All of lore.kernel.org
 help / color / mirror / Atom feed
From: Linus Torvalds <torvalds@osdl.org>
To: "Bill Rugolsky Jr." <brugolsky@telemetry-investments.com>
Cc: Paul Venezia <pvenezia@jpj.net>,
	Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Ulrich Drepper <drepper@redhat.com>
Subject: Re: ext3 performance inconsistencies, 2.4/2.6
Date: Tue, 4 Nov 2003 13:40:51 -0800 (PST)	[thread overview]
Message-ID: <Pine.LNX.4.44.0311041335200.20373-100000@home.osdl.org> (raw)
In-Reply-To: <20031104212813.GC30612@ti19.telemetry-investments.com>


On Tue, 4 Nov 2003, Bill Rugolsky Jr. wrote:
> 
> Well, I'm too lazy to wait for a long test, but with a mere
> 100MB file, on 1GHz P3:
> 
> Version  1.03       ------Sequential Output------ --Sequential Input- --Random-
>                     -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
> NPTL          100M  7735  99 127068  98 63048  84  7890  98 +++++ +++ +++++ +++
> LinuxThreads  100M 11000  99 127928  97 59075  84 11290  98 +++++ +++ +++++ +++
> 
> So something is amiss.

Ok, so NPTL locking (even in the absense of any threads and thus any 
contention) seems to be noticeably higher-overhead than the old 
LinuxThreads. 

90% of the overhead of a putc()/getc() implementation these days is likely
just locking. Even so, this implies that NPTL locking is about twice as 
expensive as the old LinuxThreads one.

Don't ask me why. But I'm cc'ing Uli, who can probably tell us. Maybe the 
RH-9 libraries are just not very good, and LinuxThreads has had a lot 
longer to optimize their lock behaviour..

			Linus



  reply	other threads:[~2003-11-04 21:41 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-11-04 19:10 ext3 performance inconsistencies, 2.4/2.6 Paul Venezia
2003-11-04 19:36 ` Linus Torvalds
2003-11-04 20:20   ` Bill Rugolsky Jr.
2003-11-04 20:30     ` Linus Torvalds
2003-11-04 21:07       ` Paul Venezia
2003-11-04 21:28         ` Bill Rugolsky Jr.
2003-11-04 21:40           ` Linus Torvalds [this message]
2003-11-04 22:00             ` Ulrich Drepper
2003-11-04 22:31               ` Linus Torvalds
2003-11-04 23:48                 ` Ulrich Drepper
2003-11-04 23:56                   ` Linus Torvalds
2003-11-05  0:58                   ` jlnance
2003-11-05  7:08                     ` Jakub Jelinek
2003-11-04 22:19             ` Bill Rugolsky Jr.
2003-11-04 22:26               ` Bill Rugolsky Jr.
2003-11-05  7:14               ` Jakub Jelinek
2003-11-04 21:39       ` Bill Rugolsky Jr.

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=Pine.LNX.4.44.0311041335200.20373-100000@home.osdl.org \
    --to=torvalds@osdl.org \
    --cc=brugolsky@telemetry-investments.com \
    --cc=drepper@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pvenezia@jpj.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.