From: Ted Ts'o <tytso@mit.edu>
To: Rogier Wolff <R.E.Wolff@BitWizard.nl>
Cc: linux-ext4@vger.kernel.org
Subject: Re: fsck performance.
Date: Sun, 20 Feb 2011 14:34:06 -0500 [thread overview]
Message-ID: <20110220193406.GC3017@thunk.org> (raw)
In-Reply-To: <20110220170931.GB3017@thunk.org>
On Sun, Feb 20, 2011 at 12:09:31PM -0500, Ted Ts'o wrote:
>
> Ah, you're using tdb. Tdb can be really slow. It's been on my todo
> list to replace tdb with something else, but I haven't gotten around
> to it.
Hmm... after taking a quick look at the TDB sources, why don't you try
this. In lib/ext2fs/icount.c and e2fsck/dirinfo.c, try replacing the
flag TDB_CLEAR_IF_FIRST with TDB_NOLOCK | TDB_NOSYNC. i.e., try
replacing:
icount->tdb = tdb_open(fn, 0, TDB_CLEAR_IF_FIRST,
O_RDWR | O_CREAT | O_TRUNC, 0600);
with:
icount->tdb = tdb_open(fn, 0, TDB_NOLOCK | TDB_NOSYNC,
O_RDWR | O_CREAT | O_TRUNC, 0600);
Could you let me know what this does to the performance of e2fsck with
scratch files enabled?
Oh, and BTW, it would be useful if you tried configuring
tests/test_config so that it sets E2FSCK_CONFIG with a test
e2fsck.conf that enables the scratch files somewhere in tmp, and then
run the regression test suite with these changes.
If they work, and it solves the performance problem, let me know and
send me patches. If we can figure out some way of improving the
performance without needing to replace tdb, that would be great...
- Ted
next prev parent reply other threads:[~2011-02-20 19:34 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-20 9:06 fsck performance Rogier Wolff
2011-02-20 17:09 ` Ted Ts'o
2011-02-20 19:34 ` Ted Ts'o [this message]
2011-02-20 21:55 ` Rogier Wolff
2011-02-20 22:20 ` Ted Ts'o
2011-02-20 23:15 ` Rogier Wolff
2011-02-20 23:41 ` Ted Ts'o
2011-02-21 10:31 ` Amir Goldstein
2011-02-21 16:04 ` Paweł Brodacki
2011-02-21 18:00 ` Andreas Dilger
2011-02-22 10:20 ` Rogier Wolff
2011-02-22 13:36 ` Rogier Wolff
2011-02-22 13:54 ` Rogier Wolff
2011-02-22 16:32 ` Andreas Dilger
2011-02-22 22:13 ` Ted Ts'o
2011-02-23 4:44 ` Rogier Wolff
2011-02-23 11:32 ` Theodore Tso
2011-02-23 20:53 ` Rogier Wolff
2011-02-23 22:24 ` Andreas Dilger
2011-02-23 23:17 ` Ted Ts'o
2011-02-24 0:41 ` Andreas Dilger
2011-02-24 8:59 ` Rogier Wolff
2011-02-24 7:29 ` Rogier Wolff
2011-02-24 8:59 ` Amir Goldstein
2011-02-24 9:02 ` Rogier Wolff
2011-02-24 9:33 ` Amir Goldstein
2011-02-24 23:53 ` Rogier Wolff
2011-02-25 0:26 ` Daniel Taylor
2011-02-23 2:54 ` Rogier Wolff
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=20110220193406.GC3017@thunk.org \
--to=tytso@mit.edu \
--cc=R.E.Wolff@BitWizard.nl \
--cc=linux-ext4@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;
as well as URLs for NNTP newsgroup(s).