From: Christoph Lameter <cl@linux.com>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>,
Andi Kleen <andi@firstfloor.org>,
tj@kernel.org, Metathronius Galabant <m.galabant@googlemail.com>,
Matt Mackall <mpm@selenic.com>,
Eric Dumazet <eric.dumazet@gmail.com>,
Adrian Drzewiecki <z@drze.net>, Shaohua Li <shaohua.li@intel.com>,
Alex Shi <alex.shi@intel.com>,
linux-mm@kvack.org
Subject: [rfc 00/18] slub: irqless/lockless slow allocation paths
Date: Fri, 11 Nov 2011 14:07:11 -0600 [thread overview]
Message-ID: <20111111200711.156817886@linux.com> (raw)
This is a patchset that makes the allocator slow path also lockless like
the free paths. However, in the process it is making processing more
complex so that this is not a performance improvement. I am going to
drop this series unless someone comes up with a bright idea to fix the
following performance issues:
1. Had to reduce the per cpu state kept to two words in order to
be able to operate without preempt disable / interrupt disable only
through cmpxchg_double(). This means that the node information and
the page struct location have to be calculated from the free pointer.
That is possible but relatively expensive and has to be done frequently
in fast paths.
2. If the freepointer becomes NULL then the page struct location can
no longer be determined. So per cpu slabs must be deactivated when
the last object is retrieved from them causing more regressions.
If these issues remain unresolved then I am fine with the way things are
right now in slub. Currently interrupts are disabled in the slow paths and
then multiple fields in the kmem_cache_cpu structure are modified without
regard to instruction atomicity.
--
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:[~2011-11-11 20:07 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-11-11 20:07 Christoph Lameter [this message]
2011-11-11 20:07 ` [rfc 01/18] slub: Get rid of the node field Christoph Lameter
2011-11-14 21:42 ` Pekka Enberg
2011-11-15 16:07 ` Christoph Lameter
2011-11-20 23:01 ` David Rientjes
2011-11-21 17:17 ` Christoph Lameter
2011-11-11 20:07 ` [rfc 02/18] slub: Separate out kmem_cache_cpu processing from deactivate_slab Christoph Lameter
2011-11-20 23:10 ` David Rientjes
2011-11-11 20:07 ` [rfc 03/18] slub: Extract get_freelist from __slab_alloc Christoph Lameter
2011-11-14 21:43 ` Pekka Enberg
2011-11-15 16:08 ` Christoph Lameter
2011-12-13 20:31 ` Pekka Enberg
2011-11-20 23:18 ` David Rientjes
2011-11-11 20:07 ` [rfc 04/18] slub: Use freelist instead of "object" in __slab_alloc Christoph Lameter
2011-11-14 21:44 ` Pekka Enberg
2011-11-20 23:22 ` David Rientjes
2011-11-11 20:07 ` [rfc 05/18] slub: Simplify control flow in __slab_alloc() Christoph Lameter
2011-11-14 21:45 ` Pekka Enberg
2011-11-20 23:24 ` David Rientjes
2011-11-11 20:07 ` [rfc 06/18] slub: Use page variable instead of c->page Christoph Lameter
2011-11-14 21:46 ` Pekka Enberg
2011-11-20 23:27 ` David Rientjes
2011-11-11 20:07 ` [rfc 07/18] slub: pass page to node_match() instead of kmem_cache_cpu structure Christoph Lameter
2011-11-20 23:28 ` David Rientjes
2011-11-11 20:07 ` [rfc 08/18] slub: enable use of deactivate_slab with interrupts on Christoph Lameter
2011-11-11 20:07 ` [rfc 09/18] slub: Run deactivate_slab with interrupts enabled Christoph Lameter
2011-11-11 20:07 ` [rfc 10/18] slub: Enable use of get_partial " Christoph Lameter
2011-11-11 20:07 ` [rfc 11/18] slub: Acquire_slab() avoid loop Christoph Lameter
2011-11-11 20:07 ` [rfc 12/18] slub: Remove kmem_cache_cpu dependency from acquire slab Christoph Lameter
2011-11-11 20:07 ` [rfc 13/18] slub: Add functions to manage per cpu freelists Christoph Lameter
2011-11-11 20:07 ` [rfc 14/18] slub: Decomplicate the get_pointer_safe call and fixup statistics Christoph Lameter
2011-11-11 20:07 ` [rfc 15/18] slub: new_slab_objects() can also get objects from partial list Christoph Lameter
2011-11-11 20:07 ` [rfc 16/18] slub: Drop page field from kmem_cache_cpu Christoph Lameter
2011-11-11 20:07 ` [rfc 17/18] slub: Move __slab_free() into slab_free() Christoph Lameter
2011-11-11 20:07 ` [rfc 18/18] slub: Move __slab_alloc() into slab_alloc() Christoph Lameter
2011-11-16 17:39 ` [rfc 00/18] slub: irqless/lockless slow allocation paths Eric Dumazet
2011-11-16 17:45 ` Eric Dumazet
2011-11-20 23:32 ` David Rientjes
2011-11-20 23:30 ` David Rientjes
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=20111111200711.156817886@linux.com \
--to=cl@linux.com \
--cc=alex.shi@intel.com \
--cc=andi@firstfloor.org \
--cc=eric.dumazet@gmail.com \
--cc=linux-mm@kvack.org \
--cc=m.galabant@googlemail.com \
--cc=mpm@selenic.com \
--cc=penberg@cs.helsinki.fi \
--cc=rientjes@google.com \
--cc=shaohua.li@intel.com \
--cc=tj@kernel.org \
--cc=z@drze.net \
/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).