Re: [PATCH v4] locking/mutex: Prevent lock starvation when spinning is disabled

[Jason Low]

On Thu, 2016-08-18 at 17:39 -0700, Jason Low wrote:
> Imre reported an issue where threads are getting starved when trying
> to acquire a mutex. Threads acquiring a mutex can get arbitrarily delayed
> sleeping on a mutex because other threads can continually steal the lock
> in the fastpath and/or through optimistic spinning.
> 
> Waiman has developed patches that allow waiters to return to optimistic
> spinning, thus reducing the probability that starvation occurs. However,
> Imre still sees this starvation problem in the workloads when optimistic
> spinning is disabled.
> 
> This patch adds an additional boolean to the mutex that gets used in
> the CONFIG_SMP && !CONFIG_MUTEX_SPIN_ON_OWNER cases. The flag signifies
> whether or not other threads need to yield to a waiter and gets set
> when a waiter spends too much time waiting for the mutex. The threshold
> is currently set to 16 wakeups, and once the wakeup threshold is exceeded,
> other threads must yield to the top waiter. The flag gets cleared
> immediately after the top waiter acquires the mutex.
> 
> This prevents waiters from getting starved without sacrificing much
> much performance, as lock stealing is still allowed and only
> temporarily disabled when it is detected that a waiter has been waiting
> for too long.

Changes from v3 (in peterz locking/core) -> v4:

1. Fixed patch title. It should be "Prevent lock starvation when spinning is
   disabled" instead of "when spinning is enabled".

2. Call clear_yield_to_waiter() when a top waiter exits in the 'err' case.

3. Only clear yield_to_waiter if the thread is the top waiter and not if it
   is a non-top waiter that received a signal.