From: Eric Dumazet <dada1@cosmosbay.com>
To: Pekka J Enberg <penberg@cs.Helsinki.FI>
Cc: akpm@osdl.org, linux-kernel@vger.kernel.org,
manfred@colorfullife.com, christoph@lameter.com
Subject: Re: [PATCH] slab: minor cleanup to kmem_cache_alloc_node
Date: Mon, 21 Nov 2005 16:58:21 +0100 [thread overview]
Message-ID: <4381EE9D.1000506@cosmosbay.com> (raw)
In-Reply-To: <Pine.LNX.4.58.0511211627460.18869@sbz-30.cs.Helsinki.FI>
Pekka J Enberg a écrit :
> This patch gets rid of one if-else statement by moving current node allocation
> check at the beginning of kmem_cache_alloc_node().
>
Are you sure this is valid ?
What about preemption ?
The "if (nodeid == numa_node_id())" check was done with IRQ off, and you want
do do it with IRQ on.
> Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
> ---
>
> slab.c | 7 ++-----
> 1 file changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/mm/slab.c b/mm/slab.c
> index 7f80ec3..a05bbfe 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -2881,7 +2881,7 @@ void *kmem_cache_alloc_node(kmem_cache_t
> unsigned long save_flags;
> void *ptr;
>
> - if (nodeid == -1)
> + if (nodeid == -1 || nodeid == numa_node_id())
<Imagine preemption here, and thread migrated to another NUMA node.>
> return __cache_alloc(cachep, flags);
>
> if (unlikely(!cachep->nodelists[nodeid])) {
> @@ -2892,10 +2892,7 @@ void *kmem_cache_alloc_node(kmem_cache_t
>
> cache_alloc_debugcheck_before(cachep, flags);
> local_irq_save(save_flags);
> - if (nodeid == numa_node_id())
> - ptr = ____cache_alloc(cachep, flags);
> - else
> - ptr = __cache_alloc_node(cachep, flags, nodeid);
> + ptr = __cache_alloc_node(cachep, flags, nodeid);
> local_irq_restore(save_flags);
> ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, __builtin_return_address(0));
>
next prev parent reply other threads:[~2005-11-21 15:58 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-11-21 14:30 [PATCH] slab: minor cleanup to kmem_cache_alloc_node Pekka J Enberg
2005-11-21 15:58 ` Eric Dumazet [this message]
2005-11-21 16:23 ` Pekka Enberg
2005-11-21 17:21 ` Christoph Lameter
2005-11-21 18:36 ` Pekka Enberg
2005-11-21 19:47 ` Christoph Lameter
2005-11-21 21:07 ` Pekka Enberg
2005-11-21 21:17 ` Christoph Lameter
2005-11-22 6:57 ` Pekka J Enberg
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=4381EE9D.1000506@cosmosbay.com \
--to=dada1@cosmosbay.com \
--cc=akpm@osdl.org \
--cc=christoph@lameter.com \
--cc=linux-kernel@vger.kernel.org \
--cc=manfred@colorfullife.com \
--cc=penberg@cs.Helsinki.FI \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.