Re: Thousands of semops for every i/o - Mailing list pgsql-general

From Tom Lane
Subject Re: Thousands of semops for every i/o
Date
Msg-id 5321.1055280276@sss.pgh.pa.us
Whole thread Raw
In response to Re: Thousands of semops for every i/o  ("Jeffrey W. Baker" <jwbaker@acm.org>)
List pgsql-general
"Jeffrey W. Baker" <jwbaker@acm.org> writes:
> On Mon, 2003-06-09 at 23:08, Tom Lane wrote:
>> The first thing that comes to mind is that the thing is using SysV
>> semaphores as a substitute for spinlocks.

> It looks like a simple change in s_lock.h from
> #if defined(__i386__)
> to
> #if defined(__i386__) || defined(__x86_64__)
> Will be necessary for this platform.

Cool.  I assume it still passes regression tests and so forth?

            regards, tom lane

pgsql-general by date:

Previous
From: "Nigel J. Andrews"
Date:
Subject: Re: Pg_dump for 7.0.2
Next
From: Tom Lane
Date:
Subject: Re: increment_by@