From: Michal Hocko <mhocko@suse.com>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Vlastimil Babka <vbabka@suse.cz>,
Christoph Lameter <cl@linux.com>,
Bharata B Rao <bharata@linux.ibm.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
linux-mm@kvack.org, David Rientjes <rientjes@google.com>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Andrew Morton <akpm@linux-foundation.org>,
guro@fb.com, Shakeel Butt <shakeelb@google.com>,
Johannes Weiner <hannes@cmpxchg.org>,
aneesh.kumar@linux.ibm.com, Jann Horn <jannh@google.com>
Subject: Re: [RFC PATCH v0] mm/slub: Let number of online CPUs determine the slub page order
Date: Tue, 26 Jan 2021 14:59:18 +0100 [thread overview]
Message-ID: <20210126135918.GQ827@dhcp22.suse.cz> (raw)
In-Reply-To: <CAKfTPtAhqiHtPMUTZv8Bs3Cg5=HXLmrda=j4_HFrF=7ztYZLGA@mail.gmail.com>
On Tue 26-01-21 14:38:14, Vincent Guittot wrote:
> On Tue, 26 Jan 2021 at 09:52, Michal Hocko <mhocko@suse.com> wrote:
> >
> > On Thu 21-01-21 19:19:21, Vlastimil Babka wrote:
> > [...]
> > > We could also start questioning the very assumption that number of cpus should
> > > affect slab page size in the first place. Should it? After all, each CPU will
> > > have one or more slab pages privately cached, as we discuss in the other
> > > thread... So why make the slab pages also larger?
> >
> > I do agree. What is the acutal justification for this scaling?
> > /*
> > * Attempt to find best configuration for a slab. This
> > * works by first attempting to generate a layout with
> > * the best configuration and backing off gradually.
> > *
> > * First we increase the acceptable waste in a slab. Then
> > * we reduce the minimum objects required in a slab.
> > */
> >
> > doesn't speak about CPUs. 9b2cd506e5f2 ("slub: Calculate min_objects
> > based on number of processors.") does talk about hackbench "This has
> > been shown to address the performance issues in hackbench on 16p etc."
> > but it doesn't give any more details to tell actually _why_ that works.
> >
> > This thread shows that this is still somehow related to performance but
> > the real reason is not clear. I believe we should be focusing on the
> > actual reasons for the performance impact than playing with some fancy
> > math and tuning for a benchmark on a particular machine which doesn't
> > work for others due to subtle initialization timing issues.
> >
> > Fundamentally why should higher number of CPUs imply the size of slab in
> > the first place?
>
> A 1st answer is that the activity and the number of threads involved
> scales with the number of CPUs. Regarding the hackbench benchmark as
> an example, the number of group/threads raise to a higher level on the
> server than on the small system which doesn't seem unreasonable.
>
> On 8 CPUs, I run hackbench with up to 16 groups which means 16*40
> threads. But I raise up to 256 groups, which means 256*40 threads, on
> the 224 CPUs system. In fact, hackbench -g 1 (with 1 group) doesn't
> regress on the 224 CPUs system. The next test with 4 groups starts
> to regress by -7%. But the next one: hackbench -g 16 regresses by 187%
> (duration is almost 3 times longer). It seems reasonable to assume
> that the number of running threads and resources scale with the number
> of CPUs because we want to run more stuff.
OK, I do understand that more jobs scale with the number of CPUs but I
would also expect that higher order pages are generally more expensive
to get so this is not really a clear cut especially under some more
demand on the memory where allocations are smooth. So the question
really is whether this is not just optimizing for artificial conditions.
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2021-01-26 13:59 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-18 8:27 [RFC PATCH v0] mm/slub: Let number of online CPUs determine the slub page order Bharata B Rao
2020-11-18 11:25 ` Vlastimil Babka
2020-11-18 19:34 ` Roman Gushchin
2020-11-18 19:53 ` David Rientjes
2021-01-20 17:36 ` Vincent Guittot
2021-01-21 5:30 ` Bharata B Rao
2021-01-21 9:09 ` Vincent Guittot
2021-01-21 10:01 ` Christoph Lameter
2021-01-21 10:48 ` Vincent Guittot
2021-01-21 18:19 ` Vlastimil Babka
2021-01-22 8:03 ` Vincent Guittot
2021-01-22 12:03 ` Vlastimil Babka
2021-01-22 13:16 ` Vincent Guittot
2021-01-23 5:16 ` Bharata B Rao
2021-01-23 12:32 ` Vincent Guittot
2021-01-25 11:20 ` Vlastimil Babka
2021-01-26 23:03 ` Will Deacon
2021-01-27 9:10 ` Christoph Lameter
2021-01-27 11:04 ` Vlastimil Babka
2021-02-03 11:10 ` Bharata B Rao
2021-02-04 7:32 ` Vincent Guittot
2021-02-04 9:07 ` Christoph Lameter
2021-02-04 9:33 ` Vlastimil Babka
2021-02-08 13:41 ` [PATCH] mm, slub: better heuristic for number of cpus when calculating slab order Vlastimil Babka
2021-02-08 14:54 ` Vincent Guittot
2021-02-10 14:07 ` Mel Gorman
2021-01-22 13:05 ` [RFC PATCH v0] mm/slub: Let number of online CPUs determine the slub page order Jann Horn
2021-01-22 13:09 ` Jann Horn
2021-01-22 15:27 ` Vlastimil Babka
2021-01-25 4:28 ` Bharata B Rao
2021-01-26 8:52 ` Michal Hocko
2021-01-26 13:38 ` Vincent Guittot
2021-01-26 13:59 ` Michal Hocko [this message]
2021-01-28 13:45 ` Mel Gorman
2021-01-28 13:57 ` Michal Hocko
2021-01-28 14:42 ` Mel Gorman
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=20210126135918.GQ827@dhcp22.suse.cz \
--to=mhocko@suse.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.ibm.com \
--cc=bharata@linux.ibm.com \
--cc=cl@linux.com \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=iamjoonsoo.kim@lge.com \
--cc=jannh@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rientjes@google.com \
--cc=shakeelb@google.com \
--cc=vbabka@suse.cz \
--cc=vincent.guittot@linaro.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).