From: Johannes Weiner <firstname.lastname@example.org> To: Rik van Riel <email@example.com> Cc: Andrew Morton <firstname.lastname@example.org>, Rik van Riel <email@example.com>, "firstname.lastname@example.org" <email@example.com>, "firstname.lastname@example.org" <email@example.com>, Kernel Team <Kernelfirstname.lastname@example.org> Subject: Re: [PATCH 4/4] mm: zero-seek shrinkers Date: Wed, 10 Oct 2018 11:15:49 -0400 [thread overview] Message-ID: <20181010151549.GC2527@cmpxchg.org> (raw) In-Reply-To: <email@example.com> On Wed, Oct 10, 2018 at 01:03:50AM +0000, Rik van Riel wrote: > On Tue, 2018-10-09 at 14:47 -0400, Johannes Weiner wrote: > > > These workloads also deal with tens of thousands of open files and > > use > > /proc for introspection, which ends up growing the proc_inode_cache > > to > > absurdly large sizes - again at the cost of valuable cache space, > > which isn't a reasonable trade-off, given that proc inodes can be > > re-created without involving the disk. > > > > This patch implements a "zero-seek" setting for shrinkers that > > results > > in a target ratio of 0:1 between their objects and IO-backed > > caches. This allows such virtual caches to grow when memory is > > available (they do cache/avoid CPU work after all), but effectively > > disables them as soon as IO-backed objects are under pressure. > > > > It then switches the shrinkers for procfs and sysfs metadata, as well > > as excess page cache shadow nodes, to the new zero-seek setting. > > This patch looks like a great step in the right > direction, though I do not know whether it is > aggressive enough. > > Given that internal slab fragmentation will > prevent the slab cache from returning a slab to > the VM if just one object in that slab is still > in use, there may well be workloads where we > should just put a hard cap on the number of > freeable items these slabs, and reclaim them > preemptively. > > However, I do not know for sure, and this patch > seems like a big improvement over what we had > before, so ... Fully agreed, fragmentation is still a concern. I'm still working on that part, but artificial caps and pro-active reclaim are trickier to get right than prioritization, and since these patches here are useful on their own I didn't want to hold them back. > > Reported-by: Domas Mituzas <firstname.lastname@example.org> > > Signed-off-by: Johannes Weiner <email@example.com> > > Reviewed-by: Rik van Riel <firstname.lastname@example.org> Thanks!
next prev parent reply other threads:[~2018-10-10 15:16 UTC|newest] Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-10-09 18:47 [PATCH 0/4] mm: workingset & shrinker fixes Johannes Weiner 2018-10-09 18:47 ` [PATCH 1/4] mm: workingset: don't drop refault information prematurely fix Johannes Weiner 2018-10-10 0:55 ` Rik van Riel 2018-10-09 18:47 ` [PATCH 2/4] mm: workingset: use cheaper __inc_lruvec_state in irqsafe node reclaim Johannes Weiner 2018-10-10 0:55 ` Rik van Riel 2018-10-09 18:47 ` [PATCH 3/4] mm: workingset: add vmstat counter for shadow nodes Johannes Weiner 2018-10-09 22:04 ` Andrew Morton 2018-10-10 14:02 ` Johannes Weiner 2018-10-09 22:08 ` Andrew Morton 2018-10-10 15:05 ` Johannes Weiner 2018-10-16 8:49 ` Mel Gorman 2018-10-16 22:27 ` Andrew Morton 2018-10-09 18:47 ` [PATCH 4/4] mm: zero-seek shrinkers Johannes Weiner 2018-10-09 22:15 ` Andrew Morton 2018-10-09 22:17 ` Andrew Morton 2018-10-10 1:03 ` Rik van Riel 2018-10-10 15:15 ` Johannes Weiner [this message] 2018-10-12 13:48 ` Vlastimil Babka
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20181010151549.GC2527@cmpxchg.org \ --email@example.com \ --cc=Kernelfirstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --subject='Re: [PATCH 4/4] mm: zero-seek shrinkers' \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.