Skip to content

Commit

Permalink
dashboards: overview: qps and latency w/ cortex_request_duration_seconds
Browse files Browse the repository at this point in the history 
Allow using  cortex_request_duration_seconds native histogram in
overview dashboard everywhere.
Followup to #7627

Signed-off-by: György Krajcsovits <gyorgy.krajcsovits@grafana.com>
  • Loading branch information
@krajorama
krajorama committed Mar 21, 2024
1 parent 61f4291 commit afadcce
Show file tree
Hide file tree
Showing 7 changed files with 222 additions and 58 deletions.
76 changes: 62 additions & 14 deletions ...oring-values-generated/mimir-distributed/templates/metamonitoring/grafana-dashboards.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9728,7 +9728,13 @@ data:
"span": 3,
"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\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$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-zA-Z]+)\"))\n < ($latency_metrics * +Inf)\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A_classic"
},
{
"expr": "sum by (status) (\n label_replace(label_replace(histogram_count(rate(cortex_request_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n < ($latency_metrics * -Inf)\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
Expand Down Expand Up @@ -9777,22 +9783,40 @@ data:
"span": 3,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$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=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A"
"refId": "A_classic"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A_native"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B"
"refId": "B_classic"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((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": "histogram_quantile(0.50, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B_native"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) /\nsum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})\n < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C"
"refId": "C_classic"
},
{
"expr": "1e3 * sum(histogram_sum(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) /\nsum(histogram_count(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}))\n < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C_native"
}
],
"title": "Write latency",
Expand Down Expand Up @@ -10050,7 +10074,13 @@ data:
"span": 3,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$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-zA-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\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n < ($latency_metrics * +Inf)\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A_classic"
},
{
"expr": "sum by (status) (\n label_replace(label_replace(histogram_count(rate(cortex_request_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n < ($latency_metrics * -Inf)\n",
"format": "time_series",
"legendFormat": "{{status}}",
"refId": "A"
Expand Down Expand Up @@ -10099,22 +10129,40 @@ data:
"span": 3,
"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 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A"
"refId": "A_classic"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "99th percentile",
"refId": "A_native"
},
{
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3 < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B"
"refId": "B_classic"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
"expr": "histogram_quantile(0.50, sum (cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3 < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "50th percentile",
"refId": "B_native"
},
{
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) /\nsum(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_.+\"})\n < ($latency_metrics * +Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C"
"refId": "C_classic"
},
{
"expr": "1e3 * sum(histogram_sum(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) /\nsum(histogram_count(cluster_job_route:cortex_request_duration_seconds:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n < ($latency_metrics * -Inf)",
"format": "time_series",
"legendFormat": "Average",
"refId": "C_native"
}
],
"title": "Read latency",
Expand Down
Loading

0 comments on commit afadcce

Please sign in to comment.