fix(pcie): verify GPU links under real bandwidth load

This commit is contained in:
Mikhail Chusavitin
2026-09-03 10:23:39 +03:00
parent 642e68631d
commit 347bc8310a
27 changed files with 384 additions and 902 deletions
+1 -2
View File
@@ -101,7 +101,6 @@ func (h *handler) planSATRunAll(ctx context.Context, req satRunAllRequest) ([]sa
satRunAllSpec{target: "cpu", params: taskParams{Duration: cpuDur, StressMode: req.StressMode}},
satRunAllSpec{target: "memory", params: taskParams{StressMode: req.StressMode}},
satRunAllSpec{target: "storage", params: taskParams{StressMode: req.StressMode}},
satRunAllSpec{target: "pcie-link", params: taskParams{}},
)
if h.opts.App.TPMPresent() {
@@ -139,7 +138,7 @@ func (h *handler) planSATRunAll(ctx context.Context, req satRunAllRequest) ([]sa
if !health.CUDAReady {
notes = append(notes, "NVIDIA: CUDA runtime not confirmed ready; GPU tests queued anyway")
}
gpuTargets := []string{"nvidia", "nvidia-interconnect", "nvidia-bandwidth", "nvidia-pcie-bandwidth"}
gpuTargets := []string{"nvidia", "nvidia-interconnect", "nvidia-bandwidth"}
if req.StressMode {
// Stress tier adds the targeted dcgmi diag load tests.
gpuTargets = append(gpuTargets, "nvidia-targeted-stress", "nvidia-targeted-power", "nvidia-pulse")