Peter Zijlstra wrote: > I really don't like this, it means the system is really screwed up and > doesn't deserve to continue. It can be said that after timeout we just back to previous state, where machine already limp(=partially screwed up), but have some degree of performance. We might be able to do some recovery, such as killing process, restart or reset of subsystem and so on. Even if a CPU get stuck, it might be possible to continue its service with remaining CPUs, ex. assume there are 1024 CPUs total. (I wish if we were able to force-reset such unstable CPU in future...) I agree that there are much amount of situation where this feature is not acceptable. But there would be others. Thanks, H.Seto _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/virtualization
