On 1/17/19 2:02 PM, Jeff Moyer wrote: > Jens Axboe <axboe@xxxxxxxxx> writes: > >>>>>>>> It seems that sq_entries, cq_entries are not limited at all. Can nasty >>>>>>>> app consume a lot of kernel pages calling io_setup_uring() from a loop >>>>>>>> passing random entries number? (or even better: decreasing entries >>>>>>>> number, >>>>>>>> in order to consume all pages orders with min number of loops). > ... >>>> One concern here is that, at least looking at my boxes, the default >>>> setting for RLIMIT_MEMLOCK is really low. I'd hate for everyone to run >>>> into issues using io_uring just because it seems to require root, >>>> because the memlock limit is so low. >>>> >>>> That's much less of a concern with the fixed buffers, since it's a more >>>> esoteric part of it. But everyone should be able to setup a few io_uring >>>> queues and use them without having to worry about failing due to an >>>> absurdly low RLIMIT_MEMLOCK. >>>> >>>> Comments? >>> >>> Yeah, the default is 64k here. We should probably up that. I'd say we >>> either tackle the ridiculously low rlimits, or I guess we just go the >>> aio route and add a sysctl. :-\ I'll see what's involved in the >>> former. >> >> After giving it a bit of thought, let's go the rlimit route. It is cleaner, >> and I don't want a sysctl knob for this either. 64k will enable anyone to >> set up at least one decently sized ring. > > OK. Note that the MLOCK_LIMIT size has been dictated by gpg's > requirements: > > commit f947ff8af30f75cb9cf0e966caf8f4809ad1b92e > Author: Rik van Riel <riel@xxxxxxxxxx> > Date: Sun Aug 22 23:06:58 2004 -0700 > > [PATCH] increase per-user mlock limit default to 32k > > Since various gnupg users have indicated that gpg wants to mlock 32kB of > memory, I created the patch below that increases the default mlock ulimit > to 32kB. > > and then > > commit 0833422274ff00729a603b020fac297e69a03e40 > Author: Kurt Garloff <garloff@xxxxxxx> > Date: Wed Oct 29 14:00:48 2008 -0700 > > mm: increase the default mlock limit from 32k to 64k > > ... > However, newer gpg2 needs 64k in various circumstances and otherwise > fails miserably, see bnc#329675. > > So all we need to do is modify gpg2 so that is requires more locked > memory, and we're golden! ;-) Haha, that's some nice digging there! Yes, we could bump it, but with the default, we can get a 512 sized ring per user, that's 13 pages (rounded up). Probably good enough to get things off the ground? -- Jens Axboe
