Re: Bug: Buffer cache is not scan resistant - Mailing list pgsql-hackers

From Mark Kirkwood
Subject Re: Bug: Buffer cache is not scan resistant
Date
Msg-id 45ECB096.2050709@paradise.net.nz
Whole thread Raw
In response to Re: Bug: Buffer cache is not scan resistant  (Tom Lane <tgl@sss.pgh.pa.us>)
Responses Re: Bug: Buffer cache is not scan resistant  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
Tom Lane wrote:
> 
> But what I wanted to see was the curve of
> elapsed time vs shared_buffers?
> 

Of course! (lets just write that off to me being pre coffee...).

With the patch applied:

Shared Buffers  Elapsed  vmstat IO rate
--------------  -------  --------------
400MB           101 s    122 MB/s
2MB             101 s
1MB              97 s
768KB            94 s
512KB            84 s
256KB            79 s
128KB            75 s    166 MB/s

Looks *very* similar.

Cheers

Mark


pgsql-hackers by date:

Previous
From: Andrew Dunstan
Date:
Subject: Re: proposal: custom variables management
Next
From: Tom Lane
Date:
Subject: Re: Bug: Buffer cache is not scan resistant