All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Dobson <colpatch@us.ibm.com>
To: Christoph Lameter <christoph@lameter.com>
Cc: Dave Hansen <haveblue@us.ibm.com>,
	"Martin J. Bligh" <mbligh@mbligh.org>,
	Jesse Barnes <jbarnes@virtuousgeek.org>,
	Andy Whitcroft <apw@shadowen.org>, Andrew Morton <akpm@osdl.org>,
	linux-mm <linux-mm@kvack.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	shai@scalex86.org, steiner@sgi.com
Subject: Re: NUMA aware slab allocator V3
Date: Thu, 19 May 2005 12:03:11 -0700	[thread overview]
Message-ID: <428CE2EF.803@us.ibm.com> (raw)
In-Reply-To: <Pine.LNX.4.62.0505182105310.17811@graphe.net>

Christoph Lameter wrote:
> On Wed, 18 May 2005, Christoph Lameter wrote:
> 
>>Fixes to the slab allocator in 2.6.12-rc4-mm2
>>- Remove MAX_NUMNODES check
>>- use for_each_node/cpu
>>- Fix determination of INDEX_AC
> 
> Rats! The whole thing with cpu online and node online is not as easy as I 
> thought. There may be bugs in V3 of the numa slab allocator 
> because offline cpus and offline are not properly handled. Maybe 
> that also contributed to the ppc64 issues. 

Running this test through the "wringer" (aka building/booting on one of our
PPC64 boxen).  I'll let you know if this fixes any problems.


> The earlier patch fails if I boot an x86_64 NUMA kernel on a x86_64 single 
> processor system.
> 
> Here is a revised patch. Would be good if someone could review my use 
> of online_cpu / online_node etc. Is there some way to bring cpus 
> online and offline to test if this really works? Seems that the code in 
> alloc_percpu is suspect even in the old allocator because it may have
> to allocate memory for non present cpus.

I'll look through and see what I can tell you, but I gotta run to a meeting
now. :(

-Matt


WARNING: multiple messages have this Message-ID (diff)
From: Matthew Dobson <colpatch@us.ibm.com>
To: Christoph Lameter <christoph@lameter.com>
Cc: Dave Hansen <haveblue@us.ibm.com>,
	"Martin J. Bligh" <mbligh@mbligh.org>,
	Jesse Barnes <jbarnes@virtuousgeek.org>,
	Andy Whitcroft <apw@shadowen.org>, Andrew Morton <akpm@osdl.org>,
	linux-mm <linux-mm@kvack.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	shai@scalex86.org, steiner@sgi.com
Subject: Re: NUMA aware slab allocator V3
Date: Thu, 19 May 2005 12:03:11 -0700	[thread overview]
Message-ID: <428CE2EF.803@us.ibm.com> (raw)
In-Reply-To: <Pine.LNX.4.62.0505182105310.17811@graphe.net>

Christoph Lameter wrote:
> On Wed, 18 May 2005, Christoph Lameter wrote:
> 
>>Fixes to the slab allocator in 2.6.12-rc4-mm2
>>- Remove MAX_NUMNODES check
>>- use for_each_node/cpu
>>- Fix determination of INDEX_AC
> 
> Rats! The whole thing with cpu online and node online is not as easy as I 
> thought. There may be bugs in V3 of the numa slab allocator 
> because offline cpus and offline are not properly handled. Maybe 
> that also contributed to the ppc64 issues. 

Running this test through the "wringer" (aka building/booting on one of our
PPC64 boxen).  I'll let you know if this fixes any problems.


> The earlier patch fails if I boot an x86_64 NUMA kernel on a x86_64 single 
> processor system.
> 
> Here is a revised patch. Would be good if someone could review my use 
> of online_cpu / online_node etc. Is there some way to bring cpus 
> online and offline to test if this really works? Seems that the code in 
> alloc_percpu is suspect even in the old allocator because it may have
> to allocate memory for non present cpus.

I'll look through and see what I can tell you, but I gotta run to a meeting
now. :(

-Matt

--
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:"aart@kvack.org"> aart@kvack.org </a>

  parent reply	other threads:[~2005-05-19 19:03 UTC|newest]

Thread overview: 105+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-05-11 15:17 NUMA aware slab allocator V2 Christoph Lameter
2005-05-11 15:17 ` Christoph Lameter
2005-05-11 15:46 ` Jack Steiner
2005-05-11 15:46   ` Jack Steiner
2005-05-12  7:04 ` Andrew Morton
2005-05-12  7:04   ` Andrew Morton
2005-05-12  9:39   ` Niraj kumar
2005-05-12  9:39     ` Niraj kumar
2005-05-12 20:02   ` Christoph Lameter
2005-05-12 20:02     ` Christoph Lameter
2005-05-12 20:22     ` Andrew Morton
2005-05-12 20:22       ` Andrew Morton
2005-05-13  7:06     ` Andrew Morton
2005-05-13  7:06       ` Andrew Morton
2005-05-13 11:21       ` Christoph Lameter
2005-05-13 11:21         ` Christoph Lameter
2005-05-13 11:33         ` Andrew Morton
2005-05-13 11:33           ` Andrew Morton
2005-05-13 11:37           ` Christoph Lameter
2005-05-13 11:37             ` Christoph Lameter
2005-05-13 13:56             ` Dave Hansen
2005-05-13 13:56               ` Dave Hansen
2005-05-13 16:20               ` Christoph Lameter
2005-05-13 16:20                 ` Christoph Lameter
2005-05-14  1:24           ` NUMA aware slab allocator V3 Christoph Lameter
2005-05-14  1:24             ` Christoph Lameter
2005-05-14  7:42             ` Andrew Morton
2005-05-14  7:42               ` Andrew Morton
2005-05-14 16:24               ` Christoph Lameter
2005-05-14 16:24                 ` Christoph Lameter
2005-05-16  5:00                 ` Andrew Morton
2005-05-16  5:00                   ` Andrew Morton
2005-05-16 13:52             ` Dave Hansen
2005-05-16 13:52               ` Dave Hansen
2005-05-16 16:47               ` Christoph Lameter
2005-05-16 16:47                 ` Christoph Lameter
2005-05-16 17:22                 ` Dave Hansen
2005-05-16 17:22                   ` Dave Hansen
2005-05-16 17:54                   ` Christoph Lameter
2005-05-16 17:54                     ` Christoph Lameter
2005-05-16 18:08                     ` Martin J. Bligh
2005-05-16 18:08                       ` Martin J. Bligh
2005-05-16 21:10                       ` Jesse Barnes
2005-05-16 21:10                         ` Jesse Barnes
2005-05-16 21:21                         ` Martin J. Bligh
2005-05-16 21:21                           ` Martin J. Bligh
2005-05-17  0:14                           ` Christoph Lameter
2005-05-17  0:14                             ` Christoph Lameter
2005-05-17  0:26                             ` Dave Hansen
2005-05-17  0:26                               ` Dave Hansen
2005-05-17 23:36                               ` Matthew Dobson
2005-05-17 23:36                                 ` Matthew Dobson
2005-05-17 23:49                                 ` Christoph Lameter
2005-05-17 23:49                                   ` Christoph Lameter
2005-05-18 17:27                                   ` Matthew Dobson
2005-05-18 17:27                                     ` Matthew Dobson
2005-05-18 17:48                                     ` Christoph Lameter
2005-05-18 17:48                                       ` Christoph Lameter
2005-05-18 21:15                                       ` Matthew Dobson
2005-05-18 21:15                                         ` Matthew Dobson
2005-05-18 21:40                                         ` Christoph Lameter
2005-05-18 21:40                                           ` Christoph Lameter
2005-05-19  5:07                                           ` Christoph Lameter
2005-05-19  5:07                                             ` Christoph Lameter
2005-05-19 16:14                                             ` Jesse Barnes
2005-05-19 16:14                                               ` Jesse Barnes
2005-05-19 19:03                                             ` Matthew Dobson [this message]
2005-05-19 19:03                                               ` Matthew Dobson
2005-05-19 21:46                                             ` Matthew Dobson
2005-05-20 19:03                                             ` Matthew Dobson
2005-05-20 19:03                                               ` Matthew Dobson
2005-05-20 19:23                                               ` Christoph Lameter
2005-05-20 19:23                                                 ` Christoph Lameter
2005-05-20 20:20                                                 ` Matthew Dobson
2005-05-20 20:20                                                   ` Matthew Dobson
2005-05-20 21:30                                                 ` Matthew Dobson
2005-05-20 21:30                                                   ` Matthew Dobson
2005-05-20 23:42                                                   ` Christoph Lameter
2005-05-20 23:42                                                     ` Christoph Lameter
2005-05-24 21:37                                                   ` Christoph Lameter
2005-05-24 21:37                                                     ` Christoph Lameter
2005-05-24 23:02                                                     ` Matthew Dobson
2005-05-24 23:02                                                       ` Matthew Dobson
2005-05-25  5:21                                                       ` Christoph Lameter
2005-05-25  5:21                                                         ` Christoph Lameter
2005-05-25 18:27                                                         ` Matthew Dobson
2005-05-25 18:27                                                           ` Matthew Dobson
2005-05-25 21:03                                                           ` Christoph Lameter
2005-05-25 21:03                                                             ` Christoph Lameter
2005-05-26  6:48                                                             ` Martin J. Bligh
2005-05-26  6:48                                                               ` Martin J. Bligh
2005-05-28  1:59                                                       ` NUMA aware slab allocator V4 Christoph Lameter
2005-05-28  1:59                                                         ` Christoph Lameter
2005-05-16 21:54                         ` NUMA aware slab allocator V3 Dave Hansen
2005-05-16 21:54                           ` Dave Hansen
2005-05-16 18:12                     ` Dave Hansen
2005-05-16 18:12                       ` Dave Hansen
2005-05-13 13:46         ` NUMA aware slab allocator V2 Dave Hansen
2005-05-13 13:46           ` Dave Hansen
2005-05-17 23:29       ` Matthew Dobson
2005-05-17 23:29         ` Matthew Dobson
2005-05-18  1:07         ` Christoph Lameter
2005-05-18  1:07           ` Christoph Lameter
2005-05-12 21:49 ` Robin Holt
2005-05-12 21:49   ` Robin Holt

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=428CE2EF.803@us.ibm.com \
    --to=colpatch@us.ibm.com \
    --cc=akpm@osdl.org \
    --cc=apw@shadowen.org \
    --cc=christoph@lameter.com \
    --cc=haveblue@us.ibm.com \
    --cc=jbarnes@virtuousgeek.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mbligh@mbligh.org \
    --cc=shai@scalex86.org \
    --cc=steiner@sgi.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 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.