Re: [Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-25 Thread Roger Pau Monné
On Thu, Jan 25, 2018 at 02:03:35PM +, George Dunlap wrote: > On Thu, Jan 25, 2018 at 9:14 AM, Roger Pau Monné wrote: > > On Wed, Jan 24, 2018 at 06:03:28PM +, George Dunlap wrote: > >> On Wed, Jan 17, 2018 at 9:48 AM, Roger Pau Monne > >>

Re: [Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-25 Thread George Dunlap
On Thu, Jan 25, 2018 at 9:14 AM, Roger Pau Monné wrote: > On Wed, Jan 24, 2018 at 06:03:28PM +, George Dunlap wrote: >> On Wed, Jan 17, 2018 at 9:48 AM, Roger Pau Monne >> wrote: >> > Since VCPUOP_{up/down} already identity pins vCPU hotplug to

Re: [Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-25 Thread Roger Pau Monné
On Wed, Jan 24, 2018 at 06:03:28PM +, George Dunlap wrote: > On Wed, Jan 17, 2018 at 9:48 AM, Roger Pau Monne wrote: > > Since VCPUOP_{up/down} already identity pins vCPU hotplug to pCPU > > hotplug also pin the vCPUs to the pCPUs in the scheduler. This prevent > > vCPU

Re: [Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-24 Thread George Dunlap
On Wed, Jan 17, 2018 at 9:48 AM, Roger Pau Monne wrote: > Since VCPUOP_{up/down} already identity pins vCPU hotplug to pCPU > hotplug also pin the vCPUs to the pCPUs in the scheduler. This prevent > vCPU migration and should improve performance. > > While there also use

Re: [Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-17 Thread Wei Liu
On Wed, Jan 17, 2018 at 09:48:11AM +, Roger Pau Monne wrote: > Since VCPUOP_{up/down} already identity pins vCPU hotplug to pCPU > hotplug also pin the vCPUs to the pCPUs in the scheduler. This prevent The description is a bit ambiguous. I read it as "the shim hotplug code pins vcpu to pcpu

[Xen-devel] [PATCH 3/6] xen/pvshim: identity pin shim vCPUs to pCPUs

2018-01-17 Thread Roger Pau Monne
Since VCPUOP_{up/down} already identity pins vCPU hotplug to pCPU hotplug also pin the vCPUs to the pCPUs in the scheduler. This prevent vCPU migration and should improve performance. While there also use __cpumask_set_cpu instead of cpumask_set_cpu, there's no need to use the locked variant.