|
103 | 103 | "uid": "prometheus" |
104 | 104 | }, |
105 | 105 | "editorMode": "code", |
106 | | - "expr": "sum(rate(operator_sdk_reconciliations_started_total{service_name=\"josdk\"}[5m])) by (kind, version)", |
107 | | - "legendFormat": "{{kind}} ({{version}})", |
| 106 | + "expr": "sum(rate(operator_sdk_reconciliations_started_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 107 | + "legendFormat": "{{controller_name}}", |
108 | 108 | "range": true, |
109 | 109 | "refId": "A" |
110 | 110 | } |
|
224 | 224 | "uid": "prometheus" |
225 | 225 | }, |
226 | 226 | "editorMode": "code", |
227 | | - "expr": "sum(rate(operator_sdk_reconciliations_success_total{service_name=\"josdk\"}[5m]))", |
228 | | - "legendFormat": "Success", |
| 227 | + "expr": "sum(rate(operator_sdk_reconciliations_success_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 228 | + "legendFormat": "Success - {{controller_name}}", |
229 | 229 | "range": true, |
230 | 230 | "refId": "A" |
231 | 231 | }, |
|
235 | 235 | "uid": "prometheus" |
236 | 236 | }, |
237 | 237 | "editorMode": "code", |
238 | | - "expr": "sum(rate(operator_sdk_reconciliations_failed_total{service_name=\"josdk\"}[5m]))", |
239 | | - "legendFormat": "Failure", |
| 238 | + "expr": "sum(rate(operator_sdk_reconciliations_failure_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 239 | + "legendFormat": "Failure - {{controller_name}}", |
240 | 240 | "range": true, |
241 | 241 | "refId": "B" |
242 | 242 | } |
|
495 | 495 | "uid": "prometheus" |
496 | 496 | }, |
497 | 497 | "editorMode": "code", |
498 | | - "expr": "sum(rate(operator_sdk_reconciliations_failed_total{service_name=\"josdk\"}[5m]))", |
| 498 | + "expr": "sum(rate(operator_sdk_reconciliations_failure_total{service_name=\"josdk\"}[5m]))", |
499 | 499 | "legendFormat": "Error Rate", |
500 | 500 | "range": true, |
501 | 501 | "refId": "A" |
|
585 | 585 | "uid": "prometheus" |
586 | 586 | }, |
587 | 587 | "editorMode": "code", |
588 | | - "expr": "histogram_quantile(0.50, sum(rate(operator_sdk_reconciliations_execution_duration_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller))", |
589 | | - "legendFormat": "p50 - {{controller}}", |
| 588 | + "expr": "histogram_quantile(0.50, sum(rate(operator_sdk_reconciliations_execution_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller_name))", |
| 589 | + "legendFormat": "p50 - {{controller_name}}", |
590 | 590 | "range": true, |
591 | 591 | "refId": "A" |
592 | 592 | }, |
|
596 | 596 | "uid": "prometheus" |
597 | 597 | }, |
598 | 598 | "editorMode": "code", |
599 | | - "expr": "histogram_quantile(0.95, sum(rate(operator_sdk_reconciliations_execution_duration_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller))", |
600 | | - "legendFormat": "p95 - {{controller}}", |
| 599 | + "expr": "histogram_quantile(0.95, sum(rate(operator_sdk_reconciliations_execution_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller_name))", |
| 600 | + "legendFormat": "p95 - {{controller_name}}", |
601 | 601 | "range": true, |
602 | 602 | "refId": "B" |
603 | 603 | }, |
|
607 | 607 | "uid": "prometheus" |
608 | 608 | }, |
609 | 609 | "editorMode": "code", |
610 | | - "expr": "histogram_quantile(0.99, sum(rate(operator_sdk_reconciliations_execution_duration_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller))", |
611 | | - "legendFormat": "p99 - {{controller}}", |
| 610 | + "expr": "histogram_quantile(0.99, sum(rate(operator_sdk_reconciliations_execution_seconds_bucket{service_name=\"josdk\"}[5m])) by (le, controller_name))", |
| 611 | + "legendFormat": "p99 - {{controller_name}}", |
612 | 612 | "range": true, |
613 | 613 | "refId": "C" |
614 | 614 | } |
|
711 | 711 | "type": "prometheus", |
712 | 712 | "uid": "prometheus" |
713 | 713 | }, |
714 | | - "description": "Failures by exception type", |
| 714 | + "description": "Failures by controller", |
715 | 715 | "fieldConfig": { |
716 | 716 | "defaults": { |
717 | 717 | "color": { |
|
787 | 787 | "uid": "prometheus" |
788 | 788 | }, |
789 | 789 | "editorMode": "code", |
790 | | - "expr": "sum(rate(operator_sdk_reconciliations_failed_total{service_name=\"josdk\"}[5m])) by (exception)", |
791 | | - "legendFormat": "{{exception}}", |
| 790 | + "expr": "sum(rate(operator_sdk_reconciliations_failure_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 791 | + "legendFormat": "{{controller_name}}", |
792 | 792 | "range": true, |
793 | 793 | "refId": "A" |
794 | 794 | } |
795 | 795 | ], |
796 | | - "title": "Failures by Exception Type", |
| 796 | + "title": "Failures by Controller", |
797 | 797 | "type": "timeseries" |
798 | 798 | }, |
799 | 799 | { |
|
877 | 877 | "uid": "prometheus" |
878 | 878 | }, |
879 | 879 | "editorMode": "code", |
880 | | - "expr": "sum(rate(operator_sdk_controllers_success_total{service_name=\"josdk\"}[5m])) by (controller)", |
881 | | - "legendFormat": "Success - {{controller}}", |
| 880 | + "expr": "sum(rate(operator_sdk_controllers_success_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 881 | + "legendFormat": "Success - {{controller_name}}", |
882 | 882 | "range": true, |
883 | 883 | "refId": "A" |
884 | 884 | }, |
|
888 | 888 | "uid": "prometheus" |
889 | 889 | }, |
890 | 890 | "editorMode": "code", |
891 | | - "expr": "sum(rate(operator_sdk_controllers_failure_total{service_name=\"josdk\"}[5m])) by (controller)", |
892 | | - "legendFormat": "Failure - {{controller}}", |
| 891 | + "expr": "sum(rate(operator_sdk_controllers_failure_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 892 | + "legendFormat": "Failure - {{controller_name}}", |
893 | 893 | "range": true, |
894 | 894 | "refId": "B" |
895 | 895 | } |
|
978 | 978 | "uid": "prometheus" |
979 | 979 | }, |
980 | 980 | "editorMode": "code", |
981 | | - "expr": "sum(rate(operator_sdk_events_delete_total{service_name=\"josdk\"}[5m])) by (kind, version)", |
982 | | - "legendFormat": "{{kind}} ({{version}})", |
| 981 | + "expr": "sum(rate(operator_sdk_events_delete_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 982 | + "legendFormat": "{{controller_name}}", |
983 | 983 | "range": true, |
984 | 984 | "refId": "A" |
985 | 985 | } |
|
992 | 992 | "type": "prometheus", |
993 | 993 | "uid": "prometheus" |
994 | 994 | }, |
995 | | - "description": "Current retry attempt number for resources being retried", |
| 995 | + "description": "Rate of retry attempts", |
996 | 996 | "fieldConfig": { |
997 | 997 | "defaults": { |
998 | 998 | "color": { |
|
1076 | 1076 | "uid": "prometheus" |
1077 | 1077 | }, |
1078 | 1078 | "editorMode": "code", |
1079 | | - "expr": "operator_sdk_reconciliations_retries_number{service_name=\"josdk\"}", |
1080 | | - "legendFormat": "{{kind}}/{{name}} ({{namespace}})", |
| 1079 | + "expr": "sum(rate(operator_sdk_reconciliations_retries_total{service_name=\"josdk\"}[5m])) by (controller_name)", |
| 1080 | + "legendFormat": "Retries - {{controller_name}}", |
1081 | 1081 | "range": true, |
1082 | 1082 | "refId": "A" |
1083 | 1083 | } |
1084 | 1084 | ], |
1085 | | - "title": "Reconciliation Retry Attempts", |
| 1085 | + "title": "Reconciliation Retry Rate", |
1086 | 1086 | "type": "timeseries" |
1087 | 1087 | } |
1088 | 1088 | ], |
|
0 commit comments