Re: Single client performance on trivial SELECTs - Mailing list pgsql-hackers

From Andres Freund
Subject Re: Single client performance on trivial SELECTs
Date
Msg-id 201104142208.34998.andres@anarazel.de
Whole thread Raw
In response to Re: Single client performance on trivial SELECTs  (Tom Lane <tgl@sss.pgh.pa.us>)
Responses Re: Single client performance on trivial SELECTs  (Alvaro Herrera <alvherre@commandprompt.com>)
List pgsql-hackers
Hi,

On Thursday 14 April 2011 16:43:16 Tom Lane wrote:
> I doubt that it's possible to make AllocSetAlloc radically cheaper.
I actually doubt your doubt. I think you could add some SLAB like interface 
for common allocation sizes making it significantly faster for some uses 
(because allocation/deallocation is a single linked list operation).
Maybe even treat everything < some_size as a slab object in the next bigger 
slab.

Note that I think youre otherwise right...

Andres


pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: Single client performance on trivial SELECTs
Next
From: Alvaro Herrera
Date:
Subject: Re: Single client performance on trivial SELECTs