Re: [PATCH 3/3] locking/osq: Drop the overload of osq_lock()

[Peter Zijlstra]

On Mon, Jun 27, 2016 at 01:41:30PM -0400, Pan Xinhui wrote:
> @@ -118,8 +123,17 @@ bool osq_lock(struct optimistic_spin_queue *lock)
>  	while (!READ_ONCE(node->locked)) {
>  		/*
>  		 * If we need to reschedule bail... so we can block.
> +		 * An over-committed guest with more vCPUs than pCPUs
> +		 * might fall in this loop and cause a huge overload.
> +		 * This is because vCPU A(prev) hold the osq lock and yield out
> +		 * vCPU B(node) wait ->locked to be set, IOW, it wait utill
> +		 * vCPU A run and unlock the osq lock. Such spin is meaningless
> +		 * use vcpu_is_preempted to detech such case. IF arch does not
> +		 * support vcpu preempted check, vcpu_is_preempted is a macro
> +		 * defined by false.

Or you could mention lock holder preemption and everybody will know what
you're talking about.

>  		 */
> -		if (need_resched())
> +		if (need_resched() ||
> +			vcpu_is_preempted(node_cpu(node->prev)))

Did you really need that linebreak?

>  			goto unqueue;
>  
>  		cpu_relax_lowlatency();
> -- 
> 2.4.11
>