DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com;
	h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references;
	b=PoUtsl1+zUyT13R5ETmzREg2wGQN2XBh27QvU8i+0BdquaEgwtsU69bMFYU5hW7Czf76uzXaZxAWOwlfIM3XPJmkBvbbOZ3JmLHnyayih5TKuphk7Xnl3/X1o21lL6y8Lf3lqGvEmnDQNrWC4ZU7dcnEWxBzD6bywsjB4tWZhNw=
Message-ID: <33c6269f050816125266a62d5d@mail.gmail.com>
Date: Tue, 16 Aug 2005 15:52:45 -0400
From: Alex Turner <armtuk@gmail.com>
To: John A Meinel <john@arbash-meinel.com>
Subject: Re: choosing RAID level for xlogs
Cc: Anjan Dave <adave@vantage.com>, mudfoot@rawbw.com,
	pgsql-performance@postgresql.org
In-Reply-To: <43023BA0.5030608@arbash-meinel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
References: 
 <4BAFBB6B9CC46F41B2AD7D9F4BBAF785098BE0@vt-pe2550-001.VANTAGE.vantage.com>
	<43023BA0.5030608@arbash-meinel.com>

Don't forget that often controlers don't obey fsyncs like a plain
drive does.  thats the point of having a BBU ;)

Alex Turner
NetEconomist

On 8/16/05, John A Meinel <john@arbash-meinel.com> wrote:
> Anjan Dave wrote:
> > Yes, that's true, though, I am a bit confused because the Clariion arra=
y
> > document I am reading talks about how the write cache can eliminate the
> > RAID5 Write Penalty for sequential and large IOs...resulting in better
> > sequential write performance than RAID10.
> >
> > anjan
> >
>=20
> To give a shorter statement after my long one...
> If you have enough cache that the controller can write out big chunks to
> the disk at a time, you can get very good sequential RAID5 performance,
> because the stripe size is large (so it can do a parallel write to all
> disks).
>=20
> But for small chunk writes, you suffer the penalty of the read before
> write, and possible multi-disk read (depends on what is in cache).
>=20
> RAID10 generally handles small writes better, and I would guess that
> 4disks would perform almost identically to 6disks, since you aren't
> usually writing enough data to span multiple stripes.
>=20
> If your battery-backed cache is big enough that you don't fill it, they
> probably perform about the same (superfast) since the cache hides the
> latency of the disks.
>=20
> If you start filling up your cache, RAID5 probably can do better because
> of the parallelization.
>=20
> But small writes followed by an fsync do favor RAID10 over RAID5.
>=20
> John
> =3D:->
>=20
>=20
>