gpu: collect reset-required/row-remap status and classify Xid codes by severity
nvidia-smi exposes reset_status.reset_required and remapped_rows.* only on newer drivers for Ampere+ GPUs; queried via a separate exec call since an unrecognized field name fails the whole --query-gpu command and would have wiped out unrelated telemetry (temp/ECC/power) on older drivers otherwise. Also refines Xid severity in both the ingest dmesg collector and the always-on kmsg watcher: Xid 64 (row-remap InfoROM write failure) now escalates to Critical instead of the generic warning every other Xid got, and fixes the SAT-window flush path which previously hardcoded "Warning" and ignored pattern severity entirely. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Sonnet 5
parent
d850d4fc3a
commit
1175e6ccd8
@@ -109,6 +109,12 @@ func matchesAny(s string, patterns []*regexp.Regexp) bool {
|
||||
}
|
||||
|
||||
func dmesgSeverity(msg string) string {
|
||||
if sev, ok := XidSeverity(msg); ok {
|
||||
if sev == "critical" {
|
||||
return statusCritical
|
||||
}
|
||||
return statusWarning
|
||||
}
|
||||
lower := strings.ToLower(msg)
|
||||
switch {
|
||||
case strings.Contains(lower, "panic") ||
|
||||
|
||||
Reference in New Issue
Block a user