linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Martin J. Bligh" <mbligh@aracnet.com>
To: Andrew Morton <akpm@digeo.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: 2.5.70-mm1
Date: Wed, 28 May 2003 23:23:23 -0700	[thread overview]
Message-ID: <1980000.1054189401@[10.10.2.4]> (raw)
In-Reply-To: <20030527004255.5e32297b.akpm@digeo.com>

> . A number of fixes against the ext3 work which Alex and I have been doing.
>   This code is stable now.  I'm using it on my main SMP desktop machine.
> 
>   These are major changes to a major filesystem.  I would ask that
>   interested parties now subject these patches to stresstesting and to
>   performance testing.  The performance gains on SMP will be significant.

Sexy. SDET beats the hell out of this, and is much improved:

SDET 128  (see disclaimer)
                           Throughput    Std. Dev
               2.5.66-mm2       100.0%         0.6%
          2.5.66-mm2-ext3         3.9%         0.4%

SDET 128  (see disclaimer)
                           Throughput    Std. Dev
          2.5.70-mm1-ext2       100.0%         0.1%
          2.5.70-mm1-ext3        22.7%         2.0%


diffprofile 2.5.70-mm1-ext2 2.5.70-mm1-ext3
(for SDET 128: + worse with ext3, - better.)
   1857406   245.2% total
   1531720   431.5% default_idle
    106589     0.0% .text.lock.transaction
     40119     0.0% do_get_write_access
     37170     0.0% journal_dirty_metadata
     35031  6560.1% __down
     24412  8030.3% .text.lock.attr
     19535  2556.9% __wake_up
     19201   907.0% schedule
     11344     0.0% start_this_handle
     10104     0.0% journal_add_journal_head
     10007     0.0% .text.lock.sched
      7352     0.0% journal_stop
      5949  99150.0% prepare_to_wait_exclusive
      5867  3008.7% __blk_queue_bounce
      4724   335.3% __find_get_block
      4618     0.0% ext3_get_inode_loc
      4410     0.0% journal_dirty_data
      3754   590.3% __find_get_block_slow
      3079   738.4% .text.lock.base
      2176     0.0% ext3_do_update_inode
      2132  11844.4% unlock_buffer
      1995     0.0% ext3_journal_start
      1888     0.0% ext3_orphan_del
      1783   145.2% __brelse
      1642  4829.4% blk_run_queues
      1555     0.0% ext3_orphan_add
      1495     0.0% ext3_new_inode
      1430     0.0% ext3_reserve_inode_write
      1412     0.0% journal_destroy_handle_cache
      1344     0.0% journal_cancel_revoke
      1279     0.0% journal_unmap_buffer
      1198     0.0% ext3_free_blocks
...
     -1057   -88.4% .text.lock.highmem
     -1064   -24.5% remove_shared_vm_struct
     -1112   -52.8% .text.lock.dec_and_lock
     -1126  -100.0% ext2_new_inode
     -1516  -100.0% grab_block
     -1594   -28.3% path_lookup
     -1599   -28.0% atomic_dec_and_lock
     -1660   -10.4% copy_page_range
     -1695   -15.4% __d_lookup
     -2585   -23.6% release_pages
     -2614   -13.5% zap_pte_range
     -9758   -20.7% page_add_rmap
    -26185   -25.3% page_remove_rmap

--
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:"aart@kvack.org"> aart@kvack.org </a>

  parent reply	other threads:[~2003-05-29  6:23 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-05-27  7:42 2.5.70-mm1 Andrew Morton
2003-05-27 10:38 ` 2.5.70-mm1 Marc-Christian Petersen
2003-05-27 20:33   ` 2.5.70-mm1 Ed Tomlinson
2003-05-27 20:49     ` 2.5.70-mm1 Andrew Morton
2003-05-27 23:05       ` 2.5.70-mm1 Ed Tomlinson
2003-05-28 17:10 ` 2.5.70-mm1 Mingming Cao
2003-05-28 19:44   ` 2.5.70-mm1 Andrew Morton
2003-05-29  6:23 ` Martin J. Bligh [this message]
2003-05-29 18:40   ` 2.5.70-mm1 Martin J. Bligh
2003-05-29 18:52     ` 2.5.70-mm1 Andrew Morton
2003-05-29 20:30       ` 2.5.70-mm1 Martin J. Bligh
2003-05-29 21:14         ` 2.5.70-mm1 Andrew Morton
2003-05-30 15:51           ` 2.5.70-mm1 Martin J. Bligh
2003-05-30 16:43             ` 2.5.70-mm1 Andrew Morton
2003-05-30 23:51               ` 2.5.70-mm1 Martin J. Bligh
2003-06-03  6:34                 ` ext3 semaphore tracing Martin J. Bligh
2003-05-28 13:26 2.5.70-mm1 Downing, Thomas

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='1980000.1054189401@[10.10.2.4]' \
    --to=mbligh@aracnet.com \
    --cc=akpm@digeo.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