fix: pcie gen, nccl binary, netconf sudo, boot noise, firmware cleanup
- nvidia collector: read pcie.link.gen.current/max from nvidia-smi instead of sysfs to avoid false Gen1 readings when GPU is in ASPM idle state - build: remove bee-nccl-gpu-stress from rm -f list so shell script from overlay is not silently dropped from the ISO - smoketest: add explicit checks for bee-gpu-burn, bee-john-gpu-stress, bee-nccl-gpu-stress, all_reduce_perf - netconf: re-exec via sudo when not root to fix RTNETLINK/resolv.conf errors - auto/config: reduce loglevel 7→3 to show clean systemd output on boot - auto/config: blacklist snd_hda_intel and related audio modules (unused on servers) - package-lists: remove firmware-intel-sound and firmware-amd-graphics from base list; move firmware-amd-graphics to bee-amd variant only - bible-local: mark memtest ADR resolved, document working solution Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -6,7 +6,7 @@ import (
|
||||
)
|
||||
|
||||
func TestParseNVIDIASMIQuery(t *testing.T) {
|
||||
raw := "0, 00000000:65:00.0, GPU-SERIAL-1, 96.00.1F.00.02, 54, 210.33, 0, 5, Not Active\n"
|
||||
raw := "0, 00000000:65:00.0, GPU-SERIAL-1, 96.00.1F.00.02, 54, 210.33, 0, 5, Not Active, 4, 4, 16, 16\n"
|
||||
byBDF, err := parseNVIDIASMIQuery(raw)
|
||||
if err != nil {
|
||||
t.Fatalf("parse failed: %v", err)
|
||||
@@ -28,6 +28,12 @@ func TestParseNVIDIASMIQuery(t *testing.T) {
|
||||
if gpu.HWSlowdown == nil || *gpu.HWSlowdown {
|
||||
t.Fatalf("hw slowdown: got %v, want false", gpu.HWSlowdown)
|
||||
}
|
||||
if gpu.PCIeLinkGenCurrent == nil || *gpu.PCIeLinkGenCurrent != 4 {
|
||||
t.Fatalf("pcie link gen current: got %v, want 4", gpu.PCIeLinkGenCurrent)
|
||||
}
|
||||
if gpu.PCIeLinkGenMax == nil || *gpu.PCIeLinkGenMax != 4 {
|
||||
t.Fatalf("pcie link gen max: got %v, want 4", gpu.PCIeLinkGenMax)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNormalizePCIeBDF(t *testing.T) {
|
||||
|
||||
Reference in New Issue
Block a user