On Wed, Mar 16, 2011 at 10:55:02PM +0300, Michael Tokarev wrote:
> 16.03.2011 22:48, Marcelo Tosatti wrote:
> > On Fri, Mar 11, 2011 at 03:02:33PM +0300, Michael Tokarev wrote:
> >> I tried Openbsd 4.8 in kvm today and immediately noticed
> >> that it is running _very_ slow, boot takes several minu
On Thu, Mar 17, 2011 at 09:00:30AM +0100, Jean-Philippe Menil wrote:
> >>Are you running a preemptible kernel?
> >>Does the following help at all?
> >>
> >>diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
> >>index 2ca4535..cdf51c9 100644
> >>--- a/virt/kvm/eventfd.c
> >>+++ b/virt/kvm/eventfd.
irqfd in kvm used flush_work incorrectly:
it assumed that work scheduled previously can't run
after flush_work, but since kvm uses a non-reentrant
workqueue (by means of schedule_work)
we need flush_work_sync to get that guarantee.
Signed-off-by: Michael S. Tsirkin
Reported-by: Jean-Philippe Meni
hi,all:
I noticed a news that kvm can use the SR-IOV function of LSI
MegaRAID storage controller on 2009 IDT, have anyone been succeed in
testing this function, and how to configure the kernel and qemu?
thanks.
Regards.
Green.
--
To unsubscribe from this list: send the line "unsubscribe kvm
On Tue, Mar 15, 2011 at 12:06:06PM -0700, Chris Wright wrote:
> * Anthony Liguori (anth...@codemonkey.ws) wrote:
> > On 03/15/2011 09:53 AM, Chris Wright wrote:
> > > QAPI
>
> > >- c library implementation is critical to have unit tests and test
> > > driven development
> > > - thread safe?
>
On Wed, 16 Mar 2011 17:12:55 -0700, Shirley Ma wrote:
> Signed-off-by: Shirley Ma
This is fascinating... and deeply weird.
OK, what's the difference between calling xmit_skb and ignoring failure,
and this patch which figures out it's going to fail before calling
xmit_skb?
ie. what if you *just
The following is needed on top: still compiled only, post
here in case Tom is willing to test this meanwhile.
-->
virtio: fix vring_last_used
Reported-by: Shirley Ma
Signed-off-by: Michael S. Tsirkin
---
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index a6fc5
The following tree has fixes for vhost-net for 2.6.39.
These are easier to apply on top of Jason's and Krishna's
cleanups, and they got tested this way, so I thought it's
better for everyone to include that, and the trivial
copy_from_user optimization.
But if you think it's too late for that, pls
Hello all
I am seeing, perhaps unsurprisingly, a skewed system clock after pausing
and then resuming a qemu-kvm guest. The guest continues with its earlier
time.
Since I'd like to use the pause technique for backups, which can take 1
hour, this is significant.
This is with windows guests, and it d
Have you checked with Windows Time service enabled in the guest?
net start w32time
Best Regards,
Timur
2011/3/17 Virtbie :
> Hello all
> I am seeing, perhaps unsurprisingly, a skewed system clock after pausing
> and then resuming a qemu-kvm guest. The guest continues with its earlier
> time.
>
On Thu, 2011-03-17 at 08:00 +0200, Michael S. Tsirkin wrote:
> On Wed, Mar 16, 2011 at 05:20:14PM -0700, Shirley Ma wrote:
> > This patch doesn't seem to help guest TX queue overrun.
>
> Just making sure: what exactly was tested?
> You did combine this with a vhost-net and qemu patches, right?
>
On Thu, 2011-03-17 at 15:40 +1030, Rusty Russell wrote:
> This is fascinating... and deeply weird.
>
> OK, what's the difference between calling xmit_skb and ignoring
> failure,
> and this patch which figures out it's going to fail before calling
> xmit_skb?
>
> ie. what if you *just* delete this
On Thu, 2011-03-17 at 07:02 +0200, Michael S. Tsirkin wrote:
> So, this just tries to make sure there's enough space for
> max packet in the ring, if not - drop and return OK.
> Why bother checking beforehand though?
> If that's what we want to do, we can just call add_buf and see
> if it fails?
I
On Thu, Mar 17, 2011 at 10:53:33AM +0200, Michael S. Tsirkin wrote:
> irqfd in kvm used flush_work incorrectly:
> it assumed that work scheduled previously can't run
> after flush_work, but since kvm uses a non-reentrant
> workqueue (by means of schedule_work)
> we need flush_work_sync to get that
Linus, please pull from
git://git.kernel.org/pub/scm/virt/kvm/kvm.git kvm-updates/2.6.39
To receive the following updates.
Avi Kivity (11):
KVM: MMU: Don't flush shadow when enabling dirty tracking
KVM: VMX: Save and restore tr selector across mode switches
KVM: VMX: Avoid
On Thu, 2011-03-17 at 07:05 +0200, Michael S. Tsirkin wrote:
> Could you add CPU utilization data pls? I also wonder what does this
> do
> to UDP? Won't a lot of packets be dropped?
Guest CPU utilization slightly increased a few %.
UDP performance send rate increased 200% - 400%, recv rate incre
Le jeudi 17 mars 2011 à 09:50 -0700, Shirley Ma a écrit :
> On Thu, 2011-03-17 at 07:05 +0200, Michael S. Tsirkin wrote:
> > Could you add CPU utilization data pls? I also wonder what does this
> > do
> > to UDP? Won't a lot of packets be dropped?
>
> Guest CPU utilization slightly increased a fe
On Thu, 2011-03-17 at 17:58 +0100, Eric Dumazet wrote:
> Could you run your tests with only one cpu ?
> (offline all cpus but cpu0 on your hypervisor)
>
> Dropping packets is fine, unless consumer cant run ;)
Sure, will report the data soon.
Thanks
Shirley
--
To unsubscribe from this list: sen
erik.r...@rdsoftware.de wrote:
Hi all,
I've tested the following:
- EHCI patch without auto_add and adding the devices manually
Result:
Works fine, all devices could be added. I've tested only 2 but it is more
than with the auto_add feature :-)
- UHCI only (no EHCI patch) with enabled "-device
On Wed, Mar 16, 2011 at 11:09:11PM +0300, Michael Tokarev wrote:
> 16.03.2011 22:44, Marcelo Tosatti wrote:
> > On Fri, Mar 11, 2011 at 02:54:00PM +0300, Michael Tokarev wrote:
> >> Hello.
> >>
> >> I installed an openbsd 4.8 image today to play with,
> >> and noticed that when issuing "system_powe
On Thu, 2011-03-17 at 10:01 -0700, Shirley Ma wrote:
> On Thu, 2011-03-17 at 17:58 +0100, Eric Dumazet wrote:
> > Could you run your tests with only one cpu ?
> > (offline all cpus but cpu0 on your hypervisor)
> >
> > Dropping packets is fine, unless consumer cant run ;)
>
> Sure, will report th
On Thu, 2011-03-17 at 11:49 -0700, Shirley Ma wrote:
> With a single CPU, before/after with this patch the performance has no
> difference for both UDP and TCP, and it seems hitting TX overrun, CPU
> is
> 100% used.
Sorry, should be: it seems never hitting TX overrun.
Shirley
--
To unsubscribe
On system reset, we currently try to quiesce DMA by clearing the
command register. This assumes that nothing re-enables bus master
support without first de-programming the device. Use a bigger
hammer to help the guest not shoot itself by issuing a function
reset via sysfs on each system reset.
S
17.03.2011 20:52, Marcelo Tosatti wrote:
[]
> iret emulation is only partially implemented. Why is iret faulting
> in the first place i don't know. Can you enable tracing with
>
> echo kvm > /$debugfs/tracing/set_event
>
> And save the tail of the log, including events at $RIP?
Something like t
* Alex Williamson (alex.william...@redhat.com) wrote:
> static void reset_assigned_device(DeviceState *dev)
> {
> -PCIDevice *d = DO_UPCAST(PCIDevice, qdev, dev);
> +PCIDevice *pci_dev = DO_UPCAST(PCIDevice, qdev, dev);
> +AssignedDevice *adev = DO_UPCAST(AssignedDevice, dev, pci_dev)
On Thu, 2011-03-17 at 14:12 -0700, Chris Wright wrote:
> * Alex Williamson (alex.william...@redhat.com) wrote:
> > static void reset_assigned_device(DeviceState *dev)
> > {
> > -PCIDevice *d = DO_UPCAST(PCIDevice, qdev, dev);
> > +PCIDevice *pci_dev = DO_UPCAST(PCIDevice, qdev, dev);
> >
On system reset, we currently try to quiesce DMA by clearing the
command register. This assumes that nothing re-enables bus master
support without first de-programming the device. Use a bigger
hammer to help the guest not shoot itself by issuing a function
reset via sysfs on each system reset.
S
* Alex Williamson (alex.william...@redhat.com) wrote:
> On system reset, we currently try to quiesce DMA by clearing the
> command register. This assumes that nothing re-enables bus master
> support without first de-programming the device. Use a bigger
> hammer to help the guest not shoot itself
* Alex Williamson (alex.william...@redhat.com) wrote:
> On Thu, 2011-03-17 at 14:12 -0700, Chris Wright wrote:
> > * Alex Williamson (alex.william...@redhat.com) wrote:
> > > +fd = open(reset_file, O_WRONLY);
> > > +if (fd != -1) {
> > > +ret = write(fd, reset, strlen(reset));
> > >
This patch is a follow up to an earlier one that aims to enable
kvmclock newer msr set. This time I'm doing it through a more sane
mechanism of consulting the kernel about the supported msr set.
Glauber Costa (3):
use kernel-provided para_features instead of statically coming up
with new cap
According to Avi's comments over my last submission, I decided to take a
different, and more correct direction - we hope.
This patch is now using the features provided by KVM_GET_SUPPORTED_CPUID
directly to
mask out features from guest-visible cpuid.
The old get_para_features() mechanism is kept
We have two bits that can represent kvmclock in cpuid.
They signal the guest which msr set to use. When we tweak flags
involving this value - specially when we use "-", we have to act on both.
Besides adding it to the kvm features list, we also have to "break" the
assumption represented by the bre
kvmclock presence can be signalled by two different flags. So for
device creation, we have to test for both.
Signed-off-by: Glauber Costa
---
hw/kvmclock.c |6 +-
1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/hw/kvmclock.c b/hw/kvmclock.c
index b6ceddf..004c4ad 100644
--
On Thu, 2011-03-17 at 08:18 -0700, Shirley Ma wrote:
> On Thu, 2011-03-17 at 07:02 +0200, Michael S. Tsirkin wrote:
> > So, this just tries to make sure there's enough space for
> > max packet in the ring, if not - drop and return OK.
> > Why bother checking beforehand though?
> > If that's what we
34 matches
Mail list logo
