On 05/23/2010 07:30 PM, Michael S. Tsirkin wrote:
Maybe we should use atomics on index then?
This should only be helpful if you access the cacheline several times in
a row. That's not the case in virtio (or here).
So why does it help?
We actually do access the cachel
At Fri, 21 May 2010 18:57:36 +0200,
Kevin Wolf wrote:
>
> Am 20.05.2010 07:36, schrieb MORITA Kazutaka:
> > +
> > +/*
> > + * Append an option list (list) to an option list (dest).
> > + *
> > + * If dest is NULL, a new copy of list is created.
> > + *
> > + * Returns a pointer to the first elemen
On 05/24/2010 05:31 AM, Xiao Guangrong wrote:
Avi Kivity wrote:
On 05/23/2010 03:16 PM, Xiao Guangrong wrote:
Allow more page become asynchronous at getting sp time, if need create
new
shadow page for gfn but it not allow unsync(level> 1), we should
unsync all
gfn's unsync page
On 05/24/2010 05:03 AM, Xiao Guangrong wrote:
Avi Kivity wrote:
+if (need_unsync)
+kvm_unsync_pages(vcpu, gfn);
return 0;
}
Looks good, I'm just uncertain about role.invalid handling. What's the
reasoning here?
Avi,
Thanks for your reply.
We no n
At Fri, 21 May 2010 13:40:31 +0200,
Kevin Wolf wrote:
>
> Am 20.05.2010 07:36, schrieb MORITA Kazutaka:
> > This patch enables protocol drivers to use their create options which
> > are not supported by the format. For example, protcol drivers can use
> > a backing_file option with raw format.
>
Non-migrated memory is useful for devices that do not want to take memory
region data with them on migration.
As suggested by Avi, an alternative approach could add a "flags" parameter to
cpu_register_physical_memory() rather than explicityly call
cpu_mark_pages_no_migrate(). However, having a se
The phys_ram_dirty array consists of 8-bit values for storing 3 dirty bits.
Change to more generic phys_ram_flags and use lower 4-bits for dirty status and
leave upper 4 for other uses of marking memory pages.
One potential use for upper bits is to mark certain device pages to not be
migrated.
So
Avi Kivity wrote:
> On 05/23/2010 03:16 PM, Xiao Guangrong wrote:
>> Allow more page become asynchronous at getting sp time, if need create
>> new
>> shadow page for gfn but it not allow unsync(level> 1), we should
>> unsync all
>> gfn's unsync page
>>
>>
>>
>> +/* @gfn should be write-protected
On Sun, May 23, 2010 at 12:59 AM, Blue Swirl wrote:
> On Thu, May 20, 2010 at 11:02 PM, Yehuda Sadeh Weinraub
> wrote:
>> On Thu, May 20, 2010 at 1:31 PM, Blue Swirl wrote:
>>> On Wed, May 19, 2010 at 7:22 PM, Christian Brunner wrote:
The attached patch is a block driver for the distribute
Avi Kivity wrote:
>> +if (need_unsync)
>> +kvm_unsync_pages(vcpu, gfn);
>> return 0;
>> }
>>
>>
>
> Looks good, I'm just uncertain about role.invalid handling. What's the
> reasoning here?
>
Avi,
Thanks for your reply.
We no need worry about 'role.invalid' here, sinc
This patch address bug report in https://bugs.launchpad.net/qemu/+bug/530077.
Failed vmentries were handled with handle_unhandled() which prints a rather
unfriendly message to the user. This patch separates handling vmentry failures
from unknown exit reasons and prints a friendly message to the us
For the sake of completeness, this patch adds a symbolic
constant for VMX exit reason 0x21 (invalid guest state).
Signed-off-by: Mohammed Gamal
---
arch/x86/include/asm/vmx.h |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/as
The vmexit handler returns KVM_EXIT_UNKNOWN since there is no handler
for vmentry failures. This intercepts vmentry failures and returns
KVM_FAIL_ENTRY to userspace instead.
Signed-off-by: Mohammed Gamal
---
arch/x86/kvm/vmx.c |7 +++
1 files changed, 7 insertions(+), 0 deletions(-)
dif
-- Original Message ---
From: Avi Kivity
To: Riccardo
Cc: kvm@vger.kernel.org
Sent: Sun, 23 May 2010 16:30:06 +0300
Subject: Re: Gentoo guest with smp: emerge freeze while recompile world
> On 05/23/2010 03:12 PM, Riccardo wrote:
> > -- Original Message ---
On Sun, May 23, 2010 at 5:18 PM, Antoine Martin wrote:
> Why does it work in a chroot for the other options (aio=native, if=ide, etc)
> but not for aio!=native??
> Looks like I am misunderstanding the semantics of chroot...
It might not be the chroot() semantics but the environment inside that
ch
On Sun, May 23, 2010 at 07:03:10PM +0300, Avi Kivity wrote:
> On 05/23/2010 06:51 PM, Michael S. Tsirkin wrote:
>>>
So locked version seems to be faster than unlocked,
and share/unshare not to matter?
>>> May be due to the processor using the LOCK operation as a hint to
On Sun, May 23, 2010 at 07:03:10PM +0300, Avi Kivity wrote:
> On 05/23/2010 06:51 PM, Michael S. Tsirkin wrote:
>>>
So locked version seems to be faster than unlocked,
and share/unshare not to matter?
>>> May be due to the processor using the LOCK operation as a hint to
On 05/23/2010 10:12 PM, Avi Kivity wrote:
On 05/23/2010 05:43 PM, Antoine Martin wrote:
Description of the problem:
A guest tries to mount a large raw partition (1.5TB /dev/sda9 in my
case), this fails with pread enabled, works with it disabled.
Did you mean: preadv?
Yes, here's what makes
On 05/23/2010 06:51 PM, Michael S. Tsirkin wrote:
So locked version seems to be faster than unlocked,
and share/unshare not to matter?
May be due to the processor using the LOCK operation as a hint to
reserve the cacheline for a bit.
Maybe we should use atomics on index then?
On Thu, May 20, 2010 at 02:38:16PM +0930, Rusty Russell wrote:
> On Thu, 20 May 2010 02:31:50 pm Rusty Russell wrote:
> > On Wed, 19 May 2010 05:36:42 pm Avi Kivity wrote:
> > > > Note that this is a exclusive->shared->exclusive bounce only, too.
> > > >
> > >
> > > A bounce is a bounce.
> >
On Sun, May 23, 2010 at 06:41:33PM +0300, Avi Kivity wrote:
> On 05/23/2010 06:31 PM, Michael S. Tsirkin wrote:
>> On Thu, May 20, 2010 at 02:38:16PM +0930, Rusty Russell wrote:
>>
>>> On Thu, 20 May 2010 02:31:50 pm Rusty Russell wrote:
>>>
On Wed, 19 May 2010 05:36:42 pm Avi Kivity
Stefan Hajnoczi wrote:
> This patch adds LTTng Userspace Tracer (UST) backend support. The UST
> system requires no kernel support but libust and liburcu must be
> installed.
>
> $ ./configure --trace-backend ust
> $ make
>
> Start the UST daemon:
> $ ustd &
>
> List available tracepoints and e
Stefan Hajnoczi wrote:
> The following patches against qemu.git allow static trace events to be
> declared
> in QEMU. Trace events use a lightweight syntax and are independent of the
> backend tracing system (e.g. LTTng UST).
>
> Supported backends are:
> * my trivial tracer ("simple")
> * LTT
On 05/23/2010 06:31 PM, Michael S. Tsirkin wrote:
On Thu, May 20, 2010 at 02:38:16PM +0930, Rusty Russell wrote:
On Thu, 20 May 2010 02:31:50 pm Rusty Russell wrote:
On Wed, 19 May 2010 05:36:42 pm Avi Kivity wrote:
Note that this is a exclusive->shared->exclusive bounce only
On Thu, May 20, 2010 at 02:38:16PM +0930, Rusty Russell wrote:
> On Thu, 20 May 2010 02:31:50 pm Rusty Russell wrote:
> > On Wed, 19 May 2010 05:36:42 pm Avi Kivity wrote:
> > > > Note that this is a exclusive->shared->exclusive bounce only, too.
> > > >
> > >
> > > A bounce is a bounce.
> >
On 05/23/2010 05:43 PM, Antoine Martin wrote:
Description of the problem:
A guest tries to mount a large raw partition (1.5TB /dev/sda9 in my
case), this fails with pread enabled, works with it disabled.
Did you mean: preadv?
Yes, here's what makes it work ok (as suggested by Christoph earli
On 05/23/2010 09:43 PM, Antoine Martin wrote:
On 05/23/2010 09:18 PM, Avi Kivity wrote:
On 05/23/2010 05:07 PM, Antoine Martin wrote:
On 05/23/2010 06:57 PM, Avi Kivity wrote:
On 05/23/2010 11:53 AM, Antoine Martin wrote:
I'm not: 64-bit host and 64-bit guest.
Just to be sure, I've tested tha
On 05/23/2010 05:53 PM, Antoine Martin wrote:
How about if=ide?
Will test with another kernel and report back (this one doesn't have
any non-virtio drivers)
Can anyone tell me which kernel module I need for "if=ide"? Google was
no help here.
(before I include dozens of unnecessary modules i
How about if=ide?
Will test with another kernel and report back (this one doesn't have
any non-virtio drivers)
Can anyone tell me which kernel module I need for "if=ide"? Google was
no help here.
(before I include dozens of unnecessary modules in my slimmed down and
non modular kernel)
Th
On 05/23/2010 09:18 PM, Avi Kivity wrote:
On 05/23/2010 05:07 PM, Antoine Martin wrote:
On 05/23/2010 06:57 PM, Avi Kivity wrote:
On 05/23/2010 11:53 AM, Antoine Martin wrote:
I'm not: 64-bit host and 64-bit guest.
Just to be sure, I've tested that patch and still no joy:
/dev/vdc: read fail
On 05/23/2010 05:07 PM, Antoine Martin wrote:
On 05/23/2010 06:57 PM, Avi Kivity wrote:
On 05/23/2010 11:53 AM, Antoine Martin wrote:
I'm not: 64-bit host and 64-bit guest.
Just to be sure, I've tested that patch and still no joy:
/dev/vdc: read failed after 0 of 512 at 0: Input/output error
On 05/23/2010 03:16 PM, Xiao Guangrong wrote:
Allow more page become asynchronous at getting sp time, if need create new
shadow page for gfn but it not allow unsync(level> 1), we should unsync all
gfn's unsync page
+/* @gfn should be write-protected at the call site */
+static void kvm_sync_p
On 05/23/2010 06:57 PM, Avi Kivity wrote:
On 05/23/2010 11:53 AM, Antoine Martin wrote:
I'm not: 64-bit host and 64-bit guest.
Just to be sure, I've tested that patch and still no joy:
/dev/vdc: read failed after 0 of 512 at 0: Input/output error
/dev/vdc: read failed after 0 of 512 at 0: In
On 05/23/2010 03:14 PM, Xiao Guangrong wrote:
In current code, shadow page can become asynchronous only if one
shadow page for a gfn, this rule is too strict, in fact, we can
let all last mapping page(i.e, it's the pte page) become unsync,
and sync them at invlpg or flush tlb time.
This patch al
On 05/23/2010 03:12 PM, Riccardo wrote:
-- Original Message ---
From: Avi Kivity
To: Riccardo
Cc: kvm@vger.kernel.org
Sent: Sun, 23 May 2010 14:38:42 +0300
Subject: Re: Gentoo guest with smp: emerge freeze while recompile world
On 05/21/2010 07:47 PM, Riccardo wrot
Allow more page become asynchronous at getting sp time, if need create new
shadow page for gfn but it not allow unsync(level > 1), we should unsync all
gfn's unsync page
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/mmu.c | 47 +--
1 files changed,
In current code, shadow page can become asynchronous only if one
shadow page for a gfn, this rule is too strict, in fact, we can
let all last mapping page(i.e, it's the pte page) become unsync,
and sync them at invlpg or flush tlb time.
This patch allow more page become asynchronous at gfn mapping
-- Original Message ---
From: Avi Kivity
To: Riccardo
Cc: kvm@vger.kernel.org
Sent: Sun, 23 May 2010 14:38:42 +0300
Subject: Re: Gentoo guest with smp: emerge freeze while recompile world
> On 05/21/2010 07:47 PM, Riccardo wrote:
> >
> >> If you are using kvm-clock, m
On 05/21/2010 12:29 AM, Anthony Liguori wrote:
I'd be more interested in enabling people to build these types of
storage systems without touching qemu.
Both sheepdog and ceph ultimately transmit I/O over a socket to a
central daemon, right?
That incurs an extra copy.
So could we not stan
On 05/23/2010 11:53 AM, Antoine Martin wrote:
I'm not: 64-bit host and 64-bit guest.
Just to be sure, I've tested that patch and still no joy:
/dev/vdc: read failed after 0 of 512 at 0: Input/output error
/dev/vdc: read failed after 0 of 512 at 0: Input/output error
/dev/vdc: read failed af
On 05/22/2010 04:53 PM, Erik Rull wrote:
Hi all,
is it possible to detect a guest shutdown?
qemu exits on guest shutdown.
I want to stop a service if my windows guest is shutted down and force
a sync of the disks - because it could be possible that the user
switches off the system afterwa
On 05/21/2010 07:47 PM, Riccardo wrote:
If you are using kvm-clock, maybe try disabling that.
$ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
hpet
This is from server, not from VM (that have freeze).
What about the guest?
--
error compiling committee.c: t
On 05/23/2010 02:28 PM, Gleb Natapov wrote:
On SVM interrupts are injected by svm_set_irq() not svm_inject_irq().
The later is used only to wait for irq window.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line
On SVM interrupts are injected by svm_set_irq() not svm_inject_irq().
The later is used only to wait for irq window.
Signed-off-by: Gleb Natapov
---
ChangeLog:
v1->v2:
- fix stupid cut&paste error.
v2->v3:
- Move also kvm_stat accounting of irq_injections to correct place.
diff --git a/a
On 05/20/2010 01:16 PM, Gleb Natapov wrote:
On Thu, May 13, 2010 at 04:17:14PM +0300, Gleb Natapov wrote:
When in-kernel irqchip is used env->halted is never used for anything
except "info cpus" command. Halted state is synced in
kvm_arch_save_mpstate() and showed by do_info_cpus() but other
On 05/20/2010 01:28 AM, Jan Kiszka wrote:
From: Jan Kiszka
Guest debugging under KVM is currently broken once io-threads are
enabled. Easily fixable by switching the fake on_vcpu to the real
run_on_cpu implementation.
Applied uq/master, thanks.
--
error compiling committee.c: too many arg
On 05/20/2010 10:19 PM, Tyler Bletsch wrote:
I'm interested in moving some research prototypes from Xen to KVM, but
there are a few esoteric features I'd need to do this.
First is an efficient mechanism for direct VM-to-VM
sockets...something that bypasses the protocol stack and minimizes
ove
On 05/21/2010 03:27 AM, Chris Wright wrote:
From: Alex Williamson
We've already got an open fd for PCI config space for the device, we
might as well use it. This also makes sure that if we're making use of
a privileged file descriptor opened for us, we use it for all accesses
to the device.
Am 23.05.2010 um 12:38 schrieb Michael Tokarev:
> 23.05.2010 13:55, Peter Lieven wrote:
>> Hi,
>>
>> after live migrating ubuntu 9.10 server (2.6.31-14-server) and suse linux
>> 10.1 (2.6.16.13-4-smp)
>> it happens sometimes that the guest runs into irq problems. i mention these
>> 2 guest oss
23.05.2010 13:55, Peter Lieven wrote:
Hi,
after live migrating ubuntu 9.10 server (2.6.31-14-server) and suse linux 10.1
(2.6.16.13-4-smp)
it happens sometimes that the guest runs into irq problems. i mention these 2
guest oss
since i have seen the error there. there are likely others around w
Am 19.05.2010 um 10:18 schrieb Peter Lieven:
> Kevin Wolf wrote:
>> Am 19.05.2010 09:29, schrieb Christoph Hellwig:
>>
>>> On Tue, May 18, 2010 at 03:22:36PM +0200, Kevin Wolf wrote:
>>>
I think it's stuck here in an endless loop:
while (laiocb->ret == -EINPROGRESS)
Hi,
after live migrating ubuntu 9.10 server (2.6.31-14-server) and suse linux 10.1
(2.6.16.13-4-smp)
it happens sometimes that the guest runs into irq problems. i mention these 2
guest oss
since i have seen the error there. there are likely others around with the same
problem.
on the host i ru
Am 18.05.2010 um 15:51 schrieb Alexander Graf:
> Peter Lieven wrote:
>> Alexander Graf wrote:
>>> Peter Lieven wrote:
>>>
we are running on intel xeons here:
>>>
>>> That might be the reason. Does it break when passing -no-kvm?
>>>
>>>
processor: 0
vendor_id: Genu
On 05/17/2010 01:32 PM, qemu-...@buildbot.b1-systems.de wrote:
The Buildbot has detected a new failure of default_x86_64_debian_5_0 on
qemu-kvm.
Full details are available at:
http://buildbot.b1-systems.de/qemu-kvm/builders/default_x86_64_debian_5_0/builds/396
Buildbot URL: http://buildbot.b
On 05/18/2010 02:27 AM, Lucas Meneghel Rodrigues wrote:
On Fri, 2010-05-14 at 17:43 +0800, Feng Yang wrote:
Emulate the powercut under IO workload(dd so far) using kill -9.
Then check image in post command.
This case want to make sure powercut under IO workload will not
break qcow2 image.
The
On 05/22/2010 06:35 PM, Antoine Martin wrote:
On 05/22/2010 06:17 PM, Michael Tokarev wrote:
22.05.2010 14:44, Antoine Martin wrote:
Bump.
Now that qemu is less likely to eat my data, " *[Qemu-devel] [PATCH
4/8]
block: fix sector comparism in*"
http://marc.info/?l=qemu-devel&m=12743611471243
On Thu, May 20, 2010 at 11:02 PM, Yehuda Sadeh Weinraub
wrote:
> On Thu, May 20, 2010 at 1:31 PM, Blue Swirl wrote:
>> On Wed, May 19, 2010 at 7:22 PM, Christian Brunner wrote:
>>> The attached patch is a block driver for the distributed file system
>>> Ceph (http://ceph.newdream.net/). This dri
57 matches
Mail list logo