On Thu, Sep 30, 2021, Marc Zyngier wrote:
> On Thu, 23 Sep 2021 00:22:12 +0100, David Matlack wrote:
> >
> > On Wed, Sep 22, 2021 at 11:53 AM Marc Zyngier wrote:
> > > And I'm all for adding these hooks where it matters as long as they
> > > are not considered ABI and don't appear in /sys/debug/
On Thu, 23 Sep 2021 00:22:12 +0100,
David Matlack wrote:
>
> On Wed, Sep 22, 2021 at 11:53 AM Marc Zyngier wrote:
> >
> > On Wed, 22 Sep 2021 19:13:40 +0100,
> > Sean Christopherson wrote:
> >
> > > Stepping back a bit, this is one piece of the larger issue of how to
> > > modernize KVM for hyp
On Wed, Sep 22, 2021 at 11:53 AM Marc Zyngier wrote:
>
> On Wed, 22 Sep 2021 19:13:40 +0100,
> Sean Christopherson wrote:
>
> > Stepping back a bit, this is one piece of the larger issue of how to
> > modernize KVM for hyperscale usage. BPF and tracing are great when
> > the debugger has root ac
On 23/09/21 09:45, Marc Zyngier wrote:
On Thu, 23 Sep 2021 07:36:21 +0100,
Paolo Bonzini wrote:
On 22/09/21 20:53, Marc Zyngier wrote:
I definitely regret adding the current KVM trace points, as they
don't show what I need, and I can't change them as they are ABI.
I disagree that they are A
On Thu, 23 Sep 2021 07:36:21 +0100,
Paolo Bonzini wrote:
>
> On 22/09/21 20:53, Marc Zyngier wrote:
> > I definitely regret adding the current KVM trace points, as they
> > don't show what I need, and I can't change them as they are ABI.
>
> I disagree that they are ABI. And even if you don't w
On 22/09/21 20:53, Marc Zyngier wrote:
I definitely regret adding the current KVM trace points, as they
don't show what I need, and I can't change them as they are ABI.
I disagree that they are ABI. And even if you don't want to change
them, you can always add parameters or remove them.
Pao
+Google folks
On Wed, Sep 22, 2021, Paolo Bonzini wrote:
> On 22/09/21 13:22, Marc Zyngier wrote:
> > Frankly, this is a job for BPF and the tracing subsystem, not for some
> > hardcoded syndrome accounting. It would allow to extract meaningful
> > information, prevent bloat, and crucially make it
Hi Marc, Paolo,
On Wed, Sep 22, 2021 at 8:37 AM Paolo Bonzini wrote:
>
> On 22/09/21 13:22, Marc Zyngier wrote:
> > Frankly, this is a job for BPF and the tracing subsystem, not for some
> > hardcoded syndrome accounting. It would allow to extract meaningful
> > information, prevent bloat, and cr
On Wed, 22 Sep 2021 19:13:40 +0100,
Sean Christopherson wrote:
> Stepping back a bit, this is one piece of the larger issue of how to
> modernize KVM for hyperscale usage. BPF and tracing are great when
> the debugger has root access to the machine and can rerun the
> failing workload at will.
On 22/09/21 13:22, Marc Zyngier wrote:
Frankly, this is a job for BPF and the tracing subsystem, not for some
hardcoded syndrome accounting. It would allow to extract meaningful
information, prevent bloat, and crucially make it optional. Even empty
trace points like the ones used in the scheduler
Hi Jing,
On Wed, 22 Sep 2021 02:08:51 +0100,
Jing Zhang wrote:
>
> These logarithmic histogram stats are useful for monitoring performance
> of handling for different kinds of VCPU exit reasons.
>
> Signed-off-by: Jing Zhang
> ---
> arch/arm64/include/asm/kvm_host.h | 36
> arch/
These logarithmic histogram stats are useful for monitoring performance
of handling for different kinds of VCPU exit reasons.
Signed-off-by: Jing Zhang
---
arch/arm64/include/asm/kvm_host.h | 36
arch/arm64/kvm/arm.c | 4 ++
arch/arm64/kvm/guest.c| 43 +
12 matches
Mail list logo