fix prometheus target and update dashboard to be more full.

katanemo · Oct 10, 2024 · e042933 · e042933
1 parent 8b5db45
commit e042933
Show file tree

Hide file tree

Showing 2 changed files with 147 additions and 67 deletions.
diff --git a/demos/function_calling/grafana/dashboards/envoy_overview.json b/demos/function_calling/grafana/dashboards/envoy_overview.json
@@ -22,6 +22,7 @@
   "panels": [
     {
       "datasource": {
+        "default": true,
         "type": "prometheus",
         "uid": "PBFA97CFB590B2093"
       },
@@ -37,6 +38,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 0,
             "gradientMode": "none",
@@ -77,15 +79,40 @@
             ]
           }
         },
-        "overrides": []
+        "overrides": [
+          {
+            "__systemRef": "hideSeriesFrom",
+            "matcher": {
+              "id": "byNames",
+              "options": {
+                "mode": "exclude",
+                "names": [
+                  "api_server"
+                ],
+                "prefix": "All except:",
+                "readOnly": true
+              }
+            },
+            "properties": [
+              {
+                "id": "custom.hideFrom",
+                "value": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": true
+                }
+              }
+            ]
+          }
+        ]
       },
       "gridPos": {
         "h": 8,
         "w": 12,
         "x": 0,
         "y": 0
       },
-      "id": 2,
+      "id": 3,
       "options": {
         "legend": {
           "calcs": [],
@@ -106,22 +133,39 @@
           },
           "disableTextWrap": false,
           "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_internal_upstream_rq_time_sum[1m]) / rate(envoy_cluster_internal_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
+          "expr": "avg(rate(envoy_cluster_internal_upstream_rq_completed{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
-          "hide": false,
           "includeNullMetadata": true,
           "instant": false,
           "legendFormat": "__auto",
           "range": true,
           "refId": "A",
           "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "disableTextWrap": false,
+          "editorMode": "code",
+          "expr": "avg(rate(envoy_cluster_external_upstream_rq_completed{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
         }
       ],
-      "title": "request latency - internal (ms)",
+      "title": "Upstream request rate",
       "type": "timeseries"
     },
     {
       "datasource": {
+        "default": true,
         "type": "prometheus",
         "uid": "PBFA97CFB590B2093"
       },
@@ -137,6 +181,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 0,
             "gradientMode": "none",
@@ -206,7 +251,7 @@
           },
           "disableTextWrap": false,
           "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_external_upstream_rq_time_sum[1m]) / rate(envoy_cluster_external_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
+          "expr": "avg(rate (envoy_cluster_external_upstream_rq_time_sum{envoy_cluster_name=~\"api_server|openai\"}[1m])/ rate(envoy_cluster_external_upstream_rq_time_count{envoy_cluster_name=~\"api_server|openai\"}[1m])) by (envoy_cluster_name)",
           "fullMetaSearch": false,
           "hide": false,
           "includeNullMetadata": true,
@@ -222,45 +267,14 @@
     },
     {
       "datasource": {
+        "default": true,
         "type": "prometheus",
         "uid": "PBFA97CFB590B2093"
       },
       "fieldConfig": {
         "defaults": {
           "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
+            "mode": "thresholds"
           },
           "mappings": [],
           "thresholds": {
@@ -285,58 +299,124 @@
         "x": 0,
         "y": 8
       },
-      "id": 3,
+      "id": 4,
       "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
         },
-        "tooltip": {
-          "mode": "single",
-          "sort": "none"
-        }
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
       },
+      "pluginVersion": "11.2.0",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "PBFA97CFB590B2093"
           },
           "disableTextWrap": false,
-          "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_internal_upstream_rq_completed[1m])) by (envoy_cluster_name)",
+          "editorMode": "builder",
+          "exemplar": false,
+          "expr": "envoy_cluster_upstream_rq_completed{envoy_cluster_name=~\"openai|api_server\"}",
           "fullMetaSearch": false,
           "includeNullMetadata": true,
-          "instant": false,
-          "legendFormat": "__auto",
-          "range": true,
+          "instant": true,
+          "legendFormat": "{{envoy_cluster_name}}",
+          "range": false,
           "refId": "A",
           "useBackend": false
+        }
+      ],
+      "title": "# of Completd Requests",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "default": true,
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
         },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 5,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.2.0",
+      "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "PBFA97CFB590B2093"
           },
           "disableTextWrap": false,
-          "editorMode": "code",
-          "expr": "avg(rate(envoy_cluster_external_upstream_rq_completed[1m])) by (envoy_cluster_name)",
+          "editorMode": "builder",
+          "exemplar": false,
+          "expr": "envoy_cluster_upstream_rq_cancelled{envoy_cluster_name=~\"api_server|openai\"} + envoy_cluster_upstream_rq_pending_failure_eject{envoy_cluster_name=~\"api_server|openai\"} + envoy_cluster_upstream_rq_pending_overflow{envoy_cluster_name=~\"api_server|openai\"}",
           "fullMetaSearch": false,
-          "hide": false,
           "includeNullMetadata": true,
-          "instant": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "B",
+          "instant": true,
+          "legendFormat": "{{envoy_cluster_name}}",
+          "range": false,
+          "refId": "A",
           "useBackend": false
         }
       ],
-      "title": "Upstream request count",
-      "type": "timeseries"
+      "title": "# of Failed or Cancelled Requests",
+      "type": "stat"
     }
   ],
+  "refresh": "",
   "schemaVersion": 39,
   "tags": [],
   "templating": {
@@ -348,8 +428,8 @@
   },
   "timepicker": {},
   "timezone": "browser",
-  "title": "Intelligent Gateway Overview",
+  "title": "Arch Gateway Dashboard",
   "uid": "adt6uhx5lk8aob",
-  "version": 3,
+  "version": 1,
   "weekStart": ""
-}
+}
diff --git a/demos/function_calling/prometheus/prometheus.yaml b/demos/function_calling/prometheus/prometheus.yaml
@@ -18,6 +18,6 @@ scrape_configs:
   scheme: http
   static_configs:
   - targets:
-    - arch:9901
+    - host.docker.internal:19901
   params:
     format: ['prometheus']