Mikhail ChusavitinandClaude Sonnet 5
b11018ac5e
NVIDIA GPUs deliberately downclock PCIe to Gen1 at idle for power saving, and applyPCIeLinkSpeedWarning fired on every idle collector pass regardless - since component-status DB records never downgrade (Record() only ever raises severity), one boot-time idle sample permanently pinned pcie:gpu:nvidia to Warning for the rest of the session even after every load-bearing GPU SAT test passed clean. Two prior fixes (nvidia-smi-sourced link speed, pcie_aspm=off boot flag) didn't hold up against this hardware/driver combination - see bible-local/decisions/2026-08-24-pcie-gpu-gen1-idle-warning.md for the full history. Rather than add a downgrade path, stop writing an unverified status in the first place: parseLspciDevice no longer calls applyPCIeLinkSpeedWarning on the idle path. LinkSpeed/MaxLinkSpeed stay populated as plain descriptive fields; only a verified-under-load caller may now turn them into a status verdict. Two new SAT targets provide that verified signal: - pcie-link (platform/pcie_link_check.go): forces every enabled PCIe device - not just GPUs - to retrain via the PCIe spec's Link Control "Retrain Link" bit, then compares the negotiated speed against the device's max. Covers NICs/HBAs/switches that have no bee-gpu-burn equivalent load tool. Classifies by PCI class code + vendor ID, not name substrings. Routes gpu_nvidia/gpu_amd/other sub-verdicts into their own component-status keys so a degraded NIC never reads as a GPU fault. - nvidia-pcie-bandwidth (platform/nvidia_pcie_bandwidth.go): drives real host<->device traffic via dcgmi diag -r nvbandwidth and resamples link speed immediately after, independent of nvbandwidth's own pass/fail. Both wired into the task queue/webui the same way as nvidia-config (routes, dispatch, priority, Validate page cards, Run All Check SAT). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
67 lines
2.5 KiB
Go
67 lines
2.5 KiB
Go
package platform
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestClassifyGPUFromVendorClass(t *testing.T) {
|
|
cases := []struct {
|
|
name string
|
|
vendor string
|
|
class string
|
|
wantIsGPU bool
|
|
wantVendor string
|
|
}{
|
|
{"nvidia GPU", "0x10de", "0x030200", true, "nvidia"},
|
|
{"amd GPU", "0x1002", "0x030000", true, "amd"},
|
|
{"nvidia NIC (same vendor, not display class)", "0x10de", "0x020000", false, ""},
|
|
{"intel NIC", "0x8086", "0x020000", false, ""},
|
|
{"unrelated display-class vendor", "0x1234", "0x030000", false, ""},
|
|
}
|
|
for _, tc := range cases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
gotIsGPU, gotVendor := classifyGPUFromVendorClass(tc.vendor, tc.class)
|
|
if gotIsGPU != tc.wantIsGPU || gotVendor != tc.wantVendor {
|
|
t.Fatalf("classifyGPUFromVendorClass(%q,%q) = (%v,%q), want (%v,%q)",
|
|
tc.vendor, tc.class, gotIsGPU, gotVendor, tc.wantIsGPU, tc.wantVendor)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestRenderPCIeLinkCheckSummaryDegradedGPU(t *testing.T) {
|
|
findings := []pcieLinkFinding{
|
|
{BDF: "0000:0d:00.0", Description: "NVIDIA GPU", IsGPU: true, GPUVendor: "nvidia",
|
|
BeforeSpeed: "Gen1", AfterSpeed: "Gen1", MaxSpeed: "Gen5", Degraded: true},
|
|
{BDF: "0000:37:00.0", Description: "NVIDIA GPU", IsGPU: true, GPUVendor: "nvidia",
|
|
BeforeSpeed: "Gen1", AfterSpeed: "Gen5", MaxSpeed: "Gen5", Degraded: false},
|
|
{BDF: "0000:01:00.0", Description: "Mellanox NIC", IsGPU: false,
|
|
BeforeSpeed: "Gen3", AfterSpeed: "Gen4", MaxSpeed: "Gen4", Degraded: false},
|
|
}
|
|
summary := renderPCIeLinkCheckSummary(findings)
|
|
if !strings.Contains(summary, "gpu_nvidia_status=FAILED") {
|
|
t.Fatalf("expected gpu_nvidia_status=FAILED (one degraded GPU should fail the vendor group), got:\n%s", summary)
|
|
}
|
|
if !strings.Contains(summary, "other_status=OK") {
|
|
t.Fatalf("expected other_status=OK, got:\n%s", summary)
|
|
}
|
|
if !strings.Contains(summary, "overall_status=FAILED") {
|
|
t.Fatalf("expected overall_status=FAILED, got:\n%s", summary)
|
|
}
|
|
}
|
|
|
|
func TestRenderPCIeLinkCheckSummaryAllClean(t *testing.T) {
|
|
findings := []pcieLinkFinding{
|
|
{BDF: "0000:0d:00.0", IsGPU: true, GPUVendor: "nvidia", BeforeSpeed: "Gen1", AfterSpeed: "Gen5", MaxSpeed: "Gen5"},
|
|
{BDF: "0000:2c:00.0", Skipped: "device disabled (no data traffic; link state has no operational impact)"},
|
|
}
|
|
summary := renderPCIeLinkCheckSummary(findings)
|
|
if !strings.Contains(summary, "overall_status=OK") {
|
|
t.Fatalf("expected overall_status=OK, got:\n%s", summary)
|
|
}
|
|
if strings.Contains(summary, "other_status=") {
|
|
t.Fatalf("disabled/skipped-only device should not produce an other_status line, got:\n%s", summary)
|
|
}
|
|
}
|