If colo-compare find out the first different packet that means
the following packet almost is different. we needn't do a lot
of checkpoint in one second, so we set the no-need-checkpoint
period, default just set 3 second.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 9 -
1
On 06/09/2017 02:08 PM, Jason Wang wrote:
On 2017年06月07日 17:55, Zhang Chen wrote:
We add the vnet_hdr_support option for filter-mirror, default is
disable.
s/disable/disabled/
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object
filter-mirror,id
eries' goal. This series is preparing
work for integrating COLO compare with COLO frame and it is prerequisite.
So, we may consider implementing it later in another series.
Zhang Chen, what's your opinion ?
I agree, The current situation of COLO is not a complete HA solution.
So, We shou
Hi~ Eric.
If you have time, please give me some comments.
This series has been sent for a long time.
Thanks
Zhang Chen
On 02/06/2017 09:13 PM, Dr. David Alan Gilbert wrote:
* Jason Wang (jasow...@redhat.com) wrote:
On 2017年01月26日 11:04, Zhang Chen wrote:
Hi~
No news for a week.
We
On 02/07/2017 11:50 PM, Eric Blake wrote:
On 01/05/2017 12:08 AM, Zhang Chen wrote:
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will need this function.
Signed-off-by: Zhang Chen
Signed-off-by: Wen Congyang
---
docs/qmp-commands.txt | 24
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will need this function.
Signed-off-by: Zhang Chen
Signed-off-by: Wen Congyang
---
migration/colo.c | 17
qapi-schema.json | 60
2 files changed, 77
a0ddc0b359375b2418213966dfbdbfab593ecc6f
tools/libxl: introduction of libxl__qmp_restore to load qemu state
Zhang Chen (2):
Add a new qmp command to start/stop replication
Add a new qmp command to do checkpoint, query xen replication status
migration/colo.c | 40 ++
qapi
We can call this qmp command to start/stop replication outside of qemu.
Like Xen colo need this function.
Signed-off-by: Zhang Chen
Signed-off-by: Wen Congyang
Reviewed-by: Eric Blake
Reviewed-by: Stefano Stabellini
---
migration/colo.c | 23 +++
qapi-schema.json | 25
On 02/09/2017 05:35 AM, Eric Blake wrote:
On 02/07/2017 11:24 PM, Zhang Chen wrote:
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will need this function.
Signed-off-by: Zhang Chen
Signed-off-by: Wen Congyang
---
migration/colo.c | 17
qapi
On 05/03/2017 06:19 PM, Jason Wang wrote:
On 2017年05月03日 11:18, Zhang Chen wrote:
On 05/02/2017 12:47 PM, Jason Wang wrote:
On 2017年04月28日 17:47, Zhang Chen wrote:
In this patch, we change the send packet format from
struct {int size; const uint8_t buf[];} to {int size; int
On 05/05/2017 05:25 PM, Jason Wang wrote:
On 2017年05月05日 16:44, Zhang Chen wrote:
On 05/03/2017 06:19 PM, Jason Wang wrote:
On 2017年05月03日 11:18, Zhang Chen wrote:
On 05/02/2017 12:47 PM, Jason Wang wrote:
On 2017年04月28日 17:47, Zhang Chen wrote:
In this patch, we change the send
On 05/03/2017 06:42 PM, Jason Wang wrote:
On 2017年05月03日 11:43, Zhang Chen wrote:
On 05/02/2017 12:53 PM, Jason Wang wrote:
On 2017年04月28日 17:47, Zhang Chen wrote:
Address Jason Wang's comments add vnet header length to
SocketReadState.
Instead of saying this, you can add "
On 05/09/2017 10:40 AM, Jason Wang wrote:
On 2017年05月08日 11:47, Zhang Chen wrote:
On 05/03/2017 06:42 PM, Jason Wang wrote:
On 2017年05月03日 11:43, Zhang Chen wrote:
On 05/02/2017 12:53 PM, Jason Wang wrote:
On 2017年04月28日 17:47, Zhang Chen wrote:
Address Jason Wang's comment
On 05/09/2017 01:36 PM, Jason Wang wrote:
On 2017年05月09日 12:03, Zhang Chen wrote:
On 05/09/2017 10:40 AM, Jason Wang wrote:
On 2017年05月08日 11:47, Zhang Chen wrote:
On 05/03/2017 06:42 PM, Jason Wang wrote:
On 2017年05月03日 11:43, Zhang Chen wrote:
On 05/02/2017 12:53 PM, Jason
Fix some duplicate codes and remove unused codes.
Zhang Chen (3):
net/filter-mirror.c: Remove duplicate check code.
net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
net/filter-rewriter: Remove unused option in filter-rewirter
net/filter-mirror.c | 35
Signed-off-by: Zhang Chen
---
qemu-options.hx | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/qemu-options.hx b/qemu-options.hx
index 70c0ded..f5e088e 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4038,7 +4038,8 @@ Create a filter-redirector we need to differ
The s->outdev have checked in filter_mirror_set_outdev().
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index 72fa7c2..fd0322f 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirro
Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
both use the filter_mirror_send() to send packet, so I change
filter_mirror_send() to filter_send() that looks more common.
And fix some codestyle.
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 29
vnet_hdr option for filter-mirror, filter-redirector,
filter-rewriter,colo-compare.
- Use new design to impliment virtio-net support for colo-proxy.
- Fix codestyle.
- Remove unused option for filter-rewriter.
- Add filter-rewriter virtio-net support.
- Address other comments.
Zhang Chen (
Add vnet_hdr_len and using_vnet_hdr arguments in NetClientState
that make othermodule get real vnet_hdr_len easily.
Signed-off-by: Zhang Chen
---
include/net/net.h | 2 ++
net/net.c | 2 ++
2 files changed, 4 insertions(+)
diff --git a/include/net/net.h b/include/net/net.h
index
In this patch, if vnet_hdr=on we change the send packet format from
struct {int size; const uint8_t buf[];} to {int size; int vnet_hdr_len; const
uint8_t buf[];}.
make other module(like colo-compare) know how to parse net packet correctly.
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 35
COLO-compare can get vnet header length from filter,
Add vnet_hdr_len to struct packet and output packet with
the vnet_hdr_len.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 45 ++---
1 file changed, 34 insertions(+), 11 deletions(-)
diff --git a
We add the vnet_hdr option for filter-redirector, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object filter-redirector,id=r0,netdev=hn0,queue=tx,outdev=red0,vnet_hdr=on
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 33
Address Jason Wang's comments add vnet header length to SocketReadState.
We add a flag to dicide whether net_fill_rstate() to read
struct {int size; int vnet_hdr_len; const uint8_t buf[];} or not.
Signed-off-by: Zhang Chen
---
include/net/net.h | 9 +++--
net/colo-compare.c
We add the vnet_hdr option for colo-compare, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object
colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr=on
Signed-off-by: Zhang Chen
---
net/colo
We add the vnet_hdr option for filter-mirror, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr=on
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 34
Make colo-compare and filter-rewriter can parse vnet packet.
Signed-off-by: Zhang Chen
---
net/colo.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/colo.c b/net/colo.c
index 180eaed..28ce7c8 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -43,11 +43,11 @@ int
We can use this property flush and send packet with vnet_hdr_len.
Signed-off-by: Zhang Chen
---
net/colo-compare.c| 8 ++--
net/colo.c| 3 ++-
net/colo.h| 4 +++-
net/filter-rewriter.c | 2 +-
4 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/net
We add the vnet_hdr option for filter-rewriter, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object filter-rewriter,id=rew0,netdev=hn0,queue=all,vnet_hdr=on
Signed-off-by: Zhang Chen
---
net/filter-rewriter.c | 38
COLO-Proxy just focus on packet payload, So we skip vnet header.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index cb0b04e..bf565f3 100644
--- a/net/colo-compare.c
+++ b
We get the vnet_hdr_len from NetClientState that make us
parse net packet correctly.
Signed-off-by: Zhang Chen
---
net/filter-rewriter.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index bc6d12a..be129c7
On 05/13/2017 09:49 AM, Hailiang Zhang wrote:
Hi,
On 2017/5/12 9:41, Zhang Chen wrote:
We add the vnet_hdr option for filter-mirror, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object
filter-mirror,id=m0,netdev=hn0,queue=tx,outdev
On 05/13/2017 01:43 AM, Eric Blake wrote:
On 05/11/2017 08:35 PM, Zhang Chen wrote:
Signed-off-by: Zhang Chen
In the subject: s/rewirter/rewriter/
OK.
---
qemu-options.hx | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/qemu-options.hx b/qemu-options.hx
index
Fix some duplicate codes and remove unused codes.
v2: Address Eric's comment on patch 3.
Zhang Chen (3):
net/filter-mirror.c: Remove duplicate check code.
net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
net/filter-rewriter: Remove unused option in filter-rewriter
The s->outdev have checked in filter_mirror_set_outdev().
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index 72fa7c2..fd0322f 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirro
Signed-off-by: Zhang Chen
---
qemu-options.hx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/qemu-options.hx b/qemu-options.hx
index f806af9..85cf0f5 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4038,7 +4038,7 @@ Create a filter-redirector we need to differ outdev
Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
both use the filter_mirror_send() to send packet, so I change
filter_mirror_send() to filter_send() that looks more common.
And fix some codestyle.
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 29
Signed-off-by: Zhang Chen
---
qemu-options.hx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/qemu-options.hx b/qemu-options.hx
index f806af9..cbec279 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4038,7 +4038,7 @@ Create a filter-redirector we need to differ outdev
The s->outdev have checked in filter_mirror_set_outdev().
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index 72fa7c2..fd0322f 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirro
Fix some duplicate codes and remove unused codes.
v2: Address Eric's comment on patch 3.
Zhang Chen (3):
net/filter-mirror.c: Remove duplicate check code.
net/filter-mirror.c: Rename filter_mirror_send() and fix codestyle
net/filter-rewriter: Remove unused option in filter-rewriter
Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
both use the filter_mirror_send() to send packet, so I change
filter_mirror_send() to filter_send() that looks more common.
And fix some codestyle.
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 29
On 05/15/2017 11:24 AM, Jason Wang wrote:
On 2017年05月14日 05:24, Philippe Mathieu-Daudé wrote:
Hi Zhang
On 05/11/2017 10:41 PM, Zhang Chen wrote:
Add vnet_hdr_len and using_vnet_hdr arguments in NetClientState
that make othermodule get real vnet_hdr_len easily.
Signed-off-by: Zhang Chen
On 05/15/2017 11:26 AM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
We add the vnet_hdr option for filter-mirror, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object
filter-mirror,id=m0,netdev=hn0,queue=tx,outdev
On 05/15/2017 11:28 AM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
In this patch, if vnet_hdr=on we change the send packet format from
struct {int size; const uint8_t buf[];} to {int size; int
vnet_hdr_len; const uint8_t buf[];}.
make other module(like colo-compare) know how
On 05/15/2017 11:31 AM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
We add the vnet_hdr option for filter-redirector, default is disable.
If you use virtio-net-pci net driver, please enable it.
We need a better commit log here to explain e.g why we need this option.
OK. I
On 05/15/2017 12:02 PM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
Address Jason Wang's comments add vnet header length to SocketReadState.
Better to use "Suggested-by" instead of this :).
I got it~
We add a flag to dicide whether net_fill_rstate()
On 05/15/2017 12:03 PM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
We add the vnet_hdr option for colo-compare, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object
colo-compare,id=comp0,primary_in=compare0-0
On 05/15/2017 12:05 PM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
We can use this property flush and send packet with vnet_hdr_len.
Signed-off-by: Zhang Chen
Then I think it's not necessary to store vnet_hdr_len in SocketReadState?
Do you means we keep the patch
On 05/15/2017 12:11 PM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
COLO-Proxy just focus on packet payload, So we skip vnet header.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/net/colo
On 05/15/2017 12:12 PM, Jason Wang wrote:
On 2017年05月12日 09:41, Zhang Chen wrote:
We add the vnet_hdr option for filter-rewriter, default is disable.
If you use virtio-net-pci net driver, please enable it.
You can use it for example:
-object filter-rewriter,id=rew0,netdev=hn0,queue=all
On 05/15/2017 04:06 PM, Jason Wang wrote:
On 2017年05月15日 14:56, Zhang Chen wrote:
On 05/15/2017 11:24 AM, Jason Wang wrote:
On 2017年05月14日 05:24, Philippe Mathieu-Daudé wrote:
Hi Zhang
On 05/11/2017 10:41 PM, Zhang Chen wrote:
Add vnet_hdr_len and using_vnet_hdr arguments in
On 05/16/2017 02:48 PM, Jason Wang wrote:
On 2017年05月15日 14:18, Zhang Chen wrote:
Fix some duplicate codes and remove unused codes.
v2: Address Eric's comment on patch 3.
Zhang Chen (3):
net/filter-mirror.c: Remove duplicate check code.
net/filter-mirror.c: Rename filter_mirror
On 05/16/2017 10:42 PM, Eric Blake wrote:
On 05/16/2017 03:22 AM, Zhang Chen wrote:
What's the difference compared with V2? I think I should apply this
series?
In V2 I forgot remove "," in patch 3/3, Yes, please apply this series.
If you changed the patches, even just to
The s->outdev have checked in filter_mirror_set_outdev().
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index 72fa7c2..fd0322f 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirro
Fix some duplicate codes and remove unused codes.
v3:
- Remove the ',' in patch 3/3
v2:
- Address Eric's comment fix typo and keep a long lien on patch 3.
Zhang Chen (3):
net/filter-mirror.c: Remove duplicate check code.
net/filter-mirror.c: Rename filter_mirror_send() an
Signed-off-by: Zhang Chen
---
qemu-options.hx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/qemu-options.hx b/qemu-options.hx
index f806af9..cbec279 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4038,7 +4038,7 @@ Create a filter-redirector we need to differ outdev
Because filter_mirror_receive_iov() and filter_redirector_receive_iov()
both use the filter_mirror_send() to send packet, so I change
filter_mirror_send() to filter_send() that looks more common.
And fix some codestyle.
Signed-off-by: Zhang Chen
---
net/filter-mirror.c | 29
d release all queued secondary packets here, so combine this patch
with 3/5 patch as
one patch is a better choose.
Thanks
Zhang Chen
+
+ g_queue_free(&s->conn_list);
g_free(s->pri_indev);
g_free(s->sec_indev);
--
Thanks
Zhang Chen
;colo-compare and filter-rewriter work with
colo-frame "
Named 'colo_flush_connection', I think use 'flush' instead of 'release'
is better,
Thanks
Zhang Chen
+static void colo_release_packets(void *opaque, void *user_data)
+{
+CompareState *s = u
Ping...
No new for a long time.
Who can pick up this patch?
Thanks
Zhang Chen
On 02/14/2017 04:28 AM, Stefano Stabellini wrote:
On Wed, 8 Feb 2017, Eric Blake wrote:
On 02/07/2017 11:24 PM, Zhang Chen wrote:
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will
On 02/16/2017 01:08 PM, Jason Wang wrote:
On 2017年02月16日 11:25, Zhang Chen wrote:
Ping...
No new for a long time.
Who can pick up this patch?
I believe you'd better cc migration maintainers (cced), have you tried
scripts/get_maintainer ?
Thanks Jason.
Add cc Markus Armbr
is_self(&s->thread))'
branch.
Before compare thead exits, some cleanup works need to be
done, All unhandled packets need to be released and connection_track_table
needs to be freed, or there will be memory leak.
Signed-off-by: zhanghailiang
Reviewed-by: Zhang Chen
---
n
ed while
call qemu_chr_fe_set_handlers();
Fix it by pass the worker_context parameter to qemu_chr_fe_set_handlers().
Signed-off-by: zhanghailiang
Reviewed-by: Zhang Chen
---
net/colo-compare.c | 20 +++-
1 file changed, 11 insertions(+), 9 deletions(-)
--
Thanks
Zhang Chen
safe to remove the timer_check_lock.
Signed-off-by: zhanghailiang
Reviewed-by: Zhang Chen
---
net/colo-compare.c | 62 +++---
1 file changed, 22 insertions(+), 40 deletions(-)
--
Thanks
Zhang Chen
he elements in queue . If queue elements contain
dynamically-allocated memory, they should be freed first.
Thanks
Zhang Chen
g_slice_free(Connection, conn);
}
--
Thanks
Zhang Chen
We use g_queue_init() to init s->conn_list, so we should use g_queue_clear()
to instead of g_queue_free().
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 162fd6a..cf8c4c9 100
Hi~ Markus.
This patch set has been reviewed for a long time, can you pick up it?
[PATCH V7 0/2] Add new qmp commands to suppurt Xen COLO
Thanks
Zhang Chen
On 02/20/2017 09:33 PM, Markus Armbruster wrote:
The following changes since commit d514cfd763b271b4e97a9fc6adaabc8fd50084ab
On 02/21/2017 07:15 PM, Markus Armbruster wrote:
Zhang Chen writes:
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will need this function.
I know nothing about "Xen colo", but I'll try anyway.
I *guess* "Xen colo" is a long-running activ
On 02/21/2017 07:21 PM, Markus Armbruster wrote:
Zhang Chen writes:
Hi~ Markus.
This patch set has been reviewed for a long time, can you pick up it?
[PATCH V7 0/2] Add new qmp commands to suppurt Xen COLO
I think this should go through a COLO maintainer chain, or perhaps the
Xen
On 02/21/2017 09:01 PM, Hailiang Zhang wrote:
On 2017/2/8 13:24, Zhang Chen wrote:
We can call this qmp command to do checkpoint outside of qemu.
Xen colo will need this function.
Signed-off-by: Zhang Chen
Signed-off-by: Wen Congyang
---
migration/colo.c | 17
qapi
On 02/22/2017 11:15 AM, Jason Wang wrote:
On 2017年02月22日 11:09, Jason Wang wrote:
On 2017年02月22日 09:47, Hailiang Zhang wrote:
On 2017/2/21 10:44, Zhang Chen wrote:
We use g_queue_init() to init s->conn_list, so we should use
g_queue_clear()
to instead of g_queue_free().
Signed-off
We use g_queue_init() to init s->conn_list, so we should use g_queue_clear()
to instead of g_queue_free().
Signed-off-by: Zhang Chen
Reviewed-by: zhanghailiang
---
net/colo-compare.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/colo-compare.c b/net/colo-compar
or: ld returned 1 exit status
make[1]: *** [Makefile:208: qemu-system-aarch64] Error 1
make: *** [Makefile:322: subdir-aarch64-softmmu] Error 2
We should fix that.
COLO needs replication enable.
So, should I add a new option enable/disable COLO ?
Then, If you disable replication, colo will be dis
On 03/06/2017 08:54 PM, Paolo Bonzini wrote:
On 06/03/2017 11:03, Zhang Chen wrote:
On 03/06/2017 05:08 PM, Dr. David Alan Gilbert wrote:
* Bruce Rogers (brog...@suse.com) wrote:
On 2/6/2017 at 4:57 AM, wrote:
* Paolo Bonzini (pbonz...@redhat.com) wrote:
On 03/02/2017 07:00, Stefan
Because of inet_ntoa() return a statically allocated buffer,
subsequent calls will overwrite, So we fix this bug.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 33 +
1 file changed, 25 insertions(+), 8 deletions(-)
diff --git a/net/colo-compare.c b/net/colo
Hi~~~ All~
No news for a long time, anyone can give me some comments?
Thanks
Zhang Chen
On 02/28/2017 06:48 PM, Zhang Chen wrote:
This series focus on COLO Xen support.
We add a new chardev socket in colo-compare as the way
of communicate with Xen COLO-frame.
Xen part:
https
On 03/13/2017 02:28 PM, Jason Wang wrote:
On 2017年03月13日 14:18, Zhang Chen wrote:
Hi~~~ All~
No news for a long time, anyone can give me some comments?
Hi,
A question is why use two kinds of colo-frames? This seems not good as
lots of the code were duplicated.
Because Xen colo-frame
On 03/13/2017 03:10 PM, Zhang Chen wrote:
On 03/13/2017 02:28 PM, Jason Wang wrote:
On 2017年03月13日 14:18, Zhang Chen wrote:
Hi~~~ All~
No news for a long time, anyone can give me some comments?
Hi,
A question is why use two kinds of colo-frames? This seems not good
as lots of the
Signed-off-by: Zhang Chen
---
hw/net/virtio-net.c | 53 +
1 file changed, 33 insertions(+), 20 deletions(-)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index c321680..ede618e 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio
On 03/14/2017 03:37 PM, Jason Wang wrote:
On 2017年03月13日 15:21, Zhang Chen wrote:
On 03/13/2017 03:10 PM, Zhang Chen wrote:
On 03/13/2017 02:28 PM, Jason Wang wrote:
On 2017年03月13日 14:18, Zhang Chen wrote:
Hi~~~ All~
No news for a long time, anyone can give me some comments?
Hi
On 03/14/2017 11:01 AM, Jason Wang wrote:
Hi:
This series contains several fixes for virito region caches, please
review.
Title and comments typo:
S/virito/virtio
Thanks
Zhang Chen
Thanks.
Jason Wang (3):
virtio: guard against NULL pfn
virtio: destroy region cache during reset
of patch we pushing.
Has anyone ever run it successfully? Any help is appreciated!
In our internal version can run it successfully,
The failover detail you can ask Zhanghailiang for help.
Next time if you have some question about COLO,
please cc me and zhanghailiang .
Thanks
Zhan
Change parse_packet_early(Packet *pkt) to parse_packet_early(Packet *pkt, int
offset)
that we can skip virtio-net header.
Signed-off-by: Zhang Chen
---
net/colo-compare.c| 11 +++
net/colo.c| 8
net/colo.h| 5 -
net/filter-rewriter.c | 15
If packet is virtio-net packet we will skip the virtio-net header
compare packet's payload.
Signed-off-by: Zhang Chen
---
net/colo-compare.c | 31 ++-
1 file changed, 26 insertions(+), 5 deletions(-)
diff --git a/net/colo-compare.c b/net/colo-compare.c
index ce
If user use -device virtio-net-pci, virtio-net driver will add a header
to raw net packet that colo-proxy can't handle it. COLO-proxy just
focus on the packet payload, so we skip the virtio-net header to compare
the sent packet that primary guest's to secondary guest's.
Zhang C
Add this tag that compare can recognize virtio-net packet.
Signed-off-by: Zhang Chen
---
net/colo.c | 6 ++
net/colo.h | 2 ++
2 files changed, 8 insertions(+)
diff --git a/net/colo.c b/net/colo.c
index 060e822..d2b3683 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -79,6 +79,12 @@ int
Hi~ paolo~~
Just a ping...
Have any comments for this patch?
Thanks
Zhang Chen
On 08/04/2016 04:49 PM, Zhang Chen wrote:
Add qemu_chr_add_handlers_full() API, we can use
this API pass in a GMainContext,make handler run
in the context rather than main_loop.
This comments from Daniel P
On 08/10/2016 10:57 PM, Paolo Bonzini wrote:
On 10/08/2016 10:16, Zhang Chen wrote:
Hi~ paolo~~
Just a ping...
Have any comments for this patch?
Same as before: the patch is pointless alone, it makes sense to include
it as part of CoLo, if CoLo needs it.
OK, I will move this patch to
;s own conn.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net/colo-compare.c | 51 ++-
net/colo.c | 117 +
net/colo.h | 27 +
3 files changed, 185 insert
Jhash used by colo-compare and filter-rewriter
to save and lookup net connection info
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
include/qemu/jhash.h | 59
1 file changed, 59 insertions(+)
create
Add qemu_chr_add_handlers_full() API, we can use
this API pass in a GMainContext,make handler run
in the context rather than main_loop.
This comments from Daniel P . Berrange.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
Reviewed-by: Daniel P. Berrange
Cc
We add TCP,UDP,ICMP packet comparison to replace
IP packet comparison. This can increase the
accuracy of the package comparison.
Less checkpoint more efficiency.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net/colo-compare.c | 152
- add some comments
- other bug fix
- add RFC index
- add usage in patch 1/4
v2:
- add jhash.h
v1:
- initial patch
Zhang Chen (10):
qemu-char: Add qemu_chr_add_handlers_full() for GMaincontext
colo-compare: introduce colo compare initialization
net/colo.c: add colo.c to define and handl
The net/colo.c is used by colo-compare and filter-rewriter.
this can share common data structure like net packet,
and other functions.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net/Makefile.objs | 1 +
net/colo-compare.c | 113
condary.
usage:
colo secondary:
-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
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Con
checkpoint.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net/colo-compare.c | 216 +
net/colo.c | 1 +
net/colo.h | 3 +
trace-events | 2 +
4 files changed, 222 insertions
,id=red0,host=3.3.3.3,port=9003
-chardev socket,id=red1,host=3.3.3.3,port=9004
-object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
-object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net
ction kept good.
In code We use offset( = secondary_seq - primary_seq )
to rewrite seq or ack.
handle_primary_tcp_pkt: tcp_pkt->th_ack += offset;
handle_secondary_tcp_pkt: tcp_pkt->th_seq -= offset;
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
We use net/colo.h to track connection and parse packet
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
Signed-off-by: Wen Congyang
---
net/colo.c| 14 ++
net/colo.h| 1 +
net/filter-rewriter.c | 50 ++
3
When network is busy, we will receive multiple packets
at one time. this bug will lost packets that comes late.
Signed-off-by: Zhang Chen
Signed-off-by: Li Zhijian
---
net/net.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/net.c b/net/net.c
index a8e2e6b..8f3237e
701 - 800 of 1739 matches
Mail list logo
