Collect IPMI sensors, SEL and dmesg errors into audit JSON and support bundle
- audit JSON: IPMI sensor readings (ipmitool sensor) merged into hardware.sensors alongside lm-sensors data - audit JSON: IPMI SEL entries (ipmitool sel list) in hardware.event_logs with source "ipmi-sel" - audit JSON: dmesg error/warning lines in hardware.event_logs with source "dmesg" (filtered by error/warn/AER/Xid/NVRM/ECC/panic patterns) - support bundle: added ipmitool-sensor.txt, ipmitool-sel.txt, ipmitool-sel-time.txt to techdump - saa_dmi.go: fix dmiItemRE to accept SHN with parentheses (e.g. PS(4)LC for PSU fields) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
@@ -0,0 +1,216 @@
|
||||
package collector
|
||||
|
||||
import (
|
||||
"bee/audit/internal/schema"
|
||||
"log/slog"
|
||||
"os/exec"
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// collectIPMISensors runs `ipmitool sensor` and returns parsed sensor readings.
|
||||
// Returns nil if ipmitool is unavailable or produces no output.
|
||||
func collectIPMISensors() *schema.HardwareSensors {
|
||||
out, err := exec.Command("ipmitool", "sensor").Output()
|
||||
if err != nil || len(out) == 0 {
|
||||
return nil
|
||||
}
|
||||
result := parseIPMISensorOutput(string(out))
|
||||
if result == nil {
|
||||
return nil
|
||||
}
|
||||
slog.Info("ipmi sensors: collected",
|
||||
"fans", len(result.Fans),
|
||||
"temperatures", len(result.Temperatures),
|
||||
"power", len(result.Power),
|
||||
"other", len(result.Other),
|
||||
)
|
||||
return result
|
||||
}
|
||||
|
||||
// parseIPMISensorOutput parses `ipmitool sensor` text output.
|
||||
// Each line: name | value | unit | status | lnr | lcr | lnc | unc | ucr | unr
|
||||
func parseIPMISensorOutput(output string) *schema.HardwareSensors {
|
||||
result := &schema.HardwareSensors{}
|
||||
seen := map[string]struct{}{}
|
||||
|
||||
for _, line := range strings.Split(output, "\n") {
|
||||
line = strings.TrimSpace(line)
|
||||
if line == "" {
|
||||
continue
|
||||
}
|
||||
parts := strings.Split(line, "|")
|
||||
if len(parts) < 4 {
|
||||
continue
|
||||
}
|
||||
name := strings.TrimSpace(parts[0])
|
||||
rawVal := strings.TrimSpace(parts[1])
|
||||
unit := strings.TrimSpace(parts[2])
|
||||
status := strings.TrimSpace(parts[3])
|
||||
|
||||
if name == "" || rawVal == "na" || rawVal == "N/A" || rawVal == "" {
|
||||
continue
|
||||
}
|
||||
|
||||
value, err := strconv.ParseFloat(rawVal, 64)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
|
||||
statusStr := normalizeIPMISensorStatus(status)
|
||||
|
||||
switch {
|
||||
case strings.EqualFold(unit, "RPM"):
|
||||
if duplicateSensor(seen, "fan", name) {
|
||||
continue
|
||||
}
|
||||
rpm := int(value)
|
||||
item := schema.HardwareFanSensor{Name: name, RPM: &rpm}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
}
|
||||
result.Fans = append(result.Fans, item)
|
||||
|
||||
case strings.EqualFold(unit, "degrees C") || strings.EqualFold(unit, "C"):
|
||||
if duplicateSensor(seen, "temp", name) {
|
||||
continue
|
||||
}
|
||||
item := schema.HardwareTemperatureSensor{Name: name, Celsius: &value}
|
||||
if len(parts) >= 9 {
|
||||
if unc := parseIPMIThreshold(parts[7]); unc != nil {
|
||||
item.ThresholdWarningCelsius = unc
|
||||
}
|
||||
if ucr := parseIPMIThreshold(parts[8]); ucr != nil {
|
||||
item.ThresholdCriticalCelsius = ucr
|
||||
}
|
||||
}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
} else {
|
||||
item.Status = deriveTemperatureStatus(item.Celsius, item.ThresholdWarningCelsius, item.ThresholdCriticalCelsius)
|
||||
}
|
||||
result.Temperatures = append(result.Temperatures, item)
|
||||
|
||||
case strings.EqualFold(unit, "Volts") || strings.EqualFold(unit, "V"):
|
||||
if duplicateSensor(seen, "power", name) {
|
||||
continue
|
||||
}
|
||||
item := schema.HardwarePowerSensor{Name: name, VoltageV: &value}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
}
|
||||
result.Power = append(result.Power, item)
|
||||
|
||||
case strings.EqualFold(unit, "Watts") || strings.EqualFold(unit, "W"):
|
||||
if duplicateSensor(seen, "power", name) {
|
||||
continue
|
||||
}
|
||||
item := schema.HardwarePowerSensor{Name: name, PowerW: &value}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
}
|
||||
result.Power = append(result.Power, item)
|
||||
|
||||
case strings.EqualFold(unit, "Amps") || strings.EqualFold(unit, "A"):
|
||||
if duplicateSensor(seen, "power", name) {
|
||||
continue
|
||||
}
|
||||
item := schema.HardwarePowerSensor{Name: name, CurrentA: &value}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
}
|
||||
result.Power = append(result.Power, item)
|
||||
|
||||
default:
|
||||
if duplicateSensor(seen, "other", name) {
|
||||
continue
|
||||
}
|
||||
item := schema.HardwareOtherSensor{Name: name, Value: &value}
|
||||
if unit != "" {
|
||||
item.Unit = &unit
|
||||
}
|
||||
if statusStr != "" {
|
||||
item.Status = &statusStr
|
||||
}
|
||||
result.Other = append(result.Other, item)
|
||||
}
|
||||
}
|
||||
|
||||
if len(result.Fans) == 0 && len(result.Temperatures) == 0 && len(result.Power) == 0 && len(result.Other) == 0 {
|
||||
return nil
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
func parseIPMIThreshold(raw string) *float64 {
|
||||
s := strings.TrimSpace(raw)
|
||||
if s == "" || s == "na" || s == "N/A" {
|
||||
return nil
|
||||
}
|
||||
v, err := strconv.ParseFloat(s, 64)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
return &v
|
||||
}
|
||||
|
||||
func normalizeIPMISensorStatus(s string) string {
|
||||
switch strings.ToLower(s) {
|
||||
case "ok":
|
||||
return statusOK
|
||||
case "cr", "ucr", "lcr":
|
||||
return statusCritical
|
||||
case "nc", "unc", "lnc", "nr", "unr", "lnr":
|
||||
return statusWarning
|
||||
case "ns", "na":
|
||||
return ""
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
// mergeIPMISensors appends IPMI sensor entries into existing, skipping names already present.
|
||||
func mergeIPMISensors(existing, ipmi *schema.HardwareSensors) *schema.HardwareSensors {
|
||||
if ipmi == nil {
|
||||
return existing
|
||||
}
|
||||
if existing == nil {
|
||||
return ipmi
|
||||
}
|
||||
|
||||
existingNames := map[string]struct{}{}
|
||||
for _, s := range existing.Fans {
|
||||
existingNames["fan\x00"+s.Name] = struct{}{}
|
||||
}
|
||||
for _, s := range existing.Temperatures {
|
||||
existingNames["temp\x00"+s.Name] = struct{}{}
|
||||
}
|
||||
for _, s := range existing.Power {
|
||||
existingNames["power\x00"+s.Name] = struct{}{}
|
||||
}
|
||||
for _, s := range existing.Other {
|
||||
existingNames["other\x00"+s.Name] = struct{}{}
|
||||
}
|
||||
|
||||
for _, s := range ipmi.Fans {
|
||||
if _, ok := existingNames["fan\x00"+s.Name]; !ok {
|
||||
existing.Fans = append(existing.Fans, s)
|
||||
}
|
||||
}
|
||||
for _, s := range ipmi.Temperatures {
|
||||
if _, ok := existingNames["temp\x00"+s.Name]; !ok {
|
||||
existing.Temperatures = append(existing.Temperatures, s)
|
||||
}
|
||||
}
|
||||
for _, s := range ipmi.Power {
|
||||
if _, ok := existingNames["power\x00"+s.Name]; !ok {
|
||||
existing.Power = append(existing.Power, s)
|
||||
}
|
||||
}
|
||||
for _, s := range ipmi.Other {
|
||||
if _, ok := existingNames["other\x00"+s.Name]; !ok {
|
||||
existing.Other = append(existing.Other, s)
|
||||
}
|
||||
}
|
||||
return existing
|
||||
}
|
||||
Reference in New Issue
Block a user