From: | Robert Haas <robertmhaas(at)gmail(dot)com> |
---|---|
To: | Alvaro Herrera <alvherre(at)commandprompt(dot)com> |
Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Christopher Browne <cbbrowne(at)gmail(dot)com>, Simon Riggs <simon(at)2ndquadrant(dot)com>, Pg Hackers <pgsql-hackers(at)postgresql(dot)org> |
Subject: | Re: extending relations more efficiently |
Date: | 2012-05-01 19:35:04 |
Message-ID: | CA+TgmoaWBDgLst4XT42pkKVT6oTD3mi0NhzDRAhcOHt7y-vj+w@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
On Tue, May 1, 2012 at 3:01 PM, Alvaro Herrera
<alvherre(at)commandprompt(dot)com> wrote:
>> The system is supposed to be designed to avoid that; we try to hand out
>> pages with free space to different backends. One of the advantages of
>> the current page-at-a-time setup is that when there is *no* free space
>> according to the FSM, each such backend will create and fill its own
>> page independently. They do serialize on the extension lock, but the
>> intervening tuple additions are parallelized. We have to be careful to
>> not make that case worse in a multi-page-extension scheme.
>
> This didn't work all that well for toast tables that have lots of very
> large tuples inserted concurrently, at least with older releases. Each
> backend would acquire the extension lock many times per tuple inserted.
> The result was really high contention on the extension lock.
Hmm, this sounds like a good test case - a small number of SQL
statements triggering a large amount of relation extension work.
Using an unlogged table would probably make it easier to see the
relation-extension contention, too, since you'd get WALInsertLock
mostly out of the way.
--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company
From | Date | Subject | |
---|---|---|---|
Next Message | Noah Misch | 2012-05-01 19:36:22 | Re: proposal: additional error fields |
Previous Message | Peter Eisentraut | 2012-05-01 19:30:25 | port _srv.o makefile rules don't observe dependency tracking |