Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages.

[RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-04-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Mingming Cao <hidden> · 2010-05-04
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Ric Wheeler <hidden> · 2010-05-04
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Christoph Hellwig <hch@infradead.org> · 2010-05-04
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · tytso@mit.edu · 2010-06-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Ric Wheeler <hidden> · 2010-06-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · tytso@mit.edu · 2010-06-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Ric Wheeler <hidden> · 2010-06-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Andreas Dilger <hidden> · 2010-06-30
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Jan Kara <jack@suse.cz> · 2010-07-21
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-08-03
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Christoph Hellwig <hch@infradead.org> · 2010-08-03
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-08-04
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Jan Kara <jack@suse.cz> · 2010-08-03
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Avi Kivity <hidden> · 2010-08-03
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · "Ted Ts'o" <tytso@mit.edu> · 2010-08-04
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Avi Kivity <hidden> · 2010-08-05
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · "Ted Ts'o" <tytso@mit.edu> · 2010-08-05
Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Mingming Cao <hidden> · 2010-05-04
[RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-06-29
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · "Ted Ts'o" <tytso@mit.edu> · 2010-08-05
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · "Ted Ts'o" <tytso@mit.edu> · 2010-08-05
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-08-06
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Ric Wheeler <hidden> · 2010-08-06
[RFC v3] ext4: Combine barrier requests coming from fsync · Darrick J. Wong <hidden> · 2010-08-09
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Christoph Hellwig <hch@infradead.org> · 2010-08-09
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Darrick J. Wong <hidden> · 2010-08-16
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Darrick J. Wong <hidden> · 2010-08-19
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Christoph Hellwig <hch@infradead.org> · 2010-08-19
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Tejun Heo <tj@kernel.org> · 2010-08-19
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Tejun Heo <tj@kernel.org> · 2010-08-19
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Andreas Dilger <hidden> · 2010-08-09
Re: [RFC v3] ext4: Combine barrier requests coming from fsync · Darrick J. Wong <hidden> · 2010-08-09
[RFC v4] ext4: Coordinate fsync requests · Darrick J. Wong <hidden> · 2010-08-19
Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-08-23
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-09-23
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Andreas Dilger <adilger.kernel@dilger.ca> · 2010-09-24
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Ric Wheeler <hidden> · 2010-09-24
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-09-27
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-10-08
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Ric Wheeler <hidden> · 2010-10-08
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-10-11
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Christoph Hellwig <hch@lst.de> · 2010-10-12
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-10-15
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Christoph Hellwig <hch@lst.de> · 2010-10-15
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-10-16
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · "Ted Ts'o" <tytso@mit.edu> · 2010-10-11
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Darrick J. Wong <hidden> · 2010-10-18
Re: Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] · Christoph Hellwig <hch@lst.de> · 2010-10-19
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-08-06
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · "Ted Ts'o" <tytso@mit.edu> · 2010-08-06
Re: [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages. · Darrick J. Wong <hidden> · 2010-08-09

From: Christoph Hellwig <hch@infradead.org>
Date: 2010-08-03 09:01:58
Also in: lkml

On Mon, Aug 02, 2010 at 05:09:39PM -0700, Darrick J. Wong wrote:

Well... on my fsync-happy workloads, this seems to cut the barrier count down
by about 20%, and speeds it up by about 20%.

Care to share the test case for this?  I'd be especially interesting on
how it behaves with non-draining barriers / cache flushes in fsync.

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help