On Fri, Jul 17, 2015 at 3:38 AM, Qu Wenruo quwen...@cn.fujitsu.com wrote:
Hi all,
While I'm developing a new btrfs inband dedup mechanism, I found btrfsck and
kernel doing strange behavior for clone.
[Reproducer]
# mount /dev/sdc -t btrfs /mnt/test
# dd if=/dev/zero of=/mnt/test/file1
Zygo Blaxell wrote on 2015/07/21 23:49 -0400:
On Wed, Jul 22, 2015 at 09:49:52AM +0800, Qu Wenruo wrote:
Change subject to reflect the core of the conversation.
Zygo Blaxell wrote on 2015/07/21 18:14 -0400:
On Tue, Jul 21, 2015 at 02:52:38PM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on
On Wed, Jul 22, 2015 at 09:49:52AM +0800, Qu Wenruo wrote:
Change subject to reflect the core of the conversation.
Zygo Blaxell wrote on 2015/07/21 18:14 -0400:
On Tue, Jul 21, 2015 at 02:52:38PM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on 2015/07/21 00:55 -0400:
There's already a
Change subject to reflect the core of the conversation.
Zygo Blaxell wrote on 2015/07/21 18:14 -0400:
On Tue, Jul 21, 2015 at 02:52:38PM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on 2015/07/21 00:55 -0400:
An in-band dedup can avoid some of these problems, especially if it
intercepts writes
On Tue, Jul 21, 2015 at 02:52:38PM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on 2015/07/21 00:55 -0400:
An in-band dedup can avoid some of these problems, especially if it
intercepts writes before they make it to disk. There is no need for
complicated on-disk-extent-splitting algorithms if
Zygo Blaxell wrote on 2015/07/21 00:55 -0400:
On Mon, Jul 20, 2015 at 10:24:38AM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on 2015/07/19 03:23 -0400:
But I'm a little considered about the facts that extents get quite small(4K)
and the increasing number of backref/file extents may affect
On Mon, Jul 20, 2015 at 10:24:38AM +0800, Qu Wenruo wrote:
Zygo Blaxell wrote on 2015/07/19 03:23 -0400:
But I'm a little considered about the facts that extents get quite small(4K)
and the increasing number of backref/file extents may affect performance.
At the moment I just ignore any block
On Sat, Jul 18, 2015 at 07:35:31PM +0800, Liu Bo wrote:
On Fri, Jul 17, 2015 at 10:38:32AM +0800, Qu Wenruo wrote:
Hi all,
While I'm developing a new btrfs inband dedup mechanism, I found btrfsck and
kernel doing strange behavior for clone.
[Reproducer]
# mount /dev/sdc -t btrfs
Zygo Blaxell wrote on 2015/07/19 03:23 -0400:
On Sat, Jul 18, 2015 at 07:35:31PM +0800, Liu Bo wrote:
On Fri, Jul 17, 2015 at 10:38:32AM +0800, Qu Wenruo wrote:
Hi all,
While I'm developing a new btrfs inband dedup mechanism, I found btrfsck and
kernel doing strange behavior for clone.
On Fri, Jul 17, 2015 at 10:38:32AM +0800, Qu Wenruo wrote:
Hi all,
While I'm developing a new btrfs inband dedup mechanism, I found btrfsck and
kernel doing strange behavior for clone.
[Reproducer]
# mount /dev/sdc -t btrfs /mnt/test
# dd if=/dev/zero of=/mnt/test/file1 bs=4K count=4
#
Hi all,
While I'm developing a new btrfs inband dedup mechanism, I found btrfsck
and kernel doing strange behavior for clone.
[Reproducer]
# mount /dev/sdc -t btrfs /mnt/test
# dd if=/dev/zero of=/mnt/test/file1 bs=4K count=4
# sync
# ~/xfstests/src/cloner -s 4096 -l 4096 /mnt/test/file1
11 matches
Mail list logo
