fix(stress): label loaders and improve john opencl diagnostics

This commit is contained in:
2026-04-01 07:31:52 +03:00
parent 3869788bac
commit 45221d1e9a
6 changed files with 112 additions and 10 deletions

View File

@@ -16,7 +16,7 @@ func (s *System) RunNvidiaStressPack(ctx context.Context, baseDir string, opts N
return "", err
}
return runAcceptancePackCtx(ctx, baseDir, "gpu-nvidia-stress", []satJob{
return runAcceptancePackCtx(ctx, baseDir, nvidiaStressArchivePrefix(opts.Loader), []satJob{
{name: "01-nvidia-smi-q.log", cmd: []string{"nvidia-smi", "-q"}},
{name: "02-nvidia-smi-list.log", cmd: []string{"nvidia-smi", "-L"}},
job,
@@ -24,6 +24,17 @@ func (s *System) RunNvidiaStressPack(ctx context.Context, baseDir string, opts N
}, logFunc)
}
func nvidiaStressArchivePrefix(loader string) string {
switch strings.TrimSpace(strings.ToLower(loader)) {
case NvidiaStressLoaderJohn:
return "gpu-nvidia-john"
case NvidiaStressLoaderNCCL:
return "gpu-nvidia-nccl"
default:
return "gpu-nvidia-burn"
}
}
func buildNvidiaStressJob(opts NvidiaStressOptions) (satJob, error) {
selected, err := resolveNvidiaGPUSelection(opts.GPUIndices, opts.ExcludeGPUIndices)
if err != nil {

View File

@@ -162,6 +162,25 @@ func TestBuildNvidiaStressJobUsesNCCLLoader(t *testing.T) {
}
}
func TestNvidiaStressArchivePrefixByLoader(t *testing.T) {
t.Parallel()
tests := []struct {
loader string
want string
}{
{loader: NvidiaStressLoaderBuiltin, want: "gpu-nvidia-burn"},
{loader: NvidiaStressLoaderJohn, want: "gpu-nvidia-john"},
{loader: NvidiaStressLoaderNCCL, want: "gpu-nvidia-nccl"},
{loader: "", want: "gpu-nvidia-burn"},
}
for _, tt := range tests {
if got := nvidiaStressArchivePrefix(tt.loader); got != tt.want {
t.Fatalf("loader=%q prefix=%q want %q", tt.loader, got, tt.want)
}
}
}
func TestEnvIntFallback(t *testing.T) {
os.Unsetenv("BEE_MEMTESTER_SIZE_MB")
if got := envInt("BEE_MEMTESTER_SIZE_MB", 123); got != 123 {