Add NVIDIA self-heal tools and per-GPU SAT status

This commit is contained in:
Mikhail Chusavitin
2026-04-07 20:20:05 +03:00
parent 93cfa78e8c
commit 531d1ca366
13 changed files with 863 additions and 14 deletions

View File

@@ -3,6 +3,7 @@ package app
import (
"os"
"path/filepath"
"strconv"
"sort"
"strings"
@@ -18,6 +19,7 @@ func applyLatestSATStatuses(snap *schema.HardwareSnapshot, baseDir string, db *C
}
if summary, ok := loadLatestSATSummary(baseDir, "gpu-nvidia-"); ok {
applyGPUVendorSAT(snap.PCIeDevices, "nvidia", summary)
applyNvidiaPerGPUStatus(snap.PCIeDevices, baseDir)
}
if summary, ok := loadLatestSATSummary(baseDir, "memory-"); ok {
applyMemorySAT(snap.Memory, summary)
@@ -32,6 +34,100 @@ func applyLatestSATStatuses(snap *schema.HardwareSnapshot, baseDir string, db *C
applyComponentStatusDB(snap, db)
}
type nvidiaPerGPUStatus struct {
runStatus string
reason string
}
func applyNvidiaPerGPUStatus(devs []schema.HardwarePCIeDevice, baseDir string) {
statusByIndex, ts, ok := loadLatestNvidiaPerGPUStatus(baseDir)
if !ok {
return
}
for i := range devs {
if devs[i].Telemetry == nil {
continue
}
rawIdx, ok := devs[i].Telemetry["nvidia_gpu_index"]
if !ok {
continue
}
idx, ok := telemetryInt(rawIdx)
if !ok {
continue
}
st, ok := statusByIndex[idx]
if !ok {
continue
}
status, description, ok := satKeyStatus(st.runStatus, firstNonEmpty(strings.TrimSpace(st.reason), "nvidia GPU SAT"))
if !ok {
continue
}
mergeComponentStatusPreferDetail(&devs[i].HardwareComponentStatus, ts, status, description)
}
}
func loadLatestNvidiaPerGPUStatus(baseDir string) (map[int]nvidiaPerGPUStatus, string, bool) {
matches, err := filepath.Glob(filepath.Join(baseDir, "gpu-nvidia-*"))
if err != nil || len(matches) == 0 {
return nil, "", false
}
sort.Strings(matches)
runDir := matches[len(matches)-1]
summaryRaw, err := os.ReadFile(filepath.Join(runDir, "summary.txt"))
if err != nil {
return nil, "", false
}
summaryKV := parseKeyValueSummary(string(summaryRaw))
runAtUTC := strings.TrimSpace(summaryKV["run_at_utc"])
files, err := filepath.Glob(filepath.Join(runDir, "gpu-*-status.txt"))
if err != nil || len(files) == 0 {
return nil, "", false
}
out := make(map[int]nvidiaPerGPUStatus, len(files))
for _, file := range files {
raw, err := os.ReadFile(file)
if err != nil {
continue
}
kv := parseKeyValueSummary(string(raw))
idx, err := strconv.Atoi(strings.TrimSpace(kv["gpu_index"]))
if err != nil {
continue
}
out[idx] = nvidiaPerGPUStatus{
runStatus: strings.ToUpper(strings.TrimSpace(kv["run_status"])),
reason: strings.TrimSpace(kv["reason"]),
}
}
if len(out) == 0 {
return nil, "", false
}
return out, runAtUTC, true
}
func telemetryInt(v any) (int, bool) {
switch value := v.(type) {
case int:
return value, true
case int32:
return int(value), true
case int64:
return int(value), true
case float64:
return int(value), true
case string:
n, err := strconv.Atoi(strings.TrimSpace(value))
if err != nil {
return 0, false
}
return n, true
default:
return 0, false
}
}
type satSummary struct {
runAtUTC string
overall string
@@ -176,6 +272,31 @@ func mergeComponentStatus(component *schema.HardwareComponentStatus, changedAt,
}
}
func mergeComponentStatusPreferDetail(component *schema.HardwareComponentStatus, changedAt, satStatus, description string) {
if component == nil || satStatus == "" {
return
}
current := strings.TrimSpace(ptrString(component.Status))
newSeverity := statusSeverity(satStatus)
currentSeverity := statusSeverity(current)
if current == "" || current == "Unknown" || newSeverity > currentSeverity {
mergeComponentStatus(component, changedAt, satStatus, description)
return
}
if newSeverity == currentSeverity && strings.TrimSpace(description) != "" {
component.Status = appStringPtr(satStatus)
component.ErrorDescription = appStringPtr(description)
if strings.TrimSpace(changedAt) != "" {
component.StatusChangedAt = appStringPtr(changedAt)
component.StatusHistory = append(component.StatusHistory, schema.HardwareStatusHistory{
Status: satStatus,
ChangedAt: changedAt,
Details: appStringPtr(description),
})
}
}
}
func statusSeverity(status string) int {
switch strings.TrimSpace(status) {
case "Critical":