Skip to content

Commit

Permalink
Allow dashboards to show gRPC codes as labels (#6574)
Browse files Browse the repository at this point in the history
Signed-off-by: Yuri Nikolic <[email protected]>
  • Loading branch information
duricanikolic authored Nov 6, 2023
1 parent c3b7e81 commit 890d1d3
Show file tree
Hide file tree
Showing 17 changed files with 129 additions and 65 deletions.
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,7 @@

### Mixin

* [CHANGE] Dashboards: enabled reporting gRPC codes as `status_code` label in Mimir dashboards. In case of gRPC calls, the successful `status_code` label on `cortex_request_duration_seconds` and gRPC client request duration metrics has changed from 'success' and '2xx' to 'OK'. #6561
* [ENHANCEMENT] Dashboards: Optionally show rejected requests on Mimir Writes dashboard. Useful when used together with "early request rejection" in ingester and distributor. #6132 #6556
* [ENHANCEMENT] Alerts: added a critical alert for `CompactorSkippedBlocksWithOutOfOrderChunks` when multiple blocks are affected. #6410
* [ENHANCEMENT] Dashboards: Added the min-replicas for autoscaling dashboards. #6528
Expand Down

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
Expand Up @@ -281,6 +281,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -315,7 +316,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1994,6 +1994,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -2028,7 +2029,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -214,7 +215,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -461,6 +462,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -495,7 +497,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -461,6 +461,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -495,7 +496,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -710,6 +711,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -744,7 +746,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -1074,6 +1076,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -1108,7 +1111,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -1312,6 +1315,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -1346,7 +1350,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -1550,6 +1554,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -1584,7 +1589,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -2062,6 +2067,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -2096,7 +2102,7 @@
"steppedLine": false,
"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-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -187,7 +188,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval]),\n \"status\", \"${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=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -391,6 +392,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -425,7 +427,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down Expand Up @@ -576,6 +578,7 @@
"3xx": "#6ED0E0",
"4xx": "#EF843C",
"5xx": "#E24D42",
"OK": "#7EB26D",
"cancel": "#A9A9A9",
"error": "#E24D42",
"success": "#7EB26D"
Expand Down Expand Up @@ -610,7 +613,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", 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=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{status}}",
Expand Down
Loading

0 comments on commit 890d1d3

Please sign in to comment.