From: | Marko Kreen <markokr(at)gmail(dot)com> |
---|---|
To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
Cc: | Simon Riggs <simon(at)2ndquadrant(dot)com>, Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com>, Erik Rijkers <er(at)xs4all(dot)nl>, pgsql-hackers(at)postgresql(dot)org |
Subject: | Re: testing HS/SR - 1 vs 2 performance |
Date: | 2010-04-23 18:22:55 |
Message-ID: | r2we51f66da1004231122zc9789db6td117e913ea72ca76@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
On 4/23/10, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:
> Marko Kreen <markokr(at)gmail(dot)com> writes:
> > Um, you have been burned by exactly this on x86 also:
> > http://archives.postgresql.org/pgsql-hackers/2009-03/msg01265.php
>
>
> Yeah, we never did figure out exactly how come you were observing that
> failure on Intel-ish hardware. I was under the impression that Intel
> machines didn't have weak-memory-ordering behavior.
>
> I wonder whether your compiler had rearranged the code in ProcArrayAdd
> so that the increment happened before the array element store at the
> machine-code level. I think it would be entitled to do that under
> standard C semantics, since that ProcArrayStruct pointer isn't marked
> volatile.
Sounds likely.
Which seems to hint its better to handle all processors as weak ordered
and then work with explicit locks/memory barriers, than to sprinkle
code with 'volatile' to supress optimizations on intel and then still
fail on non-intel.
--
marko
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2010-04-23 18:28:38 | Re: psql: Add setting to make '+' on \d implicit |
Previous Message | Heikki Linnakangas | 2010-04-23 18:21:57 | Re: recovery_connections cannot start (was Re: master in standby mode croaks) |