Re: [PATCH RFC 0/4] Paravirtual spinlocks

* Jeremy Fitzhardinge [off-list ref] wrote:

My experiments show that using a Xen-specific lock helps guest 
performance a bit (reduction in elapsed and system time in a kernbench 
run), but most significantly, reduces overall physical CPU consumption 
by 10%, and so increases overall system scalability.

that's rather impressive and looks nice, considering the fairly low 
impact.

as there were no fundamental objections in this thread i've created a 
tip/x86/paravirt-spinlocks topic branch for these patches and started 
testing them.

i based the topic branch on tip/xen-64bit, so you should be able to get 
the latest code by doing:

  git-merge tip/x86/paravirt-spinlocks

on tip/master.

	Ingo