Split NVIDIA tasks by homogeneous GPU groups

This commit is contained in:
Mikhail Chusavitin
2026-04-06 11:58:13 +03:00
parent fc5c100a29
commit 981315e6fd
5 changed files with 569 additions and 75 deletions

View File

@@ -325,6 +325,78 @@ func TestFinalizeTaskRunCreatesReportFolderAndArtifacts(t *testing.T) {
}
}
func TestWriteTaskReportArtifactsIncludesBenchmarkResultsForTask(t *testing.T) {
dir := t.TempDir()
metricsPath := filepath.Join(dir, "metrics.db")
prevMetricsPath := taskReportMetricsDBPath
taskReportMetricsDBPath = metricsPath
t.Cleanup(func() { taskReportMetricsDBPath = prevMetricsPath })
benchmarkDir := filepath.Join(dir, "bee-benchmark", "gpu-benchmark-20260406-120000")
if err := os.MkdirAll(benchmarkDir, 0755); err != nil {
t.Fatal(err)
}
result := platform.NvidiaBenchmarkResult{
GeneratedAt: time.Date(2026, time.April, 6, 12, 0, 0, 0, time.UTC),
BenchmarkProfile: "standard",
OverallStatus: "OK",
GPUs: []platform.BenchmarkGPUResult{
{
Index: 0,
Name: "NVIDIA H100 PCIe",
Scores: platform.BenchmarkScorecard{
CompositeScore: 1176.25,
},
},
},
}
raw, err := json.Marshal(result)
if err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(benchmarkDir, "result.json"), raw, 0644); err != nil {
t.Fatal(err)
}
artifactsDir := filepath.Join(dir, "tasks", "task-bench_done")
if err := os.MkdirAll(artifactsDir, 0755); err != nil {
t.Fatal(err)
}
task := &Task{
ID: "task-bench",
Name: "NVIDIA Benchmark",
Target: "nvidia-benchmark",
Status: TaskDone,
CreatedAt: time.Now().UTC().Add(-time.Minute),
ArtifactsDir: artifactsDir,
}
ensureTaskReportPaths(task)
logText := "line-1\nArchive: " + filepath.Join(dir, "bee-benchmark", "gpu-benchmark-20260406-120000.tar.gz") + "\n"
if err := os.WriteFile(task.LogPath, []byte(logText), 0644); err != nil {
t.Fatal(err)
}
if err := writeTaskReportArtifacts(task); err != nil {
t.Fatalf("writeTaskReportArtifacts: %v", err)
}
body, err := os.ReadFile(task.ReportHTMLPath)
if err != nil {
t.Fatalf("ReadFile(report.html): %v", err)
}
html := string(body)
for _, needle := range []string{
`Benchmark Results`,
`Composite score for this benchmark task.`,
`NVIDIA H100 PCIe / GPU 0`,
`1176.25`,
} {
if !strings.Contains(html, needle) {
t.Fatalf("report missing %q: %s", needle, html)
}
}
}
func TestTaskLifecycleMirrorsToSerialConsole(t *testing.T) {
var lines []string
prev := taskSerialWriteLine