linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Brian Twichell <tbrian@us.ibm.com>
To: Ray Bryant <raybry@mpdtxmail.amd.com>
Cc: Hugh Dickins <hugh@veritas.com>,
	Dave McCracken <dmccr@us.ibm.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: Tue, 31 Jan 2006 12:47:51 -0600	[thread overview]
Message-ID: <43DFB0D7.3070805@us.ibm.com> (raw)
In-Reply-To: <200601301246.27455.raybry@mpdtxmail.amd.com>

Ray Bryant wrote:

>On Friday 27 January 2006 16:50, Brian Twichell wrote:
><snip>
>
>  
>
>>Hi,
>>
>>We collected more granular performance data for the ppc64/hugepage case.
>>
>>CPI decreased by 3% when shared pagetables were used.  Underlying this was
>>a 7% decrease in the overall TLB miss rate.  The TLB miss rate for
>>hugepages decreased 39%.  TLB miss rates are calculated per instruction
>>executed.
>>
>>    
>>
>
>Interesting.
>
>Do you know if Dave's patch supports sharing of pte's for 2 MB pages on 
>X86_64?
>  
>
I believe it does.  Dave, can you confirm ?

>Was there a corresponding improvement in overall transaction throughput for 
>the hugetlb, shared pte case?    That is, did the 3% improvement in CPI 
>translate to a measurable improvement in the overall OLTP benchmark score?
>  
>
Yes.  My original post with performance data described a 3% improvement
in the ppc64/hugepage case.  This is a transaction throughput statement.

>(I'm assuming your 25-50% improvement measurements, as mentioned in a previous 
>note, was for small pages.)
>
>  
>
That's correct.



  reply	other threads:[~2006-01-31 18:48 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-01-05 16:19 [PATCH/RFC] Shared page tables Dave McCracken
2006-01-07 12:25 ` Heiko Carstens
2006-01-07 18:09   ` Dave McCracken
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 [this message]
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=43DFB0D7.3070805@us.ibm.com \
    --to=tbrian@us.ibm.com \
    --cc=akpm@osdl.org \
    --cc=dmccr@us.ibm.com \
    --cc=hugh@veritas.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=raybry@mpdtxmail.amd.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;
as well as URLs for NNTP newsgroup(s).