Function validateDriverContainer

cmd/nvidia-validator/main.go:765–808

(silent bool, driverManagedByOperator bool)

}

func validateDriverContainer(silent bool, driverManagedByOperator bool) error {
	if driverManagedByOperator {
		log.Infof("Driver is not pre-installed on the host and is managed by GPU Operator. Checking driver container status.")
		if err := assertDriverContainerReady(silent); err != nil {
			return fmt.Errorf("error checking driver container status: %w", err)
		}
	}

	driverRoot := root(driverInstallDirCtrPathFlag)

	validateDriver := func(silent bool) error {
		driverLibraryPath, err := driverRoot.getDriverLibraryPath()
		if err != nil {
			return fmt.Errorf("failed to locate driver libraries: %w", err)
		}

		nvidiaSMIPath, err := driverRoot.getNvidiaSMIPath()
		if err != nil {
			return fmt.Errorf("failed to locate nvidia-smi: %w", err)
		}
		cmd := exec.Command(nvidiaSMIPath)
		// In order for nvidia-smi to run, we need to update LD_PRELOAD to include the path to libnvidia-ml.so.1.
		cmd.Env = setEnvVar(os.Environ(), "LD_PRELOAD", prependPathListEnvvar("LD_PRELOAD", driverLibraryPath))
		if !silent {
			cmd.Stdout = os.Stdout
			cmd.Stderr = os.Stderr
		}
		return cmd.Run()
	}

	for {
		log.Info("Attempting to validate a driver container installation")
		err := validateDriver(silent)
		if err != nil {
			if !withWaitFlag {
				return fmt.Errorf("error validating driver: %w", err)
			}
			log.Warningf("failed to validate the driver, retrying after %d seconds\n", sleepIntervalSecondsFlag)
			time.Sleep(time.Duration(sleepIntervalSecondsFlag) * time.Second)
			continue
		}
		return nil
	}
}

func (d *Driver) runValidation(silent bool) (driverInfo, error) {
	err := validateHostDriver(silent)