Prechádzať zdrojové kódy

chore: update grafana template (#721)

AlpinDale 6 mesiacov pred
rodič
commit
12e40ae6fd
1 zmenil súbory, kde vykonal 245 pridanie a 197 odobranie
  1. 245 197
      examples/monitoring/grafana.json

+ 245 - 197
examples/monitoring/grafana.json

@@ -1,4 +1,33 @@
 {
+  "__inputs": [
+  ],
+  "__elements": {},
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "10.4.2"
+    },
+    {
+      "type": "panel",
+      "id": "heatmap",
+      "name": "Heatmap",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    },
+    {
+      "type": "panel",
+      "id": "timeseries",
+      "name": "Time series",
+      "version": ""
+    }
+  ],
   "annotations": {
     "list": [
       {
@@ -25,14 +54,14 @@
   "editable": true,
   "fiscalYearStartMonth": 0,
   "graphTooltip": 0,
-  "id": 29,
+  "id": null,
   "links": [],
   "liveNow": false,
   "panels": [
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "End to end request latency measured in seconds.",
       "fieldConfig": {
@@ -41,6 +70,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -54,6 +84,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -111,7 +142,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -127,7 +158,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -144,7 +175,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -161,7 +192,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -178,7 +209,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
           "expr": "rate(aphrodite:e2e_request_latency_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(aphrodite:e2e_request_latency_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
@@ -195,7 +226,7 @@
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "Number of tokens processed per second",
       "fieldConfig": {
@@ -204,6 +235,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -217,6 +249,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -273,7 +306,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -289,7 +322,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -310,7 +343,7 @@
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "Inter token latency in seconds.",
       "fieldConfig": {
@@ -319,6 +352,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -332,6 +366,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -389,7 +424,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -405,7 +440,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -422,7 +457,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -439,7 +474,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -456,7 +491,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
           "expr": "rate(aphrodite:time_per_output_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(aphrodite:time_per_output_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
@@ -473,7 +508,7 @@
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "Number of requests in RUNNING, WAITING, and SWAPPED state",
       "fieldConfig": {
@@ -482,6 +517,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -495,6 +531,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -552,7 +589,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -568,7 +605,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -585,7 +622,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -606,7 +643,7 @@
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "P50, P90, P95, and P99 TTFT latency in seconds.",
       "fieldConfig": {
@@ -615,6 +652,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -628,6 +666,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -685,7 +724,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -702,7 +741,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -718,7 +757,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -735,7 +774,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -752,7 +791,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
           "expr": "rate(aphrodite:time_to_first_token_seconds_sum{model_name=\"$model_name\"}[$__rate_interval])\n/\nrate(aphrodite:time_to_first_token_seconds_count{model_name=\"$model_name\"}[$__rate_interval])",
@@ -769,7 +808,7 @@
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
       "description": "Percentage of used cache blocks by Aphrodite.",
       "fieldConfig": {
@@ -778,6 +817,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -791,6 +831,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -848,7 +889,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
           "expr": "aphrodite:gpu_cache_usage_perc{model_name=\"$model_name\"}",
@@ -860,7 +901,7 @@
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
           "expr": "aphrodite:cpu_cache_usage_perc{model_name=\"$model_name\"}",
@@ -875,229 +916,232 @@
       "type": "timeseries"
     },
     {
-      "type": "heatmap",
-      "title": "Request Prompt Length",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
       "description": "Heatmap of request prompt length",
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "scaleDistribution": {
+              "type": "linear"
+            }
+          }
+        },
+        "overrides": []
+      },
       "gridPos": {
-        "x": 0,
-        "y": 24,
+        "h": 8,
         "w": 12,
-        "h": 8
-      },
-      "datasource": {
-        "uid": "prometheus",
-        "type": "prometheus"
+        "x": 0,
+        "y": 24
       },
       "id": 12,
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "prometheus"
-          },
-          "refId": "A",
-          "expr": "sum by(le) (increase(aphrodite:request_prompt_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
-          "range": true,
-          "instant": false,
-          "editorMode": "builder",
-          "legendFormat": "{{le}}",
-          "useBackend": false,
-          "disableTextWrap": false,
-          "fullMetaSearch": false,
-          "includeNullMetadata": true,
-          "format": "heatmap"
-        }
-      ],
       "options": {
         "calculate": false,
-        "yAxis": {
-          "axisPlacement": "left",
-          "reverse": false,
-          "unit": "none",
-          "axisLabel": "Prompt Length"
-        },
-        "rowsFrame": {
-          "layout": "auto",
-          "value": "Request count"
+        "cellGap": 1,
+        "cellValues": {
+          "unit": "none"
         },
         "color": {
-          "mode": "scheme",
+          "exponent": 0.5,
           "fill": "dark-orange",
+          "min": 0,
+          "mode": "scheme",
+          "reverse": false,
           "scale": "exponential",
-          "exponent": 0.5,
           "scheme": "Spectral",
-          "steps": 64,
-          "reverse": false,
-          "min": 0
+          "steps": 64
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
         },
-        "cellGap": 1,
         "filterValues": {
           "le": 1e-9
         },
-        "tooltip": {
-          "show": true,
-          "yHistogram": true
-        },
         "legend": {
           "show": true
         },
-        "exemplars": {
-          "color": "rgba(255,0,255,0.7)"
+        "rowsFrame": {
+          "layout": "auto",
+          "value": "Request count"
         },
-        "cellValues": {
+        "tooltip": {
+          "mode": "single",
+          "showColorScale": false,
+          "yHistogram": true
+        },
+        "yAxis": {
+          "axisLabel": "Prompt Length",
+          "axisPlacement": "left",
+          "reverse": false,
           "unit": "none"
         }
       },
+      "pluginVersion": "10.4.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "sum by(le) (increase(aphrodite:request_prompt_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
+          "format": "heatmap",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Request Prompt Length",
+      "type": "heatmap"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Heatmap of request generation length",
       "fieldConfig": {
         "defaults": {
           "custom": {
-            "scaleDistribution": {
-              "type": "linear"
-            },
             "hideFrom": {
+              "legend": false,
               "tooltip": false,
-              "viz": false,
-              "legend": false
+              "viz": false
+            },
+            "scaleDistribution": {
+              "type": "linear"
             }
           }
         },
         "overrides": []
       },
-      "pluginVersion": "10.2.0"
-    },
-    {
-      "datasource": {
-        "uid": "prometheus",
-        "type": "prometheus"
-      },
-      "type": "heatmap",
-      "title": "Request Generation Length",
-      "description": "Heatmap of request generation length",
       "gridPos": {
-        "x": 12,
-        "y": 24,
+        "h": 8,
         "w": 12,
-        "h": 8
+        "x": 12,
+        "y": 24
       },
       "id": 13,
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "prometheus"
-          },
-          "refId": "A",
-          "expr": "sum by(le) (increase(aphrodite:request_generation_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
-          "range": true,
-          "instant": false,
-          "editorMode": "builder",
-          "legendFormat": "{{le}}",
-          "useBackend": false,
-          "disableTextWrap": false,
-          "fullMetaSearch": false,
-          "includeNullMetadata": true,
-          "format": "heatmap"
-        }
-      ],
       "options": {
         "calculate": false,
-        "yAxis": {
-          "axisPlacement": "left",
-          "reverse": false,
-          "unit": "none",
-          "axisLabel": "Generation Length"
-        },
-        "rowsFrame": {
-          "layout": "auto",
-          "value": "Request count"
+        "cellGap": 1,
+        "cellValues": {
+          "unit": "none"
         },
         "color": {
-          "mode": "scheme",
+          "exponent": 0.5,
           "fill": "dark-orange",
+          "min": 0,
+          "mode": "scheme",
+          "reverse": false,
           "scale": "exponential",
-          "exponent": 0.5,
           "scheme": "Spectral",
-          "steps": 64,
-          "reverse": false,
-          "min": 0
+          "steps": 64
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
         },
-        "cellGap": 1,
         "filterValues": {
           "le": 1e-9
         },
-        "tooltip": {
-          "show": true,
-          "yHistogram": true
-        },
         "legend": {
           "show": true
         },
-        "exemplars": {
-          "color": "rgba(255,0,255,0.7)"
+        "rowsFrame": {
+          "layout": "auto",
+          "value": "Request count"
         },
-        "cellValues": {
+        "tooltip": {
+          "mode": "single",
+          "showColorScale": false,
+          "yHistogram": true
+        },
+        "yAxis": {
+          "axisLabel": "Generation Length",
+          "axisPlacement": "left",
+          "reverse": false,
           "unit": "none"
         }
       },
-      "fieldConfig": {
-        "defaults": {
-          "custom": {
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "hideFrom": {
-              "tooltip": false,
-              "viz": false,
-              "legend": false
-            }
-          }
-        },
-        "overrides": []
-      },
-      "pluginVersion": "10.2.0"
+      "pluginVersion": "10.4.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "sum by(le) (increase(aphrodite:request_generation_tokens_bucket{model_name=\"$model_name\"}[$__rate_interval]))",
+          "format": "heatmap",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Request Generation Length",
+      "type": "heatmap"
     },
     {
       "datasource": {
         "type": "prometheus",
-        "uid": "prometheus"
+        "uid": "${DS_PROMETHEUS}"
       },
+      "description": "Number of finished requests by their finish reason: either an EOS token was generated or the max sequence length was reached.",
       "fieldConfig": {
         "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
           "custom": {
-            "drawStyle": "line",
-            "lineInterpolation": "linear",
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
             "barAlignment": 0,
-            "lineWidth": 1,
+            "drawStyle": "line",
             "fillOpacity": 0,
             "gradientMode": "none",
-            "spanNulls": false,
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
             "insertNulls": false,
-            "showPoints": "auto",
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
             "pointSize": 5,
-            "stacking": {
-              "mode": "none",
-              "group": "A"
-            },
-            "axisPlacement": "auto",
-            "axisLabel": "",
-            "axisColorMode": "text",
-            "axisBorderShow": false,
             "scaleDistribution": {
               "type": "linear"
             },
-            "axisCenteredZero": false,
-            "hideFrom": {
-              "tooltip": false,
-              "viz": false,
-              "legend": false
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
             },
             "thresholdsStyle": {
               "mode": "off"
             }
           },
-          "color": {
-            "mode": "palette-classic"
-          },
           "mappings": [],
           "thresholds": {
             "mode": "absolute",
@@ -1123,22 +1167,22 @@
       },
       "id": 11,
       "options": {
-        "tooltip": {
-          "mode": "single",
-          "sort": "none"
-        },
         "legend": {
-          "showLegend": true,
+          "calcs": [],
           "displayMode": "list",
           "placement": "bottom",
-          "calcs": []
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
         }
       },
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
-            "uid": "prometheus"
+            "uid": "${DS_PROMETHEUS}"
           },
           "disableTextWrap": false,
           "editorMode": "builder",
@@ -1154,26 +1198,30 @@
         }
       ],
       "title": "Finish Reason",
-      "description": "Number of finished requests by their finish reason: either an EOS token was generated or the max sequence length was reached.",
       "type": "timeseries"
     }
   ],
   "refresh": "",
-  "schemaVersion": 37,
-  "style": "dark",
+  "schemaVersion": 39,
   "tags": [],
   "templating": {
     "list": [
       {
-        "current": {
-          "selected": false,
-          "text": "aphrodite",
-          "value": "aphrodite"
-        },
-        "datasource": {
-          "type": "prometheus",
-          "uid": "prometheus"
-        },
+        "type": "datasource",
+        "name": "DS_PROMETHEUS",
+        "label": "datasource",
+        "current": {},
+        "hide": 0,
+        "includeAll": false,
+        "multi": false,
+        "options": [],
+        "query": "prometheus",
+        "queryValue": "",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false
+      },
+      {
         "definition": "label_values(model_name)",
         "hide": 0,
         "includeAll": false,
@@ -1199,8 +1247,8 @@
   },
   "timepicker": {},
   "timezone": "",
-  "title": "Aphrodite Engine",
+  "title": "Aphrodite",
   "uid": "b281712d-8bff-41ef-9f3f-71ad43c05e9b",
-  "version": 2,
+  "version": 1,
   "weekStart": ""
 }