On Wed, Jun 18, 2014 at 3:56 PM, Andres Freund <andres@2ndquadrant.com> wrote:
>> > I'm looking at the way you did this in the context of the atomics
>> > patch. Won't:
>> > s_init_lock_sema(volatile slock_t *lock)
>> > {
>> > static int counter = 0;
>> >
>> > *lock = (++counter) % NUM_SPINLOCK_SEMAPHORES;
>> > }
>> >
>> > lead to bad results if spinlocks are intialized after startup?
>>
>> Why?
>
> Because every further process will start with a copy of the postmaster's
> counter or with 0 (EXEC_BACKEND)?
Oh, true. Maybe we should randomize that.
>> > Essentially mapping new spinlocks to the same semaphore?
>>
>> Yeah, but so what? If we're mapping a bajillion spinlocks to the same
>> semaphore already, what's a few more?
>
> Well, imagine something like parallel query creating new segments,
> including a spinlock (possibly via a lwlock) at runtime. If there were
> several backends processing such queries this they'd all map to the same
> semaphore.
Yeah.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company