From: "Frank Ch. Eigler" <fche@redhat.com>
To: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Junio C Hamano <gitster@pobox.com>,
Git Mailing List <git@vger.kernel.org>
Subject: Re: reducing prune sync()s
Date: Thu, 29 May 2008 21:50:43 -0400 [thread overview]
Message-ID: <20080530015043.GB4032@redhat.com> (raw)
In-Reply-To: <alpine.LFD.1.10.0805291727490.3141@woody.linux-foundation.org>
Hi --
On Thu, May 29, 2008 at 05:32:30PM -0700, Linus Torvalds wrote:
> [...] Side note: a lot of systems make "fsync()" pretty expensive
> too. It's one of my main disagreements with most log-based
> filesystems - fsync() can in theory be fast, but almost always
> implies flushing the whole log, even if 99.9% of that log is totally
> unrelated to the actual file you want to fsync(). [...]
The scenario where I ran into this was different: a usb-drive
filesystem was busy running receiving backups, collecting, oh, several
GB of dirty data, while git was working on a normal local disk on a
separate filesystem. The system-wide git sync unnecessarily blocked
on the usb filesystem too.
- FChE
next prev parent reply other threads:[~2008-05-30 1:53 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-29 20:57 reducing prune sync()s Frank Ch. Eigler
2008-05-30 0:27 ` Linus Torvalds
2008-05-30 0:32 ` Linus Torvalds
2008-05-30 1:50 ` Frank Ch. Eigler [this message]
2008-05-30 20:07 ` Florian Weimer
2008-05-30 1:51 ` David Dillow
2008-05-30 2:17 ` Linus Torvalds
2008-05-30 2:30 ` Linus Torvalds
2008-05-30 15:25 ` Frank Ch. Eigler
2008-05-30 15:57 ` Linus Torvalds
2008-05-30 16:08 ` [PATCH 1/2] Make pack creation always fsync() the result Linus Torvalds
2008-05-30 16:11 ` [PATCH 2/2] Remove now unnecessary 'sync()' calls Linus Torvalds
2008-05-30 20:27 ` [PATCH 1/2] Make pack creation always fsync() the result Nicolas Pitre
2008-05-31 14:19 ` Frank Ch. Eigler
2008-06-02 22:23 ` Linus Torvalds
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=20080530015043.GB4032@redhat.com \
--to=fche@redhat.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=torvalds@linuxfoundation.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 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.