reanimator/bee
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

gpu: collect reset-required/row-remap status and classify Xid codes by severity

Browse Source 
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:
Mikhail Chusavitin
2026-07-07 19:28:59 +03:00
co-authored by Claude Sonnet 5
parent d850d4fc3a
commit 1175e6ccd8
10 changed files with 477 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
audit/internal/schema/hardware.go
+47 -42
View File
@@ -178,48 +178,53 @@ type HardwareStorage struct {
type HardwarePCIeDevice struct {
HardwareComponentStatus
Slot *string `json:"slot,omitempty"`
VendorID *int `json:"vendor_id,omitempty"`
DeviceID *int `json:"device_id,omitempty"`
NUMANode *int `json:"numa_node,omitempty"`
TemperatureC *float64 `json:"temperature_c,omitempty"`
PowerW *float64 `json:"power_w,omitempty"`
LifeRemainingPct *float64 `json:"life_remaining_pct,omitempty"`
LifeUsedPct *float64 `json:"life_used_pct,omitempty"`
ECCCorrectedTotal *int64 `json:"ecc_corrected_total,omitempty"`
ECCUncorrectedTotal *int64 `json:"ecc_uncorrected_total,omitempty"`
HWSlowdown *bool `json:"hw_slowdown,omitempty"`
BatteryChargePct *float64 `json:"battery_charge_pct,omitempty"`
BatteryHealthPct *float64 `json:"battery_health_pct,omitempty"`
BatteryTemperatureC *float64 `json:"battery_temperature_c,omitempty"`
BatteryVoltageV *float64 `json:"battery_voltage_v,omitempty"`
BatteryReplaceRequired *bool `json:"battery_replace_required,omitempty"`
SFPPresent *bool `json:"sfp_present,omitempty"`
SFPIdentifier *string `json:"sfp_identifier,omitempty"`
SFPConnector *string `json:"sfp_connector,omitempty"`
SFPVendor *string `json:"sfp_vendor,omitempty"`
SFPPartNumber *string `json:"sfp_part_number,omitempty"`
SFPSerialNumber *string `json:"sfp_serial_number,omitempty"`
SFPWavelengthNM *float64 `json:"sfp_wavelength_nm,omitempty"`
SFPTemperatureC *float64 `json:"sfp_temperature_c,omitempty"`
SFPTXPowerDBM *float64 `json:"sfp_tx_power_dbm,omitempty"`
SFPRXPowerDBM *float64 `json:"sfp_rx_power_dbm,omitempty"`
SFPVoltageV *float64 `json:"sfp_voltage_v,omitempty"`
SFPBiasMA *float64 `json:"sfp_bias_ma,omitempty"`
BDF *string `json:"-"`
DeviceClass *string `json:"device_class,omitempty"`
Manufacturer *string `json:"manufacturer,omitempty"`
Model *string `json:"model,omitempty"`
LinkWidth *int `json:"link_width,omitempty"`
LinkSpeed *string `json:"link_speed,omitempty"`
MaxLinkWidth *int `json:"max_link_width,omitempty"`
MaxLinkSpeed *string `json:"max_link_speed,omitempty"`
SerialNumber *string `json:"serial_number,omitempty"`
Firmware *string `json:"firmware,omitempty"`
MacAddresses []string `json:"mac_addresses,omitempty"`
Present *bool `json:"present,omitempty"`
IOMMUGroup *int `json:"iommu_group,omitempty"`
Telemetry map[string]any `json:"-"`
Slot *string `json:"slot,omitempty"`
VendorID *int `json:"vendor_id,omitempty"`
DeviceID *int `json:"device_id,omitempty"`
NUMANode *int `json:"numa_node,omitempty"`
TemperatureC *float64 `json:"temperature_c,omitempty"`
PowerW *float64 `json:"power_w,omitempty"`
LifeRemainingPct *float64 `json:"life_remaining_pct,omitempty"`
LifeUsedPct *float64 `json:"life_used_pct,omitempty"`
ECCCorrectedTotal *int64 `json:"ecc_corrected_total,omitempty"`
ECCUncorrectedTotal *int64 `json:"ecc_uncorrected_total,omitempty"`
HWSlowdown *bool `json:"hw_slowdown,omitempty"`
ResetRequired *bool `json:"reset_required,omitempty"`
RemappedRowsCorrectable *int64 `json:"remapped_rows_correctable,omitempty"`
RemappedRowsUncorrectable *int64 `json:"remapped_rows_uncorrectable,omitempty"`
RemappedRowsPending *bool `json:"remapped_rows_pending,omitempty"`
RemappedRowsFailure *bool `json:"remapped_rows_failure,omitempty"`
BatteryChargePct *float64 `json:"battery_charge_pct,omitempty"`
BatteryHealthPct *float64 `json:"battery_health_pct,omitempty"`
BatteryTemperatureC *float64 `json:"battery_temperature_c,omitempty"`
BatteryVoltageV *float64 `json:"battery_voltage_v,omitempty"`
BatteryReplaceRequired *bool `json:"battery_replace_required,omitempty"`
SFPPresent *bool `json:"sfp_present,omitempty"`
SFPIdentifier *string `json:"sfp_identifier,omitempty"`
SFPConnector *string `json:"sfp_connector,omitempty"`
SFPVendor *string `json:"sfp_vendor,omitempty"`
SFPPartNumber *string `json:"sfp_part_number,omitempty"`
SFPSerialNumber *string `json:"sfp_serial_number,omitempty"`
SFPWavelengthNM *float64 `json:"sfp_wavelength_nm,omitempty"`
SFPTemperatureC *float64 `json:"sfp_temperature_c,omitempty"`
SFPTXPowerDBM *float64 `json:"sfp_tx_power_dbm,omitempty"`
SFPRXPowerDBM *float64 `json:"sfp_rx_power_dbm,omitempty"`
SFPVoltageV *float64 `json:"sfp_voltage_v,omitempty"`
SFPBiasMA *float64 `json:"sfp_bias_ma,omitempty"`
BDF *string `json:"-"`
DeviceClass *string `json:"device_class,omitempty"`
Manufacturer *string `json:"manufacturer,omitempty"`
Model *string `json:"model,omitempty"`
LinkWidth *int `json:"link_width,omitempty"`
LinkSpeed *string `json:"link_speed,omitempty"`
MaxLinkWidth *int `json:"max_link_width,omitempty"`
MaxLinkSpeed *string `json:"max_link_speed,omitempty"`
SerialNumber *string `json:"serial_number,omitempty"`
Firmware *string `json:"firmware,omitempty"`
MacAddresses []string `json:"mac_addresses,omitempty"`
Present *bool `json:"present,omitempty"`
IOMMUGroup *int `json:"iommu_group,omitempty"`
Telemetry map[string]any `json:"-"`
}
type HardwarePowerSupply struct {