From: Andi Kleen <ak@suse.de>
To: Rohit Seth <rohit.seth@intel.com>
Cc: akpm@osdl.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH]: Clean up of __alloc_pages
Date: 04 Oct 2005 15:27:08 +0200 [thread overview]
Message-ID: <p733bnh1kgj.fsf@verdi.suse.de> (raw)
In-Reply-To: <1128361714.8472.44.camel@akash.sc.intel.com>
Rohit Seth <rohit.seth@intel.com> writes:
>
> I think conceptually this ask for a new flag __GFP_NODEONLY that
> indicate allocations to come from current node only.
>
> This definitely though means I will need to separate out the allocation
> from pcp patch (as Nick suggested earlier).
This reminds me - the current logic is currently a bit suboptimal on
many NUMA systems. Often it would be better to be a bit more
aggressive at freeing memory (maybe do a very low overhead light try to
free pages) in the first node before falling back to other nodes. What
right now happens is that when you have even minor memory pressure
because e.g. you node is filled up with disk cache the local memory
affinity doesn't work too well anymore.
-Andi
--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2005-10-04 13:27 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-10-01 19:00 Seth, Rohit
2005-10-02 3:09 ` Nick Piggin
2005-10-03 16:50 ` Rohit Seth
2005-10-03 15:34 ` Christoph Lameter
2005-10-03 16:55 ` Rohit Seth
2005-10-03 16:57 ` Christoph Lameter
2005-10-03 17:48 ` Rohit Seth
2005-10-04 13:27 ` Andi Kleen [this message]
2005-10-04 16:26 ` Ray Bryant
2005-10-04 16:10 ` Martin J. Bligh
2005-10-04 17:02 ` Ray Bryant
2005-10-29 1:33 Rohit, Seth
2005-10-29 2:33 ` Nick Piggin
2005-10-31 20:55 ` Rohit Seth
2005-11-01 1:14 ` Nick Piggin
2005-11-04 18:15 ` Rohit Seth
2005-11-05 0:00 ` Nick Piggin
2005-10-30 0:16 ` Paul Jackson
2005-10-31 19:09 ` Rohit Seth
2005-11-05 17:09 ` Andi Kleen
2005-11-06 4:18 ` Paul Jackson
2005-11-06 17:35 ` Andi Kleen
2005-11-06 20:49 ` Paul Jackson
2005-11-07 2:57 ` Nick Piggin
2005-11-07 3:42 ` Andi Kleen
2005-11-07 4:37 ` Paul Jackson
2005-11-07 6:08 ` Nick Piggin
2005-11-07 9:46 ` Paul Jackson
2005-11-07 10:17 ` Nick Piggin
2005-11-07 14:41 ` Paul Jackson
2005-11-07 3:44 ` Paul Jackson
2005-10-30 1:47 ` Paul Jackson
2005-10-30 2:01 ` Nick Piggin
2005-10-30 2:19 ` Paul Jackson
2005-10-30 2:32 ` Nick Piggin
2005-10-30 3:06 ` Paul Jackson
2005-10-30 3:53 ` Nick Piggin
2005-10-30 2:26 ` Paul Jackson
2005-10-30 2:36 ` Nick Piggin
2005-10-30 3:09 ` Paul Jackson
2005-10-30 3:55 ` Nick Piggin
2005-10-30 4:11 ` Paul Jackson
2005-10-31 21:20 ` Rohit Seth
2005-10-31 21:28 ` Paul Jackson
2005-11-05 1:57 Seth, Rohit
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=p733bnh1kgj.fsf@verdi.suse.de \
--to=ak@suse.de \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rohit.seth@intel.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