Rusty Russell wrote:
> On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
>
>> +fire_sched_out_preempt_hooks(current);
>> prepare_lock_switch(rq, next);
>> prepare_arch_switch(next);
>>
>
> Damn, I just found a use for this in lguest.
>
> Any chance of handing "next" to the
Luca wrote:
> On 7/11/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
>> Current kvm disables preemption while the new virtualization
>> registers are
>> in use. This of course is not very good for latency sensitive
>> workloads (one
>> use of virtualization is to offload user interface and other latenc
Dave Hansen wrote:
> On Tue, 2007-07-10 at 08:44 +0300, Avi Kivity wrote:
>
>> What does 'top' on the host show in both cases?
>>
>
> On the fast one (kvm-27) I just see the dd as a flash in top. It
> doesn't stay for long. The VM isn't very responsive during the dd.
>
> On the slow (kvm-
Chuck Ebbert wrote:
> On 07/11/2007 03:08 AM, Avi Kivity wrote:
>
>> Linus, please do your usual thing from the repository and branch at
>>
>> git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm.git for-linus
>>
>> This contains kvm updates for the 2.6.23 merge window, including
>>
>> - perf
Here is the update with adding HLT cap.
diff --git a/drivers/kvm/i8259.c b/drivers/kvm/i8259.c
index f4ae5f7..e84e665 100644
--- a/drivers/kvm/i8259.c
+++ b/drivers/kvm/i8259.c
@@ -411,8 +411,13 @@ static void picdev_read(struct kvm_io_device *this,
static void pic_irq_request(void *opaque, int
On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
> + fire_sched_out_preempt_hooks(current);
> prepare_lock_switch(rq, next);
> prepare_arch_switch(next);
Damn, I just found a use for this in lguest.
Any chance of handing "next" to the sched_out hook so we can optimize
the lgue
On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
> +config PREEMPT_HOOKS
> + bool
> + depends on X86
> + default y
Hmm, I would have thought that having CONFIG_KVM "select PREEMPT_HOOKS"
would be a little clearer.
> +static void fire_sched_in_preempt_hooks(struct task_struct *tsk)
Hi,
1 month passed, and we still stop at kvm-28?
Thanks,
Jun
-
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE version of DB2 express and take
control of your XML. No limits. Just data. Click
On 7/10/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
> Anthony Liguori wrote:
> > This looks like a typo. I think the intention of the if is to normalize
> > i[3456]86 to i386 since that's the target name for QEMU.
> >
> > Signed-off-by: Anthony Liguori <[EMAIL PROTECTED]>
> >
> > diff --git a/config
On 07/11/2007 03:08 AM, Avi Kivity wrote:
> Linus, please do your usual thing from the repository and branch at
>
> git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm.git for-linus
>
> This contains kvm updates for the 2.6.23 merge window, including
>
> - performance improvements
> - suspe
On 7/11/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
> Current kvm disables preemption while the new virtualization registers are
> in use. This of course is not very good for latency sensitive workloads (one
> use of virtualization is to offload user interface and other latency
> insensitive stuff t
On Tue, 2007-07-10 at 08:44 +0300, Avi Kivity wrote:
> What does 'top' on the host show in both cases?
On the fast one (kvm-27) I just see the dd as a flash in top. It
doesn't stay for long. The VM isn't very responsive during the dd.
On the slow (kvm-28) one, I see the dd in top creeping along
This adds a general mechanism whereby a task can request the scheduler to
notify it whenever it is preempted or scheduled back in. This allows the
task to swap any special-purpose registers like the fpu or Intel's VT
registers.
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
include/linux/pree
Current kvm disables preemption while the new virtualization registers are
in use. This of course is not very good for latency sensitive workloads (one
use of virtualization is to offload user interface and other latency
insensitive stuff to a container, so that it is easier to analyze the
remaini
I redid the the scheduler preemption patches based on Rusty's feedback.
Things do look much cleaner this time around.
Changes:
- split into core and kvm parts
- incorporated Shaohua Li's fix
- each task now has a list of independently managed preemption hooks
- move preempt hook pointer to a hot c
Attn: Beneficiary
I am delighted to inform you that the UNITED NATION CRIME PREVENTION UNIT
Management through the Office of the SKYE BANK GOVERNOR and other bank
directors have decided to call back all approved fund Payment through offshore
payment centers to the bank treasury following In
Nguyen Anh Quynh wrote:
> On 7/11/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
>> Nguyen Anh Quynh wrote:
>> > *nopage() in kvm_main.c should only store the type of mmap() fault if
>> > the pointers are not NULL. This patch fixes the problem.
>> >
>>
>> What caller of ->nopage() passes a NULL for typ
On 7/11/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
> Nguyen Anh Quynh wrote:
> > *nopage() in kvm_main.c should only store the type of mmap() fault if
> > the pointers are not NULL. This patch fixes the problem.
> >
>
> What caller of ->nopage() passes a NULL for type?
In that case we simply do no
Nguyen Anh Quynh wrote:
> *nopage() in kvm_main.c should only store the type of mmap() fault if
> the pointers are not NULL. This patch fixes the problem.
>
What caller of ->nopage() passes a NULL for type?
--
error compiling committee.c: too many arguments to function
---
On Wed, Jul 11, 2007 at 11:43:26AM +0200, Benjamin Budts wrote:
> I'm a bit confused using the -march=xxx options for gcc when using a
> kernel virtual machine...
> Getting errors on smp when using the -march=nocoma for gcc... possibly
What errors?
> because smp is not fully supported yet I s
*nopage() in kvm_main.c should only store the type of mmap() fault if
the pointers are not NULL. This patch fixes the problem.
Signed-off-by: Nguyen Anh Quynh <[EMAIL PROTECTED]>
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 83bb284..0520d15 100644
--- a/drivers/kvm/kvm_main
Benjamin Budts wrote:
> Hi all,
>
> question...
>
> I'm a bit confused using the -march=xxx options for gcc when using a
> kernel virtual machine...
> Getting errors on smp when using the -march=nocoma for gcc... possibly
> because smp is not fully supported yet I suppse.
>
> I guess my question
Hi all,
question...
I'm a bit confused using the -march=xxx options for gcc when using a
kernel virtual machine...
Getting errors on smp when using the -march=nocoma for gcc... possibly
because smp is not fully supported yet I suppse.
I guess my question is, when installing kvm, is the virtu
On 7/11/07, Avi Kivity <[EMAIL PROTECTED]> wrote:
> [...]
>
> It's not proposed. Andi mentioned it in passing.
Ok, thanks for clarifying that.
-
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE
Satyam Sharma wrote:
>
> And I think what's proposed is:
>
> 1. Change smp_call_function() semantics, to run given function
> on _all_ CPUs (thus getting rid of the on_each_cpu() "mistake")
>
> 2. Resort to (most probably implement another function?) using
> smp_call_function_mask() or flags approp
Linus, please do your usual thing from the repository and branch at
git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm.git for-linus
This contains kvm updates for the 2.6.23 merge window, including
- performance improvements
- suspend/resume fixes
- guest smp
- random fixes and cleanups
26 matches
Mail list logo