Anthony Liguori wrote:
> On 11/23/2010 05:02 PM, Juan Quintela wrote:
>> From: Juan Quintela
>>
>> When printing debug information for migration, print total time spent.
>>
>> Signed-off-by: Juan Quintela
>> Signed-off-by: Juan Quintela
>> ---
>> migration.c | 13 +
>> 1 files cha
Anthony Liguori wrote:
> On 11/23/2010 05:03 PM, Juan Quintela wrote:
>> From: Juan Quintela
>>
>> TLB handling is only used in TCG mode. It is very costly for guests with
>> lots
>> of memory ad lots of CPU's.
>>
>> Signed-off-by: Juan Quintela
>> Signed-off-by: Juan Quintela
>> ---
>> exec.c
On 11/24/2010 09:16 AM, Paolo Bonzini wrote:
On 11/24/2010 12:14 PM, Michael S. Tsirkin wrote:
> buffered_file timer runs each 100ms. And we "try" to measure
channel
> bandwidth from there. If we are not able to run the timer, all the
> calculations are wrong, and then stalls happens.
So
On 11/23/2010 05:02 PM, Juan Quintela wrote:
From: Juan Quintela
This time is each time that buffered_file ticks happen
Signed-off-by: Juan Quintela
Signed-off-by: Juan Quintela
This patch is wrong.
The point of the tick is to establish a period during which only a
certain amount of tra
On Sun, Nov 28, 2010 at 08:47:34PM +0200, Gleb Natapov wrote:
> On Sun, Nov 28, 2010 at 12:15:44PM -0500, Kevin O'Connor wrote:
> > It's unclear to me how SeaBIOS is supposed to do that.
> >
> Suppose we have "/p...@i0cf8/s...@3/d...@0,0" with boot index 5 in
> boot devices list and suppose pci de
Anthony Liguori wrote:
> On 11/23/2010 05:03 PM, Juan Quintela wrote:
>> From: Juan Quintela
>>
>> cheking each 64 pages is a random magic number as good as any other.
>> We don't want to test too many times, but on the other hand,
>> qemu_get_clock_ns() is not so expensive either.
>>
>> Signed-of
On Mon, Nov 29, 2010 at 11:50:45AM +0100, Gerd Hoffmann wrote:
> >>If scsi card has optionrom with only one bcv then Seabios can determine
> >>its boot order from device path, so why not provide user with this
> >>option today?
> >It's unclear to me how SeaBIOS is supposed to do that.
> Try to keep
On 11/23/2010 05:03 PM, Juan Quintela wrote:
From: Juan Quintela
If buffers are full, don't iterate
Signed-off-by: Juan Quintela
Signed-off-by: Juan Quintela
Reviewed-by: Anthony Liguori
Regards,
Anthony Liguori
---
savevm.c |3 +++
1 files changed, 3 insertions(+), 0 deletion
Stefan Hajnoczi wrote:
> On Mon, Nov 29, 2010 at 08:00:18PM -0600, Anthony Liguori wrote:
>> Yeah, all of this should be done via tracing. Maybe Stefan can make
>> some suggestions.
>
> Here is an example of how to record savevm timestamps using tracing.
> Actually the timestamp is recorded autom
On Tue, 30 Nov 2010 16:27:13 +0200
Avi Kivity wrote:
> On 11/30/2010 04:17 PM, Anthony Liguori wrote:
> >> What's the problem with burning that cpu? per guest page,
> >> compressing takes less than sending. Is it just an issue of qemu
> >> mutex hold time?
> >
> >
> > If you have a 512GB gues
Aurelien,
Attached is a patch for Godson-3a CPU support.
Godson-3a is a newly developed MIPS-III like, multicore CPU by ICT, China.
For you review. Any comment is welcomed.
Jin Guojie
www.loongson.cn
0001-MIPS-Initial-support-of-Godson-3a-multicore-CPU.patch
Description: Binary data
Ping.
Maintainers, please tell me if still something is required for
this patch before applying it.
Thanks,
H.Seto
(2010/11/24 17:01), Jes Sorensen wrote:
> On 11/24/10 03:38, Hidetoshi Seto wrote:
>> This patch introduce a fallback mechanism for old systems that do not
>> support utimensat().
At last! I was able to reproduce this using a copy of fedora 1 from
http://archive.kernel.org/fedora-
archive/fedora/linux/core/1/i386/iso/yarrow-i386-disc1.iso
This would segfault before completing install from disc 1 more than 50%
of the time. With the qemu-kvm from -proposed, I've not been a
On 11/30/2010 02:21 PM, Blue Swirl wrote:
On Mon, Nov 29, 2010 at 8:02 PM, Anthony Liguori wrote:
Savannah is down (and has been for two days) due to an intrusion that's
still being investigated. There is not ETA for when service will be
restored.
I'd like to propose that we that we use t
On 11/24/2010 09:57 AM, Michael S. Tsirkin wrote:
Note: to avoid conflict in a merge I cherry-picked a patch by Stefan
from master to my branch. git seems to resolve this without effort.
The following changes since commit e927d48722fdcba50f82d653c5a1927752483054:
pci: allow hotplug removal
This patch replaces explicit bswaps with endianness hints to the
mmio layer.
Because we don't depend on the target endianness anymore, we can also
move the driver over to Makefile.objs.
Signed-off-by: Alexander Graf
---
Makefile.objs |1 +
Makefile.target |3 ---
hw/usb-ohci.c |
This patch replaces explicit bswaps with endianness hints to the
mmio layer.
Signed-off-by: Alexander Graf
---
hw/openpic.c | 23 ++-
1 files changed, 2 insertions(+), 21 deletions(-)
diff --git a/hw/openpic.c b/hw/openpic.c
index 0e287bd..7b75d3f 100644
--- a/hw/openpic.c
The way mmio endianness is currently implemented is horrifying.
In the real world, CPUs have an endianness and write out data
to the memory bus. Instead of RAM, a receiving side here can be
a device. This device gets a byte stream again and needs to
make sense of it.
Since big endian systems writ
The way we're currently modeling mmio is too simplified. We assume that
every device has the same endianness as the target CPU. In reality,
most devices are little endian (all PCI and ISA ones I'm aware of). Some
are big endian (special system devices) and a very little fraction is
target native en
---
Makefile.objs |2 +-
qemu-char.c |7 ++
qemu-config.c |9 ++
qemu-options.hx | 18 -
spice-qemu-char.c | 222 +
spice-qemu-char.h |9 ++
6 files changed, 265 insertions(+), 2 deletions(-)
create mode 10
Anthony Liguori wrote:
> On 11/30/2010 10:32 AM, Juan Quintela wrote:
>> "Michael S. Tsirkin" wrote:
>>
>>> On Tue, Nov 30, 2010 at 04:40:41PM +0100, Juan Quintela wrote:
>>>
Basically our bitmap handling code is "exponential" on memory size,
>>> I didn't realize this.
protocol_client_auth_vnc() has two places where the auth can fail,
with identical code sending the reject message to the client.
Move the common code to the end of the function and make both
error paths jump there. No functional change.
Signed-off-by: Gerd Hoffmann
---
ui/vnc.c | 30 +
All drivers use bs->file instead of s->hd for quite a while now, so it's time
to remove s->hd.
Signed-off-by: Kevin Wolf
Reviewed-by: Stefan Hajnoczi
---
block/qcow.c |1 -
block/qcow2.h |1 -
block/vdi.c |1 -
block/vmdk.c |1 -
block/vpc.c |2 --
5 files changed, 0 i
Anthony,
Can you please apply this patch and update the submodule in QEMU
to use it? Its the only diff between qemu-kvm's vgabios and qemu's.
Thanks
On Mon, Nov 22, 2010 at 12:24:04PM +0100, Gerd Hoffmann wrote:
> On 11/21/10 16:33, Avi Kivity wrote:
> >+{ 1280, 768, 16 , 0
The following changes since commit f711df67d611e4762966a249742a5f7499e19f99:
microblaze: target-ify target_ucontext (2010-11-23 10:04:30 +0100)
are available in the git repository at:
git://repo.or.cz/qemu/kevin.git for-anthony
Avi Kivity (1):
ide: convert bmdma address ioport to iopor
Hi,
This tiny patch series adds spice connection events and a monitor
command for qmü+hmp to query the spice status.
v2 splits the single patch into two to ease review and also adds
documentation for the commands.
please review,
Gerd
Gerd Hoffmann (2):
spice: connection events.
spic
From: Hannes Reinecke
The SCSI parallel interface has a limit of 8 devices, but
not the SCSI stack in general. So we should be removing the
hard-coded limit and use MAX_SCSI_DEVS instead.
And we only need to scan those devices which are allocated
by the bus.
Signed-off-by: Hannes Reinecke
Acked
On Tue, Nov 30, 2010 at 07:35:54PM +0900, Yoshiaki Tamura wrote:
> Marcelo Tosatti wrote:
> >On Tue, Nov 30, 2010 at 06:28:55PM +0900, Yoshiaki Tamura wrote:
> >>2010/11/30 Marcelo Tosatti:
> >>>On Thu, Nov 25, 2010 at 03:06:48PM +0900, Yoshiaki Tamura wrote:
> event-tap controls when to start
Anthony Liguori wrote:
> On 11/30/2010 08:12 AM, Paolo Bonzini wrote:
>> On 11/30/2010 02:47 PM, Anthony Liguori wrote:
>>> On 11/30/2010 01:15 AM, Paolo Bonzini wrote:
> Juan's patch, IIUC, does the following: If you've been iterating in a
> tight loop, return to the main loop for *one* iteratio
From: Hannes Reinecke
Traditionally, the linux stack is using SCSI status codes
which are shifted by one as compared to those defined in SAM.
A SCSI emulation should naturally return the SAM defined codes,
not the linux ones.
So to avoid any confusion this patch modifies the existing
definitions
Hi,
On 11/30/2010 12:32 PM, Alon Levy wrote:
On Tue, Nov 30, 2010 at 12:26:56PM +0100, Hans de Goede wrote:
Then there would be multiple ways to add a virtual usb device using
usb-net-redir.c to
the virtual machine. One way of adding such a device could be starting a tcp/ip
server
on a ma
On Wed, 01 Dec 2010 02:52:08 +0100
Juan Quintela wrote:
> > Since we are planning to do some profiling for these, taking into account
> > Kemari, can you please share these information?
>
> If you see the 0/10 email with this setup, you can see how much time are
> we spending on stuff. Just now
From: Ryan Harper
Currently device hotplug removal code is tied to device removal via
ACPI. All pci devices that are removable via device_del() require the
guest to respond to the request. In some cases the guest may not
respond leaving the device still accessible to the guest. The management
From: Avi Kivity
cmd646, via compile tested, pci lightly boot tested.
Signed-off-by: Avi Kivity
Signed-off-by: Kevin Wolf
---
hw/ide/cmd646.c |8 +
hw/ide/internal.h |2 +
hw/ide/pci.c | 71 +---
hw/ide/pci.h |7 +--
From: Marcelo Tosatti
An old version of this patch was applied to master, so this contains the
differences between v1 and v2.
Signed-off-by: Marcelo Tosatti
Signed-off-by: Kevin Wolf
---
block-migration.c | 14 +-
1 files changed, 5 insertions(+), 9 deletions(-)
diff --git a/bl
On 11/30/2010 09:53 AM, Chris Wright wrote:
2011 KVM Conference
- together with LF event like LinuxCon Vancouver BC (Aug), KS Prague (Nov)
- wider audience
- include qemu (tcg)
- include libvirt
- include xen
0.14.0 release plan
- could push things out, mainly want to keep on track for
On 11/29/2010 11:40 PM, Anthony Liguori wrote:
In the interim, I've updated the wiki to make the latest release
download point to qemu.org, and I also wanted to remind everyone that
http://git.qemu.org/qemu.git is an up-to-date mirror of the QEMU
development tree. I expect that we'll shortly st
Anthony Liguori wrote:
> On 11/30/2010 05:56 AM, Juan Quintela wrote:
>> No, I benchmarked against two workloads:
>> a- idle guest (because it was faster to test)
>> b- busy guest (each test takes forever, that is the reason that I tested
>> last).
>>
>> So, I don't agree with that.
>>
>
> But
On Fri, Nov 19, 2010 at 04:19:01PM -0700, Alex Williamson wrote:
> v3:
>
> - Rework to avoid introducing conflicts with qemu.git hw/pci
> - Drop capability lookup table
> - Add back minimal device assignment PM, EXP, X, VPD, VNDR
>capabilities
>
> This version should do a much better job a
Backing filenames may contain a protocol. The code currently doesn't
consider this case and produces filenames that embed ":".
Don't combine filenames if the backing filename contains a protocol.
Based on an earlier patch by Anthony Liguori .
Signed-off-by: Stefan Hajnoczi
---
block.c | 15 +
On Tue, Nov 30, 2010 at 04:01:00PM +0200, Gleb Natapov wrote:
> On Mon, Nov 29, 2010 at 08:34:03PM -0500, Kevin O'Connor wrote:
> > On Sun, Nov 28, 2010 at 08:47:34PM +0200, Gleb Natapov wrote:
> > > If you let go to the idea of exact matching of string built by qemu in
> > > Seabios it will be eas
Anthony sent out a patch to make backing filenames that contain a protocol
work. An issue with bdrv_find_protocol() was identified because its interface
makes it impossible to distinguish between filenames that start with "file:"
and those that have no ":" at all.
This patch series solves the iss
The bdrv_find_protocol() function returns NULL if an unknown protocol
name is given. It returns the "file" protocol when the filename
contains no protocol at all. This makes it difficult to distinguish
between paths which contain a protocol and those which do not.
Factor out a helper function th
Filenames may start with ":" to explicitly use a protocol like
nbd. Filenames with unknown protocols are rejected in most of QEMU
except for bdrv_create_file(). Even if a file with an invalid filename
can be created, QEMU cannot use it since all the other relevant
functions reject such paths. Ma
Takuya Yoshikawa wrote:
> On Tue, 30 Nov 2010 16:27:13 +0200
> Avi Kivity wrote:
> Does anyone is profiling these dirty bitmap things?
I am.
> - 512GB guest is really the target?
no, problems exist with smaller amounts of RAM. with 16GB guest it is
trivial to get 1s stalls, 64GB guest, 3-4s
Avi Kivity wrote:
> On 11/30/2010 04:17 PM, Anthony Liguori wrote:
>>> What's the problem with burning that cpu? per guest page,
>>> compressing takes less than sending. Is it just an issue of qemu
>>> mutex hold time?
>>
>>
>> If you have a 512GB guest, then you have a 16MB dirty bitmap which
>
This patch replaces explicit bswaps with endianness hints to the
mmio layer.
Signed-off-by: Alexander Graf
---
hw/ppc4xx_pci.c | 17 ++---
1 files changed, 2 insertions(+), 15 deletions(-)
diff --git a/hw/ppc4xx_pci.c b/hw/ppc4xx_pci.c
index f2ecece..f62f1f9 100644
--- a/hw/ppc4xx
On Tue, Nov 30, 2010 at 08:02:56AM -0600, Anthony Liguori wrote:
> If we're burning excess CPU walking a 100MB bitmap, then let's fix
> that problem. Stopping every 1MB worth of the bitmap to do other
> work just papers over the real problem (that we're walking 100MB
> bitmap).
Just using a bit p
Anthony Liguori wrote:
> On 11/23/2010 05:03 PM, Juan Quintela wrote:
>> From: Juan Quintela
>>
>> It returns a counter of things, not a ram address.
>>
>> Signed-off-by: Juan Quintela
>> Signed-off-by: Juan Quintela
>> ---
>> arch_init.c |4 ++--
>> 1 files changed, 2 insertions(+), 2 dele
On 11/30/2010 10:32 AM, Juan Quintela wrote:
"Michael S. Tsirkin" wrote:
On Tue, Nov 30, 2010 at 04:40:41PM +0100, Juan Quintela wrote:
Basically our bitmap handling code is "exponential" on memory size,
I didn't realize this. What makes it exponential?
Well, 1st of a
Hi,
The following changes since commit 661a1799ba6544a54888283db19dd51469da01e5:
Add pcnet-pci.c (2010-11-27 11:56:02 +)
are available in the git repository at:
git://anongit.freedesktop.org/spice/qemu qxl
Gerd Hoffmann (2):
spice: add qxl vgabios binary.
spice: add qxl d
As an alternative to the 3 individual handlers, there is also a simplified
io mem hook function. To be consistent, let's add an endianness parameter
there too.
Signed-off-by: Alexander Graf
---
hw/apb_pci.c |3 ++-
hw/pci_host.c | 12
hw/unin_pci.c |6 --
rwhandler.c
The e1000 has compatibility code to handle big endianness which makes it
mandatory to be recompiled on different targets.
With the generic mmio endianness solution, there's no need for that anymore.
We just declare all mmio to be little endian and call it a day.
Because we don't depend on the tar
Hi,
This patch series adds new monitor commands to set and expire
the password:
set-password $protocol $secret
expire-password $protocol [ now | never | +secs | secs ]
The time when the password expires can be specified either relative
(+60 == password expires in 60 seconds from now) or ab
On 11/18/2010 10:07 AM, Arun R Bharadwaj wrote:
> Cleanup posix-aio.compat.c off all the old code which
> is now useless after introducing the generic threadlet
> infrasturcture.
>
> Signed-off-by: Arun R Bharadwaj
Looks good to me.
Acked-by: Venkateswararao Jujjuri
> ---
> posix-aio-compat.
This patch replaces explicit bswaps with endianness hints to the
mmio layer.
Because we don't depend on the target endianness anymore, we can also
move the driver over to Makefile.objs.
Signed-off-by: Alexander Graf
---
Makefile.objs |1 +
Makefile.target |3 ---
hw/rtl8139.c| 1
The only reason we have bswap versions of the pci host code is that
most pci host devices are little endian. The ppc e500 is the only
odd one here, being big endian.
So let's directly pass the endianness down to the mmio layer and not
worry about it on the pci host layer.
Signed-off-by: Alexander
On 11/18/2010 10:07 AM, Arun R Bharadwaj wrote:
> Move qemu_paio_submit() to the new infrastructure and
> introduce the necessary APIs.
>
> Signed-off-by: Arun R Bharadwaj
Looks good to me.
Acked-by: Venkateswararao Jujjuri
> ---
> posix-aio-compat.c | 224
> +++
There's no need to bswap once we correctly set the mmio to be little endian.
Signed-off-by: Alexander Graf
---
hw/unin_pci.c |6 ++
1 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/hw/unin_pci.c b/hw/unin_pci.c
index f2e440e..5f15058 100644
--- a/hw/unin_pci.c
+++ b/hw/unin
This patch adds support for connection events to spice. The events are
quite simliar to the vnc events. Unlike vnc spice uses multiple tcp
channels though. qemu will report every single tcp connection (aka
spice channel). If you want track spice sessions only you can filter
for the main channel
On 11/19/2010 2:07 AM, Stefan Hajnoczi wrote:
> On Thu, Nov 18, 2010 at 6:06 PM, Arun R Bharadwaj
> wrote:
>> Move paio_cancel() to new infrastructure and introduce
>> the necessary APIs for this.
>>
>> Signed-off-by: Arun R Bharadwaj
>> ---
>> posix-aio-compat.c | 92
>> +
On 11/30/2010 07:58 AM, Avi Kivity wrote:
On 11/30/2010 03:47 PM, Anthony Liguori wrote:
On 11/30/2010 01:15 AM, Paolo Bonzini wrote:
On 11/30/2010 03:11 AM, Anthony Liguori wrote:
BufferedFile should hit the qemu_file_rate_limit check when the socket
buffer gets filled up.
The problem is t
The patch adds a 'query-spice' monitor command which returns
informations about the spice server configuration and also a list of
channel connections.
Signed-off-by: Gerd Hoffmann
---
monitor.c | 20
qmp-commands.hx | 70
ui/qemu-spice.h |3 +
Hi,
On 11/29/2010 06:49 PM, Anthony Liguori wrote:
On 11/29/2010 11:37 AM, Attila Sukosd wrote:
Hi,
I guess it should be abstract enough to support multiple back-ends, be it a
kernel driver or through libusb?
Is this something that should just live in libusb?
If what libusb presented QEMU
On 11/19/2010 2:17 AM, Stefan Hajnoczi wrote:
> On Thu, Nov 18, 2010 at 6:07 PM, Arun R Bharadwaj
> wrote:
>> From: Gautham R Shenoy
>>
>> infrastructure for offloading blocking tasks such as making posix calls on
>> to the helper threads and handle the post_posix_operations() from the
>> context
On 11/18/2010 10:07 AM, Arun R Bharadwaj wrote:
> The reason for creating this generic infrastructure is so that other
> subsystems,
> such as virtio-9p could make use of it for offloading tasks that could block.
If I read it right..this patch is nothing but reorganizing the code.
i.e moving the
Add some unit tests especially for the ordering and request merging in
block-queue.
Signed-off-by: Kevin Wolf
---
Makefile|1 +
check-block-queue.c | 402 +++
2 files changed, 403 insertions(+), 0 deletions(-)
create mode 100644 c
On 11/30/2010 05:56 AM, Juan Quintela wrote:
No, I benchmarked against two workloads:
a- idle guest (because it was faster to test)
b- busy guest (each test takes forever, that is the reason that I tested
last).
So, I don't agree with that.
But in both cases, it's a large memory guest wher
This is a first hack that makes qcow2 use block-queue. Will be reworked to pass
down the blkqueue context to all functions that queue requests instead of using
a global per-image context.
---
block/qcow2-cluster.c | 39 +++---
block/qcow2-refcount.c | 62 ++
On Tue, Nov 30, 2010 at 03:34:29PM +0200, Michael S. Tsirkin wrote:
> On Tue, Nov 30, 2010 at 10:45:40AM -0200, Marcelo Tosatti wrote:
> > On Wed, Nov 24, 2010 at 05:52:58PM +0200, Michael S. Tsirkin wrote:
> > > Make sure disk is in consistent state.
> > >
> > > Signed-off-by: Michael S. Tsirkin
On 11/30/2010 01:15 AM, Paolo Bonzini wrote:
On 11/30/2010 03:11 AM, Anthony Liguori wrote:
BufferedFile should hit the qemu_file_rate_limit check when the socket
buffer gets filled up.
The problem is that the file rate limit is not hit because work is
done elsewhere. The rate can limit the
The softfloat functions float*_is_nan() were badly misnamed,
because they return true only for quiet NaNs, not for all NaNs.
Rename them to float*_is_quiet_nan() to more accurately reflect
what they do.
This change was produced by:
perl -p -i -e 's/_is_nan/_is_quiet_nan/g' $(git grep -l is_nan)
(
This patch adds a field to PCIDeviceInfo to tag devices as being
not hotpluggable. Any attempt to plug-in or -out such a device
will throw an error.
Signed-off-by: Gerd Hoffmann
---
hw/pci.c | 10 ++
hw/pci.h |3 +++
qerror.c |4
qerror.h |3 +++
4 files changed, 20 i
We added qemu_ram_alloc_from_ptr, but we need its corresponding "free"
function. With that, we can properly remove the ivshmem memory on unplug.
Cam Macdonell (2):
add qemu_ram_free_from_ptr
Unregister shared memory on unplug.
cpu-common.h |1 +
exec.c | 13 +
hw/iv
Anthony Liguori wrote:
> On 11/30/2010 01:15 PM, Juan Quintela wrote:
At the end of the ram_save_live(). This was the reason that I put the
information there.
for the 24mins stall (I don't have that machine anymore) I had less
"exact" measurements. It was the amount tha
On Tue, Nov 30, 2010 at 10:45:40AM -0200, Marcelo Tosatti wrote:
> On Wed, Nov 24, 2010 at 05:52:58PM +0200, Michael S. Tsirkin wrote:
> > Make sure disk is in consistent state.
> >
> > Signed-off-by: Michael S. Tsirkin
> > Tested-by: Jason Wang
> > ---
> > cpus.c |2 ++
> > 1 files changed
On Wed, Nov 24, 2010 at 05:52:58PM +0200, Michael S. Tsirkin wrote:
> Make sure disk is in consistent state.
>
> Signed-off-by: Michael S. Tsirkin
> Tested-by: Jason Wang
> ---
> cpus.c |2 ++
> 1 files changed, 2 insertions(+), 0 deletions(-)
>
> diff --git a/cpus.c b/cpus.c
> index 91a0f
77 matches
Mail list logo