From: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
To: Nish Aravamudan <nish.aravamudan@gmail.com>
Cc: Christoph Lameter <clameter@sgi.com>,
Anton Blanchard <anton@samba.org>,
linux-mm@kvack.org, ak@suse.de, mel@csn.ul.ie, apw@shadowen.org,
Andrew Morton <akpm@linux-foundation.org>,
Eric Whitney <eric.whitney@hp.com>,
andyw@uk.ibm.com
Subject: Re: [PATCH] Fix hugetlb pool allocation with empty nodes - V2 -> V3
Date: Wed, 16 May 2007 16:32:06 -0400 [thread overview]
Message-ID: <1179347526.5867.44.camel@localhost> (raw)
In-Reply-To: <29495f1d0705161259p70a1e499tb831889fd2bcebcb@mail.gmail.com>
On Wed, 2007-05-16 at 12:59 -0700, Nish Aravamudan wrote:
>
> This completely breaks hugepage allocation on 4-node x86_64 box I have
> here. Each node has <4GB of memory, so all memory is ZONE_DMA and
> ZONE_DMA32. gfp_zone(GFP_HIGHUSER) is ZONE_NORMAL, though. So all
> nodes are not populated by the default initialization to an empty
> nodemask.
>
> Thanks to Andy Whitcroft for helping me debug this.
>
> I'm not sure how to fix this -- but I ran into while trying to base my
> sysfs hugepage allocation patches on top of yours.
>
> Thoughts?
I'm looking at this now on a 2 socket x86_64 blade with 2GB/node. Just
noticed that I'm not seeing any nodes in the node_populated_map.
Haven't figured out how to fix it yet. Stand by...
Lee
--
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:[~2007-05-16 20:32 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-05-03 2:21 [PATCH] Fix hugetlb pool allocation with empty nodes Anton Blanchard
2007-05-03 3:02 ` Christoph Lameter
2007-05-03 6:07 ` Anton Blanchard
2007-05-03 6:37 ` Christoph Lameter
2007-05-03 8:59 ` Andi Kleen
2007-05-03 13:22 ` Anton Blanchard
2007-05-04 20:29 ` [PATCH] Fix hugetlb pool allocation with empty nodes - V2 Lee Schermerhorn
2007-05-04 21:27 ` Christoph Lameter
2007-05-04 22:39 ` Nish Aravamudan
2007-05-07 13:40 ` Lee Schermerhorn
2007-05-09 16:37 ` [PATCH] Fix hugetlb pool allocation with empty nodes - V2 -> V3 Lee Schermerhorn
2007-05-09 16:57 ` Christoph Lameter
2007-05-09 19:17 ` Lee Schermerhorn
2007-05-16 17:27 ` Nish Aravamudan
2007-05-16 20:01 ` Lee Schermerhorn
2007-05-09 19:59 ` Nish Aravamudan
2007-05-09 20:37 ` Lee Schermerhorn
2007-05-09 20:54 ` Christoph Lameter
2007-05-09 22:34 ` Nish Aravamudan
2007-05-15 16:30 ` Lee Schermerhorn
2007-05-16 23:47 ` Nish Aravamudan
2007-05-16 19:59 ` Nish Aravamudan
2007-05-16 20:32 ` Lee Schermerhorn [this message]
2007-05-16 22:17 ` [PATCH/RFC] Fix hugetlb pool allocation with empty nodes - V4 Lee Schermerhorn
2007-05-18 0:30 ` Nish Aravamudan
2007-05-21 14:57 ` Lee Schermerhorn
2007-05-21 17:51 ` Nish Aravamudan
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=1179347526.5867.44.camel@localhost \
--to=lee.schermerhorn@hp.com \
--cc=ak@suse.de \
--cc=akpm@linux-foundation.org \
--cc=andyw@uk.ibm.com \
--cc=anton@samba.org \
--cc=apw@shadowen.org \
--cc=clameter@sgi.com \
--cc=eric.whitney@hp.com \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=nish.aravamudan@gmail.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.