From 95f9f8dc355deb4c8e64449094d1ca99cb0f4902 Mon Sep 17 00:00:00 2001 From: Andrew Seigner Date: Fri, 25 May 2018 14:10:57 -0700 Subject: [PATCH] Add meshed label support to Grafana (#1021) The Grafana dashboards currently show Request Volume by ns/deploy/pod. Add a `meshed` dimension to the Request Volume graphs, in anticipation of the `meshed`/`secured` label from the proxy. Also increase `irate` time window queries from `20s` to `30s`, per recommendation from Prometheus team. Relates to #388. Signed-off-by: Andrew Seigner --- grafana/dashboards/deployment.json | 102 ++++++++++++------ grafana/dashboards/health.json | 22 ++-- grafana/dashboards/pod.json | 80 +++++++++----- .../dashboards/replication-controller.json | 76 ++++++++----- grafana/dashboards/service.json | 55 +++++++--- grafana/dashboards/top-line.json | 36 +++++-- 6 files changed, 251 insertions(+), 120 deletions(-) diff --git a/grafana/dashboards/deployment.json b/grafana/dashboards/deployment.json index 08859d4fa..b348d044c 100644 --- a/grafana/dashboards/deployment.json +++ b/grafana/dashboards/deployment.json @@ -96,7 +96,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -180,7 +180,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -419,7 +419,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (deployment)", "format": "time_series", "intervalFactor": 1, "legendFormat": "deploy/{{deployment}}", @@ -504,11 +504,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\", meshed=\"true\"}[30s])) by (deployment)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "deploy/{{deployment}}", + "legendFormat": "🔒deploy/{{deployment}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\", meshed=\"false\"}[30s])) by (deployment)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️deploy/{{deployment}}", + "refId": "B" } ], "thresholds": [], @@ -589,14 +596,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 deploy/{{deployment}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -604,7 +611,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 deploy/{{deployment}}", @@ -929,7 +936,7 @@ "h": 2, "w": 24, "x": 0, - "y": 43 + "y": 20.8 }, "id": 39, "links": [], @@ -949,7 +956,7 @@ "h": 7, "w": 8, "x": 0, - "y": 45 + "y": 22.8 }, "id": 36, "legend": { @@ -975,7 +982,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (deployment, pod) / sum(irate(response_total{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (deployment, pod)", + "expr": "sum(irate(response_total{classification=\"success\", deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (deployment, pod) / sum(irate(response_total{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (deployment, pod)", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -1018,7 +1025,11 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "aliasColors": {}, @@ -1031,7 +1042,7 @@ "h": 7, "w": 8, "x": 8, - "y": 45 + "y": 22.8 }, "id": 22, "legend": { @@ -1057,11 +1068,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (deployment, pod)", + "expr": "sum(irate(request_total{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\", meshed=\"true\"}[30s])) by (deployment, pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\", meshed=\"false\"}[30s])) by (deployment, pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -1099,7 +1117,11 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "aliasColors": {}, @@ -1112,7 +1134,7 @@ "h": 7, "w": 8, "x": 16, - "y": 45 + "y": 22.8 }, "id": 29, "legend": { @@ -1138,21 +1160,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (le, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P50 deploy/{{deployment}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (le, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 deploy/{{deployment}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{deployment!=\"\", deployment=\"$inbound\", dst_namespace=\"$namespace\", dst_deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (le, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P99 deploy/{{deployment}}", @@ -1193,7 +1215,11 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } } ], "repeat": "inbound", @@ -1266,7 +1292,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (dst_deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (dst_deployment)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (dst_deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (dst_deployment)", "format": "time_series", "intervalFactor": 1, "legendFormat": "deploy/{{dst_deployment}}", @@ -1351,11 +1377,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (dst_deployment)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_deployment)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "deploy/{{dst_deployment}}", + "legendFormat": "🔒deploy/{{dst_deployment}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_deployment)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️deploy/{{dst_deployment}}", + "refId": "B" } ], "thresholds": [], @@ -1435,7 +1468,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[20s])) by (le, dst_deployment))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", direction=\"outbound\"}[30s])) by (le, dst_deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 deploy/{{dst_deployment}}", @@ -1814,7 +1847,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_deployment)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[30s])) by (dst_deployment) / sum(irate(response_total{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[30s])) by (dst_deployment)", "format": "time_series", "intervalFactor": 1, "legendFormat": "deploy/{{dst_deployment}}", @@ -1899,11 +1932,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_deployment)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_deployment)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "deploy/{{dst_deployment}}", + "legendFormat": "🔒deploy/{{dst_deployment}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_deployment)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️deploy/{{dst_deployment}}", + "refId": "B" } ], "thresholds": [], @@ -1983,21 +2023,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_deployment))", + "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P50 deploy/{{dst_deployment}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_deployment))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 deploy/{{dst_deployment}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_deployment))", + "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", deployment=\"$deployment\", dst_deployment=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P99 deploy/{{dst_deployment}}", diff --git a/grafana/dashboards/health.json b/grafana/dashboards/health.json index e7067820c..ad2cb64d0 100644 --- a/grafana/dashboards/health.json +++ b/grafana/dashboards/health.json @@ -85,7 +85,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment, pod) / sum(irate(response_total{deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment, pod)", + "expr": "sum(irate(response_total{classification=\"success\", deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (deployment, pod) / sum(irate(response_total{deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (deployment, pod)", "format": "time_series", "intervalFactor": 1, "legendFormat": "po/{{pod}}", @@ -169,7 +169,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (deployment, pod)", + "expr": "sum(irate(request_total{deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (deployment, pod)", "format": "time_series", "intervalFactor": 1, "legendFormat": "po/{{pod}}", @@ -253,21 +253,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment, pod))", + "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 po/{{pod}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment, pod))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p95 po/{{pod}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[20s])) by (le, deployment, pod))", + "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{deployment=\"$deployment\", direction=\"inbound\"}[30s])) by (le, deployment, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 po/{{pod}}", @@ -1014,21 +1014,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[20s])) by (le, component, code))", + "expr": "histogram_quantile(0.5, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[30s])) by (le, component, code))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P50 {{component}}/{{code}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[20s])) by (le, component, code))", + "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[30s])) by (le, component, code))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 {{component}}/{{code}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[20s])) by (le, component, code))", + "expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket{job=\"conduit-controller\"}[30s])) by (le, component, code))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P99 {{component}}/{{code}}", @@ -1148,7 +1148,7 @@ "refId": "A" }, { - "expr": "irate(go_memstats_alloc_bytes_total{job=\"conduit-controller\", component=\"$component\"}[20s])", + "expr": "irate(go_memstats_alloc_bytes_total{job=\"conduit-controller\", component=\"$component\"}[30s])", "format": "time_series", "intervalFactor": 1, "legendFormat": "alloc rate/{{component}}", @@ -1344,14 +1344,14 @@ "steppedLine": false, "targets": [ { - "expr": "irate(grpc_server_msg_sent_total{job=\"conduit-controller\", component=\"$component\"}[20s])", + "expr": "irate(grpc_server_msg_sent_total{job=\"conduit-controller\", component=\"$component\"}[30s])", "format": "time_series", "intervalFactor": 1, "legendFormat": "sent/{{component}}/{{grpc_method}}", "refId": "A" }, { - "expr": "irate(grpc_server_msg_received_total{job=\"conduit-controller\", component=\"$component\"}[20s])", + "expr": "irate(grpc_server_msg_received_total{job=\"conduit-controller\", component=\"$component\"}[30s])", "format": "time_series", "intervalFactor": 1, "legendFormat": "received/{{component}}/{{grpc_method}}", diff --git a/grafana/dashboards/pod.json b/grafana/dashboards/pod.json index c74296fb7..bd71754aa 100644 --- a/grafana/dashboards/pod.json +++ b/grafana/dashboards/pod.json @@ -96,7 +96,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -180,7 +180,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -420,7 +420,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (pod)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) by (pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) by (pod)", "format": "time_series", "intervalFactor": 1, "legendFormat": "po/{{pod}}", @@ -505,11 +505,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (pod)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\", meshed=\"true\"}[30s])) by (pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\", meshed=\"false\"}[30s])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -590,14 +597,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 po/{{pod}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) by (le, pod))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -605,7 +612,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"inbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 po/{{pod}}", @@ -705,7 +712,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod) / sum(irate(response_total{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod)", + "expr": "sum(irate(response_total{classification=\"success\", dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[30s])) by (pod) / sum(irate(response_total{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[30s])) by (pod)", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -791,11 +798,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod)", + "expr": "sum(irate(request_total{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\", meshed=\"true\"}[30s])) by (pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\", meshed=\"false\"}[30s])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -876,14 +890,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 po/{{pod}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -891,7 +905,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{dst_namespace=\"$namespace\", dst_pod!=\"\", dst_pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 po/{{pod}}", @@ -991,7 +1005,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (pod)", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -1077,11 +1091,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (pod)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\", meshed=\"true\"}[30s])) by (pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\", meshed=\"false\"}[30s])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -1162,14 +1183,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 po/{{pod}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -1177,7 +1198,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, pod))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 po/{{pod}}", @@ -1277,7 +1298,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (dst_pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (dst_pod)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (dst_pod) / sum(irate(response_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (dst_pod)", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -1363,11 +1384,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (dst_pod)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{dst_pod}}", + "legendFormat": "🔒po/{{dst_pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{dst_pod}}", + "refId": "B" } ], "thresholds": [], @@ -1448,14 +1476,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, dst_pod))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, dst_pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 po/{{dst_pod}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, dst_pod))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, dst_pod))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -1463,7 +1491,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[20s])) by (le, dst_pod))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", pod=\"$pod\", direction=\"outbound\"}[30s])) by (le, dst_pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 po/{{dst_pod}}", diff --git a/grafana/dashboards/replication-controller.json b/grafana/dashboards/replication-controller.json index 14221d52f..cb8432fef 100644 --- a/grafana/dashboards/replication-controller.json +++ b/grafana/dashboards/replication-controller.json @@ -96,7 +96,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -180,7 +180,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s]))", + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -419,7 +419,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (replication_controller)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) by (replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) by (replication_controller)", "format": "time_series", "intervalFactor": 1, "legendFormat": "rc/{{replication_controller}}", @@ -504,11 +504,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (replication_controller)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\", meshed=\"true\"}[30s])) by (replication_controller)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "rc/{{replication_controller}}", + "legendFormat": "🔒rc/{{replication_controller}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\", meshed=\"false\"}[30s])) by (replication_controller)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️rc/{{replication_controller}}", + "refId": "B" } ], "thresholds": [], @@ -589,14 +596,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 rc/{{replication_controller}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -604,7 +611,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"inbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 rc/{{replication_controller}}", @@ -729,7 +736,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (replication_controller, pod) / sum(irate(response_total{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (replication_controller, pod)", + "expr": "sum(irate(response_total{classification=\"success\", replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (replication_controller, pod) / sum(irate(response_total{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (replication_controller, pod)", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -815,11 +822,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (replication_controller, pod)", + "expr": "sum(irate(request_total{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\", meshed=\"true\"}[30s])) by (replication_controller, pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\", meshed=\"false\"}[30s])) by (replication_controller, pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -900,21 +914,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P50 rc/{{replication_controller}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 rc/{{replication_controller}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (le, replication_controller))", + "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{replication_controller!=\"\", replication_controller=\"$inbound\", dst_namespace=\"$namespace\", dst_replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (le, replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P99 rc/{{replication_controller}}", @@ -1032,7 +1046,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (dst_replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (dst_replication_controller)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (dst_replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (dst_replication_controller)", "format": "time_series", "intervalFactor": 1, "legendFormat": "rc/{{dst_replication_controller}}", @@ -1117,11 +1131,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (dst_replication_controller)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_replication_controller)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "rc/{{dst_replication_controller}}", + "legendFormat": "🔒rc/{{dst_replication_controller}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_replication_controller)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️rc/{{dst_replication_controller}}", + "refId": "B" } ], "thresholds": [], @@ -1201,7 +1222,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[20s])) by (le, dst_replication_controller))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", direction=\"outbound\"}[30s])) by (le, dst_replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 rc/{{dst_replication_controller}}", @@ -1325,7 +1346,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_replication_controller)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[30s])) by (dst_replication_controller) / sum(irate(response_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[30s])) by (dst_replication_controller)", "format": "time_series", "intervalFactor": 1, "legendFormat": "rc/{{dst_replication_controller}}", @@ -1410,11 +1431,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (dst_replication_controller)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_replication_controller)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "rc/{{dst_replication_controller}}", + "legendFormat": "🔒rc/{{dst_replication_controller}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_replication_controller)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️rc/{{dst_replication_controller}}", + "refId": "B" } ], "thresholds": [], @@ -1494,21 +1522,21 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_replication_controller))", + "expr": "histogram_quantile(0.5, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P50 rc/{{dst_replication_controller}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_replication_controller))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 rc/{{dst_replication_controller}}", "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[20s])) by (le, dst_replication_controller))", + "expr": "histogram_quantile(0.99, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", replication_controller=\"$replication_controller\", dst_replication_controller=\"$outbound\", direction=\"outbound\"}[30s])) by (le, dst_replication_controller))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P99 rc/{{dst_replication_controller}}", diff --git a/grafana/dashboards/service.json b/grafana/dashboards/service.json index 016bddd84..950147ffe 100644 --- a/grafana/dashboards/service.json +++ b/grafana/dashboards/service.json @@ -96,7 +96,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s]))", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -180,7 +180,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s]))", + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -264,7 +264,7 @@ "tableColumn": "", "targets": [ { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -338,7 +338,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service)", "format": "time_series", "intervalFactor": 1, "legendFormat": "svc/{{dst_service}}", @@ -423,11 +423,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_service)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "svc/{{dst_service}}", + "legendFormat": "🔒svc/{{dst_service}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_service)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️svc/{{dst_service}}", + "refId": "B" } ], "thresholds": [], @@ -508,14 +515,14 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service))", + "expr": "histogram_quantile(0.5, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p50 svc/{{dst_service}}", "refId": "A" }, { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service))", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -523,7 +530,7 @@ "refId": "B" }, { - "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service))", + "expr": "histogram_quantile(0.99, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p99 svc/{{dst_service}}", @@ -623,7 +630,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, deployment) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, deployment)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service, deployment) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service, deployment)", "format": "time_series", "intervalFactor": 1, "legendFormat": "deploy/{{deployment}}", @@ -708,11 +715,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, deployment)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_service, deployment)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "deploy/{{deployment}}", + "legendFormat": "🔒deploy/{{deployment}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_service, deployment)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️deploy/{{deployment}}", + "refId": "B" } ], "thresholds": [], @@ -792,7 +806,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service, deployment))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service, deployment))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 deploy/{{deployment}}", @@ -891,7 +905,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, pod) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, pod)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service, pod) / sum(irate(response_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (dst_service, pod)", "format": "time_series", "intervalFactor": 1, "legendFormat": "po/{{pod}}", @@ -976,11 +990,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (dst_service, pod)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"true\"}[30s])) by (dst_service, pod)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "po/{{pod}}", + "legendFormat": "🔒po/{{pod}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\", meshed=\"false\"}[30s])) by (dst_service, pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️po/{{pod}}", + "refId": "B" } ], "thresholds": [], @@ -1060,7 +1081,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[20s])) by (le, dst_service, pod))", + "expr": "histogram_quantile(0.95, sum(rate(response_latency_ms_bucket{namespace=\"$namespace\", dst_service=\"$service\", direction=\"outbound\"}[30s])) by (le, dst_service, pod))", "format": "time_series", "intervalFactor": 1, "legendFormat": "P95 po/{{pod}}", diff --git a/grafana/dashboards/top-line.json b/grafana/dashboards/top-line.json index 19d507278..d8d702127 100644 --- a/grafana/dashboards/top-line.json +++ b/grafana/dashboards/top-line.json @@ -97,7 +97,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", deployment=~\"$deployment\"}[20s])) / sum(irate(response_total{deployment=~\"$deployment\"}[20s]))", + "expr": "sum(irate(response_total{classification=\"success\", deployment=~\"$deployment\"}[30s])) / sum(irate(response_total{deployment=~\"$deployment\"}[30s]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "", @@ -179,7 +179,7 @@ "tableColumn": "", "targets": [ { - "expr": "sum(irate(request_total{deployment=~\"$deployment\"}[20s]))", + "expr": "sum(irate(request_total{deployment=~\"$deployment\"}[30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", @@ -416,7 +416,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=~\"$namespace\", direction=\"inbound\"}[20s])) by (namespace) / sum(irate(response_total{namespace=~\"$namespace\", direction=\"inbound\"}[20s])) by (namespace)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=~\"$namespace\", direction=\"inbound\"}[30s])) by (namespace) / sum(irate(response_total{namespace=~\"$namespace\", direction=\"inbound\"}[30s])) by (namespace)", "format": "time_series", "intervalFactor": 1, "legendFormat": "ns/{{namespace}}", @@ -500,11 +500,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=~\"$namespace\", direction=\"inbound\"}[20s])) by (namespace)", + "expr": "sum(irate(request_total{namespace=~\"$namespace\", direction=\"inbound\", meshed=\"true\"}[30s])) by (namespace)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "ns/{{namespace}}", + "legendFormat": "🔒ns/{{namespace}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=~\"$namespace\", direction=\"inbound\", meshed=\"false\"}[30s])) by (namespace)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️ns/{{namespace}}", + "refId": "B" } ], "thresholds": [], @@ -513,7 +520,7 @@ "title": "REQUEST VOLUME", "tooltip": { "shared": true, - "sort": 1, + "sort": 2, "value_type": "individual" }, "type": "graph", @@ -584,7 +591,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=~\"$namespace\", direction=\"inbound\"}[20s])) by (le, namespace))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=~\"$namespace\", direction=\"inbound\"}[30s])) by (le, namespace))", "format": "time_series", "intervalFactor": 1, "legendFormat": "p95 ns/{{namespace}}", @@ -714,7 +721,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", direction=\"inbound\"}[20s])) by (deployment) / sum(irate(response_total{namespace=\"$namespace\", direction=\"inbound\"}[20s])) by (deployment)", + "expr": "sum(irate(response_total{classification=\"success\", namespace=\"$namespace\", direction=\"inbound\"}[30s])) by (deployment) / sum(irate(response_total{namespace=\"$namespace\", direction=\"inbound\"}[30s])) by (deployment)", "format": "time_series", "intervalFactor": 1, "legendFormat": "deploy/{{deployment}}", @@ -798,11 +805,18 @@ "steppedLine": false, "targets": [ { - "expr": "sum(irate(request_total{namespace=\"$namespace\", direction=\"inbound\"}[20s])) by (deployment)", + "expr": "sum(irate(request_total{namespace=\"$namespace\", direction=\"inbound\", meshed=\"true\"}[30s])) by (deployment)", "format": "time_series", "intervalFactor": 1, - "legendFormat": "deploy/{{deployment}}", + "legendFormat": "🔒deploy/{{deployment}}", "refId": "A" + }, + { + "expr": "sum(irate(request_total{namespace=\"$namespace\", direction=\"inbound\", meshed=\"false\"}[30s])) by (deployment)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "⚠️deploy/{{deployment}}", + "refId": "B" } ], "thresholds": [], @@ -882,7 +896,7 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", direction=\"inbound\"}[20s])) by (le, deployment))", + "expr": "histogram_quantile(0.95, sum(irate(response_latency_ms_bucket{namespace=\"$namespace\", direction=\"inbound\"}[30s])) by (le, deployment))", "format": "time_series", "hide": false, "intervalFactor": 1,