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
audit/internal/platform/sat_fan_stress.go
+9 -13
View File
@@ -130,26 +130,21 @@ func (s *System) RunFanStressTest(ctx context.Context, baseDir string, opts FanS
stats.OK++
}
// loadPhase runs bee-gpu-stress for durSec; sampler stamps phaseName on each row.
// loadPhase runs bee-gpu-burn for durSec; sampler stamps phaseName on each row.
loadPhase := func(phaseName, stepName string, durSec int) {
if ctx.Err() != nil {
return
}
setPhase(phaseName)
var env []string
if len(opts.GPUIndices) > 0 {
ids := make([]string, len(opts.GPUIndices))
for i, idx := range opts.GPUIndices {
ids[i] = strconv.Itoa(idx)
}
env = []string{"CUDA_VISIBLE_DEVICES=" + strings.Join(ids, ",")}
}
cmd := []string{
"bee-gpu-stress",
"bee-gpu-burn",
"--seconds", strconv.Itoa(durSec),
"--size-mb", strconv.Itoa(opts.SizeMB),
}
out, err := runSATCommandCtx(ctx, verboseLog, stepName, cmd, env, nil)
if len(opts.GPUIndices) > 0 {
cmd = append(cmd, "--devices", joinIndexList(dedupeSortedIndices(opts.GPUIndices)))
}
out, err := runSATCommandCtx(ctx, verboseLog, stepName, cmd, nil, nil)
_ = os.WriteFile(filepath.Join(runDir, stepName+".log"), out, 0644)
if err != nil && err != context.Canceled && err.Error() != "signal: killed" {
fmt.Fprintf(&summary, "%s_status=FAILED\n", stepName)
@@ -323,8 +318,9 @@ func sampleFanSpeeds() ([]FanReading, error) {
// parseFanSpeeds parses "ipmitool sdr type Fan" output.
// Handles two formats:
// Old: "FAN1 | 2400.000 | RPM | ok" (value in col[1], unit in col[2])
// New: "FAN1 | 41h | ok | 29.1 | 4340 RPM" (value+unit combined in last col)
//
// Old: "FAN1 | 2400.000 | RPM | ok" (value in col[1], unit in col[2])
// New: "FAN1 | 41h | ok | 29.1 | 4340 RPM" (value+unit combined in last col)
func parseFanSpeeds(raw string) []FanReading {
var fans []FanReading
for _, line := range strings.Split(strings.TrimSpace(raw), "\n") {