public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Rik van Riel <riel@redhat.com>
To: Eric Dumazet <dada1@cosmosbay.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>, shak <dshaks@redhat.com>
Subject: Re: [PATCH] lazy freeing of memory through MADV_FREE
Date: Fri, 20 Apr 2007 23:58:32 -0400	[thread overview]
Message-ID: <46298BE8.8020900@redhat.com> (raw)
In-Reply-To: <46295F59.8000506@cosmosbay.com>

Eric Dumazet wrote:
> Rik van Riel a écrit :
>> Andrew Morton wrote:
>>> On Fri, 20 Apr 2007 17:38:06 -0400
>>> Rik van Riel <riel@redhat.com> wrote:
>>>
>>>> Andrew Morton wrote:
>>>>
>>>>> I've also merged Nick's "mm: madvise avoid exclusive mmap_sem".
>>>>>
>>>>> - Nick's patch also will help this problem.  It could be that your 
>>>>> patch
>>>>>   no longer offers a 2x speedup when combined with Nick's patch.
>>>>>
>>>>>   It could well be that the combination of the two is even better, 
>>>>> but it
>>>>>   would be nice to firm that up a bit.  
>>>> I'll test that.
>>>
>>> Thanks.
>>
>> Well, good news.
>>
>> It turns out that Nick's patch does not improve peak
>> performance much, but it does prevent the decline when
>> running with 16 threads on my quad core CPU!
>>
>> We _definately_ want both patches, there's a huge benefit
>> in having them both.
>>
>> Here are the transactions/seconds for each combination:
>>
>>    vanilla   new glibc  madv_free kernel   madv_free + mmap_sem
>> threads
>>
>> 1     610         609             596                545
> 
> 545 tps versus 610 tps for one thread ? It seems quite bad, no ?
> 
> Could you please find an explanation for this ?

I have no idea why this happens.  Especially the last one,
going from a write lock to a read lock on the mmap_sem
should not make ANY difference whatsoever since we're
running single threaded!

>> 2    1032        1136            1196               1200
>> 4    1070        1128            2014               2024
>> 8    1000        1088            1665               2087
>> 16    779        1073            1310               1999

Performance with 2 database threads is way better though,
and performance with 4 or more threads more than doubles...

If you have an explanation on why single threaded performance
went down a little on my quad core system, please let me know.

Does performance suffer at all on a real UP system?

-- 
Politics is the struggle between those who want to make their country
the best in the world, and those who believe it already is.  Each group
calls the other unpatriotic.

  reply	other threads:[~2007-04-21  4:00 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-04-17  7:15 [PATCH] lazy freeing of memory through MADV_FREE Rik van Riel
2007-04-19 21:15 ` [PATCH] lazy freeing of memory through MADV_FREE 2/2 Rik van Riel
2007-04-20 21:03   ` Andrew Morton
2007-04-20 21:24     ` Ulrich Drepper
2007-04-21  7:37       ` Hugh Dickins
2007-04-21 16:32         ` Ulrich Drepper
2007-04-20 20:57 ` [PATCH] lazy freeing of memory through MADV_FREE Andrew Morton
2007-04-20 21:38   ` Rik van Riel
2007-04-20 22:06     ` Andrew Morton
2007-04-20 23:52       ` Rik van Riel
2007-04-21  0:48         ` Eric Dumazet
2007-04-21  3:58           ` Rik van Riel [this message]
2007-04-21  7:12         ` Jakub Jelinek
2007-04-23  4:36           ` Nick Piggin
2007-04-22  2:36         ` Nick Piggin
2007-04-22  2:50           ` Nick Piggin
2007-04-22  6:31           ` Rik van Riel
2007-04-23  0:16             ` Nick Piggin
2007-04-23  3:53               ` Rik van Riel
2007-04-23  3:58                 ` Nick Piggin
2007-04-23 10:07                   ` Nick Piggin
2007-04-23 10:12                     ` Rik van Riel
2007-04-23  3:59                 ` Rik van Riel
2007-04-23  9:20                   ` Rik van Riel
2007-04-23 10:21                     ` Nick Piggin
2007-04-23 10:31                       ` Rik van Riel
2007-04-23 10:35                         ` Nick Piggin
2007-04-23 10:44                           ` Rik van Riel
2007-04-24  1:15                             ` Nick Piggin
2007-04-24  1:58                               ` Rik van Riel
2007-04-24  2:16                                 ` Nick Piggin
2007-04-24  4:42                                 ` Paul Mackerras
2007-04-24  5:13                                   ` Rik van Riel
2007-04-24  2:53                           ` Rik van Riel
2007-04-24  3:08                             ` Andrew Morton
2007-04-23 10:44                       ` Jakub Jelinek
2007-04-23 11:45                     ` Rik van Riel
2007-04-23  4:28           ` Rik van Riel
2007-04-21  7:24     ` Hugh Dickins
2007-04-21 18:06       ` Rik van Riel
2007-04-22  8:18 ` Andrew Morton
2007-04-22  9:16   ` Christoph Hellwig
2007-04-22 16:55     ` Ulrich Drepper

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=46298BE8.8020900@redhat.com \
    --to=riel@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=dada1@cosmosbay.com \
    --cc=dshaks@redhat.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