From: "Chen, Kenneth W" <kenneth.w.chen@intel.com>
To: "'Andrew Morton'" <akpm@osdl.org>,
"Christoph Lameter" <clameter@sgi.com>
Cc: <wli@holomorphy.com>, <raybry@sgi.com>, <linux-kernel@vger.kernel.org>
Subject: RE: Hugepages demand paging V1 [3/4]: Overcommit handling
Date: Fri, 22 Oct 2004 08:32:41 -0700 [thread overview]
Message-ID: <200410221530.i9MFUWq30084@unix-os.sc.intel.com> (raw)
In-Reply-To: <20041022032823.215bd95f.akpm@osdl.org>
Andrew Morton wrote on Friday, October 22, 2004 3:28 AM
> Christoph Lameter <clameter@sgi.com> wrote:
> >
> > * overcommit handling
>
> What does this do, and why do we want it?
The name of "overcommit" is definitely misleading. It means the
opposite. Since physical hugetlb backing page pool is fixed and
controlled by sys admin, the fault handler can not allocate free
pages when hugetlb page pool exhaust because of user over commits
hugetlb page. Thus we enforce strict accounting upfront to
guarantee that there will be hugetlb page available at fault time.
The down side of not having it is we SIGBUS if the kernel doesn't
have any free hugetlb pages left.
- Ken
next prev parent reply other threads:[~2004-10-22 15:35 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <B05667366EE6204181EABE9C1B1C0EB501F2ADFB@scsmsx401.amr.corp.intel.com>
2004-10-22 4:55 ` Hugepages demand paging V1 [0/4]: Discussion and overview Christoph Lameter
2004-10-22 4:56 ` Hugepages demand paging V1 [1/4]: demand paging core Christoph Lameter
2004-10-22 10:47 ` William Lee Irwin III
2004-10-22 15:33 ` Christoph Lameter
2004-10-22 4:57 ` Hugepages demand paging V1 [2/4]: set_huge_pte() arch updates Christoph Lameter
2004-10-22 10:37 ` William Lee Irwin III
2004-10-22 15:32 ` Christoph Lameter
2004-10-22 15:42 ` William Lee Irwin III
2004-10-22 20:29 ` Christoph Lameter
2004-10-22 20:45 ` William Lee Irwin III
2004-10-22 20:49 ` Christoph Lameter
2004-10-22 4:58 ` Hugepages demand paging V1 [3/4]: Overcommit handling Christoph Lameter
2004-10-22 10:28 ` Andrew Morton
2004-10-22 15:08 ` Christoph Lameter
2004-10-22 15:32 ` Chen, Kenneth W [this message]
2004-10-22 10:49 ` William Lee Irwin III
2004-10-22 11:01 ` Christoph Hellwig
2004-10-22 11:12 ` William Lee Irwin III
2004-10-22 11:16 ` Christoph Hellwig
2004-10-22 11:21 ` William Lee Irwin III
2004-10-22 11:23 ` William Lee Irwin III
2004-10-22 4:58 ` Hugepages demand paging V1 [4/4]: Numa patch Christoph Lameter
2004-10-22 6:05 ` Chen, Kenneth W
2004-10-22 11:00 ` William Lee Irwin III
2004-10-22 19:37 ` Christoph Lameter
2004-10-22 19:40 ` William Lee Irwin III
2004-10-25 21:25 ` Chen, Kenneth W
2004-10-25 21:52 ` William Lee Irwin III
2004-10-25 21:55 ` William Lee Irwin III
2004-10-25 21:05 ` Chen, Kenneth W
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=200410221530.i9MFUWq30084@unix-os.sc.intel.com \
--to=kenneth.w.chen@intel.com \
--cc=akpm@osdl.org \
--cc=clameter@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=raybry@sgi.com \
--cc=wli@holomorphy.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
all inboxes | Powered by JetHome®