feat(cag): PrometheusRule + Grafana panels for KV cache observability

- cag-kv-cache-rules.yaml: recording rule vllm:prefix_cache_hit_rate (from cache_query_hit/miss counters), 3 alert rules: KVWarmupFailureHigh, KVWarmupMissHigh, VLLMPrefixCacheHitRateLow - api-latency-dashboard.yaml: 5 new panels (id 7-11): prefix cache hit rate, warmup hit/miss, warmup latency p50/p95, standing context tier hits, alert panel with fixed threshold 0.01/s
2026-09-27 18:37:03 +08:00
parent 920693df1b
commit 605bc706e0
3 changed files with 222 additions and 0 deletions
@@ -123,6 +123,156 @@ data:
              "custom": {"fillOpacity": 10}
            }
          }
+        },
+        {
+          "id": 7,
+          "title": "vLLM Prefix Cache Hit Rate",
+          "type": "timeseries",
+          "gridPos": {"h": 8, "w": 12, "x": 0, "y": 36},
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "targets": [
+            {
+              "expr": "vllm:prefix_cache_hit_rate",
+              "legendFormat": "prefix cache hit rate"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percentunit",
+              "min": 0,
+              "max": 1,
+              "custom": {"fillOpacity": 15},
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {"color": "red", "value": 0},
+                  {"color": "yellow", "value": 0.7},
+                  {"color": "green", "value": 0.85}
+                ]
+              }
+            }
+          }
+        },
+        {
+          "id": 8,
+          "title": "KV Warmup Hit vs Miss",
+          "type": "timeseries",
+          "gridPos": {"h": 8, "w": 12, "x": 12, "y": 36},
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "targets": [
+            {
+              "expr": "rate(memory_kv_cache_warmup_hit_total[5m])",
+              "legendFormat": "warmup hit"
+            },
+            {
+              "expr": "rate(memory_kv_cache_warmup_miss_total[5m])",
+              "legendFormat": "warmup miss"
+            },
+            {
+              "expr": "rate(memory_kv_cache_warmup_error_total[5m])",
+              "legendFormat": "warmup error"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "ops",
+              "custom": {"fillOpacity": 10}
+            }
+          }
+        },
+        {
+          "id": 9,
+          "title": "KV Warmup Latency p50/p95 (ms)",
+          "type": "timeseries",
+          "gridPos": {"h": 8, "w": 12, "x": 0, "y": 44},
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "targets": [
+            {
+              "expr": "histogram_quantile(0.50, sum(rate(memory_kv_cache_warmup_latency_ms_bucket[5m])) by (le))",
+              "legendFormat": "p50 warmup latency"
+            },
+            {
+              "expr": "histogram_quantile(0.95, sum(rate(memory_kv_cache_warmup_latency_ms_bucket[5m])) by (le))",
+              "legendFormat": "p95 warmup latency"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "ms",
+              "custom": {"fillOpacity": 10}
+            }
+          }
+        },
+        {
+          "id": 10,
+          "title": "Standing Context Cache Tier Hits",
+          "type": "timeseries",
+          "gridPos": {"h": 8, "w": 12, "x": 12, "y": 44},
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "targets": [
+            {
+              "expr": "rate(memory_standing_ctx_hit_redis_total[5m])",
+              "legendFormat": "Redis L1 hit"
+            },
+            {
+              "expr": "rate(memory_standing_ctx_hit_db_total[5m])",
+              "legendFormat": "DB L2 hit"
+            },
+            {
+              "expr": "rate(memory_standing_ctx_recompute_total[5m])",
+              "legendFormat": "recompute (L3)"
+            },
+            {
+              "expr": "rate(memory_standing_ctx_304_total[5m])",
+              "legendFormat": "304 Not Modified"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "ops",
+              "custom": {"fillOpacity": 10}
+            }
+          }
+        },
+        {
+          "id": 11,
+          "title": "Standing Context Alert: Stale > 10min post-ingest",
+          "type": "timeseries",
+          "description": "Alert if standing context was not refreshed within 10min of an ingest event. Indicates staleness propagation failure.",
+          "gridPos": {"h": 8, "w": 24, "x": 0, "y": 52},
+          "datasource": {"type": "prometheus", "uid": "prometheus"},
+          "targets": [
+            {
+              "expr": "rate(memory_standing_ctx_recompute_total[5m]) > 0",
+              "legendFormat": "recompute rate (non-zero = fresh)"
+            },
+            {
+              "expr": "rate(memory_kv_cache_warmup_miss_total[5m])",
+              "legendFormat": "warmup miss rate (alert if > 3/5min)"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "ops",
+              "custom": {"fillOpacity": 10},
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {"color": "green", "value": 0},
+                  {"color": "red", "value": 0.01}
+                ]
+              }
+            },
+            "overrides": [
+              {
+                "matcher": {"id": "byName", "options": "warmup miss rate (alert if > 3/5min)"},
+                "properties": [
+                  {"id": "thresholds", "value": {"mode": "absolute", "steps": [{"color": "green", "value": 0}, {"color": "red", "value": 0.01}]}},
+                  {"id": "custom.thresholdsStyle", "value": {"mode": "area"}}
+                ]
+              }
+            ]
+          }
        }
      ]
    }