Files
bee/audit/internal/platform/nvidia_stress.go
Mikhail Chusavitin 4e4debd4da refactor(webui): redesign Burn tab and fix gpu-burn memory defaults
- Burn tab: replace 6 flat cards with 3 grouped cards (GPU Stress,
  Compute Stress, Platform Thermal Cycling) + global Burn Profile
- Run All button at top enqueues all enabled tests across all cards
- GPU Stress: tool checkboxes enabled/disabled via new /api/gpu/tools
  endpoint based on driver status (/dev/nvidia0, /dev/kfd)
- Compute Stress: checkboxes for cpu/memory-stress/stressapptest
- Platform Thermal Cycling: component checkboxes (cpu/nvidia/amd)
  with platform_components param wired through to PlatformStressOptions
- bee-gpu-burn: default size-mb changed from 64 to 0 (auto); script
  now queries nvidia-smi memory.total per GPU and uses 95% of it
- platform_stress: removed hardcoded --size-mb 64; respects Components
  field to selectively run CPU and/or GPU load goroutines

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-01 09:39:07 +03:00

204 lines
5.1 KiB
Go

package platform
import (
"context"
"fmt"
"sort"
"strconv"
"strings"
)
func (s *System) RunNvidiaStressPack(ctx context.Context, baseDir string, opts NvidiaStressOptions, logFunc func(string)) (string, error) {
normalizeNvidiaStressOptions(&opts)
job, err := buildNvidiaStressJob(opts)
if err != nil {
return "", err
}
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,
{name: "04-nvidia-smi-after.log", cmd: []string{"nvidia-smi", "--query-gpu=index,name,temperature.gpu,power.draw,utilization.gpu,memory.used,memory.total", "--format=csv,noheader,nounits"}},
}, 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 {
return satJob{}, err
}
loader := strings.TrimSpace(strings.ToLower(opts.Loader))
switch loader {
case "", NvidiaStressLoaderBuiltin:
cmd := []string{
"bee-gpu-burn",
"--seconds", strconv.Itoa(opts.DurationSec),
"--size-mb", strconv.Itoa(opts.SizeMB),
}
if len(selected) > 0 {
cmd = append(cmd, "--devices", joinIndexList(selected))
}
return satJob{
name: "03-bee-gpu-burn.log",
cmd: cmd,
collectGPU: true,
gpuIndices: selected,
}, nil
case NvidiaStressLoaderJohn:
cmd := []string{
"bee-john-gpu-stress",
"--seconds", strconv.Itoa(opts.DurationSec),
}
if len(selected) > 0 {
cmd = append(cmd, "--devices", joinIndexList(selected))
}
return satJob{
name: "03-john-gpu-stress.log",
cmd: cmd,
collectGPU: true,
gpuIndices: selected,
}, nil
case NvidiaStressLoaderNCCL:
cmd := []string{
"bee-nccl-gpu-stress",
"--seconds", strconv.Itoa(opts.DurationSec),
}
if len(selected) > 0 {
cmd = append(cmd, "--devices", joinIndexList(selected))
}
return satJob{
name: "03-bee-nccl-gpu-stress.log",
cmd: cmd,
collectGPU: true,
gpuIndices: selected,
}, nil
default:
return satJob{}, fmt.Errorf("unknown NVIDIA stress loader %q", opts.Loader)
}
}
func normalizeNvidiaStressOptions(opts *NvidiaStressOptions) {
if opts.DurationSec <= 0 {
opts.DurationSec = 300
}
// SizeMB=0 means "auto" — bee-gpu-burn will query per-GPU memory at runtime.
switch strings.TrimSpace(strings.ToLower(opts.Loader)) {
case "", NvidiaStressLoaderBuiltin:
opts.Loader = NvidiaStressLoaderBuiltin
case NvidiaStressLoaderJohn:
opts.Loader = NvidiaStressLoaderJohn
case NvidiaStressLoaderNCCL:
opts.Loader = NvidiaStressLoaderNCCL
default:
opts.Loader = NvidiaStressLoaderBuiltin
}
opts.GPUIndices = dedupeSortedIndices(opts.GPUIndices)
opts.ExcludeGPUIndices = dedupeSortedIndices(opts.ExcludeGPUIndices)
}
func resolveNvidiaGPUSelection(include, exclude []int) ([]int, error) {
all, err := listNvidiaGPUIndices()
if err != nil {
return nil, err
}
if len(all) == 0 {
return nil, fmt.Errorf("nvidia-smi found no NVIDIA GPUs")
}
selected := all
if len(include) > 0 {
want := make(map[int]struct{}, len(include))
for _, idx := range include {
want[idx] = struct{}{}
}
selected = selected[:0]
for _, idx := range all {
if _, ok := want[idx]; ok {
selected = append(selected, idx)
}
}
}
if len(exclude) > 0 {
skip := make(map[int]struct{}, len(exclude))
for _, idx := range exclude {
skip[idx] = struct{}{}
}
filtered := selected[:0]
for _, idx := range selected {
if _, ok := skip[idx]; ok {
continue
}
filtered = append(filtered, idx)
}
selected = filtered
}
if len(selected) == 0 {
return nil, fmt.Errorf("no NVIDIA GPUs selected after applying filters")
}
out := append([]int(nil), selected...)
sort.Ints(out)
return out, nil
}
func listNvidiaGPUIndices() ([]int, error) {
out, err := satExecCommand("nvidia-smi", "--query-gpu=index", "--format=csv,noheader,nounits").Output()
if err != nil {
return nil, fmt.Errorf("nvidia-smi: %w", err)
}
var indices []int
for _, line := range strings.Split(strings.TrimSpace(string(out)), "\n") {
line = strings.TrimSpace(line)
if line == "" {
continue
}
idx, err := strconv.Atoi(line)
if err != nil {
continue
}
indices = append(indices, idx)
}
return dedupeSortedIndices(indices), nil
}
func dedupeSortedIndices(values []int) []int {
if len(values) == 0 {
return nil
}
seen := make(map[int]struct{}, len(values))
out := make([]int, 0, len(values))
for _, value := range values {
if value < 0 {
continue
}
if _, ok := seen[value]; ok {
continue
}
seen[value] = struct{}{}
out = append(out, value)
}
sort.Ints(out)
return out
}
func joinIndexList(values []int) string {
parts := make([]string, 0, len(values))
for _, value := range values {
parts = append(parts, strconv.Itoa(value))
}
return strings.Join(parts, ",")
}