public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Robert Love <rml@tech9.net>
To: Dave Jones <davej@suse.de>
Cc: Andrew Morton <akpm@zip.com.au>,
	Linus Torvalds <torvalds@transmeta.com>,
	viro@math.psu.edu, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] 2.5: push BKL out of llseek
Date: 29 Jan 2002 21:37:57 -0500	[thread overview]
Message-ID: <1012358278.817.83.camel@phantasy> (raw)
In-Reply-To: <20020130032138.H16379@suse.de>
In-Reply-To: <Pine.LNX.4.33.0201291602510.1747-100000@penguin.transmeta.com>, <Pine.LNX.4.33.0201291602510.1747-100000@penguin.transmeta.com> <1012351309.813.56.camel@phantasy> <3C574BD1.E5343312@zip.com.au> <1012357211.817.67.camel@phantasy>  <20020130032138.H16379@suse.de>

On Tue, 2002-01-29 at 21:21, Dave Jones wrote:

>  did you benchmark with anything other than dbench ?

No, and I really don't want to hear how dbench is a terrible benchmark. 
I didn't craft the patch around dbench and I think, here at least,
dbench is an OK benchmark.  I ran it numerous times over multiple client
loads.

I think its clear there won't be a negative impact, because:

- acquiring the inode semaphore isn't any heavier (in the acquire
  case) than the BKL

- the lock contention on each inode semaphore is relatively
  zero

- besides just scaling badly with the using a global lock against
  all inodes, we use the BKL which in such workloads is already
  highly contested.

That said, I did do some lock profiling and latency tests.  Contention
was near-zero, but I only did 2-way testing.  Under the preemptible
kernel, while running dbench, scheduling latency improved 8.9%.

	Robert Love


  reply	other threads:[~2002-01-30  2:32 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-01-30  0:00 [PATCH] 2.5: push BKL out of llseek Robert Love
2002-01-30  0:09 ` Linus Torvalds
2002-01-30  0:41   ` Robert Love
2002-01-30  0:52     ` Linus Torvalds
2002-01-30  2:24       ` Robert Love
2002-01-30  1:26     ` Andrew Morton
2002-01-30  2:16       ` Linus Torvalds
2002-01-30  2:20       ` Robert Love
2002-01-30  2:20         ` Andrew Morton
2002-01-30  2:21         ` Dave Jones
2002-01-30  2:37           ` Robert Love [this message]
2002-01-30  2:50         ` Nigel Gamble
2002-01-30  3:19           ` Andrew Morton
2002-01-30  9:34             ` Nigel Gamble
2002-01-30 10:36         ` Russell King
2002-01-30  4:54   ` Alexander Viro
2002-01-30  8:00     ` Trond Myklebust
2002-01-30 13:39       ` Robert Love
2002-01-30  4:50 ` Anton Blanchard
2002-01-30  5:03 ` Robert Love
  -- strict thread matches above, loose matches on Subject: below --
2002-01-30 21:14 Martin Wirth
2002-01-31 15:39 Martin Wirth
2002-01-31 21:06 ` Nigel Gamble
2002-02-01 19:29 John Hawkes

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=1012358278.817.83.camel@phantasy \
    --to=rml@tech9.net \
    --cc=akpm@zip.com.au \
    --cc=davej@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@transmeta.com \
    --cc=viro@math.psu.edu \
    /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