Re: Spinlocks, yet again: analysis and proposed patches

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: Gavin Sherry <swm(at)linuxworld(dot)com(dot)au>
Cc: Marko Kreen <marko(at)l-t(dot)ee>, pgsql-hackers(at)postgresql(dot)org, Michael Paesold <mpaesold(at)gmx(dot)at>
Subject: Re: Spinlocks, yet again: analysis and proposed patches
Date: 2005-09-16 00:05:53
Message-ID: 18351.1126829153@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

Gavin Sherry <swm(at)linuxworld(dot)com(dot)au> writes:
> What about padding the LWLock to 64 bytes on these architectures. Both P4
> and Opteron have 64 byte cache lines, IIRC. This would ensure that a
> cacheline doesn't hold two LWLocks.

I tried that first, actually, but it was a net loss. I guess enlarging
the array that much wastes too much cache space.

regards, tom lane

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Marc G. Fournier 2005-09-16 00:09:13 Beta2 Wrap Up ...
Previous Message Gavin Sherry 2005-09-15 23:56:01 Re: Spinlocks, yet again: analysis and proposed patches