Dima,
I agree that the ploop barrier code is broken in many ways, but I don't
think the patch actually fixes it. I hope you would agree that
completion of REQ_FUA guarantees only landing that particular bio to the
disk; it says nothing about flushing previously submitted (and
completed)
Hi, Vladimir!
Thanks for a quick response.
I created JIRA issue and uploaded the dumps.
All the information is included into JIRA issue:
https://bugs.openvz.org/browse/OVZ-6756
On Wed, Jun 15, 2016 at 11:47 AM, Vladimir Davydov
wrote:
> Hi,
>
> Thanks for the report.
ACK-ed, but see a minor nit below
On 06/15/2016 07:49 AM, Dmitry Monakhov wrote:
Signed-off-by: Dmitry Monakhov
---
drivers/block/ploop/io_direct.c | 22 +-
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git
Acked-by: Maxim Patlasov
On 06/15/2016 07:49 AM, Dmitry Monakhov wrote:
(rw & REQ_FUA) branch is impossible because REQ_FUA was cleared line above.
Logic was moved to ploop_req_delay_fua_possible() long time ago.
Signed-off-by: Dmitry Monakhov
barrier code is broken in many ways:
Currently only ->dio_submit() handles PLOOP_REQ_FORCE_{FLUSH,FUA} correctly.
But request also can goes though ->dio_submit_alloc()->dio_submit_pad and
write_page (for indexes)
So in case of grow_dev we have following sequance:
E_RELOC_DATA_READ:
(rw & REQ_FUA) branch is impossible because REQ_FUA was cleared line above.
Logic was moved to ploop_req_delay_fua_possible() long time ago.
Signed-off-by: Dmitry Monakhov
---
drivers/block/ploop/io_direct.c | 9 -
1 file changed, 9 deletions(-)
diff --git
Signed-off-by: Dmitry Monakhov
---
drivers/block/ploop/io_direct.c | 22 +-
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/drivers/block/ploop/io_direct.c b/drivers/block/ploop/io_direct.c
index b844a80..74a554a 100644
---
Changelog:
OpenVZ kernel rh7-3.10.0-327.18.2.vz7.14.15
* vtty: Container's offline console can be opened before a Container start,
survives start/stop/cpt/rst cycles
* fs: deny umounting rootfs
* sysrq: correct the fix to avoid cpu soft lockups on long print triggered by
sysrq
* ploop: fix
The commit is pushed to "branch-rh7-3.10.0-327.18.2.vz7.14.x-ovz" and will
appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.18.2.vz7.14.14
-->
commit a9532c96e6a0c64fbb4a128ba6ca99b9081e85cc
Author: Cyrill Gorcunov
Date: Wed Jun 15 13:32:23
The commit is pushed to "branch-rh7-3.10.0-327.18.2.vz7.14.x-ovz" and will
appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.18.2.vz7.14.14
-->
commit 0ae9e4e30b14404b570f62f83220637506be6376
Author: Vasily Averin
Date: Wed Jun 15 13:16:38 2016
Hi,
Thanks for the report.
Could you please
- file a bug to bugzilla.openvz.org
- upload the vmcore at
rsync://fe.sw.ru/f837d67c8e2ade8cee3367cb0f880268/
On Mon, Jun 13, 2016 at 09:24:33AM +0300, Anatoly Stepanov wrote:
> Hello everyone!
>
> We encounter an issue with
Dima, please review the patchset.
--
Best regards,
Konstantin Khorenko,
Virtuozzo Linux Kernel Team
On 06/15/2016 03:50 AM, Maxim Patlasov wrote:
If a ploop request waits for userspace backup tool attention for more
then plo->tune.push_backup_timeout (42 secs by default), the whole
The commit is pushed to "branch-rh7-3.10.0-327.18.2.vz7.14.x-ovz" and will
appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.18.2.vz7.14.14
-->
commit 3eada65cb70c5f2c773fcac7aabc72de5f768bac
Author: Andrey Ryabinin
Date: Wed Jun 15
The commit is pushed to "branch-rh7-3.10.0-327.18.2.vz7.14.x-ovz" and will
appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.18.2.vz7.14.14
-->
commit fc4dd8e6d4df14e5e09b6dacac74fe903d95c929
Author: Maxim Patlasov
Date: Wed Jun 15 12:38:54
We need to know flags for dumping and restoring netlink sockets.
All flags except NDIAG_FLAG_CB_RUNNING can be received with help of
getsockopt(), but in this case we need a socket descriptor and we need
to call getsockopt() to get each flag.
With this chages we will be able to show netlink
This patch adds an repair mode for netlink sockets. sendmsg queues
messages into a receive queue if a socket is in the repair mode.
---
include/uapi/linux/netlink.h | 19 ++---
net/netlink/af_netlink.c | 51 +++-
2 files changed, 47
CRIU can dump queued data for unix and tcp sockets,
now it's time for netlink sockets.
Here are there questions.
* How to dump data from a receive queue
We can set peeking offset like we do for unix sockets.
* How to restore data back to a receive queue
I suggest to add a repair mode like we
This allows us to read socket's queue without removing skbs from it.
The same logic was implemented for unix and inet sockets and we use this
to dump and restore sockets in CRIU.
Here is a question whether sk_peek_off has to be protected by locks.
Currently it isn't protected and an user who
18 matches
Mail list logo