Received: from localhost (unknown [200.46.204.191]) by postgresql.org (Postfix) with ESMTP id 82C332E00BA for ; Sat, 1 Dec 2007 10:42:43 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.191]) (amavisd-maia, port 10024) with ESMTP id 05585-01 for ; Sat, 1 Dec 2007 10:42:37 -0400 (AST) Received: from bay0-omc2-s35.bay0.hotmail.com (bay0-omc2-s35.bay0.hotmail.com [65.54.246.171]) by postgresql.org (Postfix) with ESMTP id 2B6362E008C for ; Sat, 1 Dec 2007 10:42:38 -0400 (AST) Received: from BAY124-W11 ([207.46.11.174]) by bay0-omc2-s35.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.3959); Sat, 1 Dec 2007 06:42:36 -0800 Message-ID: Content-Type: multipart/alternative; boundary="_06f7f944-d03e-4586-aba2-0579a013706e_" X-Originating-IP: [86.81.58.36] From: henk de wit To: "pgsql-performance@postgresql.org" Subject: Re: Utilizing multiple cores for one query Date: Sat, 1 Dec 2007 15:42:36 +0100 Importance: Normal In-Reply-To: <36e682920712010531k47871797ge19ceaddad9a7ff6@mail.gmail.com> References: <36e682920712010531k47871797ge19ceaddad9a7ff6@mail.gmail.com> MIME-Version: 1.0 X-OriginalArrivalTime: 01 Dec 2007 14:42:36.0564 (UTC) FILETIME=[6A3AE540:01C83428] X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200712/3 X-Sequence-Number: 27819 --_06f7f944-d03e-4586-aba2-0579a013706e_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable > > I wonder whether the current versions of postgres (i.e. either 8.2 or 8= .3) > > are able to utilize multiple cores for the execution of a single query? > Nope. I see, thanks for the clarification. Btw, in this thread: http://archives.postgresql.org/pgsql-performance/2007-= 10/msg00159.php the following is said: >You can determine what runs in parellel based on the >indentation of the output. >Items at the same indentation level under the same >"parent" line will run in parallel Wouldn't this offer some opportunities for running things on multiple cores= ? Based on the above, many people already seem to think that PG is able to = utilize multiple cores for 1 query. Of course, it can be easily "proved" th= at this does not happen by simply watching at the CPU utilization graphs wh= en executing a query. Nevertheless, those people may wonder why (some of) t= hose items that already run in parallel not actually run in parallel using = multiple cores? > Currently, the only way to parallelize a query in Postgres is to use pgpo= ol-II. > > http://pgpool.projects.postgresql.org/ Yes, I noticed this project before. At the time it was not really clear how= stable and/or how well supported this is. It indeed seems to support paral= lel queries automatically by being able to rewrite standard queries. It doe= s seem it needs different DB nodes and is thus probably not able to use mul= tiple cores of a single DBMS. Also, I could not really find how well pgpool= -II is doing at making judgments of the level of parallelization it's going= to use. E.g. when there are 16 nodes in the system with a currently low ut= ilization, a single query may be split into 16 pieces. On the other hand, w= hen 8 of these nodes are heavily utilized, splitting to 8 pieces might be b= etter. etc. Anyway, are there any plans for postgresql to support parallelizing queries= natively?=20 _________________________________________________________________ Express yourself instantly with MSN Messenger! Download today it's FREE! http://messenger.msn.click-url.com/go/onm00200471ave/direct/01/= --_06f7f944-d03e-4586-aba2-0579a013706e_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable

> > I wonder whether the current versions of postgres (i.e. either 8= .2 or 8.3)

> > are able to utilize m= ultiple cores for the execution of a single query?
> Nope.

I s= ee, thanks for the clarification.

Btw, in this thread: http://archiv= es.postgresql.org/pgsql-performance/2007-10/msg00159.php

the followi= ng is said:

>You can determine what runs in parellel based on the=
>indentation of the output.
>Items at the same indentation lev= el under the same
>"parent" line will run in parallel

Wouldn't= this offer some opportunities for running things on multiple cores? Based = on the above, many people already seem to think that PG is able to utilize = multiple cores for 1 query. Of course, it can be easily "proved" that this = does not happen by simply watching at the CPU utilization graphs when execu= ting a query. Nevertheless, those people may wonder why (some of) those ite= ms that already run in parallel not actually run in parallel using multiple= cores?

> Currently, the only way to parallelize a query in Postg= res is to use pgpool-II.
>
> http://pgpool.projects.postgresql.= org/

Yes, I noticed this project before. At the time it was not real= ly clear how stable and/or how well supported this is. It indeed seems to s= upport parallel queries automatically by being able to rewrite standard que= ries. It does seem it needs different DB nodes and is thus probably not abl= e to use multiple cores of a single DBMS. Also, I could not really find how= well pgpool-II is doing at making judgments of the level of parallelizatio= n it's going to use. E.g. when there are 16 nodes in the system with a curr= ently low utilization, a single query may be split into 16 pieces. On the o= ther hand, when 8 of these nodes are heavily utilized, splitting to 8 piece= s might be better. etc.

Anyway, are there any plans for postgresql t= o support parallelizing queries natively?

Ex= press yourself instantly with MSN Messenger! MSN Messenger = --_06f7f944-d03e-4586-aba2-0579a013706e_--