From: Dave McCracken <dmccr@us.ibm.com>
To: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>, Andrew Morton <akpm@osdl.org>,
Linux Kernel <linux-kernel@vger.kernel.org>,
Linux Memory Management <linux-mm@kvack.org>
Subject: Re: [PATCH/RFC] Shared page tables
Date: Sat, 07 Jan 2006 12:09:29 -0600 [thread overview]
Message-ID: <2796BAF66E63B415FF1929B8@[10.1.1.4]> (raw)
In-Reply-To: <20060107122534.GA20442@osiris.boeblingen.de.ibm.com>
--On Saturday, January 07, 2006 13:25:34 +0100 Heiko Carstens
<heiko.carstens@de.ibm.com> wrote:
>> The primary purpose of sharing page tables is improved performance for
>> large applications that share big memory areas between multiple
>> processes. It eliminates the redundant page tables and significantly
>> reduces the number of minor page faults. Tests show significant
>> performance improvement for large database applications, including those
>> using large pages. There is no measurable performance degradation for
>> small processes.
>
> Tried to get this running with CONFIG_PTSHARE and CONFIG_PTSHARE_PTE on
> s390x. Unfortunately it crashed on boot, because pt_share_pte
> returned a broken pte pointer:
The patch as submitted only works on i386 and x86_64. Sorry.
>> +pte_t *pt_share_pte(struct vm_area_struct *vma, unsigned long address,
>> pmd_t *pmd, + ...
>> + pmd_val(spmde) = 0;
>> + ...
>> + if (pmd_present(spmde)) {
>
> This is wrong. A pmd_val of 0 will make pmd_present return true on s390x
> which is not what you want.
> Should be pmd_clear(&spmde).
>
>> +pmd_t *pt_share_pmd(struct vm_area_struct *vma, unsigned long address,
>> pud_t *pud, + ...
>> + pud_val(spude) = 0;
>
> Should be pud_clear, I guess :)
Yes, you're right. pmd_clear() and pud_clear() would be more portable.
I'll make that change.
Dave McCracken
--
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:[~2006-01-07 18:09 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-05 16:19 Dave McCracken
2006-01-07 12:25 ` Heiko Carstens
2006-01-07 18:09 ` Dave McCracken [this message]
2006-01-08 12:09 ` Heiko Carstens
2006-01-08 14:04 ` Dave McCracken
2006-01-13 5:15 ` Brian Twichell
2006-01-13 22:34 ` Ray Bryant
2006-01-17 4:50 ` Brian Twichell
2006-01-25 4:14 ` Brian Twichell
2006-01-13 15:18 ` Phillip Susi
2006-01-14 20:45 ` Brian Twichell
2006-01-17 23:53 ` Robin Holt
2006-01-18 0:17 ` Dave Hansen
2006-01-18 6:11 ` Dave McCracken
2006-01-18 1:27 ` Chen, Kenneth W
2006-01-18 3:32 ` Robin Holt
2006-01-23 23:58 ` Ray Bryant
2006-01-24 0:16 ` Ray Bryant
2006-01-24 0:39 ` Andi Kleen
2006-01-24 0:51 ` Dave McCracken
2006-01-24 1:11 ` Andi Kleen
2006-01-24 1:26 ` Dave McCracken
2006-01-24 0:53 ` Ray Bryant
2006-01-24 1:00 ` Dave McCracken
2006-01-24 1:10 ` Andi Kleen
2006-01-24 1:23 ` Benjamin LaHaise
2006-01-24 1:38 ` Andi Kleen
2006-01-24 7:08 ` Arjan van de Ven
2006-01-24 7:06 ` Arjan van de Ven
2006-01-24 7:18 ` Andi Kleen
2006-01-27 18:16 ` Martin Bligh
2006-02-01 9:49 ` Nick Piggin
2006-01-24 14:48 ` Dave McCracken
2006-01-24 14:56 ` Arjan van de Ven
2006-01-24 0:19 ` Dave McCracken
2006-01-24 0:46 ` Ray Bryant
2006-01-24 23:43 ` Ray Bryant
2006-01-24 23:50 ` Dave McCracken
2006-01-25 0:21 ` Ray Bryant
2006-01-25 22:48 ` Ray Bryant
2006-01-25 22:52 ` Dave McCracken
2006-01-26 0:16 ` Ray Bryant
2006-01-26 0:58 ` Ray Bryant
2006-01-26 4:06 ` Robin Holt
2006-01-20 21:24 ` Hugh Dickins
2006-01-20 21:54 ` Chen, Kenneth W
2006-01-23 17:39 ` Dave McCracken
2006-01-23 20:19 ` Benjamin LaHaise
2006-01-24 17:50 ` Hugh Dickins
2006-01-24 18:07 ` Dave McCracken
2006-01-24 18:20 ` Hugh Dickins
2006-01-27 22:50 ` Brian Twichell
2006-01-30 18:46 ` Ray Bryant
2006-01-31 18:47 ` Brian Twichell
2006-01-31 19:18 ` Dave McCracken
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='2796BAF66E63B415FF1929B8@[10.1.1.4]' \
--to=dmccr@us.ibm.com \
--cc=akpm@osdl.org \
--cc=heiko.carstens@de.ibm.com \
--cc=hugh@veritas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox