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

@@ -195,6 +195,53 @@ func TestResolveDCGMGPUIndicesKeepsExplicitSelection(t *testing.T) {
}
}
func TestResolveDCGMProfTesterCommandUsesVersionedBinary(t *testing.T) {
oldLookPath := satLookPath
satLookPath = func(file string) (string, error) {
switch file {
case "dcgmproftester13":
return "/usr/bin/dcgmproftester13", nil
default:
return "", exec.ErrNotFound
}
}
t.Cleanup(func() { satLookPath = oldLookPath })
cmd, err := resolveDCGMProfTesterCommand("--no-dcgm-validation", "-t", "1004")
if err != nil {
t.Fatalf("resolveDCGMProfTesterCommand error: %v", err)
}
if len(cmd) != 4 {
t.Fatalf("cmd len=%d want 4 (%v)", len(cmd), cmd)
}
if cmd[0] != "/usr/bin/dcgmproftester13" {
t.Fatalf("cmd[0]=%q want /usr/bin/dcgmproftester13", cmd[0])
}
}
func TestNvidiaDCGMNamedDiagCommandUsesDurationAndSelection(t *testing.T) {
cmd := nvidiaDCGMNamedDiagCommand("targeted_power", 900, []int{3, 1})
want := []string{"dcgmi", "diag", "-r", "targeted_power", "-p", "targeted_power.test_duration=900", "-i", "3,1"}
if len(cmd) != len(want) {
t.Fatalf("cmd len=%d want %d (%v)", len(cmd), len(want), cmd)
}
for i := range want {
if cmd[i] != want[i] {
t.Fatalf("cmd[%d]=%q want %q", i, cmd[i], want[i])
}
}
}
func TestNvidiaVisibleDevicesEnvUsesSelectedGPUs(t *testing.T) {
env := nvidiaVisibleDevicesEnv([]int{0, 2, 4})
if len(env) != 1 {
t.Fatalf("env len=%d want 1 (%v)", len(env), env)
}
if env[0] != "CUDA_VISIBLE_DEVICES=0,2,4" {
t.Fatalf("env[0]=%q want CUDA_VISIBLE_DEVICES=0,2,4", env[0])
}
}
func TestNvidiaStressArchivePrefixByLoader(t *testing.T) {
t.Parallel()