Hello,
The following Patch which fixes COLO is missing:
https://lists.nongnu.org/archive/html/qemu-devel/2019-03/msg07909.html
Regards,
Lukas Straub
e attached scripts to run Qemu, in my case both primary and
secondary run on the same Host for testing purposes. See the files in the
attached .tar.bz2 for more Info, they also contain a Coredump.
Regards,
Lukas Straub
Configure CMDline:
./configure --target-list=x86_64-softmmu,i386-softmmu --en
ange with 'd') reliably trigger the crash for
me. I use the attached scripts to run Qemu, in my case both primary and
secondary run on the same Host for testing purposes. See the files in the
attached .tar.bz2 for more Info, they also contain a Coredump.
Regards,
Lukas Straub
Configure
h 0.1 second delay (change with 'd') reliably trigger the crash for
me. I use the attached scripts to run Qemu, in my case both primary and
secondary run on the same Host for testing purposes. See the files in the
attached .tar.bz2 for more Info, they also contain a Coredump.
Regards,
Lukas S
From: Lukas Straub
Because event_unhandled_count may be accessed concurrently, it needs
to be protected by taking the lock. However the assert is outside the
lock, probably causing it to read garbage and aborting Qemu erroneously.
The Bug only happens when running Qemu in COLO mode.
This Patch
From: Lukas Straub
Fixes the following bug: https://bugs.launchpad.net/qemu/+bug/1824622
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index bf10526f05..fcb491121b 100644
On Sat, 20 Apr 2019 19:14:25 +0200
Lukas Straub wrote:
> From: Lukas Straub
> Because event_unhandled_count may be accessed concurrently, it needs
> to be protected by taking the lock. However the assert is outside the
> lock, probably causing it to read garbage and aborting Qemu
&
a Coredump.
Regards,
Lukas Straub
Configure CMDline:
./configure --target-list=x86_64-softmmu,i386-softmmu --enable-debug-info
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1824622/+subscriptions
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 185 +++
1 file changed, 138 insertions(+), 47 deletions(-)
diff --git a/docs/COLO-FT.txt b/docs/COLO-FT.txt
index ad24680d13..c08bfbd3a8 100644
--- a/docs/COLO-FT.txt
+++ b/docs/COLO-FT.txt
Hello Everyone,
These Patches add support for continious replication to colo.
Please review.
Regards,
Lukas Straub
Lukas Straub (3):
Replication: Ignore requests after failover
net/filter.c: Add Options to insert filters anywhere in the filter list
Document the qmp commands for continious
To switch the Secondary to Primary, we need to insert new filters before
the filter-rewriter.
Add the necessary options to insert filters anywhere in the filter list.
Signed-off-by: Lukas Straub
---
include/net/filter.h | 2 ++
net/filter.c | 73
After failover, the Secondary side of replication shouldn't change state.
Add the necessary checks to ignore requests after failover.
Signed-off-by: Lukas Straub
---
block/replication.c | 31 +++
1 file changed, 27 insertions(+), 4 deletions(-)
diff --git a/block
On Fri, 16 Aug 2019 01:51:20 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub [mailto:lukasstra...@web.de]
> > Sent: Friday, August 16, 2019 3:48 AM
> > To: Dr. David Alan Gilbert
> > Cc: qemu-devel ; Zhang, Chen
&g
Document the qemu command-line and qmp commands for continious replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 185 +++
1 file changed, 138 insertions(+), 47 deletions(-)
diff --git a/docs/COLO-FT.txt b/docs/COLO-FT.txt
index
Hello Everyone,
These Patches add support for continious replication to colo.
Please review.
Regards,
Lukas Straub
v2:
- fix email formating
- fix checkpatch.pl warnings
- fix patchew error
- clearer commit messages
Lukas Straub (3):
Replication: Ignore requests after failover
net
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c b/block/replication.c
ld be either "before" or "after" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
---
include/net/filter.h | 2 ++
net/filter.c | 71 +++-
qemu-options.hx | 10
On Thu, 15 Aug 2019 19:57:37 +0100
"Dr. David Alan Gilbert" wrote:
> * Lukas Straub (lukasstra...@web.de) wrote:
> > Hello Everyone,
> > These Patches add support for continious replication to colo.
> > Please review.
>
>
> OK, for those who haven'
Document the qemu command-line and qmp commands for continious replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 185 +++
1 file changed, 138 insertions(+), 47 deletions(-)
diff --git a/docs/COLO-FT.txt b/docs/COLO-FT.txt
index
ld be either "before" or "after" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
---
include/net/filter.h | 2 ++
net/filter.c | 71 +++-
qemu-options.hx | 10
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c b/block/replication.c
Hello Everyone,
These Patches add support for continious replication to colo.
Please review.
Regards,
Lukas Straub
v2:
- fix email formating
- fix checkpatch.pl warnings
- fix patchew error
- clearer commit messages
Lukas Straub (3):
Replication: Ignore requests after failover
net
ld be either "before" or "behind" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
---
include/net/filter.h | 2 ++
net/filter.c | 78 +++-
qemu-options.hx | 1
This simulates the case that happens when we resume COLO after failover.
Signed-off-by: Lukas Straub
---
tests/test-replication.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/test-replication.c b/tests/test-replication.c
index f085d1993a
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c b/block/replication.c
which I will
post when its ready.
I have to say it's quite fun to randomly kill a Node, wait for resync
and repeat and see how the VM stays alive all the time. :)
Regards,
Lukas Straub
v3:
- add test for replication changes
- check if the filter to be inserted before/behind belongs to the same
Document the qemu command-line and qmp commands for continious replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 212 +++--
docs/block-replication.txt | 26 +++--
2 files changed, 172 insertions(+), 66 deletions(-)
diff --git a/docs/COLO
On Mon, 2 Sep 2019 11:43:57 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Friday, August 23, 2019 2:21 PM
> > To: Zhang, Chen
> > Cc: qemu-devel ; Jason Wang
> > ; Wen Congyang ;
> > Xie Changlon
.
>
>
> > -Original Message-
> > From: Lukas Straub
> > Sent: Friday, August 16, 2019 2:49 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie Changlong
> > Subject: [PATCH v2 3/3] Update Docume
On Fri, 23 Aug 2019 03:24:02 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub [mailto:lukasstra...@web.de]
> > Sent: Friday, August 16, 2019 2:49 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congya
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c b/block/replication.c
which I will
post when its ready.
I have to say it's quite fun to randomly kill a Node, wait for resync
and repeat and see how the VM stays alive all the time. :)
Regards,
Lukas Straub
v4:
- fix checkpatch.pl warnings
v3:
- add test for replication changes
- check if the filter to be inserted
ld be either "before" or "behind" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
---
include/net/filter.h | 2 ++
net/filter.c | 78 +++-
qemu-options.hx | 1
Document the qemu command-line and qmp commands for continious replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 212 +++--
docs/block-replication.txt | 26 +++--
2 files changed, 172 insertions(+), 66 deletions(-)
diff --git a/docs/COLO
This simulates the case that happens when we resume COLO after failover.
Signed-off-by: Lukas Straub
---
tests/test-replication.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/test-replication.c b/tests/test-replication.c
index f085d1993a
which I will
post when its ready.
I have to say it's quite fun to randomly kill a Node, wait for resync
and repeat and see how the VM stays alive all the time. :)
Regards,
Lukas Straub
v5:
- change syntax for the position= parameter
- fix spelling mistake
v4:
- fix checkpatch.pl warnings
v3
or it should be "id=" to specify
the id of another filter.
insert should be either "before" or "behind" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
---
incl
On Tue, 10 Sep 2019 20:12:45 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Tuesday, September 10, 2019 6:15 PM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie
Document the qemu command-line and qmp commands for continuous replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 212 +++--
docs/block-replication.txt | 28 +++--
2 files changed, 173 insertions(+), 67 deletions(-)
diff --git a/docs/COLO
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c b/block/replication.c
This simulates the case that happens when we resume COLO after failover.
Signed-off-by: Lukas Straub
---
tests/test-replication.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/test-replication.c b/tests/test-replication.c
index f085d1993a
ar{netdevid},mirror net packet to
> > chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror
> > will
> > mirror packet with vnet_hdr_len.
> >
>
> Please add description for the newly added parameter in each filter.
> After that:
> Reviewed-by
On Thu, 26 Sep 2019 17:27:35 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Monday, September 16, 2019 3:20 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie
On Thu, 26 Sep 2019 17:40:03 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Monday, September 16, 2019 3:20 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie
On Sun, 15 Sep 2019 21:19:50 +0200
Lukas Straub wrote:
> Hello Everyone,
> These Patches add support for continuous replication to colo. This means
> that after the Primary fails and the Secondary did a failover, the Secondary
> can then become Primary and resume replication to a n
On Thu, 31 Oct 2019 17:05:20 +0800
Daniel Cho wrote:
> Hello all,
> I have some questions about the COLO.
> 1) Could we dynamic set fault tolerance feature on running VM?
> In your document, the primary VM could not start first (if you start
> primary VM, the secondary VM will need to start),
;:"object-add", "arguments":{ "qom-type" : "colo-compare",
> "id" : "comp0", "props": { "primary_in" : "compare0-0", "secondary_in" :
> "compare1", "outdev" : "compare_out0", "iothread" : "iothread1"} } }
> *3. Start the secondary VM with command*
> qemu-system-x86_64 -enable-kvm -cpu qemu64,+kvmclock -m 2048 -qmp
> stdio \
> -vnc :6 -device piix3-usb-uhci -device usb-tablet -name secondary \
> -netdev
> tap,id=hn0,vhost=off,helper=/usr/local/ceph/libexec/qemu-bridge-helper \
> -device rtl8139,id=e0,netdev=hn0 \
> -chardev socket,id=red0,host=127.0.0.1,port=9003,reconnect=1 \
> -chardev socket,id=red1,host=127.0.0.1,port=9004,reconnect=1 \
> -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0 \
> -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1 \
> -object filter-rewriter,id=rew0,netdev=hn0,queue=all \
> -drive if=none,id=colo-disk0,file.filename=$image_path,driver=qcow2,\
> node-name=node1 \
> -drive
> if=ide,id=active-disk0,driver=replication,mode=secondary,file.driver=qcow2,\
> top-id=active-disk0,file.file.filename=active-disk.qcow2,\
> file.backing.driver=qcow2,file.backing.file.filename=hidden-disk.qcow2,\
> file.backing.backing=colo-disk0,node-name=node2 \
> -incoming tcp:0:9998
> *4. As the document create rbd server and do migrate with qmp command*
> [image: image.png]
> *5. Kill the PVM and failover to SVM*
> [image: image.png]
> *6. Reboot the secondary VM, then we will get the error.*
> It is high possibility to occur this error.
>
> Therefore, we can solve the image problem by *xfs_repair*, then reboot the
> VM it will work.
> Command:
> xfs_repair -L /dev/sda1
>
> Do you have any idea to occur this problem?
Hi Daniel,
The disks have to be synchronized before you can start COLO. So try something
like this:
{'execute': 'drive-mirror', 'arguments':{ 'device': 'colo-disk0', 'job-id':
'resync', 'target': 'nbd://SECONDARY:?/colo-disk0', 'mode': 'existing',
'format': 'raw', 'sync': 'full'} }
Then, after the job is ready:
{'execute': 'stop'}
{'execute': 'block-job-cancel', 'arguments':{ 'device': 'resync'} }
And then you can add the replication driver and start colo.
Regards,
Lukas Straub
On Fri, 25 Oct 2019 19:06:31 +0200
Lukas Straub wrote:
> Hello Everyone,
> These Patches add support for continuous replication to colo. This means
> that after the Primary fails and the Secondary did a failover, the Secondary
> can then become Primary and resume replication to a n
Add high-level test relying on the colo resource-agent to test
all failover cases while checking guest network connectivity
Signed-off-by: Lukas Straub
---
scripts/colo-resource-agent/crm_master | 44 +++
tests/acceptance/colo.py | 444 +
2 files changed
On Thu, 21 Nov 2019 12:04:58 -0600
Eric Blake wrote:
> On 11/21/19 11:49 AM, Lukas Straub wrote:
> > If we remove the child with the highest index from the quorum,
> > decrement s->next_child_index. This way we get stable children
> > names as long as we on
Introduce a resource agent which can be used in a
Pacemaker cluster to manage qemu COLO.
Signed-off-by: Lukas Straub
---
scripts/colo-resource-agent/colo | 1026 ++
1 file changed, 1026 insertions(+)
create mode 100755 scripts/colo-resource-agent/colo
diff --git
failover, because qemu hangs while removing the replication related block nodes.
Note that this also happens in real world test when cutting power to the peer
host, so this needs to be fixed.
Based-on:
([PATCH v7 0/4] colo: Add support for continuous replication)
Lukas Straub (4):
block
While I'm not going to have much time for this, I'll still
try to test and review patches.
Signed-off-by: Lukas Straub
---
MAINTAINERS | 6 ++
1 file changed, 6 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index d6de200453..aad8356149 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
If we remove the child with the highest index from the quorum,
decrement s->next_child_index. This way we get stable children
names as long as we only remove the last child.
Signed-off-by: Lukas Straub
---
block/quorum.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/block/quorum.
or it should be "id=" to specify
the id of another filter.
insert should be either "before" or "behind" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
Reviewed-by: Zhang Chen
---
incl
Document the qemu command-line and qmp commands for continuous replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 224 +++--
docs/block-replication.txt | 28 +++--
2 files changed, 184 insertions(+), 68 deletions(-)
diff --git a/docs/COLO
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
Reviewed-by: Zhang Chen
---
block/replication.c | 35 ++-
1 file changed, 34 insertions(+), 1 deletion(-)
diff --git a/block/replication.c b
This simulates the case that happens when we resume COLO after failover.
Signed-off-by: Lukas Straub
---
tests/test-replication.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/test-replication.c b/tests/test-replication.c
index f085d1993a
On Wed, 23 Oct 2019 14:49:29 +0200
Max Reitz wrote:
> On 05.10.19 15:05, Lukas Straub wrote:
> > After failover the Secondary side of replication shouldn't change state,
> > because
> > it now functions as our primary disk.
> >
> > In replication
On Sat, 5 Oct 2019 15:05:23 +0200
Lukas Straub wrote:
> After failover the Secondary side of replication shouldn't change state,
> because
> it now functions as our primary disk.
>
> In replication_start, replication_do_checkpoint, replication_stop, ignore
> the reques
Hello Everyone,
These Patches add support for continuous replication to colo. This means
that after the Primary fails and the Secondary did a failover, the Secondary
can then become Primary and resume replication to a new Secondary.
Regards,
Lukas Straub
v7:
- clarify meaning of ip's
Hello Everyone,
These Patches add support for continuous replication to colo. This means
that after the Primary fails and the Secondary did a failover, the Secondary
can then become Primary and resume replication to a new Secondary.
Regards,
Lukas Straub
v7:
- clarify meaning of ip's
On Tue, 26 Nov 2019 15:21:37 +0100
Alberto Garcia wrote:
> On Thu 21 Nov 2019 07:34:45 PM CET, Lukas Straub wrote:
> >> > diff --git a/block/quorum.c b/block/quorum.c
> >> > index df68adcfaa..6100d4108a 100644
> >> > --- a/block/quorum.c
> >> &
On Fri, 22 Nov 2019 09:46:46 +
"Dr. David Alan Gilbert" wrote:
> * Lukas Straub (lukasstra...@web.de) wrote:
> > Hello Everyone,
> > These patches introduce a resource agent for use with the Pacemaker CRM and
> > a
> > high-level test utilizing it for te
gt; target/i386/hvf/x86_emu.c| 3 --
> target/i386/hvf/x86hvf.c | 26 +
> 6 files changed, 108 insertions(+), 84 deletions(-)
>
Hi,
I can't comment on your code, but simply resend this as v2 with the
checkpatch.pl errors fixed. You can run checkpatch.pl locally before
posting (scripts/checkpatch.pl).
Regards,
Lukas Straub
On Wed, 9 Oct 2019 06:03:03 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Saturday, October 5, 2019 9:06 PM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie
On Wed, 9 Oct 2019 08:36:52 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Saturday, October 5, 2019 9:06 PM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Jason Wang
> > ; Wen Congyang ;
> > Xie
) or
BLOCK_REPLICATION_FAILOVER (failover in progres i.e. currently merging active
and hidden images into the base image).
Signed-off-by: Lukas Straub
Reviewed-by: Zhang Chen
---
block/replication.c | 38 +++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/block/replication.c
or it should be "id=" to specify
the id of another filter.
insert should be either "before" or "behind" to specify where to
insert the new filter relative to the one specified with position.
Signed-off-by: Lukas Straub
Reviewed-by: Zhang Chen
---
incl
Hello Everyone,
These Patches add support for continuous replication to colo. This means
that after the Primary fails and the Secondary did a failover, the Secondary
can then become Primary and resume replication to a new Secondary.
Regards,
Lukas Straub
v6:
- properly documented the position
This simulates the case that happens when we resume COLO after failover.
Signed-off-by: Lukas Straub
---
tests/test-replication.c | 52
1 file changed, 52 insertions(+)
diff --git a/tests/test-replication.c b/tests/test-replication.c
index f085d1993a
Document the qemu command-line and qmp commands for continuous replication
Signed-off-by: Lukas Straub
---
docs/COLO-FT.txt | 213 +++--
docs/block-replication.txt | 28 +++--
2 files changed, 174 insertions(+), 67 deletions(-)
diff --git a/docs/COLO
On Thu, 10 Oct 2019 10:34:15 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Wednesday, October 9, 2019 11:17 PM
> > To: Zhang, Chen
> > Cc: qemu-devel ; Jason Wang
> > ; Wen Congyang ;
> > Xie
On Wed, 27 Nov 2019 22:11:34 +0100
Lukas Straub wrote:
> On Fri, 22 Nov 2019 09:46:46 +
> "Dr. David Alan Gilbert" wrote:
>
> > * Lukas Straub (lukasstra...@web.de) wrote:
> > > Hello Everyone,
> > > These patches introduce a re
process while doing operation with
> > network?
> >
>
> No, qemu_hexdump looks no relationship with network...
> Do you means it will crashed in qemu_hexdump sometimes?
Jeah, I hit that bug too, but it was fixed with
1e907a32b77e5d418538453df5945242e43224fa "COLO-compare: Fix inco
ept in the new PVM. What is its role in the new PVM?
>
> Thanks!
>
> Sincerely,
> Jing-Wei
Hi,
The filter-rewriter rewrites the TCP-Packets to increase similarity of PVM and
SVM, after the SVM takes over it needs to continue the rewriting, otherwise it
would break the TCP connections.
Regards,
Lukas Straub
Hello Everyone,
Here are fixes for bugs that I found in my tests.
Regards,
Lukas Straub
Lukas Straub (3):
net/colo-compare.c: Create event_bh with the right AioContext
chardev/char.c: Use qemu_co_sleep_ns if in coroutine
net/colo-compare.c: Fix deadlock
chardev/char.c | 7 +++-
net
. This leads to a deadlock because both event loops
get blocked.
Fix this by converting compare_chr_send to a coroutine
and return error if it is in use.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 82 +++---
1 file changed, 71 insertions(+), 11
This will be needed in the next patch.
Signed-off-by: Lukas Straub
---
chardev/char.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/chardev/char.c b/chardev/char.c
index 04075389bf..51ad0dc6b3 100644
--- a/chardev/char.c
+++ b/chardev/char.c
@@ -38,6 +38,7
locks.
Create the bh with the AioContext of the iothread to fulfill
these assumptions.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 10c0239f9d..1de4220fe2 100644
--- a/net/colo
to ~397ms.
Meanwhile the packet loss without this commit is negligible,
only 1-2 ping packets got lost during each test run.
Instead I think we should just turn the error message
into a trace so it doesn't flood the logs.
Regards,
Lukas Straub
5.0-rc1 with bugfixes:
*** iperf -c 192.168.178.65 ***
On Sat, 11 Apr 2020 19:16:54 +0200
Lukas Straub wrote:
> Hello Everyone,
> I did some Benchmarking with iperf3 and memtester (to dirty some guest memory)
> of colo performance in qemu 4.2.0 and in qemu 5.0.0-rc2
> with my bugfixes on top.(
> https://lists.nongnu.org/archive/html/
't working properly?
Regards,
Lukas Straub
pgpk5683oTPDL.pgp
Description: OpenPGP digital signature
nd works well in my tests.
Reviewed-by: Lukas Straub
Tested-by: Lukas Straub
Regards,
Lukas Straub
> ---
> net/colo-compare.c | 23 +++
> 1 file changed, 15 insertions(+), 8 deletions(-)
>
> diff --git a/net/colo-compare.c b/net/colo-compare.c
> index 7ee
;
> To address the issue, this patch drops the packet firstly.
> Then, do checkpoint and flush packets.
>
> Signed-off-by: Derek Su
Looks good and works well in my tests.
Reviewed-by: Lukas Straub
Tested-by: Lukas Straub
Regards,
Lukas Str
On Sat, 28 Mar 2020 02:20:21 +0800
Derek Su wrote:
> Lukas Straub 於 2020年3月28日 週六 上午1:46寫道:
> >
> > On Wed, 25 Mar 2020 17:43:54 +0800
> > Derek Su wrote:
> >
> > > The pervious handling of the full primary or queue is only dropping
> > > the pack
/* compare packet in the specified connection */
> colo_compare_connection(conn, s);
> +} else if (ret == QUEUE_INSERT_FULL) {
> +g_queue_foreach(>conn_list, colo_flush_packets, s);
> +colo_compare_inconsistency_notify(s);
> +} else {
> +trace_colo_compare_main("secondary: unsupported packet in");
> }
> }
>
Hi,
I don't think we have to flush here because the (post-)checkpoint event will
flush the packets for us.
Regards,
Lukas Straub
pgpojyvNhZArC.pgp
Description: OpenPGP digital signature
On Mon, 27 Apr 2020 03:36:57 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Monday, April 27, 2020 5:19 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Li Zhijian
> > ; Jason Wang ; Marc-
> > André Lu
On Mon, 27 Apr 2020 11:34:32 +0100
"Dr. David Alan Gilbert" wrote:
> * Lukas Straub (lukasstra...@web.de) wrote:
> > On Sat, 11 Apr 2020 19:16:54 +0200
> > Lukas Straub wrote:
> >
> > > Hello Everyone,
> > > I did some Benchmarking with iperf3
with a trace event.
>
> Signed-off-by: Derek Su
Looks good now and works well in my tests.
Reviewed-by: Lukas Straub
Tested-by: Lukas Straub
Regards,
Lukas Straub
> ---
> net/colo-compare.c | 23 +++
> net/trace-events | 1 +
> 2 files changed, 16 ins
and fix the crashes. This is safe, because
the bh already takes the appropriate locks.
Signed-off-by: Lukas Straub
Reviewed-by: Zhang Chen
Reviewed-by: Derek Su
Tested-by: Derek Su
---
net/colo-compare.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/colo-compare.c b/net
. This leads to a deadlock because both event loops
get blocked.
Fix this by converting compare_chr_send to a coroutine and
putting the packets in a send queue. Also create a new
function notify_chr_send, since that should be independend.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 173
hout patch: ~63 Mbit/s
with patch: ~66 Mbit/s
Server-to-client tcp:
without patch: ~771 Kbit/s
with patch: ~702 Kbit/s
Regards,
Lukas Straub
Changes in v2:
-better wording
-fix performance-regression in patch 3 "net/colo-compare.c: Fix deadlock in
compare_chr_send"
-add more bugfi
mode) and to use multiple colo-compare
for multiple network interfaces.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 34 --
net/colo-compare.h | 1 +
softmmu/vl.c | 2 ++
3 files changed, 31 insertions(+), 6 deletions(-)
diff --git a/net/colo
In colo_compare_complete, insert CompareState into net_compares
only after everything has been initialized.
In colo_compare_finalize, remove CompareState from net_compares
before anything is deinitialized.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 47
Else the log will be flooded if there is a lot of network
traffic.
Signed-off-by: Lukas Straub
---
net/colo-compare.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index ff6a740284..6634911770 100644
--- a/net/colo
This will be needed in the next patch.
Signed-off-by: Lukas Straub
Reviewed-by: Marc-André Lureau
Reviewed-by: Zhang Chen
---
chardev/char.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/chardev/char.c b/chardev/char.c
index e77564060d..5c8014199f 100644
On Wed, 22 Apr 2020 08:29:39 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Thursday, April 9, 2020 2:34 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Li Zhijian
> > ; Jason Wang ; Marc-
> > André
On Wed, 22 Apr 2020 09:03:00 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Wednesday, April 22, 2020 4:43 PM
> > To: Zhang, Chen
> > Cc: qemu-devel ; Li Zhijian
> > ; Jason Wang ; Marc-
> > André L
On Wed, 22 Apr 2020 08:40:40 +
"Zhang, Chen" wrote:
> > -Original Message-
> > From: Lukas Straub
> > Sent: Thursday, April 9, 2020 2:34 AM
> > To: qemu-devel
> > Cc: Zhang, Chen ; Li Zhijian
> > ; Jason Wang ; Marc-
> > André
1 - 100 of 601 matches
Mail list logo