On Wed, Mar 01, 2017 at 07:25:59PM -0700, Jens Axboe wrote: > On 03/01/2017 11:42 AM, Omar Sandoval wrote: > > From: Omar Sandoval <osandov@xxxxxx> > > > > This can be used to diagnose freeze-related hangs. > > Do we really need this? For the loop case, it was painfully > obvious that it was a count issue. And I can't think of any > cases where it would have helped us, outside of rewriting > core parts (like the first edition of the shadow requests > for the scheduler). > > Not strongly opposed to it, feel free to convince me. I don't feel a burning need for it, let's just drop it.
