From: | Robert Haas <robertmhaas(at)gmail(dot)com> |
---|---|
To: | Andres Freund <andres(at)2ndquadrant(dot)com> |
Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org> |
Subject: | Re: [COMMITTERS] pgsql: Reduce the number of semaphores used under --disable-spinlocks. |
Date: | 2014-06-18 20:38:09 |
Message-ID: | CA+TgmoY=OTwGJyo3LH=J3iZhjU6E7wRn_tm1vJMKytCBRQu6xw@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers pgsql-hackers |
On Wed, Jun 18, 2014 at 3:56 PM, Andres Freund <andres(at)2ndquadrant(dot)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
From | Date | Subject | |
---|---|---|---|
Next Message | Andrew Dunstan | 2014-06-18 23:32:43 | pgsql: Remove unnecessary check for jbvBinary in convertJsonbValue. |
Previous Message | Andres Freund | 2014-06-18 19:56:49 | Re: [COMMITTERS] pgsql: Reduce the number of semaphores used under --disable-spinlocks. |
From | Date | Subject | |
---|---|---|---|
Next Message | Robert Haas | 2014-06-18 20:41:30 | Re: idle_in_transaction_timeout |
Previous Message | Fabrízio de Royes Mello | 2014-06-18 20:25:28 | Re: How about a proper TEMPORARY TABLESPACE? |