xfs
[Top] [All Lists]

Re: Optimize RAID0 for max IOPS?

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: Optimize RAID0 for max IOPS?
From: Wolfgang Denk <wd@xxxxxxx>
Date: Tue, 25 Jan 2011 13:45:09 +0100
Cc: Emmanuel Florac <eflorac@xxxxxxxxxxxxxx>, linux-raid@xxxxxxxxxxxxxxx, Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx>, xfs@xxxxxxxxxxx
Comments: In-reply-to Dave Chinner <david@xxxxxxxxxxxxx> message dated "Tue, 25 Jan 2011 19:36:43 +1100."
In-reply-to: <20110125083643.GE28803@dastard>
References: <20110118210112.D13A236C@xxxxxxxxxxxxxx> <4D361F26.3060507@xxxxxxxxxxxxxxxxxx> <20110119192104.1FA92D30267@xxxxxxxxxxxxxx> <AANLkTikx4g99-Cf_09kEGfF2mmf4Dnuh2A5gTrtKweDy@xxxxxxxxxxxxxx> <alpine.DEB.2.00.1101241024230.14640@xxxxxxxxxxxxxxxx> <20110124215713.82D75B187@xxxxxxxxxxxxxx> <20110124230314.GA11040@dastard> <20110125083900.4dd65bf2@xxxxxxxxxxxxxxx> <20110125083643.GE28803@dastard>
Dear Dave Chinner,

In message <20110125083643.GE28803@dastard> you wrote:
>
> Oh, despite $subject being "RAID0" the filesystems being tested are
> on RAID5 and RAID6 with very small chunk sizes on slow SATA drives.
> This is smelling like a case of barrier IOs on software raid on
> cheap storage....

Right. [Any way to avoid these, btw?]  I got side-tracked by the
comments about the new (to me) delaylog mount option to xfs; as the
results were not exactly as exp[ected I though it might be interesting
to report these.

But as the subject says, my current topic is tuning RAID0 to avoid
exactly this type of bottleneck; or rather looking for tunable options
on RAID0

Best regards,

Wolfgang Denk

--
DENX Software Engineering GmbH,     MD: Wolfgang Denk & Detlev Zundel
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany
Phone: (+49)-8142-66989-10 Fax: (+49)-8142-66989-80 Email: wd@xxxxxxx
PLEASE NOTE: Some Quantum Physics Theories Suggest That When the Con-
sumer Is Not Directly Observing This Product, It May Cease  to  Exist
or Will Exist Only in a Vague and Undetermined State.

<Prev in Thread] Current Thread [Next in Thread>