Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-16 Thread Waiman Long
On 07/16/2015 01:46 AM, Peter Zijlstra wrote: On Wed, Jul 15, 2015 at 10:01:02PM -0400, Waiman Long wrote: On 07/15/2015 05:39 AM, Peter Zijlstra wrote: On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-16 Thread Waiman Long
On 07/16/2015 01:46 AM, Peter Zijlstra wrote: On Wed, Jul 15, 2015 at 10:01:02PM -0400, Waiman Long wrote: On 07/15/2015 05:39 AM, Peter Zijlstra wrote: On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Peter Zijlstra
On Wed, Jul 15, 2015 at 10:01:02PM -0400, Waiman Long wrote: > On 07/15/2015 05:39 AM, Peter Zijlstra wrote: > >On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: > >>Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens > >>critical section and block forward progress. This

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Waiman Long
On 07/15/2015 05:39 AM, Peter Zijlstra wrote: On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch implements a kick-ahead mechanism where the unlocker will kick

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Peter Zijlstra
On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: > Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens > critical section and block forward progress. This patch implements > a kick-ahead mechanism where the unlocker will kick the queue head > vCPUs as well as up to four

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Waiman Long
On 07/15/2015 05:39 AM, Peter Zijlstra wrote: On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch implements a kick-ahead mechanism where the unlocker will kick

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Peter Zijlstra
On Wed, Jul 15, 2015 at 10:01:02PM -0400, Waiman Long wrote: On 07/15/2015 05:39 AM, Peter Zijlstra wrote: On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch

Re: [PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-15 Thread Peter Zijlstra
On Tue, Jul 14, 2015 at 10:13:35PM -0400, Waiman Long wrote: Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch implements a kick-ahead mechanism where the unlocker will kick the queue head vCPUs as well as up to four

[PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-14 Thread Waiman Long
Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch implements a kick-ahead mechanism where the unlocker will kick the queue head vCPUs as well as up to four additional vCPUs next to the queue head if they were halted. The

[PATCH v2 4/6] locking/pvqspinlock: Allow vCPUs kick-ahead

2015-07-14 Thread Waiman Long
Frequent CPU halting (vmexit) and CPU kicking (vmenter) lengthens critical section and block forward progress. This patch implements a kick-ahead mechanism where the unlocker will kick the queue head vCPUs as well as up to four additional vCPUs next to the queue head if they were halted. The