On Fri 09-06-17 12:51:57, Chris Wilson wrote: > Quoting Michal Hocko (2017-06-09 12:17:26) > > [Add Hugh] > > > > On Fri 09-06-17 12:03:50, Chris Wilson wrote: > > > When we are called to relieve mempressue via the shrinker, the only way > > > we can make progress is either by discarding unwanted pages (those > > > objects that userspace has marked MADV_DONTNEED) or by reclaiming the > > > dirty objects via swap. As we know that is the only way to make further > > > progress, we can initiate the writeback as we invalidate the objects. > > > This means the objects we put onto the inactive anon lru list are > > > already marked for reclaim+writeback and so will trigger a wait upon the > > > writeback inside direct reclaim, greatly improving the success rate of > > > direct reclaim on i915 objects. > > > > > > The corollary is that we may start a slow swap on opportunistic > > > mempressure from the likes of the compaction + migration kthreads. This > > > is limited by those threads only being allowed to shrink idle pages, but > > > also that if we reactivate the page before it is swapped out by gpu > > > activity, we only page the cost of repinning the page. The cost is most > > > felt when an object is reused after mempressure, which hopefully > > > excludes the latency sensitive tasks (as we are just extending the > > > impact of swap thrashing to them). > > > > I am not sure you can start writeback on shmem while it is not in the > > swapcache. Hugh? > > Note this is just mm/vmscan.c::pageout(), and we call into shmem which > is indeed responsible for adding it to the swapcache. You are right. I would still like to hear from Hugh this is OK. It is quite some time since I've looked into shmem.c. > My intention was > to simply start pageout() earlier to ensure the pages we tried to shrink > were indeed being reclaimed. Yes the intention is clear... -- Michal Hocko SUSE Labs _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
