Re: PoC: Partial sort

From: Andreas Karlsson <andreas(at)proxel(dot)se>
To: David Rowley <dgrowleyml(at)gmail(dot)com>
Cc: Alexander Korotkov <aekorotkov(at)gmail(dot)com>, pgsql-hackers <pgsql-hackers(at)postgresql(dot)org>, Andres Freund <andres(at)2ndquadrant(dot)com>, Martijn van Oosterhout <kleptog(at)svana(dot)org>
Subject: Re: PoC: Partial sort
Date: 2013-12-31 01:41:32
Message-ID: 52C220CC.8030707@proxel.se
Views: Raw Message | Whole Thread | Download mbox
Thread:
Lists: pgsql-hackers

On 12/29/2013 08:24 AM, David Rowley wrote:
> If it was possible to devise some way to reuse any
> previous tuplesortstate perhaps just inventing a reset method which
> clears out tuples, then we could see performance exceed the standard
> seqscan -> sort. The code the way it is seems to lookup the sort
> functions from the syscache for each group then allocate some sort
> space, so quite a bit of time is also spent in palloc0() and pfree()
>
> If it was not possible to do this then maybe adding a cost to the number
> of sort groups would be better so that the optimization is skipped if
> there are too many sort groups.

It should be possible. I have hacked a quick proof of concept for
reusing the tuplesort state. Can you try it and see if the performance
regression is fixed by this?

One thing which have to be fixed with my patch is that we probably want
to close the tuplesort once we have returned the last tuple from ExecSort().

I have attached my patch and the incremental patch on Alexander's patch.

--
Andreas Karlsson

Attachment Content-Type Size
partial-sort-4-reset.patch text/x-patch 66.5 KB
partial-sort-4-resetdiff.patch text/x-patch 2.9 KB

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Vik Fearing 2013-12-31 03:03:03 Re: Proposal: variant of regclass
Previous Message Tatsuo Ishii 2013-12-31 01:38:54 Re: Proposal: variant of regclass