Re: [PATCH RFC V4 0/5] kvm : Paravirt-spinlock support for KVM guests

On 16.01.2012, at 15:20, Srivatsa Vaddagiri wrote:

* Alexander Graf [off-list ref] [2012-01-16 04:57:45]:

quoted

Speaking of which - have you benchmarked performance degradation of pv ticket locks on bare metal?

You mean, run kernel on bare metal with CONFIG_PARAVIRT_SPINLOCKS
enabled and compare how it performs with CONFIG_PARAVIRT_SPINLOCKS disabled for 
some workload(s)?

Yup

In some sense, the 1x overcommitcase results posted does measure the overhead
of (pv-)spinlocks no? We don't see any overhead in that case for atleast
kernbench ..

quoted

Result for Non PLE machine :
============================

[snip]

quoted

Kernbench:
              BASE                    BASE+patch

What is BASE really? Is BASE already with the PV spinlocks enabled? I'm having a hard time understanding which tree you're working against, since the prerequisites aren't upstream yet.


Alex

quoted

              %improvement
              mean (sd)               mean (sd)
Scenario A:
case 1x:	 164.233 (16.5506)	 163.584 (15.4598	0.39517

[snip]

quoted

Result for PLE machine:
======================

[snip]

quoted

Kernbench:
              BASE                    BASE+patch
              %improvement
              mean (sd)               mean (sd)
Scenario A:
case 1x:	 161.263 (56.518)        159.635 (40.5621)	1.00953

- vatsa