feat: add Prometheus metrics parser for llama-swap GPU series

src/lib/metrics-parser.ts

@@ -0,0 +1,67 @@
+export interface PromSample {
+  metric: string;
+  labels: Record<string, string>;
+  value: number;
+}
+
+const LINE_RE = /^([A-Za-z_:][A-Za-z0-9_:]*)(?:\{([^}]*)\})?\s+(-?(?:\d+\.?\d*|\.\d+)(?:[eE][+-]?\d+)?)$/;
+
+export function parsePrometheus(text: string): PromSample[] {
+  const samples: PromSample[] = [];
+  for (const rawLine of text.split("\n")) {
+    const line = rawLine.trim();
+    if (!line || line.startsWith("#")) continue;
+    const m = LINE_RE.exec(line);
+    if (!m) continue;
+    const labels: Record<string, string> = {};
+    if (m[2]) {
+      for (const pair of m[2].split(",")) {
+        const eq = pair.indexOf("=");
+        if (eq === -1) continue;
+        const value = pair.slice(eq + 1).trim();
+        labels[pair.slice(0, eq).trim()] = value.replace(/^"(.*)"$/, "$1");
+      }
+    }
+    samples.push({ metric: m[1], labels, value: parseFloat(m[3]) });
+  }
+  return samples;
+}
+
+export type GpuMetricKind = "util_percent" | "memory_util_percent" | "temperature" | "power" | "fan";
+
+export const GPU_SERIES: Record<string, GpuMetricKind> = {
+  llamaswap_gpu_util_percent: "util_percent",
+  llamaswap_gpu_memory_util_percent: "memory_util_percent",
+  llamaswap_gpu_temperature_celsius: "temperature",
+  llamaswap_gpu_power_draw_watts: "power",
+  llamaswap_gpu_fan_speed_percent: "fan",
+};
+
+export interface GpuSample {
+  id: string;
+  name: string;
+  kind: GpuMetricKind;
+  value: number;
+}
+
+export function parseGpuMetrics(text: string): GpuSample[] {
+  const out: GpuSample[] = [];
+  for (const s of parsePrometheus(text)) {
+    const kind = GPU_SERIES[s.metric];
+    if (!kind) continue;
+    const id = s.labels["id"];
+    if (id === undefined) continue;
+    out.push({ id, name: s.labels["name"] ?? "", kind, value: s.value });
+  }
+  return out;
+}
+
+export function gpuInfos(samples: GpuSample[]): { id: string; name: string }[] {
+  const byId = new Map<string, string>();
+  for (const s of samples) {
+    if (!byId.has(s.id)) byId.set(s.id, s.name);
+  }
+  return [...byId.entries()]
+    .sort((a, b) => parseInt(a[0], 10) - parseInt(b[0], 10))
+    .map(([id, name]) => ({ id, name }));
+}

tests/fixtures/metrics.txt

@@ -0,0 +1,25 @@
+# HELP llamaswap_gpu_util_percent GPU utilization percent (0-100)
+# TYPE llamaswap_gpu_util_percent gauge
+llamaswap_gpu_util_percent{id="0",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-b77149e6-c22d-599e-9728-c7d4cfee0eb4"} 100
+llamaswap_gpu_util_percent{id="1",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-a46fadfa-48d9-c9c4-8fde-9bd641142bb7"} 100
+llamaswap_gpu_util_percent{id="2",name="NVIDIA GeForce RTX 5090",uuid="GPU-9a59ac37-12fb-5bc4-4767-4f4347898c0a"} 100
+# HELP llamaswap_gpu_memory_util_percent GPU memory utilization percent (0-100)
+# TYPE llamaswap_gpu_memory_util_percent gauge
+llamaswap_gpu_memory_util_percent{id="0",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-b77149e6-c22d-599e-9728-c7d4cfee0eb4"} 98.41347676402383
+llamaswap_gpu_memory_util_percent{id="1",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-a46fadfa-48d9-c9c4-8fde-9bd641142bb7"} 98.41245517790922
+llamaswap_gpu_memory_util_percent{id="2",name="NVIDIA GeForce RTX 5090",uuid="GPU-9a59ac37-12fb-5bc4-4767-4f4347898c0a"} 97.02211181648113
+# HELP llamaswap_gpu_temperature_celsius GPU temperature in Celsius
+# TYPE llamaswap_gpu_temperature_celsius gauge
+llamaswap_gpu_temperature_celsius{id="0",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-b77149e6-c22d-599e-9728-c7d4cfee0eb4"} 51
+llamaswap_gpu_temperature_celsius{id="1",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-a46fadfa-48d9-c9c4-8fde-9bd641142bb7"} 55
+llamaswap_gpu_temperature_celsius{id="2",name="NVIDIA GeForce RTX 5090",uuid="GPU-9a59ac37-12fb-5bc4-4767-4f4347898c0a"} 64
+# HELP llamaswap_gpu_power_draw_watts GPU power draw in watts
+# TYPE llamaswap_gpu_power_draw_watts gauge
+llamaswap_gpu_power_draw_watts{id="0",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-b77149e6-c22d-599e-9728-c7d4cfee0eb4"} 316.56
+llamaswap_gpu_power_draw_watts{id="1",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-a46fadfa-48d9-c9c4-8fde-9bd641142bb7"} 336.17
+llamaswap_gpu_power_draw_watts{id="2",name="NVIDIA GeForce RTX 5090",uuid="GPU-9a59ac37-12fb-5bc4-4767-4f4347898c0a"} 377.28
+# HELP llamaswap_gpu_fan_speed_percent GPU fan speed percent (0-100)
+# TYPE llamaswap_gpu_fan_speed_percent gauge
+llamaswap_gpu_fan_speed_percent{id="0",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-b77149e6-c22d-599e-9728-c7d4cfee0eb4"} 51
+llamaswap_gpu_fan_speed_percent{id="1",name="NVIDIA RTX PRO 6000 Blackwell Workstation Edition",uuid="GPU-a46fadfa-48d9-c9c4-8fde-9bd641142bb7"} 62
+llamaswap_gpu_fan_speed_percent{id="2",name="NVIDIA GeForce RTX 5090",uuid="GPU-9a59ac37-12fb-5bc4-4767-4f4347898c0a"} 89

tests/metrics-parser.test.ts

@@ -0,0 +1,35 @@
+import assert from "node:assert/strict";
+import { readFileSync } from "node:fs";
+import { test } from "node:test";
+import { gpuInfos, parseGpuMetrics, parsePrometheus } from "../src/lib/metrics-parser";
+
+const FIXTURE = readFileSync(new URL("./fixtures/metrics.txt", import.meta.url), "utf8");
+
+test("parsePrometheus parses a gauge with labels", () => {
+  const samples = parsePrometheus(`# TYPE llamaswap_gpu_util_percent gauge\nllamaswap_gpu_util_percent{id="0",name="RTX 5090"} 42.5\n`);
+  assert.equal(samples.length, 1);
+  assert.equal(samples[0].metric, "llamaswap_gpu_util_percent");
+  assert.deepEqual(samples[0].labels, { id: "0", name: "RTX 5090" });
+  assert.equal(samples[0].value, 42.5);
+});
+
+test("parsePrometheus ignores comments and blank lines", () => {
+  const samples = parsePrometheus("# HELP x y\n# TYPE x gauge\n\n");
+  assert.equal(samples.length, 0);
+});
+
+test("parseGpuMetrics extracts all five kinds for three GPUs from the fixture", () => {
+  const samples = parseGpuMetrics(FIXTURE);
+  assert.equal(samples.length, 15);
+  const kinds = new Set(samples.map((s) => s.kind));
+  assert.deepEqual([...kinds].sort(), ["fan", "memory_util_percent", "power", "temperature", "util_percent"]);
+  const power0 = samples.find((s) => s.kind === "power" && s.id === "0");
+  assert.ok(power0);
+  assert.equal(power0.value, 316.56);
+});
+
+test("gpuInfos dedupes, preserves names, sorts numerically by id", () => {
+  const infos = gpuInfos(parseGpuMetrics(FIXTURE));
+  assert.deepEqual(infos.map((i) => i.id), ["0", "1", "2"]);
+  assert.equal(infos[2].name, "NVIDIA GeForce RTX 5090");
+});