mchusandClaude Sonnet 5
74e6bf0578
Fixes #20. This onekeylog variant has no devicefrusdr.log at all: FRU/sensors come from raw ipmitool text output, PCIe/GPU presence has a dedicated structural snapshot, SEL lives at a different path, and BMC component failures are logged separately from SEL/IDL. - Fall back to component/fru.txt (same FRU block format as devicefrusdr.log) and component/sensor.txt / sdr.txt (ipmitool sensor list / sdr elist) when devicefrusdr.log is absent. - Parse log/bmc/diagnose/OtrdDiagnoseComponent.json's PCIe Device Info array for GPU/PCIe presence and link state, independent of SEL/IDL alarm history; flag devices running below their negotiated max link speed/width as degraded with a Warning event. - Fall back to log/sel.csv (same format as selelist.csv) when selelist.csv is absent. - Parse log/bmc/commer-comp/{commerslot,commerhmc,commerswvr,commerswcpld} logs (including rotated *.tar.gz.N parts) into failure events, filtering known-noisy lines. - Collapse SEL events duplicated across sources by (timestamp, event_type, description). - Surface a CollectionError when FRU/sensors are still empty after all fallbacks, instead of silently returning an empty inventory. - Fix ParseFRU: a later placeholder "Product Serial : 0" / "Product Part Number : NULL" line in the same FRU block (e.g. SCM_FRU) was overwriting an already-parsed real Board Serial/Part Number. Verified against dump_23DB01633_20260727-1359.tar.gz (HGX B200, KR9288-X3): fru 0→21, sensors 0→303, 8 GPUs present at Gen5 x16 in slots 100-107. Deferred (not covered by this change): BIOS-change-settings context and BIOS POST codes from the same layout — see bible-local/10-decisions.md ADL-048. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
71 lines
1.8 KiB
Go
71 lines
1.8 KiB
Go
package inspur
|
|
|
|
import "testing"
|
|
|
|
const diagnoseJSONFixture = `{
|
|
"Pcie Device Info": [
|
|
{
|
|
"LocString": "#GPU0",
|
|
"PcieSlot": 100,
|
|
"PresentStatus": 1,
|
|
"VendorId": 4318,
|
|
"DeviceId": 10497,
|
|
"BusNumber": 23,
|
|
"DeviceNumber": 0,
|
|
"FunctionNumber": 0,
|
|
"CurrentLinkSpeed": 5,
|
|
"MaxLinkSpeed": 5,
|
|
"NegotiatedLinkWidth": 16,
|
|
"MaxLinkWidth": 16
|
|
},
|
|
{
|
|
"LocString": "#GPU6",
|
|
"PcieSlot": 106,
|
|
"PresentStatus": 1,
|
|
"VendorId": 4318,
|
|
"DeviceId": 10497,
|
|
"BusNumber": 220,
|
|
"DeviceNumber": 0,
|
|
"FunctionNumber": 0,
|
|
"CurrentLinkSpeed": 2,
|
|
"MaxLinkSpeed": 5,
|
|
"NegotiatedLinkWidth": 8,
|
|
"MaxLinkWidth": 16
|
|
}
|
|
]
|
|
}`
|
|
|
|
func TestParseOtrdDiagnosePCIe(t *testing.T) {
|
|
devices := ParseOtrdDiagnosePCIe([]byte(diagnoseJSONFixture))
|
|
if len(devices) != 2 {
|
|
t.Fatalf("expected 2 devices, got %d", len(devices))
|
|
}
|
|
|
|
gpu0 := devices[0]
|
|
if gpu0.Slot != "#GPU0" || gpu0.Present == nil || !*gpu0.Present {
|
|
t.Fatalf("expected GPU0 present, got %+v", gpu0)
|
|
}
|
|
if gpu0.Status == "Link Degraded" {
|
|
t.Fatalf("GPU0 should not be flagged as degraded: %+v", gpu0)
|
|
}
|
|
if gpu0.LinkSpeed != "GEN5" || gpu0.MaxLinkSpeed != "GEN5" || gpu0.LinkWidth != 16 {
|
|
t.Fatalf("unexpected GPU0 link info: %+v", gpu0)
|
|
}
|
|
|
|
gpu6 := devices[1]
|
|
if gpu6.Status != "Link Degraded" {
|
|
t.Fatalf("expected GPU6 to be flagged as degraded, got %+v", gpu6)
|
|
}
|
|
}
|
|
|
|
func TestBuildPCIeLinkDegradationEvents(t *testing.T) {
|
|
devices := ParseOtrdDiagnosePCIe([]byte(diagnoseJSONFixture))
|
|
events := BuildPCIeLinkDegradationEvents(devices)
|
|
if len(events) != 1 {
|
|
t.Fatalf("expected 1 degradation event, got %d", len(events))
|
|
}
|
|
if events[0].Severity != "warning" {
|
|
t.Fatalf("expected warning severity, got %q", events[0].Severity)
|
|
}
|
|
}
|