Messages in this thread | | | Subject | Re: [PATCH v2 0/9] Remove spin_unlock_wait() | From | Manfred Spraul <> | Date | Fri, 7 Jul 2017 19:47:58 +0200 |
| |
Hi Ingo,
On 07/07/2017 10:31 AM, Ingo Molnar wrote: > > There's another, probably just as significant advantage: queued_spin_unlock_wait() > is 'read-only', while spin_lock()+spin_unlock() dirties the lock cache line. On > any bigger system this should make a very measurable difference - if > spin_unlock_wait() is ever used in a performance critical code path. At least for ipc/sem: Dirtying the cacheline (in the slow path) allows to remove a smp_mb() in the hot path. So for sem_lock(), I either need a primitive that dirties the cacheline or sem_lock() must continue to use spin_lock()/spin_unlock().
-- Manfred
| |