On Wed, 17 Nov 2021 16:17:26 -0700 Jens Axboe <axboe@xxxxxxxxx> wrote: > On 11/17/21 3:26 PM, Johannes Weiner wrote: > >> Link: https://lkml.kernel.org/r/20211028080813.15966-1-sir@xxxxxxxxx > >> Signed-off-by: Drew DeVault <sir@xxxxxxxxx> > >> Acked-by: Jens Axboe <axboe@xxxxxxxxx> > >> Acked-by: Cyril Hrubis <chrubis@xxxxxxx> > >> Cc: Pavel Begunkov <asml.silence@xxxxxxxxx> > >> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> > > > > Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> > > > > As per above, I think basing it off of RAM size would be better, but > > this increase is overdue given all the new users beyond mlock(), and > > 8M is much better than the current value. > > That's basically my reasoning too. Let's just get something going that > will at least unblock some valid use cases, and not get bogged down with > aiming for perfection. The latter can happen in parallel, but it should > not hold it up imho. Nobody's aiming for perfection. We're discussing aiming for "better". What we should have done on day one was to set the default MLOCK_LIMIT to zero bytes. Then everyone would have infrastructure to tune it from userspace and we wouldn't ever have this discussion.
