On 11/09/2015 12:29 PM, Peter Zijlstra wrote:
On Fri, Nov 06, 2015 at 12:47:49PM -0500, Waiman Long wrote:
On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
*urgh*, last time we had:
+ if (pv_wait_head_or_steal())
+ goto stolen;
while ((val =
On Fri, Nov 06, 2015 at 12:47:49PM -0500, Waiman Long wrote:
> On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
> >*urgh*, last time we had:
> >
> >+if (pv_wait_head_or_steal())
> >+goto stolen;
> > while ((val = smp_load_acquire(>val.counter))&
> > _Q_LOCKED_PENDING_MASK)
> >
On Fri, Nov 06, 2015 at 12:47:49PM -0500, Waiman Long wrote:
> On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
> >*urgh*, last time we had:
> >
> >+if (pv_wait_head_or_steal())
> >+goto stolen;
> > while ((val = smp_load_acquire(>val.counter))&
> > _Q_LOCKED_PENDING_MASK)
> >
On 11/09/2015 12:29 PM, Peter Zijlstra wrote:
On Fri, Nov 06, 2015 at 12:47:49PM -0500, Waiman Long wrote:
On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
*urgh*, last time we had:
+ if (pv_wait_head_or_steal())
+ goto stolen;
while ((val =
On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
On Fri, Oct 30, 2015 at 07:26:36PM -0400, Waiman Long wrote:
@@ -431,35 +432,44 @@ queue:
* sequentiality; this is because the set_locked() function below
* does not imply a full barrier.
*
+* The PV
On Fri, Oct 30, 2015 at 07:26:36PM -0400, Waiman Long wrote:
> @@ -431,35 +432,44 @@ queue:
>* sequentiality; this is because the set_locked() function below
>* does not imply a full barrier.
>*
> + * The PV pv_wait_head_lock function, if active, will acquire the lock
On Fri, Oct 30, 2015 at 07:26:36PM -0400, Waiman Long wrote:
> @@ -431,35 +432,44 @@ queue:
>* sequentiality; this is because the set_locked() function below
>* does not imply a full barrier.
>*
> + * The PV pv_wait_head_lock function, if active, will acquire the lock
On 11/06/2015 09:50 AM, Peter Zijlstra wrote:
On Fri, Oct 30, 2015 at 07:26:36PM -0400, Waiman Long wrote:
@@ -431,35 +432,44 @@ queue:
* sequentiality; this is because the set_locked() function below
* does not imply a full barrier.
*
+* The PV
This patch allows one attempt for the lock waiter to steal the lock
when entering the PV slowpath. To prevent lock starvation, the pending
bit will be set by the queue head vCPU when it is in the active lock
spinning loop to disable any lock stealing attempt. This helps to
reduce the performance
This patch allows one attempt for the lock waiter to steal the lock
when entering the PV slowpath. To prevent lock starvation, the pending
bit will be set by the queue head vCPU when it is in the active lock
spinning loop to disable any lock stealing attempt. This helps to
reduce the performance
10 matches
Mail list logo