Function waitForVFs

cmd/nvidia-validator/main.go:1770–1805

waitForVFs waits for Virtual Functions to be created on all NVIDIA GPUs. It polls sriov_numvfs until all GPUs have their full VF count enabled.

(ctx context.Context, timeout time.Duration)

// waitForVFs waits for Virtual Functions to be created on all NVIDIA GPUs.
// It polls sriov_numvfs until all GPUs have their full VF count enabled.
func waitForVFs(ctx context.Context, timeout time.Duration) error {
	pollInterval := time.Duration(sleepIntervalSecondsFlag) * time.Second
	nvpciLib := nvpci.New()

	return wait.PollUntilContextTimeout(ctx, pollInterval, timeout, true, func(ctx context.Context) (bool, error) {
		gpus, err := nvpciLib.GetGPUs()
		if err != nil {
			log.Warnf("Error getting GPUs: %v", err)
			return false, nil
		}

		var totalExpected, totalEnabled uint64
		var pfCount int
		for _, gpu := range gpus {
			sriovInfo := gpu.SriovInfo
			if sriovInfo.IsPF() {
				pfCount++
				totalExpected += sriovInfo.PhysicalFunction.TotalVFs
				totalEnabled += sriovInfo.PhysicalFunction.NumVFs
			}
		}

		if totalExpected == 0 {
			log.Info("No SR-IOV capable GPUs found, skipping VF wait")
			return true, nil
		}

		if totalEnabled == totalExpected {
			log.Infof("All %d VF(s) enabled on %d NVIDIA GPU(s)", totalEnabled, pfCount)
			return true, nil
		}

		log.Infof("Waiting for VFs: %d/%d enabled across %d GPU(s)", totalEnabled, totalExpected, pfCount)
		return false, nil
	})
}

func (c *CCManager) validate() error {
	// delete status file if already present