LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: "Mike Snitzer" <snitzer@gmail.com>
To: "Eric Dumazet" <dada1@cosmosbay.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"linux kernel" <linux-kernel@vger.kernel.org>,
	netdev@vger.kernel.org, "Christoph Lameter" <clameter@sgi.com>,
	"Zhang, Yanmin" <yanmin_zhang@linux.intel.com>,
	"Peter Zijlstra" <a.p.zijlstra@chello.nl>,
	stable@kernel.org
Subject: Re: [PATCH] alloc_percpu() fails to allocate percpu data
Date: Tue, 11 Mar 2008 15:39:00 -0400	[thread overview]
Message-ID: <170fa0d20803111239u4d25b7c8p915e63a43cb389c6@mail.gmail.com> (raw)
In-Reply-To: <47D6D24D.2080007@cosmosbay.com>

On 3/11/08, Eric Dumazet <dada1@cosmosbay.com> wrote:
> Mike Snitzer a écrit :
>
> > On 2/21/08, Eric Dumazet <dada1@cosmosbay.com> wrote:
>  >
>  >> Some oprofile results obtained while using tbench on a 2x2 cpu machine
>  >>  were very surprising.
>  >>
>  >>  For example, loopback_xmit() function was using high number of cpu
>  >>  cycles to perform
>  >>  the statistic updates, supposed to be real cheap since they use percpu data
>  >>
>  >>         pcpu_lstats = netdev_priv(dev);
>  >>         lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id());
>  >>         lb_stats->packets++;  /* HERE : serious contention */
>  >>         lb_stats->bytes += skb->len;
>  >>
>  >>
>  >>  struct pcpu_lstats is a small structure containing two longs. It appears
>  >>  that on my 32bits platform,
>  >>  alloc_percpu(8) allocates a single cache line,  instead of giving to
>  >>  each cpu a separate
>  >>  cache line.
>  >>
>  >>  Using the following patch gave me impressive boost in various benchmarks
>  >>  ( 6 % in tbench)
>  >>  (all percpu_counters hit this bug too)
>  >>
>  >>  Long term fix (ie >= 2.6.26) would be to let each CPU allocate their own
>  >>  block of memory, so that we
>  >>  dont need to roudup sizes to L1_CACHE_BYTES, or merging the SGI stuffof
>  >>  course...
>  >>
>  >>  Note : SLUB vs SLAB is important here to *show* the improvement, since
>  >>  they dont have the same minimum
>  >>  allocation sizes (8 bytes vs 32 bytes).
>  >>  This could very well explain regressions some guys reported when they
>  >>  switched to SLUB.
>  >>
>  >
>  >
>  > I see that this fix was committed to mainline as commit
>  > be852795e1c8d3829ddf3cb1ce806113611fa555
>  >
>  > The commit didn't "Cc: <stable@kernel.org>", and it doesn't appear to
>  > be queued for 2.6.24.x.  Should it be?
>  >
>  >
>
> Yes, it should be queued fo 2.6.24.x

That means both of the following commits need to be cherry-picked into 2.6.24.x:
b3242151906372f30f57feaa43b4cac96a23edb1
be852795e1c8d3829ddf3cb1ce806113611fa555

>  > If I understand you correctly, SLAB doesn't create this particular
>  > cache thrashing on 32bit systems?  Is SLAB ok on other architectures
>  > too?  Can you (or others) comment on the importance of this fix
>  > relative to x86_64 (64byte cacheline) and SLAB?
>  >
>  >
>
>
> Fix is important both for 32 and 64 bits kernels, SLAB or SLUB.
>
>  SLAB does have this problem, but less prevalent than SLUB, because these
>  allocators dont have the same minimal size allocation (32 vs 8)
>
>  So with SLUB, it is possible that 8 CPUS share the same 64 bytes
>  cacheline to store their percpu counters, while only 2 cpus can share
>  this same cache line with SLAB allocator.

Thanks for the clarification.

  reply	other threads:[~2008-03-11 19:39 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-02-21 18:00 Eric Dumazet
2008-02-21 22:26 ` Peter Zijlstra
2008-02-23  9:23   ` Nick Piggin
2008-02-27 19:44     ` Christoph Lameter
2008-03-03  3:14       ` Nick Piggin
2008-03-03  7:48         ` Eric Dumazet
2008-03-03  9:41           ` Nick Piggin
2008-03-03 19:30         ` Christoph Lameter
2008-02-23  8:04 ` Andrew Morton
2008-02-27 19:59 ` Christoph Lameter
2008-02-27 20:24   ` Andrew Morton
2008-02-27 21:56     ` Christoph Lameter
2008-03-01 13:53     ` Eric Dumazet
2008-03-11 18:15 ` Mike Snitzer
2008-03-11 18:41   ` Eric Dumazet
2008-03-11 19:39     ` Mike Snitzer [this message]
2008-03-12  0:18       ` [stable] " Chris Wright

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=170fa0d20803111239u4d25b7c8p915e63a43cb389c6@mail.gmail.com \
    --to=snitzer@gmail.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=clameter@sgi.com \
    --cc=dada1@cosmosbay.com \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=stable@kernel.org \
    --cc=yanmin_zhang@linux.intel.com \
    --subject='Re: [PATCH] alloc_percpu() fails to allocate percpu data' \
    /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 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).