From: Christoph Lameter <cl@linux.com>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>,
linux-mm@kvack.org, Eric Dumazet <eric.dumazet@gmail.com>,
"H. Peter Anvin" <hpa@zytor.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: [slubll1 00/19] SLUB: Implement mostly lockless slowpaths
Date: Wed, 30 Mar 2011 15:23:42 -0500 [thread overview]
Message-ID: <20110330202342.669400887@linux.com> (raw)
Well here is another result of my obsession with SLAB allocators. There must be
some way to get an allocator done that is faster without queueing and I hope
that we are now there (maybe only almost...).
This patchset implement wider lockless operations in slub affecting most of the
slowpaths. In particular the patch decreases the overhead in the performance
critical section of __slab_free.
One test that I ran was "hackbench 200 process 200" on 2.6.29-rc1 under KVM
Run SLAB SLUB SLUB LL
1st 35.2 35.9 31.9
2nd 34.6 30.8 27.9
3rd 33.8 29.9 28.8
Note that the SLUB version in 2.6.29-rc1 already has an optimized allocation
and free path using this_cpu_cmpxchg_double(). SLUB LL takes it to new heights
by also using cmpxchg_double() in the slowpaths (especially in the kfree()
case where we cannot queue).
The patch uses a cmpxchg_double (also introduced here) to do an atomic change
on the state of a slab page that includes the following pieces of information:
1. Freelist pointer
2. Number of objects inuse
3. Frozen state of a slab
Disabling of interrupts (which is a significant latency in the
allocator paths) is avoided in the __slab_free case.
There are some concerns with this patch. The use of cmpxchg_double on
fields of the page struct requires alignment of the fields to double
word boundaries. That can only be accomplished by adding some padding
to struct page which blows it up to 64 byte (on x86_64). Comments
in the source describe these things in more detail.
The cmpxchg_double() operation introduced here could also be used to
update other doublewords in the page struct in a lockless fashone. One
can envision page state changes that involved flags and mappings or
do list operations locklessly.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2011-03-30 20:24 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-30 20:23 Christoph Lameter [this message]
2011-03-30 20:23 ` [slubll1 01/19] percpu: Fixup __this_cpu_xchg* operations Christoph Lameter
2011-03-30 20:23 ` [slubll1 02/19] slub: get_map() function to establish map of free objects in a slab Christoph Lameter
2011-03-30 20:23 ` [slubll1 03/19] slub: Eliminate repeated use of c->page through a new page variable Christoph Lameter
2011-03-30 20:23 ` [slubll1 04/19] slub: Move node determination out of hotpath Christoph Lameter
2011-03-30 20:23 ` [slubll1 05/19] slub: Move debug handlign in __slab_free Christoph Lameter
2011-03-30 20:23 ` [slubll1 06/19] slub: Do not use frozen page flag but a bit in the page counters Christoph Lameter
2011-03-30 20:23 ` [slubll1 07/19] slub: Move page->frozen handling near where the page->freelist handling occurs Christoph Lameter
2011-03-30 20:23 ` [slubll1 08/19] x86: Add support for cmpxchg_double Christoph Lameter
2011-03-30 20:23 ` [slubll1 09/19] mm: Rearrange struct page Christoph Lameter
2011-03-30 20:23 ` [slubll1 10/19] slub: Add cmpxchg_double_slab() Christoph Lameter
2011-03-30 20:23 ` [slubll1 11/19] slub: explicit list_lock taking Christoph Lameter
2011-03-30 20:23 ` [slubll1 12/19] slub: Pass kmem_cache struct to lock and freeze slab Christoph Lameter
2011-03-30 20:23 ` [slubll1 13/19] slub: Rework allocator fastpaths Christoph Lameter
2011-03-30 20:23 ` [slubll1 14/19] slub: Invert locking and avoid slab lock Christoph Lameter
2011-03-30 20:23 ` [slubll1 15/19] slub: Disable interrupts in free_debug processing Christoph Lameter
2011-03-30 20:23 ` [slubll1 16/19] slub: Avoid disabling interrupts in free slowpath Christoph Lameter
2011-03-30 20:23 ` [slubll1 17/19] slub: Get rid of the another_slab label Christoph Lameter
2011-03-30 20:24 ` [slubll1 18/19] slub: fast release on full slab Christoph Lameter
2011-03-30 20:24 ` [slubll1 19/19] slub: Not necessary to check for empty slab on load_freelist Christoph Lameter
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=20110330202342.669400887@linux.com \
--to=cl@linux.com \
--cc=eric.dumazet@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-mm@kvack.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=penberg@cs.helsinki.fi \
--cc=rientjes@google.com \
/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).