Skip to content
This repository has been archived by the owner on Jul 11, 2023. It is now read-only.

fix(grafana): use osm_request_duration_ms for latency graphs #4297

Merged
merged 1 commit into from
Nov 2, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
fix(grafana): use osm_request_duration_ms for latency graphs
This PR replaces envoy_cluster_upstream_rq_time with the existing
osm_request_duration_ms SMI metric to display latency in the mesh.
Currently, the latency graphs are present in the pod to service,
service to service, and workload to service dashboards. Unlike
envoy_cluster_upstream_rq_time, the osm_request_duration_ms metric
does not capture the src or destination service. Therefore, the
latency graphs no longer fit on the dashboards that allow the user
to specify a source service or see the latencies labeled with the
envoy cluster name (which includes the destination service name).

This PR removes the latency graphs from the pod to service, service
to service, and workload to service dashboards and creates a new
dashboard for workload to workload metrics.

Signed-off-by: jaellio <jaellio@microsoft.com>
  • Loading branch information
jaellio committed Oct 28, 2021
commit 659f5ed8e4c995797dbeef0bd2f4f77c05b88887
319 changes: 9 additions & 310 deletions charts/osm/grafana/dashboards/osm-pod.json
Original file line number Diff line number Diff line change
Expand Up @@ -364,17 +364,15 @@
"logBase": 1,
"max": null,
"min": null,
"show": true,
"$$hashKey": "object:81"
"show": true
},
{
"format": "Misc",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true,
"$$hashKey": "object:82"
"show": true
}
],
"yaxis": {
Expand All @@ -393,313 +391,14 @@
"timeFrom": null,
"timeShift": null
},
{
"collapsed": false,
"datasource": null,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 9
},
"id": 20,
"panels": [],
"title": "Request Latency",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 10
},
"hiddenSeries": false,
"id": 6,
"legend": {
"avg": false,
"current": false,
"hideEmpty": true,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99,irate(envoy_cluster_upstream_rq_time_bucket{source_pod_name=\"$source_pod\",source_namespace=\"$source_namespace\",envoy_cluster_name!~\"osm-controller|envoy-metrics-cluster|envoy-tracing-cluster|passthrough-outbound\"}[1m]))",
"interval": "",
"legendFormat": "{{envoy_cluster_name}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request Latency (P99)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "ms",
"label": "",
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 10
},
"hiddenSeries": false,
"id": 16,
"legend": {
"avg": false,
"current": false,
"hideEmpty": true,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.90,irate(envoy_cluster_upstream_rq_time_bucket{source_pod_name=\"$source_pod\",source_namespace=\"$source_namespace\",envoy_cluster_name!~\"osm-controller|envoy-metrics-cluster|envoy-tracing-cluster|passthrough-outbound\"}[1m]))",
"interval": "",
"legendFormat": "{{envoy_cluster_name}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request Latency (P90)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "ms",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 10
},
"hiddenSeries": false,
"id": 18,
"legend": {
"avg": false,
"current": false,
"hideEmpty": true,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.50,irate(envoy_cluster_upstream_rq_time_bucket{source_pod_name=\"$source_pod\",source_namespace=\"$source_namespace\",envoy_cluster_name!~\"osm-controller|envoy-metrics-cluster|envoy-tracing-cluster|passthrough-outbound\"}[1m]))",
"interval": "",
"legendFormat": "{{envoy_cluster_name}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request Latency (P50)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "timeseries",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "ms",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"datasource": "${DS_PROMETHEUS}",
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 18
"y": 26
},
"id": 10,
"panels": [],
Expand Down Expand Up @@ -730,7 +429,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 19
"y": 27
},
"id": 4,
"interval": "",
Expand Down Expand Up @@ -831,7 +530,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 19
"y": 27
},
"hiddenSeries": false,
"id": 26,
Expand Down Expand Up @@ -964,7 +663,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 27
"y": 35
},
"hiddenSeries": false,
"id": 2,
Expand Down Expand Up @@ -1058,7 +757,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 27
"y": 35
},
"hiddenSeries": false,
"id": 27,
Expand Down Expand Up @@ -1148,7 +847,7 @@
"definition": "label_values(envoy_server_live{}, source_namespace)",
"hide": 0,
"includeAll": false,
"label": "Namespace",
"label": "Source Namespace",
"multi": false,
"name": "source_namespace",
"options": [],
Expand All @@ -1170,7 +869,7 @@
"definition": "label_values(envoy_server_live{source_namespace=\"$source_namespace\"}, source_pod_name)",
"hide": 0,
"includeAll": false,
"label": "Pod",
"label": "Source Pod",
"multi": false,
"name": "source_pod",
"options": [],
Expand Down
Loading