Re: Trouble with hashagg spill I/O pattern and costing - Mailing list pgsql-hackers

From Jeff Davis
Subject Re: Trouble with hashagg spill I/O pattern and costing
Date
Msg-id 0589f869969de2f3e9713689159c7c4fbe1fcfa5.camel@j-davis.com
Whole thread Raw
In response to Re: Trouble with hashagg spill I/O pattern and costing  (Tomas Vondra <tomas.vondra@2ndquadrant.com>)
Responses Re: Trouble with hashagg spill I/O pattern and costing
Re: Trouble with hashagg spill I/O pattern and costing
List pgsql-hackers
On Tue, 2020-05-26 at 21:15 +0200, Tomas Vondra wrote:
> Yeah. I agree prefetching is definitely out of v13 scope. It might be
> interesting to try how useful would it be, if you're willing to spend
> some time on a prototype.

I think a POC would be pretty quick; I'll see if I can hack something
together.

> I think it's pretty much ready to go.

Committed with max of 128 preallocated blocks. Minor revisions.

> 
> As for the tlist fix, I think that's mostly ready too - the one thing
> we
> should do is probably only doing it for AGG_HASHED. For AGG_SORTED
> it's
> not really necessary.

Melanie previously posted a patch to avoid spilling unneeded columns,
but it introduced more code:


https://www.postgresql.org/message-id/CAAKRu_aefEsv+UkQWqu+ioEnoiL2LJu9Diuh9BR8MbyXuZ0j4A@mail.gmail.com

and it seems that Heikki also looked at it. Perhaps we should get an
acknowledgement from one of them that your one-line change is the right
approach?

Regards,
    Jeff Davis





pgsql-hackers by date:

Previous
From: "David G. Johnston"
Date:
Subject: Re: Default gucs for EXPLAIN
Next
From: Kyotaro Horiguchi
Date:
Subject: Re: Remove page-read callback from XLogReaderState.