From: Andres Freund <andres@anarazel.de>
To: pgsql-performance@postgresql.org
Subject: Re: BBU Cache vs. spindles
Date: Thu, 21 Oct 2010 22:18:09 +0200
User-Agent: KMail/1.13.5 (Linux/2.6.36-rc8-andres-00185-ge56d55b; KDE/4.5.1;
	x86_64; ; )
Cc: "Kevin Grittner" <Kevin.Grittner@wicourts.gov>,
	"Bruce Momjian" <bruce@momjian.us>, "Greg Smith" <greg@2ndquadrant.com>,
	jd@commandprompt.com, "Scott Marlowe" <scott.marlowe@gmail.com>,
	"Steve Crawford" <scrawford@pinpointresearch.com>,
	"Ben Chobot" <bench@silentmedia.com>
References: <4CC04EA50200002500036C5E@gw.wicourts.gov>
	<201010211935.o9LJZTM21744@momjian.us>
	<4CC0513E0200002500036C68@gw.wicourts.gov>
In-Reply-To: <4CC0513E0200002500036C68@gw.wicourts.gov>
MIME-Version: 1.0
Content-Type: Text/Plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
Message-Id: <201010212218.09609.andres@anarazel.de>

On Thursday 21 October 2010 21:42:06 Kevin Grittner wrote:
> Bruce Momjian <bruce@momjian.us> wrote:
> > I assume we send a full 8k to the controller, and a failure during
> > that write is not registered as a write.
> 
> On what do you base that assumption?  I assume that we send a full
> 8K to the OS cache, and the file system writes disk sectors
> according to its own algorithm.  With either platters or BBU cache,
> the data is persisted on fsync; why do you see a risk with one but
> not the other?
At least on linux pages can certainly get written out in < 8kb batches if 
youre under memory pressure.

Andres