimir
|
||||||
|
name: runtime-config
|
||||||
|
- mountPath: /data
|
||||||
|
name: storage
|
||||||
|
- mountPath: /active-query-tracker
|
||||||
|
name: active-queries
|
||||||
|
- mountPath: /etc/rules/anonymous
|
||||||
|
name: rules
|
||||||
|
dnsPolicy: ClusterFirst
|
||||||
|
restartPolicy: Always
|
||||||
|
schedulerName: default-scheduler
|
||||||
|
securityContext:
|
||||||
|
fsGroup: 10001
|
||||||
|
runAsGroup: 10001
|
||||||
|
runAsNonRoot: true
|
||||||
|
runAsUser: 10001
|
||||||
|
seccompProfile:
|
||||||
|
type: RuntimeDefault
|
||||||
|
serviceAccount: meta-mimir
|
||||||
|
serviceAccountName: meta-mimir
|
||||||
|
terminationGracePeriodSeconds: 180
|
||||||
|
topologySpreadConstraints:
|
||||||
|
- labelSelector:
|
||||||
|
matchLabels:
|
||||||
|
app.kubernetes.io/component: ruler
|
||||||
|
app.kubernetes.io/instance: meta
|
||||||
|
app.kubernetes.io/name: mimir
|
||||||
|
maxSkew: 1
|
||||||
|
topologyKey: kubernetes.io/hostname
|
||||||
|
whenUnsatisfiable: ScheduleAnyway
|
||||||
|
volumes:
|
||||||
|
- configMap:
|
||||||
|
defaultMode: 420
|
||||||
|
items:
|
||||||
|
- key: mimir.yaml
|
||||||
|
path: mimir.yaml
|
||||||
|
name: meta-mimir-config
|
||||||
|
name: config
|
||||||
|
- configMap:
|
||||||
|
defaultMode: 420
|
||||||
|
name: meta-mimir-runtime
|
||||||
|
name: runtime-config
|
||||||
|
- emptyDir: {}
|
||||||
|
name: storage
|
||||||
|
- emptyDir: {}
|
||||||
|
name: active-queries
|
||||||
|
- configMap:
|
||||||
|
defaultMode: 420
|
||||||
|
name: rules
|
||||||
|
name: rules
|
||||||
|
{{- end }}
|
18
charts/meta-monitoring/templates/ruler/rules-configmap.yaml
Normal file
18
charts/meta-monitoring/templates/ruler/rules-configmap.yaml
Normal file
@@ -0,0 +1,18 @@
|
|||||||
|
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
|
||||||
|
---
|
||||||
|
apiVersion: v1
|
||||||
|
kind: ConfigMap
|
||||||
|
metadata:
|
||||||
|
name: rules
|
||||||
|
namespace: {{ $.Release.Namespace }}
|
||||||
|
data:
|
||||||
|
{{- if .Values.dashboards.logs.enabled }}
|
||||||
|
{{ ($.Files.Glob "src/rules/loki-rules.yaml").AsConfig | indent 2 }}
|
||||||
|
{{- end }}
|
||||||
|
{{- if .Values.dashboards.metrics.enabled }}
|
||||||
|
{{ ($.Files.Glob "src/rules/mimir-rules.yaml").AsConfig | indent 2 }}
|
||||||
|
{{- end }}
|
||||||
|
{{- if .Values.dashboards.traces.enabled }}
|
||||||
|
{{ ($.Files.Glob "src/rules/tempo-rules.yaml").AsConfig | indent 2 }}
|
||||||
|
{{- end }}
|
||||||
|
{{- end }}
|
Reference in New Issue
Block a user