Merge pull request #26 from stackhpc/fix/grafana-dashboard-improvements

Add total requests panel to Grafana dashboard

Author: sd109

chart/templates/api/config-map-grafana-dashboard.yml

@@ -45,9 +45,9 @@ data:
                 "axisBorderShow": false,
                 "axisCenteredZero": false,
                 "axisColorMode": "text",
-                "axisLabel": "Request Rate",
+                "axisLabel": "Requests per minute",
                 "axisPlacement": "auto",
-                "axisWidth": 3,
+                "axisWidth": 50,
                 "barAlignment": 0,
                 "drawStyle": "line",
                 "fillOpacity": 0,
@@ -87,8 +87,7 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
@@ -125,7 +124,7 @@ data:
               "refId": "A"
             }
           ],
-          "title": "API Requests",
+          "title": "API Requests per Minute",
           "type": "timeseries"
         },
         {
@@ -142,8 +141,9 @@ data:
                 "axisBorderShow": false,
                 "axisCenteredZero": false,
                 "axisColorMode": "text",
-                "axisLabel": "Tokens / second",
+                "axisLabel": "Number of requests per minute",
                 "axisPlacement": "auto",
+                "axisWidth": 50,
                 "barAlignment": 0,
                 "drawStyle": "line",
                 "fillOpacity": 0,
@@ -183,16 +183,110 @@ data:
                     "value": 80
                   }
                 ]
+              }
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 12,
+            "w": 24,
+            "x": 0,
+            "y": 12
+          },
+          "id": 8,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "prometheus"
               },
-              "unitScale": true
+              "editorMode": "code",
+              "expr": "sum by (container, namespace, method, path) (vllm:request_success_total)",
+              "instant": false,
+              "legendFormat": "__auto",
+              "range": true,
+              "refId": "A"
+            }
+          ],
+          "title": "Total API Requests",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "Tokens / second",
+                "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"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 0,
-            "y": 12
+            "y": 24
           },
           "id": 2,
           "options": {
@@ -279,16 +373,15 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 12,
-            "y": 12
+            "y": 24
           },
           "id": 4,
           "options": {
@@ -375,16 +468,15 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 0,
-            "y": 20
+            "y": 32
           },
           "id": 3,
           "options": {
@@ -471,16 +563,15 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 12,
-            "y": 20
+            "y": 32
           },
           "id": 5,
           "options": {
@@ -567,16 +658,15 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 0,
-            "y": 28
+            "y": 40
           },
           "id": 1,
           "options": {
@@ -667,16 +757,15 @@ data:
                     "value": 80
                   }
                 ]
-              },
-              "unitScale": true
+              }
             },
             "overrides": []
           },
           "gridPos": {
             "h": 8,
             "w": 12,
             "x": 12,
-            "y": 28
+            "y": 40
           },
           "id": 6,
           "options": {
@@ -708,22 +797,6 @@ data:
           "title": "GPU Power Draw",
           "type": "timeseries"
         }
-      ],
-      "refresh": "",
-      "schemaVersion": 39,
-      "tags": [],
-      "templating": {
-        "list": []
-      },
-      "time": {
-        "from": "now-30m",
-        "to": "now"
-      },
-      "timepicker": {},
-      "timezone": "",
-      "title": "LLM Dashboard",
-      "uid": "c4114a95-8172-4a8b-99c8-963ba7d31385",
-      "version": 1,
-      "weekStart": ""
+      ]
     }
 {{- end -}}