Skip to content

Commit

Permalink
Add request latencies per API to PE dashboard (#694)
Browse files Browse the repository at this point in the history
  • Loading branch information
@david-martin
david-martin authored Jun 10, 2024
1 parent fbd8969 commit 09e48c8
Showing 1 changed file with 128 additions and 20 deletions.
148 changes: 128 additions & 20 deletions examples/dashboards/platform_engineer.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1229,7 +1229,7 @@
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Aggregated rate of bytes per API (HTTPRoute). The API name can be cross referenced with the API list to see additional details.\n\nNote: HTTPRoutes require a label `deployment` with the name of the corresponding Deployment so that istio request metrics can be paired with HTTPRoute metrics.",
"description": "Aggregated rate of requests per API (HTTPRoute). The API name can be cross referenced with the API list to see additional details.\n\nNote: HTTPRoutes require a label `deployment` with the name of the corresponding Deployment so that istio request metrics can be paired with HTTPRoute metrics.",
"fieldConfig": {
"defaults": {
"color": {
Expand Down Expand Up @@ -1270,6 +1270,7 @@
"mode": "off"
}
},
"decimals": 2,
"mappings": [],
"thresholds": {
"mode": "absolute",
Expand All @@ -1280,7 +1281,7 @@
}
]
},
"unit": "Bps"
"unit": "reqps"
},
"overrides": []
},
Expand All @@ -1290,7 +1291,7 @@
"x": 8,
"y": 24
},
"id": 137,
"id": 153,
"options": {
"legend": {
"calcs": [],
Expand All @@ -1310,26 +1311,26 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "(sum(irate(container_network_receive_bytes_total{exported_namespace=~\"$api_policy_namespace\"}[1h:5m])\n* on (namespace, exported_namespace,pod)\ngroup_left(workload,workload_type) (group without(cluster_id) (namespace_workload_pod:kube_pod_owner:relabel{exported_namespace=~\"$api_policy_namespace\", workload=~\".+\"}))) by (workload)) * on(workload) (group by(workload) (label_replace(gatewayapi_httproute_labels{exported_namespace=~\"$api_policy_namespace\",name=~\"$route_name\"}, \"workload\", \"$1\",\"service\", \"(.+)\")))",
"legendFormat": "API: {{workload}}",
"expr": "sum(rate(istio_requests_total{}[5m])) by (destination_service_name) * on(destination_service_name) group_right() (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{name=~\"${route_name}\",exported_namespace=~\"${api_policy_namespace}\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"legendFormat": "API: {{name}}",
"range": true,
"refId": "A"
}
],
"title": "Total requests (bytes/sec)",
"title": "Total requests (req/sec)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Rate of 4xx & 5xx response codes and total HTTP response code errors by API/HTTPRoute",
"description": "Aggregated request latencies per API (HTTPRoute). 99th and 95th percentiles are shown. The API name can be cross referenced with the API list to see additional details.\n\nNote: HTTPRoutes require a label `deployment` with the name of the corresponding Deployment so that istio request metrics can be paired with HTTPRoute metrics.",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "light-yellow",
"mode": "continuous-YlRd"
"fixedColor": "blue",
"mode": "fixed"
},
"custom": {
"axisCenteredZero": false,
Expand All @@ -1347,12 +1348,15 @@
"viz": false
},
"lineInterpolation": "linear",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 1,
"pointSize": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
Expand All @@ -1362,7 +1366,6 @@
"mode": "off"
}
},
"decimals": 2,
"mappings": [],
"thresholds": {
"mode": "absolute",
Expand All @@ -1373,7 +1376,7 @@
}
]
},
"unit": "reqps"
"unit": "ms"
},
"overrides": []
},
Expand All @@ -1383,7 +1386,7 @@
"x": 16,
"y": 24
},
"id": 139,
"id": 137,
"options": {
"legend": {
"calcs": [],
Expand All @@ -1403,8 +1406,8 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(istio_requests_total{response_code=~\"4.*|5.*\"}[5m])) by (destination_service_name, response_code) * on(destination_service_name) group_left(name) (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{exported_namespace=~\"${api_policy_namespace}\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"legendFormat": "{{name}} - {{response_code}}",
"expr": "histogram_quantile(0.99, sum(irate(istio_request_duration_milliseconds_bucket{destination_service_name=~\"$route_name\"}[5m])) by (le, destination_service_name)) * on(destination_service_name) group_right() (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{service=~\"$route_name\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"legendFormat": "{{service}} - 99th %ile",
"range": true,
"refId": "A"
},
Expand All @@ -1414,14 +1417,14 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(istio_requests_total{response_code=~\"4.*|5.*\"}[5m])) by (destination_service_name) * on(destination_service_name) group_left(name) (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{exported_namespace=~\"${api_policy_namespace}\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"expr": "histogram_quantile(0.95, sum(irate(istio_request_duration_milliseconds_bucket{destination_service_name=~\"$route_name\"}[5m])) by (le, destination_service_name)) * on(destination_service_name) group_right() (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{service=~\"$route_name\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"hide": false,
"legendFormat": "{{name}} - Total Errors",
"legendFormat": "{{service}} - 95th %ile",
"range": true,
"refId": "B"
"refId": "C"
}
],
"title": "Errors (req/s)",
"title": "Request latency",
"type": "timeseries"
},
{
Expand Down Expand Up @@ -1785,6 +1788,111 @@
],
"title": "Memory Usage",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Rate of 4xx & 5xx response codes and total HTTP response code errors by API/HTTPRoute",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "light-yellow",
"mode": "continuous-YlRd"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"axisSoftMin": 0,
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 5,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 1,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"decimals": 2,
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 31
},
"id": 139,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(istio_requests_total{response_code=~\"4.*|5.*\"}[5m])) by (destination_service_name, response_code) * on(destination_service_name) group_left(name) (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{exported_namespace=~\"${api_policy_namespace}\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"legendFormat": "{{name}} - {{response_code}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(istio_requests_total{response_code=~\"4.*|5.*\"}[5m])) by (destination_service_name) * on(destination_service_name) group_left(name) (group without(cluster_id, instance, app_kubernetes_io_instance) (label_replace(gatewayapi_httproute_labels{exported_namespace=~\"${api_policy_namespace}\"}, \"destination_service_name\", \"$1\",\"service\", \"(.+)\")))",
"hide": false,
"legendFormat": "{{name}} - Total Errors",
"range": true,
"refId": "B"
}
],
"title": "Errors (req/s)",
"type": "timeseries"
}
],
"refresh": "30s",
Expand Down

0 comments on commit 09e48c8

Please sign in to comment.