Files
bee/audit/internal/platform/export.go
T
Mikhail ChusavitinandClaude Sonnet 5 20cd317c87 platform/cmd/webui: add a scriptable test-scenario engine, load scenarios from blackbox USB, GPU status detail inventory fallback
Investigating the CG480-S6053 reboot needed a way to run an ad-hoc load
(nvbandwidth across a specific GPU set) while sampling IPMI/nvidia-smi
telemetry in the background — without hardcoding a one-off test into the
SAT pack code for a single investigation.

- audit/internal/platform/scenario.go: ScenarioSpec/ScenarioJob (JSON,
  no new dependency) + System.RunScenario. "command" jobs run sequential
  or parallel (per-job "parallel" flag); "sampler" jobs run concurrently
  in the background on their own interval until every command job
  finishes or the scenario's timeout elapses. "{{gpus}}" in a command's
  cmd is substituted from that job's gpu_indices. Command jobs are wired
  through the same satJobBoundaryHook/satSyncBracketHook seams the SAT
  job runner uses, so a scenario run gets the same durability treatment
  (evidence that a risky command started/finished reaches blackbox before
  a possible crash, not just whatever streamed to the RAM-backed export
  dir).
- export.go: ReadScenarioFromRemovableMedia mounts each removable target
  looking for scenarios/<name>.json — an air-gapped engineer can author a
  scenario elsewhere, drop it under scenarios/ on the same USB stick
  already plugged in for blackbox, and run it with no network path onto
  the host.
- cmd/bee: new `bee run <file.json|name>` (bare name = looked up on
  removable media); `bee scenario run <arg>` kept as a longer alias.
- scenarios/nvbandwidth-all-gpu-power-watch.json: the scenario that
  reproduced the actual reboot (full nvbandwidth across all GPUs, which
  crashed, vs. clean per-socket passes), with IPMI sensor + GPU power/temp
  sampling for a power-delivery correlation check.

Also: webui/page_topo.go — the /topo page's component-status-detail modal
(GET /api/component-detail/{type}) showed "No status data recorded yet"
for any component type ComponentStatusDB has no history for yet (e.g. GPU
before a SAT run this boot), even though the topology card for the same
component already showed "N OK" from the audit inventory snapshot.
inventoryFallbackRecords now synthesizes records from that same inventory
snapshot when StatusDB is empty, using the same device classifiers
(isGPUDeviceClass etc.) and severity mapping (classifyTopoSeverity) the
topology card itself uses, so the two views never disagree.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-28 17:51:45 +03:00

206 lines
5.9 KiB
Go

package platform
import (
"fmt"
"os"
"os/exec"
"path/filepath"
"sort"
"strings"
)
var exportExecCommand = exec.Command
func formatMountTargetError(target RemovableTarget, raw string, err error) error {
msg := strings.TrimSpace(raw)
fstype := strings.ToLower(strings.TrimSpace(target.FSType))
if fstype == "exfat" && strings.Contains(strings.ToLower(msg), "unknown filesystem type 'exfat'") {
return fmt.Errorf("mount %s: exFAT support is missing in this ISO build: %w", target.Device, err)
}
if msg == "" {
return err
}
return fmt.Errorf("%s: %w", msg, err)
}
func removableTargetReadOnly(fields map[string]string) bool {
if fields["RO"] == "1" {
return true
}
switch strings.ToLower(strings.TrimSpace(fields["FSTYPE"])) {
case "iso9660", "squashfs":
return true
default:
return false
}
}
func ensureWritableMountpoint(mountpoint string) error {
probe, err := os.CreateTemp(mountpoint, ".bee-write-test-*")
if err != nil {
return fmt.Errorf("target filesystem is not writable: %w", err)
}
name := probe.Name()
if closeErr := probe.Close(); closeErr != nil {
_ = os.Remove(name)
return closeErr
}
if err := os.Remove(name); err != nil {
return err
}
return nil
}
func (s *System) ListRemovableTargets() ([]RemovableTarget, error) {
raw, err := exportExecCommand("lsblk", "-P", "-o", "NAME,TYPE,PKNAME,RM,RO,FSTYPE,MOUNTPOINT,SIZE,LABEL,MODEL").Output()
if err != nil {
return nil, err
}
var out []RemovableTarget
for _, line := range strings.Split(strings.TrimSpace(string(raw)), "\n") {
if strings.TrimSpace(line) == "" {
continue
}
fields := parseLSBLKPairs(line)
deviceType := fields["TYPE"]
if deviceType == "rom" || deviceType == "loop" {
continue
}
removable := fields["RM"] == "1"
if !removable {
if parent := fields["PKNAME"]; parent != "" {
if data, err := os.ReadFile(filepath.Join("/sys/class/block", parent, "removable")); err == nil {
removable = strings.TrimSpace(string(data)) == "1"
}
}
}
if !removable || fields["FSTYPE"] == "" || removableTargetReadOnly(fields) {
continue
}
out = append(out, RemovableTarget{
Device: "/dev/" + fields["NAME"],
FSType: fields["FSTYPE"],
Size: fields["SIZE"],
Label: fields["LABEL"],
Model: fields["MODEL"],
Mountpoint: fields["MOUNTPOINT"],
})
}
sort.Slice(out, func(i, j int) bool { return out[i].Device < out[j].Device })
return out, nil
}
func (s *System) ExportFileToTarget(src string, target RemovableTarget) (dst string, retErr error) {
if src == "" || target.Device == "" {
return "", fmt.Errorf("source and target are required")
}
if _, err := os.Stat(src); err != nil {
return "", err
}
mountpoint := strings.TrimSpace(target.Mountpoint)
mountedHere := false
mounted := mountpoint != ""
if mountpoint == "" {
mountpoint = filepath.Join("/tmp", "bee-export-"+filepath.Base(target.Device))
if err := os.MkdirAll(mountpoint, 0755); err != nil {
return "", err
}
if raw, err := exportExecCommand("mount", target.Device, mountpoint).CombinedOutput(); err != nil {
_ = os.Remove(mountpoint)
return "", formatMountTargetError(target, string(raw), err)
}
mountedHere = true
mounted = true
}
defer func() {
if !mounted {
return
}
_ = exportExecCommand("sync").Run()
if raw, err := exportExecCommand("umount", mountpoint).CombinedOutput(); err != nil && retErr == nil {
msg := strings.TrimSpace(string(raw))
if msg == "" {
retErr = err
} else {
retErr = fmt.Errorf("%s: %w", msg, err)
}
}
if mountedHere {
_ = os.Remove(mountpoint)
}
}()
if err := ensureWritableMountpoint(mountpoint); err != nil {
return "", err
}
filename := filepath.Base(src)
dst = filepath.Join(mountpoint, filename)
data, err := os.ReadFile(src)
if err != nil {
return "", err
}
if err := os.WriteFile(dst, data, 0644); err != nil {
return "", err
}
return dst, nil
}
// mountRemovableTargetReadOnly mounts target for reading if it isn't
// already mounted (reusing its existing mountpoint otherwise), returning
// whether this call did the mounting so the caller knows whether to
// unmount afterward.
func mountRemovableTargetReadOnly(target RemovableTarget) (mountpoint string, mountedHere bool, err error) {
if mp := strings.TrimSpace(target.Mountpoint); mp != "" {
return mp, false, nil
}
mountpoint = filepath.Join("/tmp", "bee-scenario-"+filepath.Base(target.Device))
if err := os.MkdirAll(mountpoint, 0755); err != nil {
return "", false, err
}
if raw, err := exportExecCommand("mount", target.Device, mountpoint).CombinedOutput(); err != nil {
_ = os.Remove(mountpoint)
return "", false, formatMountTargetError(target, string(raw), err)
}
return mountpoint, true, nil
}
// ReadScenarioFromRemovableMedia mounts each removable target in turn
// (unmounting again afterward if it mounted it itself), looking for
// scenarios/<name>.json, and returns the contents of the first one found.
// Lets an air-gapped engineer author a scenario JSON file on another
// machine, drop it under scenarios/ on the same flash drive already
// plugged in for blackbox, and run it on the host with no network path
// required — see RunScenario/ParseScenarioJSON.
func (s *System) ReadScenarioFromRemovableMedia(name string) ([]byte, error) {
name = strings.TrimSpace(name)
if name == "" {
return nil, fmt.Errorf("scenario name is required")
}
targets, err := s.ListRemovableTargets()
if err != nil {
return nil, err
}
for _, target := range targets {
mountpoint, mountedHere, mountErr := mountRemovableTargetReadOnly(target)
if mountErr != nil {
continue
}
data, readErr := os.ReadFile(filepath.Join(mountpoint, "scenarios", name+".json"))
if mountedHere {
_, _ = exportExecCommand("umount", mountpoint).CombinedOutput()
_ = os.Remove(mountpoint)
}
if readErr == nil {
return data, nil
}
}
return nil, fmt.Errorf("scenarios/%s.json not found on any removable media", name)
}