From: Andries Brouwer <Andries.Brouwer@cwi.nl>
To: linux-kernel@vger.kernel.org
Subject: orlov/nobh
Date: Sun, 29 Aug 2004 02:36:32 +0200 [thread overview]
Message-ID: <20040829003630.GA19197@apps.cwi.nl> (raw)
> > +oldalloc Use old allocator for new inodes.
> > +orlov (*) Use Orlov allocator.
> > +
> > +nobh Do not attach buffer_heads to file pagecache.
>
> For these two it would be nice to include a description
> of why you'd want them or a pointer to something
> describing it. An admin trying to squeeze performance out
> of his server might see these options in such documentation
> and then want to know if they can help him.
See http://lwn.net/Articles/14633/ and http://lwn.net/Articles/14446/
for Orlov.
I am not aware of serious benchmark work. Simple direct tests
seem either to show no significant difference or to favor Orlov.
I have never seen a study on fragmentation after extended use
of both allocators.
Concerning nobh, I think that is a toy by Andrew, meant for
very large machines. He is in a better position to comment
(in fact on both orlov and nobh).
Andries
reply other threads:[~2004-08-29 0:36 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20040829003630.GA19197@apps.cwi.nl \
--to=andries.brouwer@cwi.nl \
--cc=linux-kernel@vger.kernel.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