From: Dave Hansen <dave-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
To: Paul Menage <menage-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org,
containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
Benjamin Blum <bblum-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH 3/3] Quick vmalloc vs kmalloc fix to the case where array size is too large
Date: Tue, 14 Jul 2009 10:47:32 -0700 [thread overview]
Message-ID: <1247593652.13426.15938.camel@nimitz> (raw)
In-Reply-To: <6599ad830907141028y50f36d63h8ea06f73ff369591-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Tue, 2009-07-14 at 10:28 -0700, Paul Menage wrote:
> On Mon, Jul 13, 2009 at 9:25 PM, KAMEZAWA
> Hiroyuki<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org> wrote:
> > My point is
> > - More PIDs, More time necessary to read procs file.
>
> Right now, many pids => impossible to read procs file due to kmalloc
> failure. (This was always the case with cpusets too). So using kmalloc
> in those cases is a strict improvement.
How big were those allocations that were failing? The code made it
appear that order-2 (PAGE_SIZE*4) allocations were failing. That's a
bit lower than I'd expect the page allocator to start failing.
-- Dave
WARNING: multiple messages have this Message-ID (diff)
From: Dave Hansen <dave@linux.vnet.ibm.com>
To: Paul Menage <menage@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
containers@lists.linux-foundation.org,
linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
Benjamin Blum <bblum@google.com>
Subject: Re: [PATCH 3/3] Quick vmalloc vs kmalloc fix to the case where array size is too large
Date: Tue, 14 Jul 2009 10:47:32 -0700 [thread overview]
Message-ID: <1247593652.13426.15938.camel@nimitz> (raw)
In-Reply-To: <6599ad830907141028y50f36d63h8ea06f73ff369591@mail.gmail.com>
On Tue, 2009-07-14 at 10:28 -0700, Paul Menage wrote:
> On Mon, Jul 13, 2009 at 9:25 PM, KAMEZAWA
> Hiroyuki<kamezawa.hiroyu@jp.fujitsu.com> wrote:
> > My point is
> > - More PIDs, More time necessary to read procs file.
>
> Right now, many pids => impossible to read procs file due to kmalloc
> failure. (This was always the case with cpusets too). So using kmalloc
> in those cases is a strict improvement.
How big were those allocations that were failing? The code made it
appear that order-2 (PAGE_SIZE*4) allocations were failing. That's a
bit lower than I'd expect the page allocator to start failing.
-- Dave
next prev parent reply other threads:[~2009-07-14 17:47 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-10 23:01 [PATCH v2 0/3] CGroups: cgroup member list enhancement/fix Ben Blum
2009-07-10 23:01 ` Ben Blum
[not found] ` <20090710230043.16778.29656.stgit-/yCBOHwbXCxd3OlUiQof+WCaruZE5nAUZeezCHUQhQ4@public.gmane.org>
2009-07-10 23:01 ` [PATCH 1/3] Adds a read-only "procs" file similar to "tasks" that shows only unique tgids Ben Blum
2009-07-10 23:01 ` Ben Blum
2009-07-13 3:46 ` Li Zefan
[not found] ` <4A5AAE02.7060106-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
2009-07-13 15:25 ` Benjamin Blum
2009-07-13 15:25 ` Benjamin Blum
[not found] ` <20090710230154.16778.58053.stgit-/yCBOHwbXCxd3OlUiQof+WCaruZE5nAUZeezCHUQhQ4@public.gmane.org>
2009-07-13 3:46 ` Li Zefan
2009-07-14 18:34 ` Dave Hansen
2009-07-14 18:34 ` Dave Hansen
2009-07-14 21:26 ` Benjamin Blum
2009-07-14 21:26 ` Benjamin Blum
[not found] ` <2f86c2480907141426r16f8ccf3o9770e25cc8d2e509-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-14 21:49 ` Dave Hansen
2009-07-14 21:49 ` Dave Hansen
2009-07-14 22:55 ` Benjamin Blum
2009-07-14 22:55 ` Benjamin Blum
2009-07-15 1:31 ` Li Zefan
2009-07-15 1:31 ` Li Zefan
2009-07-10 23:02 ` [PATCH 2/3] Ensures correct concurrent opening/reading of pidlists across pid namespaces Ben Blum
2009-07-10 23:02 ` Ben Blum
2009-07-11 21:59 ` Serge E. Hallyn
2009-07-10 23:02 ` [PATCH 3/3] Quick vmalloc vs kmalloc fix to the case where array size is too large Ben Blum
2009-07-10 23:02 ` Ben Blum
2009-07-13 3:03 ` Li Zefan
[not found] ` <4A5AA3E7.9070800-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
2009-07-13 6:03 ` KAMEZAWA Hiroyuki
2009-07-13 6:03 ` KAMEZAWA Hiroyuki
[not found] ` <20090713150303.70ab5176.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2009-07-13 15:27 ` Benjamin Blum
2009-07-13 15:27 ` Benjamin Blum
[not found] ` <2f86c2480907130827u7d2b062bw26bbb80a8e3de657-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-13 23:49 ` KAMEZAWA Hiroyuki
2009-07-13 23:49 ` KAMEZAWA Hiroyuki
[not found] ` <20090714084950.2401d9a6.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2009-07-14 3:50 ` Paul Menage
2009-07-14 3:50 ` Paul Menage
[not found] ` <6599ad830907132050n226aecb3ucab6746a4d0e81fa-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-14 3:53 ` KAMEZAWA Hiroyuki
2009-07-14 3:53 ` KAMEZAWA Hiroyuki
[not found] ` <20090714125334.b476aa78.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2009-07-14 4:04 ` Paul Menage
2009-07-14 4:04 ` Paul Menage
2009-07-14 4:25 ` KAMEZAWA Hiroyuki
2009-07-14 17:26 ` Benjamin Blum
[not found] ` <20090714132538.ac0bc44a.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2009-07-14 17:26 ` Benjamin Blum
2009-07-14 17:28 ` Paul Menage
2009-07-14 17:28 ` Paul Menage
[not found] ` <6599ad830907141028y50f36d63h8ea06f73ff369591-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-14 17:47 ` Dave Hansen [this message]
2009-07-14 17:47 ` Dave Hansen
2009-07-14 17:50 ` Paul Menage
2009-07-14 17:50 ` Paul Menage
[not found] ` <6599ad830907141050r1e9dde98l56afd37629f749e8-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-14 21:30 ` Benjamin Blum
2009-07-14 21:30 ` Benjamin Blum
[not found] ` <6599ad830907132104o55d31ccexb15e5aa35c31416e-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-07-14 4:25 ` KAMEZAWA Hiroyuki
[not found] ` <20090710230205.16778.11707.stgit-/yCBOHwbXCxd3OlUiQof+WCaruZE5nAUZeezCHUQhQ4@public.gmane.org>
2009-07-13 3:03 ` Li Zefan
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=1247593652.13426.15938.camel@nimitz \
--to=dave-23vcf4htsmix0ybbhkvfkdbpr1lh4cv8@public.gmane.org \
--cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
--cc=bblum-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=menage-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
/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.