Date: Mon, 19 May 2008 19:14:48 +0200
To: "Greg Smith" <gsmith@gregsmith.com>,
	"Matthew Wakeling" <matthew@flymine.org>
Subject: Re: I/O on select count(*)
From: PFC <lists@peufeu.com>
Cc: pgsql-performance@postgresql.org
Content-Type: text/plain; format=flowed; delsp=yes; charset=utf-8
MIME-Version: 1.0
References: <920841.71690.qm@web44808.mail.sp1.yahoo.com>
	<482B1D5F.EE98.0025.0@wicourts.gov>
	<Pine.GSO.4.64.0805142133250.27290@westnet.com>
	<20080515020553.GN9838@alvh.no-ip.org>
	<Pine.LNX.4.64.0805151245360.16756@aragorn.flymine.org>
	<20080515155232.GC8221@alvh.no-ip.org>
	<Pine.GSO.4.64.0805161118210.4987@westnet.com>
	<20080516201528.GJ13061@alvh.no-ip.org>
	<18382.1210992302@sss.pgh.pa.us>
	<Pine.LNX.4.64.0805191257020.16756@aragorn.flymine.org>
	<Pine.GSO.4.64.0805191137480.25115@westnet.com>
Content-Transfer-Encoding: 7bit
Message-ID: <op.ubeviyrgcigqcu@apollo13.peufeu.com>
In-Reply-To: <Pine.GSO.4.64.0805191137480.25115@westnet.com>
User-Agent: Opera Mail/9.24 (Linux)


> The real question in my mind is why this turns into a bottleneck before  
> the similar task of cleaning the 16MB XLOG segment does.  I expected  
> that one would need to be cracked before the CLOG switch time could  
> possibly be an issue, but reports from the field seem to suggest  
> otherwise.

	Hm, on current CPUs zeroing 8kB of RAM should take less than 2 us... now  
if it has to be written to disk, that's another story !