Refactor validate modes, fix benchmark report and IPMI power

- Replace diag level 1-4 dropdown with Validate/Stress radio buttons
- Validate: dcgmi L2, 60s CPU, 256MB/1p memtester, SMART short
- Stress: dcgmi L3 + targeted_stress in Run All, 30min CPU, 1GB/3p memtester, SMART long/NVMe extended
- Parallel GPU mode: spawn single task for all GPUs instead of splitting per model
- Benchmark table: per-GPU columns for sequential runs, server-wide column for parallel
- Benchmark report converted to Markdown with server model, GPU model, version in header; only steady-state charts
- Fix IPMI power parsing in benchmark (was looking for 'Current Power', correct field is 'Instantaneous power reading')

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-08 00:42:12 +03:00
parent dd26e03b2d
commit b2f8626fee
12 changed files with 332 additions and 164 deletions

View File

@@ -124,8 +124,8 @@ type satRunner interface {
RunNvidiaStressPack(ctx context.Context, baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error)
ListNvidiaGPUStatuses() ([]platform.NvidiaGPUStatus, error)
ResetNvidiaGPU(index int) (string, error)
RunMemoryAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunStorageAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunMemoryAcceptancePack(ctx context.Context, baseDir string, sizeMB, passes int, logFunc func(string)) (string, error)
RunStorageAcceptancePack(ctx context.Context, baseDir string, extended bool, logFunc func(string)) (string, error)
RunCPUAcceptancePack(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error)
ListNvidiaGPUs() ([]platform.NvidiaGPU, error)
DetectGPUVendor() string
@@ -602,14 +602,14 @@ func (a *App) RunNvidiaStressPackCtx(ctx context.Context, baseDir string, opts p
}
func (a *App) RunMemoryAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
return a.RunMemoryAcceptancePackCtx(context.Background(), baseDir, logFunc)
return a.RunMemoryAcceptancePackCtx(context.Background(), baseDir, 256, 1, logFunc)
}
func (a *App) RunMemoryAcceptancePackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
func (a *App) RunMemoryAcceptancePackCtx(ctx context.Context, baseDir string, sizeMB, passes int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunMemoryAcceptancePack(ctx, baseDir, logFunc)
return a.sat.RunMemoryAcceptancePack(ctx, baseDir, sizeMB, passes, logFunc)
}
func (a *App) RunMemoryAcceptancePackResult(baseDir string) (ActionResult, error) {
@@ -634,14 +634,14 @@ func (a *App) RunCPUAcceptancePackResult(baseDir string, durationSec int) (Actio
}
func (a *App) RunStorageAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
return a.RunStorageAcceptancePackCtx(context.Background(), baseDir, logFunc)
return a.RunStorageAcceptancePackCtx(context.Background(), baseDir, false, logFunc)
}
func (a *App) RunStorageAcceptancePackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
func (a *App) RunStorageAcceptancePackCtx(ctx context.Context, baseDir string, extended bool, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunStorageAcceptancePack(ctx, baseDir, logFunc)
return a.sat.RunStorageAcceptancePack(ctx, baseDir, extended, logFunc)
}
func (a *App) RunStorageAcceptancePackResult(baseDir string) (ActionResult, error) {

View File

@@ -217,11 +217,11 @@ func (f fakeSAT) ResetNvidiaGPU(index int) (string, error) {
return "", nil
}
func (f fakeSAT) RunMemoryAcceptancePack(_ context.Context, baseDir string, _ func(string)) (string, error) {
func (f fakeSAT) RunMemoryAcceptancePack(_ context.Context, baseDir string, _, _ int, _ func(string)) (string, error) {
return f.runMemoryFn(baseDir)
}
func (f fakeSAT) RunStorageAcceptancePack(_ context.Context, baseDir string, _ func(string)) (string, error) {
func (f fakeSAT) RunStorageAcceptancePack(_ context.Context, baseDir string, _ bool, _ func(string)) (string, error) {
return f.runStorageFn(baseDir)
}