| 1 | kind: PersesDashboard |
| 2 | metadata: |
| 3 | name: query-statistics |
| 4 | createdAt: 0001-01-01T00:00:00Z |
| 5 | updatedAt: 0001-01-01T00:00:00Z |
| 6 | version: 0 |
| 7 | project: "" |
| 8 | spec: |
| 9 | display: |
| 10 | name: Query Statistics_New |
| 11 | |
| 12 | variables: |
| 13 | - kind: ListVariable |
| 14 | spec: |
| 15 | name: NS |
| 16 | display: { name: Namespace } |
| 17 | allowMultiple: false |
| 18 | defaultValue: llm-d |
| 19 | plugin: |
| 20 | kind: PrometheusLabelValuesVariable |
| 21 | spec: |
| 22 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 23 | labelName: namespace |
| 24 | matchers: |
| 25 | - up{service=~".*vllm.*"} |
| 26 | |
| 27 | - kind: ListVariable |
| 28 | spec: |
| 29 | name: SVC |
| 30 | display: { name: Service } |
| 31 | allowMultiple: false |
| 32 | defaultValue: vllm-qwen2-0-5b-sim |
| 33 | plugin: |
| 34 | kind: PrometheusLabelValuesVariable |
| 35 | spec: |
| 36 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 37 | labelName: service |
| 38 | matchers: |
| 39 | - up{namespace="$NS",service=~".*vllm.*"} |
| 40 | |
| 41 | - kind: ListVariable |
| 42 | spec: |
| 43 | name: MODEL |
| 44 | display: { name: Model (real vLLM) } |
| 45 | allowAllValue: true |
| 46 | allowMultiple: true |
| 47 | defaultValue: ["$__all"] |
| 48 | plugin: |
| 49 | kind: PrometheusLabelValuesVariable |
| 50 | spec: |
| 51 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 52 | labelName: model_name |
| 53 | matchers: |
| 54 | - vllm:request_success_total{namespace="$NS",service="$SVC"} |
| 55 | |
| 56 | panels: |
| 57 | |
| 58 | # --- Core (works on Simulator & Real) --- |
| 59 | core_running_now: |
| 60 | kind: Panel |
| 61 | spec: |
| 62 | display: { name: Running Requests (now) } |
| 63 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 64 | queries: |
| 65 | - kind: TimeSeriesQuery |
| 66 | spec: |
| 67 | plugin: |
| 68 | kind: PrometheusTimeSeriesQuery |
| 69 | spec: |
| 70 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 71 | query: sum(vllm:num_requests_running{namespace="$NS",service="$SVC"}) or vector(0) |
| 72 | minStep: "15s" |
| 73 | |
| 74 | core_waiting_now: |
| 75 | kind: Panel |
| 76 | spec: |
| 77 | display: { name: Waiting Requests (now) } |
| 78 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 79 | queries: |
| 80 | - kind: TimeSeriesQuery |
| 81 | spec: |
| 82 | plugin: |
| 83 | kind: PrometheusTimeSeriesQuery |
| 84 | spec: |
| 85 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 86 | query: sum(vllm:num_requests_waiting{namespace="$NS",service="$SVC"}) or vector(0) |
| 87 | minStep: "15s" |
| 88 | |
| 89 | core_kv_usage_now: |
| 90 | kind: Panel |
| 91 | spec: |
| 92 | display: { name: KV Cache Usage (0–1) } |
| 93 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 94 | queries: |
| 95 | - kind: TimeSeriesQuery |
| 96 | spec: |
| 97 | plugin: |
| 98 | kind: PrometheusTimeSeriesQuery |
| 99 | spec: |
| 100 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 101 | query: avg(vllm:kv_cache_usage_perc{namespace="$NS",service="$SVC"}) or vector(0) |
| 102 | minStep: "15s" |
| 103 | |
| 104 | core_running_ts: |
| 105 | kind: Panel |
| 106 | spec: |
| 107 | display: { name: Running Over Time } |
| 108 | plugin: |
| 109 | kind: TimeSeriesChart |
| 110 | spec: |
| 111 | legend: { mode: table, position: bottom } |
| 112 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 113 | queries: |
| 114 | - kind: TimeSeriesQuery |
| 115 | spec: |
| 116 | plugin: |
| 117 | kind: PrometheusTimeSeriesQuery |
| 118 | spec: |
| 119 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 120 | query: sum by (service) (vllm:num_requests_running{namespace="$NS",service="$SVC"}) or vector(0) |
| 121 | minStep: "15s" |
| 122 | |
| 123 | core_waiting_ts: |
| 124 | kind: Panel |
| 125 | spec: |
| 126 | display: { name: Waiting Over Time } |
| 127 | plugin: |
| 128 | kind: TimeSeriesChart |
| 129 | spec: |
| 130 | legend: { mode: table, position: bottom } |
| 131 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 132 | queries: |
| 133 | - kind: TimeSeriesQuery |
| 134 | spec: |
| 135 | plugin: |
| 136 | kind: PrometheusTimeSeriesQuery |
| 137 | spec: |
| 138 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 139 | query: sum by (service) (vllm:num_requests_waiting{namespace="$NS",service="$SVC"}) or vector(0) |
| 140 | minStep: "15s" |
| 141 | |
| 142 | core_targets_up: |
| 143 | kind: Panel |
| 144 | spec: |
| 145 | display: { name: Scrape Targets Up } |
| 146 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 147 | queries: |
| 148 | - kind: TimeSeriesQuery |
| 149 | spec: |
| 150 | plugin: |
| 151 | kind: PrometheusTimeSeriesQuery |
| 152 | spec: |
| 153 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 154 | query: count(up{namespace="$NS",service="$SVC"} == 1) or vector(0) |
| 155 | minStep: "15s" |
| 156 | |
| 157 | # --- KV Cache as Percent (works on Simulator & Real) --- |
| 158 | core_kv_usage_pct_now: |
| 159 | kind: Panel |
| 160 | spec: |
| 161 | display: { name: KV Cache Usage (%) – now } |
| 162 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 163 | queries: |
| 164 | - kind: TimeSeriesQuery |
| 165 | spec: |
| 166 | plugin: |
| 167 | kind: PrometheusTimeSeriesQuery |
| 168 | spec: |
| 169 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 170 | # multiply by 100 to present percentage; omit format.unit to avoid schema conflicts |
| 171 | query: (avg(vllm:kv_cache_usage_perc{namespace="$NS",service="$SVC"}) * 100) or vector(0) |
| 172 | minStep: "15s" |
| 173 | |
| 174 | core_kv_usage_pct_ts: |
| 175 | kind: Panel |
| 176 | spec: |
| 177 | display: { name: KV Cache Usage (%) – over time } |
| 178 | plugin: |
| 179 | kind: TimeSeriesChart |
| 180 | spec: |
| 181 | legend: { mode: table, position: bottom } |
| 182 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 183 | queries: |
| 184 | - kind: TimeSeriesQuery |
| 185 | spec: |
| 186 | plugin: |
| 187 | kind: PrometheusTimeSeriesQuery |
| 188 | spec: |
| 189 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 190 | query: (avg by (service) (vllm:kv_cache_usage_perc{namespace="$NS",service="$SVC"}) * 100) or vector(0) |
| 191 | minStep: "15s" |
| 192 | |
| 193 | # --- Per-Pod breakdowns (works on Simulator & Real) --- |
| 194 | per_pod_running_ts: |
| 195 | kind: Panel |
| 196 | spec: |
| 197 | display: { name: Running by Pod } |
| 198 | plugin: |
| 199 | kind: TimeSeriesChart |
| 200 | spec: |
| 201 | legend: { mode: table, position: bottom } |
| 202 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 203 | queries: |
| 204 | - kind: TimeSeriesQuery |
| 205 | spec: |
| 206 | plugin: |
| 207 | kind: PrometheusTimeSeriesQuery |
| 208 | spec: |
| 209 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 210 | query: sum by (pod) (vllm:num_requests_running{namespace="$NS",service="$SVC"}) or vector(0) |
| 211 | minStep: "15s" |
| 212 | |
| 213 | per_pod_waiting_ts: |
| 214 | kind: Panel |
| 215 | spec: |
| 216 | display: { name: Waiting by Pod } |
| 217 | plugin: |
| 218 | kind: TimeSeriesChart |
| 219 | spec: |
| 220 | legend: { mode: table, position: bottom } |
| 221 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 222 | queries: |
| 223 | - kind: TimeSeriesQuery |
| 224 | spec: |
| 225 | plugin: |
| 226 | kind: PrometheusTimeSeriesQuery |
| 227 | spec: |
| 228 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 229 | query: sum by (pod) (vllm:num_requests_waiting{namespace="$NS",service="$SVC"}) or vector(0) |
| 230 | minStep: "15s" |
| 231 | |
| 232 | per_pod_kv_pct_ts: |
| 233 | kind: Panel |
| 234 | spec: |
| 235 | display: { name: KV Cache (%) by Pod } |
| 236 | plugin: |
| 237 | kind: TimeSeriesChart |
| 238 | spec: |
| 239 | legend: { mode: table, position: bottom } |
| 240 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 241 | queries: |
| 242 | - kind: TimeSeriesQuery |
| 243 | spec: |
| 244 | plugin: |
| 245 | kind: PrometheusTimeSeriesQuery |
| 246 | spec: |
| 247 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 248 | # if your exporter labels kv metric with pod (the sim does), this works; otherwise it will just return empty |
| 249 | query: (avg by (pod) (vllm:kv_cache_usage_perc{namespace="$NS",service="$SVC"}) * 100) or vector(0) |
| 250 | minStep: "15s" |
| 251 | |
| 252 | # --- Real vLLM only (zeros on simulator) --- |
| 253 | real_req_rate_ts: |
| 254 | kind: Panel |
| 255 | spec: |
| 256 | display: { name: Request Rate (real vLLM) } |
| 257 | plugin: |
| 258 | kind: TimeSeriesChart |
| 259 | spec: |
| 260 | legend: { mode: table, position: bottom } |
| 261 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 262 | queries: |
| 263 | - kind: TimeSeriesQuery |
| 264 | spec: |
| 265 | plugin: |
| 266 | kind: PrometheusTimeSeriesQuery |
| 267 | spec: |
| 268 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 269 | query: sum by (model_name) (rate(vllm:request_success_total{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval])) or vector(0) |
| 270 | minStep: "15s" |
| 271 | |
| 272 | real_p50: |
| 273 | kind: Panel |
| 274 | spec: |
| 275 | display: { name: p50 Latency (real vLLM) } |
| 276 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 277 | queries: |
| 278 | - kind: TimeSeriesQuery |
| 279 | spec: |
| 280 | plugin: |
| 281 | kind: PrometheusTimeSeriesQuery |
| 282 | spec: |
| 283 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 284 | query: histogram_quantile(0.50, sum by (le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval]))) or vector(0) |
| 285 | minStep: "15s" |
| 286 | |
| 287 | real_p90: |
| 288 | kind: Panel |
| 289 | spec: |
| 290 | display: { name: p90 Latency (real vLLM) } |
| 291 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 292 | queries: |
| 293 | - kind: TimeSeriesQuery |
| 294 | spec: |
| 295 | plugin: |
| 296 | kind: PrometheusTimeSeriesQuery |
| 297 | spec: |
| 298 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 299 | query: histogram_quantile(0.90, sum by (le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval]))) or vector(0) |
| 300 | minStep: "15s" |
| 301 | |
| 302 | real_p99: |
| 303 | kind: Panel |
| 304 | spec: |
| 305 | display: { name: p99 Latency (real vLLM) } |
| 306 | plugin: { kind: StatChart, spec: { calculation: last-number } } |
| 307 | queries: |
| 308 | - kind: TimeSeriesQuery |
| 309 | spec: |
| 310 | plugin: |
| 311 | kind: PrometheusTimeSeriesQuery |
| 312 | spec: |
| 313 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 314 | query: histogram_quantile(0.99, sum by (le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval]))) or vector(0) |
| 315 | minStep: "15s" |
| 316 | |
| 317 | real_input_tokens_ts: |
| 318 | kind: Panel |
| 319 | spec: |
| 320 | display: { name: Input Tokens / sec (real vLLM) } |
| 321 | plugin: |
| 322 | kind: TimeSeriesChart |
| 323 | spec: |
| 324 | legend: { mode: table, position: bottom } |
| 325 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 326 | queries: |
| 327 | - kind: TimeSeriesQuery |
| 328 | spec: |
| 329 | plugin: |
| 330 | kind: PrometheusTimeSeriesQuery |
| 331 | spec: |
| 332 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 333 | query: sum by (model_name) (rate(vllm:prompt_tokens_total{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval])) or vector(0) |
| 334 | minStep: "15s" |
| 335 | |
| 336 | real_output_tokens_ts: |
| 337 | kind: Panel |
| 338 | spec: |
| 339 | display: { name: Output Tokens / sec (real vLLM) } |
| 340 | plugin: |
| 341 | kind: TimeSeriesChart |
| 342 | spec: |
| 343 | legend: { mode: table, position: bottom } |
| 344 | visual: { display: line, lineWidth: 1, areaOpacity: 0.3 } |
| 345 | queries: |
| 346 | - kind: TimeSeriesQuery |
| 347 | spec: |
| 348 | plugin: |
| 349 | kind: PrometheusTimeSeriesQuery |
| 350 | spec: |
| 351 | datasource: { kind: PrometheusDatasource, name: accelerators-thanos-querier-datasource } |
| 352 | query: sum by (model_name) (rate(vllm:generation_tokens_total{namespace="$NS",service="$SVC",model_name=~"$MODEL"}[$__interval])) or vector(0) |
| 353 | minStep: "15s" |
| 354 | |
| 355 | layouts: |
| 356 | - kind: Grid |
| 357 | spec: |
| 358 | display: { title: Core (Sim & Real) } |
| 359 | items: |
| 360 | - { x: 0, y: 0, width: 6, height: 3, content: { $ref: '#/spec/panels/core_running_now' } } |
| 361 | - { x: 6, y: 0, width: 6, height: 3, content: { $ref: '#/spec/panels/core_waiting_now' } } |
| 362 | - { x: 12, y: 0, width: 6, height: 3, content: { $ref: '#/spec/panels/core_kv_usage_now' } } |
| 363 | - { x: 18, y: 0, width: 6, height: 3, content: { $ref: '#/spec/panels/core_targets_up' } } |
| 364 | - { x: 0, y: 3, width: 12, height: 6, content: { $ref: '#/spec/panels/core_running_ts' } } |
| 365 | - { x: 12, y: 3, width: 12, height: 6, content: { $ref: '#/spec/panels/core_waiting_ts' } } |
| 366 | |
| 367 | - kind: Grid |
| 368 | spec: |
| 369 | display: { title: KV Cache (%) } |
| 370 | items: |
| 371 | - { x: 0, y: 9, width: 6, height: 3, content: { $ref: '#/spec/panels/core_kv_usage_pct_now' } } |
| 372 | - { x: 6, y: 9, width: 18, height: 6, content: { $ref: '#/spec/panels/core_kv_usage_pct_ts' } } |
| 373 | |
| 374 | - kind: Grid |
| 375 | spec: |
| 376 | display: { title: Per-Pod breakdowns } |
| 377 | items: |
| 378 | - { x: 0, y: 15, width: 12, height: 6, content: { $ref: '#/spec/panels/per_pod_running_ts' } } |
| 379 | - { x: 12, y: 15, width: 12, height: 6, content: { $ref: '#/spec/panels/per_pod_waiting_ts' } } |
| 380 | - { x: 0, y: 21, width: 24, height: 6, content: { $ref: '#/spec/panels/per_pod_kv_pct_ts' } } |
| 381 | |
| 382 | - kind: Grid |
| 383 | spec: |
| 384 | display: { title: Real vLLM only (shows 0 on simulator) } |
| 385 | items: |
| 386 | - { x: 0, y: 27, width: 12, height: 6, content: { $ref: '#/spec/panels/real_req_rate_ts' } } |
| 387 | - { x: 12, y: 27, width: 4, height: 3, content: { $ref: '#/spec/panels/real_p50' } } |
| 388 | - { x: 16, y: 27, width: 4, height: 3, content: { $ref: '#/spec/panels/real_p90' } } |
| 389 | - { x: 20, y: 27, width: 4, height: 3, content: { $ref: '#/spec/panels/real_p99' } } |
| 390 | - { x: 0, y: 33, width: 12, height: 6, content: { $ref: '#/spec/panels/real_input_tokens_ts' } } |
| 391 | - { x: 12, y: 33, width: 12, height: 6, content: { $ref: '#/spec/panels/real_output_tokens_ts' } } |
| 392 |