Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 21a4edf..94218ac 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2063,7 +2063,7 @@ static int sd_snapshot_goto
Nothing big, just two simple patches to enable this commind for sheepdog.
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Liu Yuan (2):
sheepdog: fix snapshot tag initialization
sheepdog
Just call sd_create_branch() to rollback the image is good enough
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |8
On 06/06/2013 08:46 PM, Kevin Wolf wrote:
Am 06.06.2013 um 13:57 hat Liu Yuan geschrieben:
Just call sd_create_branch() to rollback the image is good enough
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa
On 06/06/2013 08:46 PM, Kevin Wolf wrote:
I'm not sure how snapshots work internally for Sheepdog, but it seems
odd to me that you need to do this only for disk-only snapshots, but not
when the snapshot has VM state. (Also, note that 'qemu-img snapshot -a'
works on images with a VM state, so
On 06/07/2013 03:31 PM, Kevin Wolf wrote:
Am 06.06.2013 um 15:09 hat Liu Yuan geschrieben:
On 06/06/2013 08:46 PM, Kevin Wolf wrote:
Am 06.06.2013 um 13:57 hat Liu Yuan geschrieben:
Just call sd_create_branch() to rollback the image is good enough
Cc: qemu-devel@nongnu.org
Cc: MORITA
morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Liu Yuan (2):
sheepdog: fix snapshot tag initialization
sheepdog: support 'qemu-img snapshot -a'
block/sheepdog.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
--
1.7.9.5
Just call sd_create_branch() to rollback the image is good enough
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 17
Reviewed-by: Kevin Wolf kw...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 21a4edf..94218ac 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2063,7
On 06/07/2013 11:22 PM, Kevin Wolf wrote:
Am 07.06.2013 um 15:48 hat Liu Yuan geschrieben:
On 06/07/2013 03:31 PM, Kevin Wolf wrote:
Am 06.06.2013 um 15:09 hat Liu Yuan geschrieben:
On 06/06/2013 08:46 PM, Kevin Wolf wrote:
Am 06.06.2013 um 13:57 hat Liu Yuan geschrieben:
Only when the write
to enable this commind for sheepdog.
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Liu Yuan (2):
sheepdog: fix snapshot tag initialization
sheepdog: support 'qemu-img snapshot -a'
block
Reviewed-by: Kevin Wolf kw...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 21a4edf..94218ac 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2063,7
)
This will fix the possible bug that QEMU exit between 2 and 3 in the old code
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |9
On 06/08/2013 12:48 AM, Kevin Wolf wrote:
Hm, yes, I was confused. :-)
Anyway, the options stay the same: Either C1 must somehow inherit the VM
state from A on the Sheepdog level, or we must make sure to get this
order:
1. Switch to (read-only) snapshot A
2. Load the VM state
3. Create
On 06/08/2013 01:20 AM, Liu Yuan wrote:
v3:
- fix sheepdog's loadvm handling, don't rely on the write to create branch
Oops, seems this version has problems. Please drop it.
Thanks,
Yuan
, it is not snapshot anymore.
Nothing big, just two simple patches to enable this commind for sheepdog.
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Liu Yuan (2):
sheepdog: fix snapshot tag
Reviewed-by: Kevin Wolf kw...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 21a4edf..94218ac 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2063,7
)
This will fix the possible bug that QEMU exit between 2 and 3 in the old code
Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 12
, passing it to sheep
daemon is just one extra null effect operation. So no compatibility problem.
With this patch, sheepdog can provide erasure coded volume for QEMU VM.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block
patch that allow passing copy_policy in request header.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 15 +--
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/block/sheepdog.c b
This patch set makes use of copy_policy in struct SheepdogInode in order to
support recently introduced erasure coding in sheepdog.
Thanks
Yuan
Hello all,
Sheepdog is a distributed storage system that QEMU VM and RESTful services (in
progress).
Erasure coding is now seamlessly functional with all other features such as
snapshot/clone/cluster-wide/multi-disk/auto-healing e.c with following
characteristics:
1 Data is erasure coded
On Wed, Oct 16, 2013 at 03:38:36PM +0800, Liu Yuan wrote:
This patch set makes use of copy_policy in struct SheepdogInode in order to
support recently introduced erasure coding in sheepdog.
Thanks
Yuan
Ping ?
...@lab.ntt.co.jp
Is it okay to add Liu Yuan tailai...@taobao.com to the sheepdog
maintainer too? He is a co-maintainer of the sheepdog project with me
and very familiar with sheepdog internals.
I'd like to appear to be 'Liu Yuan namei.u...@gmail.com' which is a long-term
reachable mail address, if allowed
v2:
- merge the reserved bits
This patch set makes use of copy_policy in struct SheepdogInode in order to
support recently introduced erasure coding volume in sheepdog.
Thanks
Yuan
Liu Yuan (2):
sheepdog: explicitly set copies as type uint8_t
sheepdog: pass copy_policy in the request
patch that allow passing copy_policy in request header.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 16 +---
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/block/sheepdog.c b
, passing it to sheep
daemon is just one extra null effect operation. So no compatibility problem.
With this patch, sheepdog can provide erasure coded volume for QEMU VM.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block
servers crash unexpectedly.
v5:
- Use AioContext timer for co_aio_sleep_ns().
Tested-and-reviewed-by: Liu Yuan namei.u...@gmail.com
Thanks
Yuan
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block/sheepdog.c | 110
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
v2:
- fix a typo in comment and commit log
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: pass copy_policy in the request
sheepdog: refactor do_sd_create()
block/sheepdog.c | 45
, passing it to sheep
daemon is just one extra null effect operation. So no compatibility problem.
With this patch, sheepdog can provide erasure coded volume for QEMU VM.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block
On Tue, Oct 29, 2013 at 04:23:33PM +0800, Liu Yuan wrote:
v2:
- fix a typo in comment and commit log
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Oops, please ignore this patch set because I formated
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
v2:
- fix a typo in comment and commit log
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block
On Thu, Oct 31, 2013 at 04:41:05AM +0900, MORITA Kazutaka wrote:
At Tue, 29 Oct 2013 16:25:52 +0800,
Liu Yuan wrote:
Sheepdog support two kinds of redundancy, full replication and erasure
coding.
# create a fully replicated vdi with x copies
-o redundancy=x (1 = x = SD_MAX_COPIES
v3:
- rework is_numeric
v2:
- fix a typo in comment and commit log
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Reviewed-by: Benoit Canet ben...@irqsave.net
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Reviewed-by: Benoit Canet ben...@irqsave.net
Signed-off-by: Liu Yuan
of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block/sheepdog.c | 127 +
include/block/block_int.h |1 +
2 files changed, 105 insertions(+), 23 deletions(-)
--
1.7.9.5
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Reviewed-by: Benoit Canet ben...@irqsave.net
Signed-off-by: Liu Yuan
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Reviewed-by: Benoit Canet ben...@irqsave.net
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37
On Thu, Oct 31, 2013 at 01:49:26PM +0800, Liu Yuan wrote:
v4:
- fix do_sd_create that forgot to pass nr_copies
- fix parse_redundancy dealing with replicated vdi
Hello Kevin,
Could you pick these two patches to your block tree (so QEMU next release
can enjoy the full erasure coding
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
On Fri, Nov 01, 2013 at 11:06:20PM +0800, Liu Yuan wrote:
v5:
- use pstrcpy instead of strncpy
- fix a segfalt for 'null' string option string
Oops, I sent the old patch set. Please ignore it I'll send a new v5.
Thanks
Yuan
specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block/sheepdog.c | 127 +
include
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block/sheepdog.c | 127 +
include
On Wed, Jul 24, 2013 at 04:56:24PM +0900, MORITA Kazutaka wrote:
Currently, if a sheepdog server exits, all the connecting VMs need to
be restarted. This series implements a feature to reconnect the
server, and enables us to do online sheepdog upgrade and avoid
restarting VMs when sheepdog
On Wed, Jul 24, 2013 at 06:07:21PM +0900, MORITA Kazutaka wrote:
At Wed, 24 Jul 2013 16:28:30 +0800,
Liu Yuan wrote:
On Wed, Jul 24, 2013 at 04:56:24PM +0900, MORITA Kazutaka wrote:
Currently, if a sheepdog server exits, all the connecting VMs need to
be restarted. This series
On Wed, Jul 24, 2013 at 11:42:49PM +0800, Liu Yuan wrote:
On Wed, Jul 24, 2013 at 06:07:21PM +0900, MORITA Kazutaka wrote:
At Wed, 24 Jul 2013 16:28:30 +0800,
Liu Yuan wrote:
On Wed, Jul 24, 2013 at 04:56:24PM +0900, MORITA Kazutaka wrote:
Currently, if a sheepdog server exits, all
When signed int compared to unsigned int, signed int will be converted to
unsigned int.
For example, (-1 sizeof(structure)) always true because -1 in the left is
converted into unsigned int, thus this restule in unexpected true.
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
Hello Kazutaka,
I have two patches fixing the problems I found on my testing and they are
complementary patches. Please consider sending them on top of your patch set.
Thanks
Yuan
qemu_co_send() in the add_aio_request might fail if connection is closed. In
this case we should it requests into failed list to be resended later when
connection is repaired.
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |8 ++--
1 file changed, 6 insertions(+), 2
On Thu, Jul 25, 2013 at 02:53:57PM +0900, MORITA Kazutaka wrote:
At Thu, 25 Jul 2013 13:25:33 +0800,
Liu Yuan wrote:
Hello Kazutaka,
I have two patches fixing the problems I found on my testing and they are
complementary patches. Please consider sending them on top of your patch
On Thu, Jul 25, 2013 at 05:31:58PM +0900, MORITA Kazutaka wrote:
If qemu_co_recv/send doesn't return the specified length, it means
that an error happened.
Signed-off-by: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
---
block/sheepdog.c | 16
1 file changed, 8
On Thu, Jul 25, 2013 at 04:46:36PM +0800, Liu Yuan wrote:
On Thu, Jul 25, 2013 at 05:31:58PM +0900, MORITA Kazutaka wrote:
If qemu_co_recv/send doesn't return the specified length, it means
that an error happened.
Signed-off-by: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
On Thu, Jul 25, 2013 at 05:32:04PM +0900, MORITA Kazutaka wrote:
This patch tries to cancel aio requests in pending queue and failed
queue. When the sheepdog driver cannot cancel the requests, it waits
for them to be completed.
Signed-off-by: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
On Thu, Jul 25, 2013 at 05:32:02PM +0900, MORITA Kazutaka wrote:
This introduces a failed request queue and links all the inflight
requests to the list after network error happens. After QEMU
reconnects to the sheepdog server successfully, the sheepdog block
driver will retry all the requests
On Thu, Jul 25, 2013 at 09:53:14PM +0900, MORITA Kazutaka wrote:
At Thu, 25 Jul 2013 17:13:46 +0800,
Liu Yuan wrote:
+
+/* Try to reconnect the sheepdog server every one second. */
+while (s-fd 0) {
+s-fd = get_sheep_fd(s);
+if (s-fd 0
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 ++
1 file changed, 2 insertions(+)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 46821df..eeb5617 100644
--- a/block/sheepdog.c
+++ b/block
On Tue, Aug 06, 2013 at 02:44:37PM +0800, Liu Yuan wrote:
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |2 ++
1 file changed, 2 insertions(+)
diff --git a/block/sheepdog.c b/block/sheepdog.c
On Tue, Aug 06, 2013 at 10:24:42AM +0200, Kevin Wolf wrote:
Am 06.08.2013 um 09:37 hat MORITA Kazutaka geschrieben:
At Tue, 6 Aug 2013 14:44:37 +0800,
Liu Yuan wrote:
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u
With this patch, qemu-img info sheepdog:image will show disk size for sheepdog
images.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 19
We can actually use BDRVSheepdogState *s to pass most of the parameters.
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c | 37 +++--
1 file changed, 15 insertions(+), 22
in comment and commit log
This patch set add one sheepdog specific option for qemu-img to control
redundancy.
This patch set is on top of Kevin's block tree.
Liu Yuan (2):
sheepdog: refactor do_sd_create()
sheepdog: support user-defined redundancy option
block/sheepdog.c | 127
SD_EC_MAX_STRIP)
E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c
On Wed, Nov 06, 2013 at 10:34:24AM +0100, Stefan Hajnoczi wrote:
On Tue, Nov 05, 2013 at 08:46:07AM -0700, Eric Blake wrote:
On 11/05/2013 07:37 AM, Stefan Hajnoczi wrote:
+
+copy = strtol(n1, NULL, 10);
+if (copy SD_MAX_COPIES) {
+return -EINVAL;
+}
On Thu, Nov 07, 2013 at 10:56:36PM +0800, Liu Yuan wrote:
v6:
- update comment typo
- remove is_number()
Anyone pick this set up?
Thanks
Yuan
This will help people find mailing list relevant to sheepdog.
Stefan Hajnoczi stefa...@redhat.com
Kevin Wolf kw...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
MAINTAINERS |1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index c19133f..3e61ac8
This will help people find mailing list relevant to sheepdog.
Cc: Stefan Hajnoczi stefa...@redhat.com
Cc: Kevin Wolf kw...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
MAINTAINERS |1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index c19133f
On Mon, Nov 18, 2013 at 01:58:50PM +0800, Liu Yuan wrote:
On Thu, Nov 07, 2013 at 10:56:36PM +0800, Liu Yuan wrote:
v6:
- update comment typo
- remove is_number()
Anyone pick this set up?
Ping again. Without this two patches, qemu-img can't create|convert erasure
coded
images
On Thu, Nov 21, 2013 at 09:23:59AM +0100, Stefan Hajnoczi wrote:
On Thu, Nov 21, 2013 at 01:22:53AM +0800, Liu Yuan wrote:
On Mon, Nov 18, 2013 at 01:58:50PM +0800, Liu Yuan wrote:
On Thu, Nov 07, 2013 at 10:56:36PM +0800, Liu Yuan wrote:
v6:
- update comment typo
- remove
On 06/20/2013 11:58 PM, Sage Weil wrote:
On Thu, 20 Jun 2013, Stefan Hajnoczi wrote:
The concrete problem here is that flashcache/dm-cache/bcache don't
work with the rbd (librbd) driver, as flashcache/dm-cache/bcache
cache access to block devices (in the host layer), and with rbd
(for
This fix a segfault (that is caused by b3af018f3) of following command:
$ qemu-img convert some_img sheepdog:some_img
Cc: qemu-devel@nongnu.org
Cc: Kevin Wolf kw...@redhat.com
Cc: Stefan Hajnoczi stefa...@redhat.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |8
Cc: Stefan Hajnoczi stefa...@redhat.com
Reported-by: Hadrien KOHL hadrien.k...@gmail.com
Signed-off-by: Liu Yuan namei.u...@gmail.com
---
block/sheepdog.c |7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/block/sheepdog.c b/block/sheepdog.c
index d1c812d..ba451a9 100644
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Reviewd-by: MORITA Kazutaka morita.kazut
On 04/03/2012 04:01 AM, Michael Tokarev wrote:
On 02.04.2012 21:35, Liu Yuan wrote:
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Cc: Michael Tokarev m...@tls.msk.ru
Cc: MORITA
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Cc: Michael Tokarev m...@tls.msk.ru
Cc: MORITA
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Cc: Michael Tokarev m...@tls.msk.ru
Cc: MORITA
From: Liu Yuan tailai...@taobao.com
Yes, I think so. Here is the patch.
Subject: [PATCH] sheepdog: fix send req helpers
From: Liu Yuan tailai...@taobao.com
We should return if reading of the header fails.
Cc: Kevin Wolf kw...@redhat.com
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Signed
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Cc: Michael Tokarev m...@tls.msk.ru
Cc: MORITA
From: Liu Yuan tailai...@taobao.com
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.
By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.
Cc: Kevin Wolf kw...@redhat.com
Cc: MORITA Kazutaka morita.kazut...@lab.ntt.co.jp
Hi kevin,
On 04/04/2012 04:53 PM, Kevin Wolf wrote:
I can update it in my queue, no problem there.
But I diffed this against v4 and it doesn't seem to have any changes,
except in the context of two hunks. Are you sure that you didn't do the
fixes in a separate commit or send the wrong
Hi list,
This segfault is met when installing RHEL 6 with Sheepdog cluster.
Program terminated with signal 11, Segmentation fault.
#0 0x7f777fc30359 in send_pending_req (s=0x7f77818a2160,
oid=71271095331718270, id=1858) at block/sheepdog.c:629
629 QLIST_FOREACH_SAFE(aio_req,
From: Liu Yuan tailai...@taobao.com
The 'qemu-img convert -h' advertise that the default cache mode is
'writeback', while in fact it is 'unsafe'.
This patch 1) changes the cache mode as 'writeback' and 2) explicitly
calls bdrv_flush() to flush the dirty bits.
2) is needed because some backend
Hi Paolo,
On 04/11/2012 03:40 AM, Paolo Bonzini wrote:
From: Liu Yuan tailai...@taobao.com
The 'qemu-img convert -h' advertise that the default cache mode is
'writeback', while in fact it is 'unsafe'.
This patch 1) changes the cache mode as 'writeback' and 2) explicitly
calls
On 04/11/2012 03:32 PM, Paolo Bonzini wrote:
Il 11/04/2012 04:42, Liu Yuan ha scritto:
1) if we use bdrv_close(), we rely on the assumption that backend
storage will do flushing while interpreting this operation. This
assumption might not always hold, for e.g, current sheepdog doesn't do
On 04/11/2012 03:49 PM, Kevin Wolf wrote:
I don't agree with this patch. If the documentation says that qemu-img
always uses writeback, then the documentation must be fixed.
We really don't care about flushes during an image conversion. It should
just go as fast as it can. If any error
On 04/11/2012 08:27 PM, Kevin Wolf wrote:
Am 11.04.2012 12:33, schrieb Kevin Wolf:
Am 11.04.2012 12:05, schrieb Liu Yuan:
On 04/11/2012 03:49 PM, Kevin Wolf wrote:
I don't agree with this patch. If the documentation says that qemu-img
always uses writeback, then the documentation must
From: Liu Yuan tailai...@taobao.com
The 'qemu-img convert -h' advertise that the default cache mode is
'writeback', while in fact it is 'unsafe'.
This patch 1) fix the help manual and 2) let bdrv_close() call bdrv_flush()
3) explicitly calls bdrv_close() to flush the dirty bits.
3) is needed
On 04/11/2012 11:01 PM, Paolo Bonzini wrote:
bdrv_delete already does this.
Paolo
Ah yes. Thanks pointing out.
From 459414f677f6449482f9cfcb7917ff0e242ad490 Mon Sep 17 00:00:00 2001
From: Liu Yuan tailai...@taobao.com
Date: Wed, 11 Apr 2012 23:19:54 +0800
Subject: [PATCH v3] qemu-img: let
On 04/11/2012 11:21 PM, Liu Yuan wrote:
On 04/11/2012 11:01 PM, Paolo Bonzini wrote:
bdrv_delete already does this.
Paolo
Ah yes. Thanks pointing out.
Hi Kevin,
If no further comment, would you pick up following patch?
Yuan
From 459414f677f6449482f9cfcb7917ff0e242ad490 Mon
From: Liu Yuan tailai...@taobao.com
The 'qemu-img convert -h' advertise that the default cache mode is
'writeback', while in fact it is 'unsafe'.
This patch 1) fix the help manual and 2) let bdrv_close() call bdrv_flush()
2) is needed because some backend storage doesn't have a self-flush
1 - 100 of 325 matches
Mail list logo