reanimator/bee
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Add NVIDIA stress loader selection and DCGM 4 support

Browse Source
This commit is contained in:
Mikhail Chusavitin
2026-03-31 11:15:15 +03:00
parent 20f834aa96
commit 6dee8f3509
31 changed files with 789 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
audit/internal/platform/sat_test.go
View File

@@ -31,8 +31,8 @@ func TestRunNvidiaAcceptancePackIncludesGPUStress(t *testing.T) {
if len(jobs) != 5 {
t.Fatalf("jobs=%d want 5", len(jobs))
}
if got := jobs[4].cmd[0]; got != "bee-gpu-stress" {
t.Fatalf("gpu stress command=%q want bee-gpu-stress", got)
if got := jobs[4].cmd[0]; got != "bee-gpu-burn" {
t.Fatalf("gpu stress command=%q want bee-gpu-burn", got)
}
if got := jobs[3].cmd[1]; got != "--output-file" {
t.Fatalf("bug report flag=%q want --output-file", got)
@@ -80,13 +80,10 @@ func TestAMDStressJobsIncludeBandwidthAndGST(t *testing.T) {
}
}
func TestNvidiaSATJobsUseEnvOverrides(t *testing.T) {
t.Setenv("BEE_GPU_STRESS_SECONDS", "9")
t.Setenv("BEE_GPU_STRESS_SIZE_MB", "96")
func TestNvidiaSATJobsUseBuiltinBurnDefaults(t *testing.T) {
jobs := nvidiaSATJobs()
got := jobs[4].cmd
want := []string{"bee-gpu-stress", "--seconds", "9", "--size-mb", "96"}
want := []string{"bee-gpu-burn", "--seconds", "5", "--size-mb", "64"}
if len(got) != len(want) {
t.Fatalf("cmd len=%d want %d", len(got), len(want))
}
@@ -97,6 +94,40 @@ func TestNvidiaSATJobsUseEnvOverrides(t *testing.T) {
}
}
func TestBuildNvidiaStressJobUsesSelectedLoaderAndDevices(t *testing.T) {
t.Parallel()
oldExecCommand := satExecCommand
satExecCommand = func(name string, args ...string) *exec.Cmd {
if name == "nvidia-smi" {
return exec.Command("sh", "-c", "printf '0\n1\n2\n'")
}
return exec.Command(name, args...)
}
t.Cleanup(func() { satExecCommand = oldExecCommand })
job, err := buildNvidiaStressJob(NvidiaStressOptions{
DurationSec: 600,
Loader: NvidiaStressLoaderJohn,
ExcludeGPUIndices: []int{1},
})
if err != nil {
t.Fatalf("buildNvidiaStressJob error: %v", err)
}
wantCmd := []string{"bee-john-gpu-stress", "--seconds", "600", "--devices", "0,2"}
if len(job.cmd) != len(wantCmd) {
t.Fatalf("cmd len=%d want %d (%v)", len(job.cmd), len(wantCmd), job.cmd)
}
for i := range wantCmd {
if job.cmd[i] != wantCmd[i] {
t.Fatalf("cmd[%d]=%q want %q", i, job.cmd[i], wantCmd[i])
}
}
if got := joinIndexList(job.gpuIndices); got != "0,2" {
t.Fatalf("gpuIndices=%q want 0,2", got)
}
}
func TestEnvIntFallback(t *testing.T) {
os.Unsetenv("BEE_MEMTESTER_SIZE_MB")
if got := envInt("BEE_MEMTESTER_SIZE_MB", 123); got != 123 {
@@ -122,8 +153,8 @@ func TestClassifySATResult(t *testing.T) {
}{
{name: "ok", job: "memtester", out: "done", err: nil, status: "OK"},
{name: "unsupported", job: "smartctl-self-test-short", out: "Self-test not supported", err: errors.New("rc 1"), status: "UNSUPPORTED"},
{name: "failed", job: "bee-gpu-stress", out: "cuda error", err: errors.New("rc 1"), status: "FAILED"},
{name: "cuda not ready", job: "bee-gpu-stress", out: "cuInit failed: CUDA_ERROR_SYSTEM_NOT_READY", err: errors.New("rc 1"), status: "UNSUPPORTED"},
{name: "failed", job: "bee-gpu-burn", out: "cuda error", err: errors.New("rc 1"), status: "FAILED"},
{name: "cuda not ready", job: "bee-gpu-burn", out: "cuInit failed: CUDA_ERROR_SYSTEM_NOT_READY", err: errors.New("rc 1"), status: "UNSUPPORTED"},
}
for _, tt := range tests {