linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* Re: Poor interactive performance with I/O loads with fsync()ing
       [not found]           ` <4BC1E4A4.1070103@redhat.com>
@ 2010-04-11 16:35             ` Ben Gamari
  2010-04-11 17:20               ` Andi Kleen
  0 siblings, 1 reply; 2+ messages in thread
From: Ben Gamari @ 2010-04-11 16:35 UTC (permalink / raw)
  To: Avi Kivity, linux-btrfs
  Cc: Andi Kleen, Arjan van de Ven, linux-kernel, tytso, npiggin, mingo,
	Ruald Andreae, Jens Axboe, Olly Betts, martin f krafft

On Sun, 11 Apr 2010 18:03:00 +0300, Avi Kivity <avi@redhat.com> wrote:
> On 04/09/2010 05:56 PM, Ben Gamari wrote:
> > On Mon, 29 Mar 2010 00:08:58 +0200, Andi Kleen<andi@firstfloor.org>  wrote:
> >    
> >> Ben Gamari<bgamari.foss@gmail.com>  writes:
> >> ext4/XFS/JFS/btrfs should be better in this regard
> >>
> >>      
> > I am using btrfs, so yes, I was expecting things to be better. Unfortunately,
> > the improvement seems to be non-existent under high IO/fsync load.
> >
> 
> btrfs is known to perform poorly under fsync.
> 
Has the reason for this been identified? Judging from the nature of metadata
loads, it would seem that it should be substantially easier to implement
fsync() efficiently.

- Ben


^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: Poor interactive performance with I/O loads with fsync()ing
  2010-04-11 16:35             ` Poor interactive performance with I/O loads with fsync()ing Ben Gamari
@ 2010-04-11 17:20               ` Andi Kleen
  0 siblings, 0 replies; 2+ messages in thread
From: Andi Kleen @ 2010-04-11 17:20 UTC (permalink / raw)
  To: Ben Gamari
  Cc: Avi Kivity, linux-btrfs, Andi Kleen, Arjan van de Ven,
	linux-kernel, tytso, npiggin, mingo, Ruald Andreae, Jens Axboe,
	Olly Betts, martin f krafft

> Has the reason for this been identified? Judging from the nature of metadata
> loads, it would seem that it should be substantially easier to implement
> fsync() efficiently.

By design a copy on write tree fs would need to flush a whole
tree hierarchy on a sync. btrfs avoids this by using a special
log for fsync, but that causes more overhead if you have that
log on the same disk.  So IO subsystem will do more work.

It's a bit like JBD data journaling.

However it should not have the stalls inherent in ext3's journaling.

-Andi
-- 
ak@linux.intel.com -- Speaking for myself only.

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2010-04-11 17:20 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <4b9fa440.12135e0a.7fc8.ffffe745@mx.google.com>
     [not found] ` <4baeaee5.c5c2f10a.7187.2688@mx.google.com>
     [not found]   ` <20100327204233.0d84542a@infradead.org>
     [not found]     ` <4baf624c.48c3f10a.16d0.ffffccb8@mx.google.com>
     [not found]       ` <87y6hcyu85.fsf@basil.nowhere.org>
     [not found]         ` <4bbf401e.a3b9e70a.13f3.4460@mx.google.com>
     [not found]           ` <4BC1E4A4.1070103@redhat.com>
2010-04-11 16:35             ` Poor interactive performance with I/O loads with fsync()ing Ben Gamari
2010-04-11 17:20               ` Andi Kleen

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).