On 04/11/2013 05:39 AM, Michael R. Hines wrote:
> On 04/10/2013 10:26 PM, Eric Blake wrote:
>>
>> New QMP commands should be named with '-' rather than '_', as in
>> 'migrate-check-for-zero'.
>>
>> Why do we need a new command, instead of adding a new capability to the
>> already-existing capabilit
On Wed, Apr 10, 2013 at 10:08:20AM -0500, Anthony Liguori wrote:
> Stefan Hajnoczi writes:
>
> > On Wed, Apr 10, 2013 at 2:05 AM, Josh Durgin
> > wrote:
> > NACK
> >
> > I think we're solving the problem at the wrong level. Writing our own
> > dynamic linker and adding boilerplate to juggle fu
On Wed, Apr 10, 2013 at 07:03:39AM -0700, Josh Durgin wrote:
> On 04/02/2013 07:10 AM, Kevin Wolf wrote:
> >Am 29.03.2013 um 21:03 hat Josh Durgin geschrieben:
> >>The existing bdrv_co_flush_to_disk implementation uses rbd_flush(),
> >>which is sychronous and causes the main qemu thread to block un
On Wed, Apr 10, 2013 at 11:19:03PM +0200, Paolo Bonzini wrote:
> Il 10/04/2013 17:08, Anthony Liguori ha scritto:
> > /* This should not be used directly. Use block_init etc. instead. */
> > #ifdef CONFIG_MODULE
> > #define module_init(function, type)\
> > const gchar *g_module_check_
On Wed, Apr 10, 2013 at 04:05:34PM -0400, Michael R. Hines wrote:
> On 04/10/2013 01:41 PM, Michael S. Tsirkin wrote:
>
> Thanks.
>
> However, IMHO restricting the policy to only used chunk-based is really
> not an acceptable choice:
>
> Here's the reason: Using my 10
On 11 April 2013 04:41, li guang wrote:
> here are instructions in the finial qemu-system-x86
> before and after my chanage, you can easily find a
> redundant 'addl' was removed
Yes, but:
* the removed instruction is not inside the loop
* the entire loop is not in a speed critical path
* remov
On Wed, Apr 10, 2013 at 10:17:04PM +0800, Amos Kong wrote:
> On Wed, Apr 10, 2013 at 02:28:40PM +0200, Andreas Färber wrote:
> > Hi,
> >
> > Am 10.04.2013 14:05, schrieb Amos Kong:
> > > If we don't assign 'id' for nic device, device name will be $model.$idx.
> > > The $idx are always 0 if we set
On 04/11/2013 12:09 AM, Alexander Graf wrote:
>
> On 09.04.2013, at 17:00, Fabien Chouteau wrote:
>
>> From: Tristan Gingold
>>
>> Raise the exception on the first occurence, do not wait for the next
>> floating point operation.
>
> Do you have a test case for this one that I could use to compa
On Wed, Apr 10, 2013 at 06:28:18PM -0400, mrhi...@linux.vnet.ibm.com wrote:
> From: "Michael R. Hines"
>
> This allows the user to disable zero page checking during migration
>
> Signed-off-by: Michael R. Hines
IMO this knob is too low level to expose to management.
Why not disable this automa
Am 11.04.2013 um 10:02 hat Stefan Hajnoczi geschrieben:
> On Wed, Apr 10, 2013 at 07:03:39AM -0700, Josh Durgin wrote:
> > On 04/02/2013 07:10 AM, Kevin Wolf wrote:
> > >Am 29.03.2013 um 21:03 hat Josh Durgin geschrieben:
> > >>The existing bdrv_co_flush_to_disk implementation uses rbd_flush(),
> >
On Wed, Apr 10, 2013 at 03:30:10PM +0800, Wenchao Xia wrote:
> 于 2013-4-8 21:33, Stefan Hajnoczi 写道:
> >On Tue, Apr 02, 2013 at 07:47:24PM +0800, Wenchao Xia wrote:
> >>diff --git a/qmp-commands.hx b/qmp-commands.hx
> >>index 6b20684..b856be7 100644
> >>--- a/qmp-commands.hx
> >>+++ b/qmp-commands.
Il 10/04/2013 19:59, Amit Shah ha scritto:
> On (Wed) 10 Apr 2013 [15:23:27], Paolo Bonzini wrote:
>> After attaching the source, we have to remove the reference we hold
>> to it, because we do not hold anymore a pointer to the source.
>>
>> If we do not do this, removing the source will not finali
Hu Tao writes:
> Hi,
>
> On Wed, Apr 10, 2013 at 01:54:04PM +0200, Markus Armbruster wrote:
>> Hu Tao writes:
>>
>> > pvpanic device is used to send guest panic event from guest to qemu.
>> >
>> > When guest panic happens, pvpanic device driver will write a event
>> > number to IO port 0x505(wh
On Tue, Apr 09, 2013 at 11:25:05AM -0700, Sriram Murthy wrote:
>
>
> Hi,
>
>
> >Personally, I think that the connection between VirtualBox and QEMU is
> >very unidirectional if there is any... So code-wise our focus should
> >rather be to avoid code copies/divergence within our tree and to shar
On Tue, Mar 26, 2013 at 03:00:21PM +0100, Lluís Vilanova wrote:
> NOTE: Applies on top of the "trace: Generic event state description" series
> (already in the tracing tree), and is based on revision a4bcea3 from
> master.
>
> TODO: Make sure no TCG code is executing during 'instr_unlo
On Tue, Apr 09, 2013 at 01:12:39PM +0800, liu ping fan wrote:
> On Mon, Apr 8, 2013 at 7:44 PM, Stefan Hajnoczi wrote:
> > On Wed, Apr 03, 2013 at 05:28:39PM +0800, liu ping fan wrote:
> >> On Thu, Mar 28, 2013 at 10:32 PM, Stefan Hajnoczi
> >> wrote:
> >> > On Thu, Mar 28, 2013 at 03:55:52PM +0
Hu Tao writes:
> Signed-off-by: Hu Tao
> ---
> docs/specs/pvpanic.txt | 37 +
> 1 file changed, 37 insertions(+)
> create mode 100644 docs/specs/pvpanic.txt
>
> diff --git a/docs/specs/pvpanic.txt b/docs/specs/pvpanic.txt
> new file mode 100644
> index 0
On Wed, Apr 10, 2013 at 7:55 PM, Stefan Hajnoczi wrote:
> On Wed, Apr 10, 2013 at 03:47:15PM +0800, liu ping fan wrote:
>> On Tue, Apr 9, 2013 at 11:22 PM, Stefan Hajnoczi wrote:
>> > On Mon, Apr 08, 2013 at 01:36:03PM +0800, Liu Ping Fan wrote:
>> >> This series focus on network backend (excludi
Il 11/04/2013 09:38, Michael S. Tsirkin ha scritto:
> On Wed, Apr 10, 2013 at 06:28:18PM -0400, mrhi...@linux.vnet.ibm.com wrote:
>> From: "Michael R. Hines"
>>
>> This allows the user to disable zero page checking during migration
>>
>> Signed-off-by: Michael R. Hines
>
> IMO this knob is too l
On Tue, Apr 09, 2013 at 01:10:29PM +0800, liu ping fan wrote:
> On Mon, Apr 8, 2013 at 7:46 PM, Stefan Hajnoczi wrote:
> > On Tue, Apr 02, 2013 at 05:49:57PM +0800, liu ping fan wrote:
> >> On Thu, Mar 28, 2013 at 9:40 PM, Stefan Hajnoczi
> >> wrote:
> >> > On Thu, Mar 28, 2013 at 09:42:47AM +01
[Cc: Wenchao Xia because of overlap with his work]
Eric Blake writes:
> On 04/10/2013 08:05 AM, Pavel Hrdina wrote:
>> Here is another proposal how to handle vm snapshots:
>>
>> QMP vm-snapshot-save:
>> - { 'command': 'vm-snapshot-save',
>> 'data': { 'name': 'str' },
>> 'ret
On Mon, Apr 01, 2013 at 01:21:45PM +, Alex Bligh wrote:
> I'd like to experiment with adding persistent writeback cache to qemu.
> The use case here is where non-local storage is used (e.g. rbd, ceph)
> using the qemu drivers, together with a local cache as a file on
> a much faster locally mou
Wenchao Xia writes:
> 于 2013-4-11 0:06, Markus Armbruster 写道:
>> Wenchao Xia writes:
>>
>>>New member *backing-image is added to reflect the backing chain
>>> status.
>>>
>>> Signed-off-by: Wenchao Xia
>>> Reviewed-by: Kevin Wolf
>>> Reviewed-by: Eric Blake
>>> ---
>>> block/qapi.c
On Mon, Apr 08, 2013 at 12:27:06PM +, Zhanghaoyu (A) wrote:
> On Sun, Apr 07, 2013 at 04:58:07AM +, Zhanghaoyu (A) wrote:
> > >>> I start a kvm VM with vnc(using the zrle protocol) connect, sometimes
> > >>> qemu program crashed during starting period, received signal SIGABRT.
> > >>> Tryi
Wenchao Xia writes:
> 于 2013-4-11 2:57, Luiz Capitulino 写道:
>> On Wed, 10 Apr 2013 18:17:04 +0200
>> Markus Armbruster wrote:
>>
>>> Stefan Hajnoczi writes:
>>>
On Tue, Apr 02, 2013 at 07:47:24PM +0800, Wenchao Xia wrote:
> diff --git a/qmp-commands.hx b/qmp-commands.hx
> index 6b2
On Tue, Apr 09, 2013 at 03:30:52PM +0100, Richard W.M. Jones wrote:
> Changes since v8:
>
> - Implement the suggestions of Stefan Hajnoczi.
>
> - Add host_key_check parameter, which you can use like this:
>
> ssh://[...]?host_key_check=no # skip the check entirely
> ssh://[...]?host_key_
On Mon, Apr 01, 2013 at 04:20:30PM +0800, Liu Ping Fan wrote:
> From: Liu Ping Fan
>
> This pair of interface are optinal, except for those device which is
> used outside the biglock's protection for hot unplug.
Not sure if this comment is true. Memory unplug safety is not about the
big lock, i
Wenchao Xia writes:
> 于 2013-4-11 0:49, Markus Armbruster 写道:
>> Wenchao Xia writes:
>>
>>>They are needed later in hmp command, dump_human_image_info()
>>> is renamed to bdrv_image_info_dump().
>>>
>>> Signed-off-by: Wenchao Xia
>>
>> I'd be tempted move everything that needs to move to
Il 01/04/2013 10:20, Liu Ping Fan ha scritto:
> From: Liu Ping Fan
>
> Signed-off-by: Liu Ping Fan
> ---
> vl.c |2 ++
> 1 files changed, 2 insertions(+), 0 deletions(-)
>
> diff --git a/vl.c b/vl.c
> index 7643f16..46a25cf 100644
> --- a/vl.c
> +++ b/vl.c
> @@ -4157,6 +4157,7 @@ int main(
Il 01/04/2013 10:20, Liu Ping Fan ha scritto:
> From: Liu Ping Fan
>
> The hostmem listener will translate gpa to hva quickly. Make it
> global, so other component can use it.
> Also this patch adopt MemoryRegionOps's ref/unref interface to
> make it survive the RAM hotunplug.
>
> Signed-off-by:
On Mon, Apr 01, 2013 at 04:20:31PM +0800, Liu Ping Fan wrote:
> From: Liu Ping Fan
>
> The hostmem listener will translate gpa to hva quickly. Make it
> global, so other component can use it.
> Also this patch adopt MemoryRegionOps's ref/unref interface to
> make it survive the RAM hotunplug.
>
On Mon, Apr 01, 2013 at 04:20:32PM +0800, Liu Ping Fan wrote:
> @@ -51,7 +50,7 @@ bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
>
> void vring_teardown(Vring *vring)
> {
> -hostmem_finalize(&vring->hostmem);
> +memory_region_unref(vring->vring_mr);
> }
dataplane keeps a re
On Mon, Apr 01, 2013 at 04:20:33PM +0800, Liu Ping Fan wrote:
> From: Liu Ping Fan
>
> virtio-blk will reference to RAM's memoryRegion when the req has been
> done. So we can avoid to call bdrv_drain_all() when RAM hot unplug.
How does the hot unplug operation work without bdrv_drain_all()? In
Il 11/04/2013 12:11, Stefan Hajnoczi ha scritto:
> Also, these sync gcc builtins are not available on all platforms or gcc
> versions. We need to be a little careful to avoid breaking builds here.
> Maybe __sync_add_and_fetch() is fine but I wanted to mention it because
> I've had trouble with the
Thanks.
I've also developed patches to incorporate this feature into libvirt
and libguestfs. Here are the latest versions of these:
https://www.redhat.com/archives/libvir-list/2013-April/thread.html#00803
https://www.redhat.com/archives/libguestfs/2013-April/thread.html#00021
Rich.
--
Richard
On Thu, Apr 11, 2013 at 11:18:38AM +0200, Paolo Bonzini wrote:
> Il 11/04/2013 09:38, Michael S. Tsirkin ha scritto:
> > On Wed, Apr 10, 2013 at 06:28:18PM -0400, mrhi...@linux.vnet.ibm.com wrote:
> >> From: "Michael R. Hines"
> >>
> >> This allows the user to disable zero page checking during mig
Hi All,
I have faced a problem using GDB with user-mode qemu. Although problem
was observed for MIPS, I think it is a generic problem. I would
appreciate an advice from experts on how best to deal with. Here is the
problem description.
GDB has ability to call function from the program bein
Add documentation of ftrace backend.
Signed-off-by: Eiichi Tsukata
---
docs/tracing.txt | 16
1 file changed, 16 insertions(+)
diff --git a/docs/tracing.txt b/docs/tracing.txt
index cf53c17..60ff9c5 100644
--- a/docs/tracing.txt
+++ b/docs/tracing.txt
@@ -175,6 +175,22 @@ unles
This patchset introduces a new tracing backend "ftrace".
Currently, QEMU tracing backends do not support userspace tracing with ftrace.
Collecting QEMU trace data and kernel trace data simultaneouly is useful for
latency analysis and debugging especially when using KVM.
With ftrace backend, you c
This patch adds a ftrace tracing backend which sends trace event to
ftrace marker file. You can effectively compare qemu trace data and
kernel(especially, kvm.ko when using KVM) trace data.
The ftrace backend is restricted to Linux only.
To try out the ftrace backend:
$ ./configure --trace-backe
On Thu, Apr 11, 2013 at 11:13 AM, liu ping fan wrote:
> On Wed, Apr 10, 2013 at 7:55 PM, Stefan Hajnoczi wrote:
>> On Wed, Apr 10, 2013 at 03:47:15PM +0800, liu ping fan wrote:
>>> On Tue, Apr 9, 2013 at 11:22 PM, Stefan Hajnoczi
>>> wrote:
>>> > On Mon, Apr 08, 2013 at 01:36:03PM +0800, Liu Pi
If we don't assign 'id' for nic device, device's name will be $model.$idx.
The $idx is always 0 if we use new style of cmdline. This problem was
introduced by commit d33d93b2.
eg:
# qemu-upstream -device virtio-net-pci,netdev=h1 -netdev tap,id=h1 \
-device virtio-net-pci,netde
On Thu, Apr 11, 2013 at 7:44 PM, Stefan Hajnoczi wrote:
> On Thu, Apr 11, 2013 at 11:13 AM, liu ping fan wrote:
>> On Wed, Apr 10, 2013 at 7:55 PM, Stefan Hajnoczi wrote:
>>> On Wed, Apr 10, 2013 at 03:47:15PM +0800, liu ping fan wrote:
On Tue, Apr 9, 2013 at 11:22 PM, Stefan Hajnoczi
>>>
Wenchao Xia writes:
>>>
>>> -void bdrv_image_info_dump(ImageInfo *info)
>>> +void bdrv_image_info_dump(GString *buf, ImageInfo *info)
>>> {
>>> char size_buf[128], dsize_buf[128];
>>> if (!info->has_actual_size) {
>>> @@ -370,43 +369,48 @@ void bdrv_image_info_dump(ImageInfo *inf
On Thu, Apr 11, 2013 at 6:02 PM, Paolo Bonzini wrote:
> Il 01/04/2013 10:20, Liu Ping Fan ha scritto:
>> From: Liu Ping Fan
>>
>> Signed-off-by: Liu Ping Fan
>> ---
>> vl.c |2 ++
>> 1 files changed, 2 insertions(+), 0 deletions(-)
>>
>> diff --git a/vl.c b/vl.c
>> index 7643f16..46a25cf 10
Wenchao Xia writes:
>>> # Statistics of a virtual block device or a block backing device.
>>> diff --git a/qmp-commands.hx b/qmp-commands.hx
>>> index 1e0e11e..6b20684 100644
>>> --- a/qmp-commands.hx
>>> +++ b/qmp-commands.hx
>>> @@ -1765,6 +1765,61 @@ EQMP
>>> },
>>>
>>> SQMP
>>> +
This patchset is a rework of the 9p live migration patchs made a few years ago
by Aneesh.
As the new vmstate API doesn't support linked list so the old API is used.
Benoît Canet (4):
migration: Create the pre migration flush hook infrastructure.
virtio-9p: Add support for 9p migration.
virti
This patch will allow the block layer and virtio-9p to cleanly register io flush
hooks to be executed by cpus.c.
Signed-off-by: Benoit Canet
---
Makefile |6 +--
Makefile.objs |2 +-
block.c |
This patch use the old migration framework because of lack
of support for migrating linked list in the new generic framework.
This patch is a rebase of Aneesh Kumar's patch.
Signed-off-by: Benoit Canet
---
hw/9pfs/virtio-9p-device.c | 154
1 file ch
The function used to wait is registered as a pre migration flush hook.
The completion status is put in the virtio ring buffer which
will be send to the guest on resume by the viring migration code
This patch is a rewrite from the one written by Aneesh Kumar.
Signed-off-by: Benoit Canet
---
hw/
Signed-off-by: Benoit Canet
---
hw/9pfs/virtio-9p-device.c |2 --
hw/9pfs/virtio-9p.c| 23 ---
hw/9pfs/virtio-9p.h|2 --
3 files changed, 27 deletions(-)
diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c
index 02b8630..f91a9b8 1006
Out of steam, got until 13/17. Rest is HMP; hope to cover that in the
next round. I had a few comments here and there, but nevertheless the
series feels pretty close to commit now.
Related to Pavel's work, cc'ing him.
On 11 April 2013 13:14, Benoît Canet wrote:
> --- /dev/null
> +++ b/include/migration/migration-flush-hooks.h
> @@ -0,0 +1,30 @@
> +/*
> + * QEMU live pre migration flush hooks
> + *
> + * Copyright Nodalink, SARL. 2013
> + *
> + * Authors:
> + * Benoît Canet
> + *
> + * This work is licensed un
On 11 April 2013 13:14, Benoît Canet wrote:
> Signed-off-by: Benoit Canet
> ---
> hw/9pfs/virtio-9p-device.c |2 --
> hw/9pfs/virtio-9p.c| 23 ---
> hw/9pfs/virtio-9p.h|2 --
> 3 files changed, 27 deletions(-)
>
> diff --git a/hw/9pfs/virtio-9p-devic
Stefan Hajnoczi writes:
[...]
> Sorry Lluís, I'm slow with review here again. Will take a look for 1.4
> soft-freeze though.
Dont' worry, there's a couple things I have to redo in this series:
* Properly handle qi_init arguments (aka, "qi_init (int argc, char **argv)").
* Rebase on latest master
Il 09/03/2013 23:22, Stefan Hajnoczi ha scritto:
> @block-backup
>
> Start a point-in-time copy of a block device to a new destination.
>
> @device: the name of the device whose writes should be mirrored.
>
> @target: the target of the new image. If the file exists, or if it
> is a dev
Il 11/04/2013 14:14, Benoît Canet ha scritto:
> diff --git a/include/migration/migration-flush-hooks.h
> b/include/migration/migration-flush-hooks.h
> new file mode 100644
> index 000..be9e597
> --- /dev/null
> +++ b/include/migration/migration-flush-hooks.h
> @@ -0,0 +1,30 @@
> +/*
> + * QEMU
On 04/11/2013 03:30 PM, Eric Blake wrote:
> On 04/11/2013 01:52 AM, Orit Wasserman wrote:
>> On 04/11/2013 05:39 AM, Michael R. Hines wrote:
>>> On 04/10/2013 10:26 PM, Eric Blake wrote:
New QMP commands should be named with '-' rather than '_', as in
'migrate-check-for-zero'.
>
> Il 10/04/2013 14:48, Liuji (Jeremy) ha scritto:
> > Hi, Paolo
> >
> > I tested your 4 patches in the latest version of qemu.git/master(commit:
> > 93b48c201eb6c0404d15550a0eaa3c0f7937e35e,2013-04-09).
> > These patches resolve the "savevm hanging" problem, which is detailedly
> described
> > in m
Il 11/04/2013 14:14, Benoît Canet ha scritto:
> The function used to wait is registered as a pre migration flush hook.
>
> The completion status is put in the virtio ring buffer which
> will be send to the guest on resume by the viring migration code
>
> This patch is a rewrite from the one writt
Hi, Juan
Thanks for your reply.
Yesterday, my disk has no space. So, the core-dump file not saved completely.
The info of core-dump file is:
#0 0x7f7a0dbff341 in migration_thread (opaque=0x7f7a0e16cbc0) at
migration.c:545
545 double bandwidth = transferred_bytes / time_spent
Acknowledged.
On 04/11/2013 02:26 AM, Paolo Bonzini wrote:
Il 11/04/2013 00:28, mrhi...@linux.vnet.ibm.com ha scritto:
+#ifdef CONFIG_RDMA
+int qemu_rdma_registration_start(QEMUFile *f, void *opaque, uint32_t flags)
+{
+DPRINTF("start section: %d\n", flags);
+qemu_put_be64(f, RAM_SAV
On 11 April 2013 13:38, Paolo Bonzini wrote:
> Il 11/04/2013 14:14, Benoīt Canet ha scritto:
>> int open_fd_hw;
>> int total_open_fd;
>> static int open_fd_rc;
>>
>> +typedef struct MigrationHelper {
>> +int32_t pending_requests;
>> +QemuCond complete;
>> +QemuMutex mutex;
>> +} Mig
On Thu, 11 Apr 2013 14:11:23 +0200
Markus Armbruster wrote:
> Wenchao Xia writes:
>
> >>> # Statistics of a virtual block device or a block backing device.
> >>> diff --git a/qmp-commands.hx b/qmp-commands.hx
> >>> index 1e0e11e..6b20684 100644
> >>> --- a/qmp-commands.hx
> >>> +++ b/qmp-comm
On Wed, 10 Apr 2013 13:12:44 -0600
Eric Blake wrote:
> * qapi-schema.json: JSON doesn't allow trailing commas.
>
> Signed-off-by: Eric Blake
Applied to the qmp branch, thanks.
> ---
>
> a multi-line regex search for ',[ \n]*[]}]' didn't turn up any
> other violations
>
> qapi-schema.json |
On 04/11/2013 01:52 AM, Orit Wasserman wrote:
> On 04/11/2013 05:39 AM, Michael R. Hines wrote:
>> On 04/10/2013 10:26 PM, Eric Blake wrote:
>>>
>>> New QMP commands should be named with '-' rather than '_', as in
>>> 'migrate-check-for-zero'.
>>>
>>> Why do we need a new command, instead of adding
On 04/11/2013 06:44 AM, Luiz Capitulino wrote:
> +-> { "execute": "query-snapshots" }
> +<- {
> + "return":[
> + {
> +"id": "1",
> +"name": "snapshot1",
> +"vm-state-size": 0,
> +"date-sec": 1200,
On 04/11/2013 03:19 AM, Michael S. Tsirkin wrote:
On Wed, Apr 10, 2013 at 04:05:34PM -0400, Michael R. Hines wrote:
Maybe we should just say "RDMA is incompatible with memory overcommit"
and be done with it then. But see below.
I would like to propose a compromise:
How about we *keep* the regi
Il 11/04/2013 14:08, liu ping fan ha scritto:
>>> >> /* clean up network at qemu process termination */
>>> >> atexit(&net_cleanup);
>>> >> +atexit(&hostmem_finalize);
>> >
>> > This should be in hostmem_init.
>> >
> Ok, thanks. And extra, for the hostmem_init, what about something li
On 04/11/2013 07:13 AM, Michael S. Tsirkin wrote:
On Thu, Apr 11, 2013 at 11:18:38AM +0200, Paolo Bonzini wrote:
Il 11/04/2013 09:38, Michael S. Tsirkin ha scritto:
On Wed, Apr 10, 2013 at 06:28:18PM -0400, mrhi...@linux.vnet.ibm.com wrote:
From: "Michael R. Hines"
This allows the user to di
That's very accurate. Zero page scanning *after* the bulk phase
is not very helpful in general.
Are we proposing to skip is_dup_page() after the bulk phase
has finished?
The testcase I'm using is a "worst-case" stress memory hog command
(apt-get install stress) - but against this does not affect
On Thu, 11 Apr 2013 07:08:41 -0600
Eric Blake wrote:
> On 04/11/2013 06:44 AM, Luiz Capitulino wrote:
>
> > +-> { "execute": "query-snapshots" }
> > +<- {
> > + "return":[
> > + {
> > +"id": "1",
> > +"name": "snapshot1",
> > +
Hi,
I am working on TLS support for VNC Websockets in QEMU and while I
already got it working I need to make some design decisions.
Websockets over TLS need certificates.
We already have the "x509" vnc parameter for VNC-TLS to provide the
certificates but user might have one webserver certifi
On Tue, 9 Apr 2013 12:04:48 +0200
fred.kon...@greensocs.com wrote:
> From: KONRAD Frederic
>
> This fix the broken aliases, by renaming the devices.
>
> So: * virtio-blk => virtio-blk-device.
> * virtio-balloon => virtio-balloon-device.
> * virtio-scsi => virtio-scsi-device.
>
> All v
On Thu, Apr 11, 2013 at 09:12:17AM -0400, Michael R. Hines wrote:
> On 04/11/2013 03:19 AM, Michael S. Tsirkin wrote:
> >On Wed, Apr 10, 2013 at 04:05:34PM -0400, Michael R. Hines wrote:
> >Maybe we should just say "RDMA is incompatible with memory
> >overcommit" and be done with it then. But see b
On Thu, Apr 11, 2013 at 09:19:43AM -0400, Michael R. Hines wrote:
> On 04/11/2013 07:13 AM, Michael S. Tsirkin wrote:
> >On Thu, Apr 11, 2013 at 11:18:38AM +0200, Paolo Bonzini wrote:
> >>Il 11/04/2013 09:38, Michael S. Tsirkin ha scritto:
> >>>On Wed, Apr 10, 2013 at 06:28:18PM -0400, mrhi...@linu
On 04/11/2013 09:51 AM, Michael S. Tsirkin wrote:
On Thu, Apr 11, 2013 at 09:19:43AM -0400, Michael R. Hines wrote:
On 04/11/2013 07:13 AM, Michael S. Tsirkin wrote:
On Thu, Apr 11, 2013 at 11:18:38AM +0200, Paolo Bonzini wrote:
Il 11/04/2013 09:38, Michael S. Tsirkin ha scritto:
On Wed, Apr
On 04/11/2013 09:48 AM, Michael S. Tsirkin wrote:
On Thu, Apr 11, 2013 at 09:12:17AM -0400, Michael R. Hines wrote:
On 04/11/2013 03:19 AM, Michael S. Tsirkin wrote:
On Wed, Apr 10, 2013 at 04:05:34PM -0400, Michael R. Hines wrote:
Maybe we should just say "RDMA is incompatible with memory
over
Il 11/04/2013 15:24, Michael R. Hines ha scritto:
> That's very accurate. Zero page scanning *after* the bulk phase
> is not very helpful in general.
>
> Are we proposing to skip is_dup_page() after the bulk phase
> has finished?
No, I'm saying that is_dup_page() should not be a problem. I'm say
Il 11/04/2013 16:06, Michael R. Hines ha scritto:
>>>
>> My understanding is the issue is protocol compatibility,
>> not optimization. E.g. you can migrate to file, for each
>> new feature you need a way to disable it to stay compatible.
>
> Ok, understood.
>
> I would be happy to add a check for
On 10 April 2013 21:16, Keith Busch wrote:
> Initial commit for emulated nvme pci storage device. Implements the
> minimum from the specification to work with existing drivers.
The commit message could be a little more informative for
those who have no idea what an nvme is...
> +static const VMS
From: KONRAD Frederic
Recent changes need two functions to VirtioDevice. This just add them
into VirtioDeviceClass.
Signed-off-by: KONRAD Frederic
---
include/hw/virtio/virtio.h | 12
1 file changed, 12 insertions(+)
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/vir
From: KONRAD Frederic
This is the next part of virtio-refactoring.
Basically it creates virtio-net-device which extends virtio-device.
Then a virtio-net-device can be connected on a virtio-bus.
virtio-net-pci, virtio-net-s390 and virtio-net-ccw are created too,
they extend respectively virtio-pc
From: KONRAD Frederic
Create virtio-net-device which extends virtio-device, so it can be connected on
virtio-bus.
Signed-off-by: KONRAD Frederic
---
hw/net/virtio-net.c| 152 +++--
hw/s390x/s390-virtio-bus.c | 6 +-
hw/s390x/virtio-ccw.c
From: KONRAD Frederic
Here the virtio-net-s390 is modified for the new API. The device
virtio-net-s390 extends virtio-s390-device as before. It creates and
connects a virtio-net-device during the init. The properties are not modified.
Signed-off-by: KONRAD Frederic
---
hw/s390x/s390-virtio-bus
From: KONRAD Frederic
Here the virtio-net-pci is modified for the new API. The device
virtio-net-pci extends virtio-pci. It creates and connects a
virtio-net-device during the init. The properties are not changed.
Signed-off-by: KONRAD Frederic
---
hw/virtio/virtio-pci.c | 114
From: KONRAD Frederic
As the virtio-net-pci and virtio-net-s390 are switched to the new API,
we can use QOM casts.
Signed-off-by: KONRAD Frederic
---
hw/net/virtio-net.c| 141 +
include/hw/virtio/virtio-net.h | 2 +-
2 files changed, 75 ins
From: KONRAD Frederic
This remove old init and exit function as they are no longer needed.
Signed-off-by: KONRAD Frederic
---
hw/net/virtio-net.c | 117 ++--
1 file changed, 22 insertions(+), 95 deletions(-)
diff --git a/hw/net/virtio-net.c b/hw
From: KONRAD Frederic
Here the virtio-net-ccw is modified for the new API. The device
virtio-net-ccw extends virtio-ccw-device as before. It creates and
connects a virtio-net-device during the init. The properties are not modified.
Signed-off-by: KONRAD Frederic
---
hw/s390x/virtio-ccw.c | 31
On Thu, Apr 11, 2013 at 09:58:50AM -0400, Michael R. Hines wrote:
> On 04/11/2013 09:48 AM, Michael S. Tsirkin wrote:
> >On Thu, Apr 11, 2013 at 09:12:17AM -0400, Michael R. Hines wrote:
> >>On 04/11/2013 03:19 AM, Michael S. Tsirkin wrote:
> >>>On Wed, Apr 10, 2013 at 04:05:34PM -0400, Michael R.
This patchset is a rework of the 9p live migration patchs made a few years ago
by Aneesh.
As the new vmstate API doesn't support linked list so the old API is used.
v2:
Drop pre migration flush hook code (Paolo)
Use vmstate change notifier (Paolo)
Use static variables instead of a stru
This patch use the old migration framework because of lack
of support for migrating linked list in the new generic framework.
This patch is a rebase of Aneesh Kumar's patch.
Signed-off-by: Benoit Canet
---
hw/9pfs/virtio-9p-device.c | 152
1 file ch
The completion status is put in the virtio ring buffer which
will be send to the guest on resume by the viring vmstate code
This patch is a rewrite from the one written by Aneesh Kumar.
Signed-off-by: Benoit Canet
---
hw/9pfs/virtio-9p-device.c |2 ++
hw/9pfs/virtio-9p.c| 75 +
Can I at least get a firm yes or no whether the maintainer will
accept this capability or not?
What you ask would require defining what a "real world scenario" is, and
I don't think that's a good discussion to have right now. Even if we did
know the
definition, I do not have the infrastructure
On Thu, Apr 11, 2013 at 04:15:54PM +0200, Paolo Bonzini wrote:
> Il 11/04/2013 15:24, Michael R. Hines ha scritto:
> > That's very accurate. Zero page scanning *after* the bulk phase
> > is not very helpful in general.
> >
> > Are we proposing to skip is_dup_page() after the bulk phase
> > has fin
Signed-off-by: Benoit Canet
---
hw/9pfs/virtio-9p.c | 23 ---
hw/9pfs/virtio-9p.h |2 --
2 files changed, 25 deletions(-)
diff --git a/hw/9pfs/virtio-9p.c b/hw/9pfs/virtio-9p.c
index 66322ee..d81087b 100644
--- a/hw/9pfs/virtio-9p.c
+++ b/hw/9pfs/virtio-9p.c
@@ -404,19
Il 11/04/2013 16:37, Michael S. Tsirkin ha scritto:
>
> pg1 -> pin -> req -> res -> rdma -> done
> pg2 -> pin -> req -> res -> rdma -> done
> pg3 -> pin -> req -> res -> rdma -> done
>pg4 -> pin -> req -> res -> rdma -> done
>
... so it could be called from without requiring CPUArchState
Signed-off-by: Igor Mammedov
Reviewed-by: Eduardo Habkost
---
cpus.c | 4 ++--
include/sysemu/kvm.h | 12 ++--
kvm-all.c| 8 ++--
kvm-stub.c | 4 ++--
4 files changed, 12 insertions(
Signed-off-by: Igor Mammedov
---
Makefile.target | 13 +++--
include/hw/pci/msi.h | 2 ++
include/sysemu/kvm.h | 4 ++--
kvm-stub.c | 2 ++
4 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/Makefile.target b/Makefile.target
index 2bd6d14..18f348c 100644
---
... it should be used only on slow path since it does recursive search
on /machine QOM tree for objects of TYPE_CPU
Signed-off-by: Igor Mammedov
Reviewed-by: Paolo Bonzini
---
v2:
* s/get_firmware_id()/get_arch_id()/ rebase fixup
* remove check for get_arch_id being NULL, since it's alwa
1 - 100 of 259 matches
Mail list logo
