Refine burn UI and NVIDIA stress flows

This commit is contained in:
2026-04-05 13:43:43 +03:00
parent 25af2df23a
commit 38e79143eb
18 changed files with 825 additions and 229 deletions

View File

@@ -115,7 +115,12 @@ func (a *App) RunInstallToRAM(ctx context.Context, logFunc func(string)) error {
type satRunner interface {
RunNvidiaAcceptancePack(baseDir string, logFunc func(string)) (string, error)
RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaTargetedStressValidatePack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaBenchmark(ctx context.Context, baseDir string, opts platform.NvidiaBenchmarkOptions, logFunc func(string)) (string, error)
RunNvidiaOfficialComputePack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaTargetedPowerPack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaPulseTestPack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaBandwidthPack(ctx context.Context, baseDir string, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaStressPack(ctx context.Context, baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error)
RunMemoryAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunStorageAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
@@ -528,6 +533,13 @@ func (a *App) RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir st
return ActionResult{Title: "NVIDIA DCGM", Body: body}, err
}
func (a *App) RunNvidiaTargetedStressValidatePack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaTargetedStressValidatePack(ctx, baseDir, durationSec, gpuIndices, logFunc)
}
func (a *App) RunNvidiaStressPack(baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error) {
return a.RunNvidiaStressPackCtx(context.Background(), baseDir, opts, logFunc)
}
@@ -543,6 +555,34 @@ func (a *App) RunNvidiaBenchmarkCtx(ctx context.Context, baseDir string, opts pl
return a.sat.RunNvidiaBenchmark(ctx, baseDir, opts, logFunc)
}
func (a *App) RunNvidiaOfficialComputePack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaOfficialComputePack(ctx, baseDir, durationSec, gpuIndices, logFunc)
}
func (a *App) RunNvidiaTargetedPowerPack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaTargetedPowerPack(ctx, baseDir, durationSec, gpuIndices, logFunc)
}
func (a *App) RunNvidiaPulseTestPack(ctx context.Context, baseDir string, durationSec int, gpuIndices []int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaPulseTestPack(ctx, baseDir, durationSec, gpuIndices, logFunc)
}
func (a *App) RunNvidiaBandwidthPack(ctx context.Context, baseDir string, gpuIndices []int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaBandwidthPack(ctx, baseDir, gpuIndices, logFunc)
}
func (a *App) RunNvidiaStressPackCtx(ctx context.Context, baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
@@ -893,6 +933,12 @@ func latestSATSummaries() []string {
prefix string
}{
{label: "NVIDIA SAT", prefix: "gpu-nvidia-"},
{label: "NVIDIA Targeted Stress Validate (dcgmi diag targeted_stress)", prefix: "gpu-nvidia-targeted-stress-"},
{label: "NVIDIA Max Compute Load (dcgmproftester)", prefix: "gpu-nvidia-compute-"},
{label: "NVIDIA Targeted Power (dcgmi diag targeted_power)", prefix: "gpu-nvidia-targeted-power-"},
{label: "NVIDIA Pulse Test (dcgmi diag pulse_test)", prefix: "gpu-nvidia-pulse-"},
{label: "NVIDIA Interconnect Test (NCCL all_reduce_perf)", prefix: "gpu-nvidia-nccl-"},
{label: "NVIDIA Bandwidth Test (NVBandwidth)", prefix: "gpu-nvidia-bandwidth-"},
{label: "Memory SAT", prefix: "memory-"},
{label: "Storage SAT", prefix: "storage-"},
{label: "CPU SAT", prefix: "cpu-"},

View File

@@ -120,16 +120,21 @@ func (f fakeTools) CheckTools(names []string) []platform.ToolStatus {
}
type fakeSAT struct {
runNvidiaFn func(string) (string, error)
runNvidiaBenchmarkFn func(string, platform.NvidiaBenchmarkOptions) (string, error)
runNvidiaStressFn func(string, platform.NvidiaStressOptions) (string, error)
runMemoryFn func(string) (string, error)
runStorageFn func(string) (string, error)
runCPUFn func(string, int) (string, error)
detectVendorFn func() string
listAMDGPUsFn func() ([]platform.AMDGPUInfo, error)
runAMDPackFn func(string) (string, error)
listNvidiaGPUsFn func() ([]platform.NvidiaGPU, error)
runNvidiaFn func(string) (string, error)
runNvidiaBenchmarkFn func(string, platform.NvidiaBenchmarkOptions) (string, error)
runNvidiaStressFn func(string, platform.NvidiaStressOptions) (string, error)
runNvidiaComputeFn func(string, int, []int) (string, error)
runNvidiaPowerFn func(string, int, []int) (string, error)
runNvidiaPulseFn func(string, int, []int) (string, error)
runNvidiaBandwidthFn func(string, []int) (string, error)
runNvidiaTargetedStressFn func(string, int, []int) (string, error)
runMemoryFn func(string) (string, error)
runStorageFn func(string) (string, error)
runCPUFn func(string, int) (string, error)
detectVendorFn func() string
listAMDGPUsFn func() ([]platform.AMDGPUInfo, error)
runAMDPackFn func(string) (string, error)
listNvidiaGPUsFn func() ([]platform.NvidiaGPU, error)
}
func (f fakeSAT) RunNvidiaAcceptancePack(baseDir string, _ func(string)) (string, error) {
@@ -147,6 +152,41 @@ func (f fakeSAT) RunNvidiaBenchmark(_ context.Context, baseDir string, opts plat
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaTargetedStressValidatePack(_ context.Context, baseDir string, durationSec int, gpuIndices []int, _ func(string)) (string, error) {
if f.runNvidiaTargetedStressFn != nil {
return f.runNvidiaTargetedStressFn(baseDir, durationSec, gpuIndices)
}
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaOfficialComputePack(_ context.Context, baseDir string, durationSec int, gpuIndices []int, _ func(string)) (string, error) {
if f.runNvidiaComputeFn != nil {
return f.runNvidiaComputeFn(baseDir, durationSec, gpuIndices)
}
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaTargetedPowerPack(_ context.Context, baseDir string, durationSec int, gpuIndices []int, _ func(string)) (string, error) {
if f.runNvidiaPowerFn != nil {
return f.runNvidiaPowerFn(baseDir, durationSec, gpuIndices)
}
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaPulseTestPack(_ context.Context, baseDir string, durationSec int, gpuIndices []int, _ func(string)) (string, error) {
if f.runNvidiaPulseFn != nil {
return f.runNvidiaPulseFn(baseDir, durationSec, gpuIndices)
}
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaBandwidthPack(_ context.Context, baseDir string, gpuIndices []int, _ func(string)) (string, error) {
if f.runNvidiaBandwidthFn != nil {
return f.runNvidiaBandwidthFn(baseDir, gpuIndices)
}
return f.runNvidiaFn(baseDir)
}
func (f fakeSAT) RunNvidiaStressPack(_ context.Context, baseDir string, opts platform.NvidiaStressOptions, _ func(string)) (string, error) {
if f.runNvidiaStressFn != nil {
return f.runNvidiaStressFn(baseDir, opts)

View File

@@ -21,12 +21,12 @@ type ComponentStatusDB struct {
// ComponentStatusRecord holds the current and historical health of one hardware component.
type ComponentStatusRecord struct {
ComponentKey string `json:"component_key"`
Status string `json:"status"` // "OK", "Warning", "Critical", "Unknown"
LastCheckedAt time.Time `json:"last_checked_at"`
LastChangedAt time.Time `json:"last_changed_at"`
ErrorSummary string `json:"error_summary,omitempty"`
History []ComponentStatusEntry `json:"history"`
ComponentKey string `json:"component_key"`
Status string `json:"status"` // "OK", "Warning", "Critical", "Unknown"
LastCheckedAt time.Time `json:"last_checked_at"`
LastChangedAt time.Time `json:"last_changed_at"`
ErrorSummary string `json:"error_summary,omitempty"`
History []ComponentStatusEntry `json:"history"`
}
// ComponentStatusEntry is one observation written to a component's history.
@@ -179,7 +179,9 @@ func ApplySATResultToDB(db *ComponentStatusDB, target, archivePath string) {
// Map SAT target to component keys.
switch target {
case "nvidia", "amd", "nvidia-stress", "amd-stress", "amd-mem", "amd-bandwidth":
case "nvidia", "nvidia-targeted-stress", "nvidia-compute", "nvidia-targeted-power", "nvidia-pulse",
"nvidia-interconnect", "nvidia-bandwidth", "amd", "nvidia-stress",
"amd-stress", "amd-mem", "amd-bandwidth":
db.Record("pcie:gpu:"+target, source, dbStatus, target+" SAT: "+overall)
case "memory", "memory-stress", "sat-stress":
db.Record("memory:all", source, dbStatus, target+" SAT: "+overall)