From: Andrew Morton <akpm@digeo.com>
To: Manfred Spraul <manfred@colorfullife.com>
Cc: Ed Tomlinson <tomlins@cam.org>, linux-kernel@vger.kernel.org
Subject: Re: [patch 3/4] slab reclaim balancing
Date: Thu, 26 Sep 2002 14:39:19 -0700 [thread overview]
Message-ID: <3D937E87.D387F358@digeo.com> (raw)
In-Reply-To: 3D9372D3.3000908@colorfullife.com
Manfred Spraul wrote:
>
> Andrew Morton wrote:
> >
> > Was the microbenchmark actually touching the memory which it was
> > allocating from slab? If so then yes, we'd expect to see cache
> > misses against those cold pages coming out of the buddy.
> >
>
> No, it was just measuring the cost of the kmem_cache_grow/shrink.
>
> Btw, 140 cycles for kmem_cache_alloc+free is inflated - someone enabled
> kmem_cache_alloc_head() even in the no-debugging version.
> As expected, done by Andrea, who neither bothered to cc me, nor actually
> understood the code.
hm, OK. Sorry, I did not realise that you were this closely
interested/involved with slab, so things have been sort of
going on behind your back :(
> >
> >>For SMP and slabs that are per-cpu cached, the change could be right,
> >>because the arrays should absorb bursts. But I do not think that the
> >>change is the right approach for UP.
> >
> >
> > I'd suggest that we wait until we have slab freeing its pages into
> > the hotlists, and allocating from them. That should pull things back.
> >
> You are asking a interesting question:
>
> The slab is by design far from LIFO - it tries to find pages with no
> allocated objects, that are possible to return to the page allocator. It
> doesn't try to optimize for cache hit rates.
>
> Is that actually the right approach? For large objects, it would be
> possible to cripple the freeable slabs list, and to perform the cache
> hit optimization (i.e. per-cpu LIFO) in page_alloc.c, but that doesn't
> work with small objects.
Well with a, what? 100:1 speed ratio, we'll generally get best results
from optimising for locality/recency of reference.
> On SMP, the per-cpu arrays are the LIFO and should give good cache hit
> rates. On UP, I haven't enabled them, because they could increase the
> internal fragmentation of the slabs.
>
> Perhaps we should enable the arrays on UP, too, and thus improve the
> cache hit rates? If there is no increase in fragmentation, we could
> ignore it. Otherwise we could replace the 3-list Bonwick slab with
> another backend, something that's stronger at reducing the internal
> fragmentation.
Definitely worthy of investigation. Memory sizes are increasing,
and the cached-versus-noncached latencies are increasing. Both
these say "optimise for cache hits".
Plus we'd lose a ton of ifdefs if we enabled it on UP as well...
Bill wrote a couple of handy slab-monitoring tools, btw.
http://www.zip.com.au/~akpm/linux/patches/ - I use bloatmeter.
next prev parent reply other threads:[~2002-09-26 21:34 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-26 14:13 [patch 3/4] slab reclaim balancing Manfred Spraul
2002-09-26 14:20 ` William Lee Irwin III
2002-09-26 15:24 ` Manfred Spraul
2002-09-26 17:37 ` Andrew Morton
2002-09-26 18:47 ` Manfred Spraul
2002-09-26 19:49 ` Andrew Morton
2002-09-26 20:49 ` Manfred Spraul
2002-09-26 21:39 ` Andrew Morton [this message]
2002-09-27 0:41 ` Ed Tomlinson
2002-09-27 17:24 ` Manfred Spraul
2002-09-27 18:26 ` Andrew Morton
2002-09-27 19:38 ` Manfred Spraul
2002-09-27 19:52 ` Andrew Morton
2002-09-27 15:59 ` Manfred Spraul
-- strict thread matches above, loose matches on Subject: below --
2002-09-26 4:08 Andrew Morton
2002-09-26 11:39 ` Ed Tomlinson
2002-09-26 15:09 ` Ed Tomlinson
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=3D937E87.D387F358@digeo.com \
--to=akpm@digeo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=manfred@colorfullife.com \
--cc=tomlins@cam.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).