Re: 9.2beta1, parallel queries, ReleasePredicateLocks, CheckForSerializableConflictIn in the oprofile

Ants Aasma <ants@cybertec.at>

From: Ants Aasma <ants@cybertec.at>

To: Robert Haas <robertmhaas@gmail.com>

Cc: Merlin Moncure <mmoncure@gmail.com>, Florian Pflug <fgp@phlo.org>, Sergey Koposov <koposov@ast.cam.ac.uk>, Jeff Janes <jeff.janes@gmail.com>, pgsql-hackers@postgresql.org, Stephen Frost <sfrost@snowman.net>

Date: 2012-06-04T14:20:59Z

Lists: pgsql-hackers

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

Improve bulk-insert performance by keeping the current target buffer pinned
- 85e2cedf985b 8.4.0 cited

On Mon, Jun 4, 2012 at 5:12 PM, Robert Haas <robertmhaas@gmail.com> wrote:
> Note sure about the rest of this patch, but this part is definitely bogus:
>
> +#if !defined(pg_atomic_fetch_and_set)
> +#define pg_atomic_fetch_and_set(dst, src, value) \
> +       do { S_LOCK(&dummy_spinlock); \
> +       dst = src; \
> +       src = value; \
> +       S_UNLOCK(&dummy_spinlock); } while (0)
> +#endif
>
> Locking a dummy backend-local spinlock doesn't provide atomicity
> across multiple processes.

Right, of course. I don't know why I assumed that dummy_spinlock would
be global. In any case, this is very WIP and doesn't even aspire to be
portable yet. The main point was to see if there's any significant
performance to be gained by this method.

Ants Aasma
-- 
Cybertec Schönig & Schönig GmbH
Gröhrmühlgasse 26
A-2700 Wiener Neustadt
Web: http://www.postgresql-support.de