[Top] [All Lists]

Re: A little RAID experiment

To: stan@xxxxxxxxxxxxxxxxx
Subject: Re: A little RAID experiment
From: Stefan Ring <stefanrin@xxxxxxxxx>
Date: Thu, 31 May 2012 08:44:53 +0200
Cc: Linux fs XFS <xfs@xxxxxxxxxxx>
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=mYuTOJewVCa5Rh/drTKhl23FTsih3W46Dp6ECkO12x0=; b=p23YgwZN/6IR5ZxPyn28Pp7YxScLKAF8taDkNB+8PWbsEEgtLfI4JinYo4czQeNp7s wLzZWUexyfUbppUODe55CM9hyzbq7oUlWvF9JpdRQfAx8enkduT06Lyi8YIXpCOe4zGt OYz+gzgSOnxHITPdQ+KlpYrvd5zRQTKGvx0QWW3hCfURT+Lzqdi6fXI0/rbJ4yum+mvK wopvee7ndfVvcOmiyXEUUcXufHcNM9lH7YZtw2G7Lm7iqTtTT31X8g5qSq0ajz8NnPkT xz1eHtEqsJ/Zb8/MmZmLGjHd7Yf2m1l927/EgkrOO/w6iN/AisdhRw9xNIelnSTCXjxl vh4g==
In-reply-to: <4FC6C9AE.1070808@xxxxxxxxxxxxxxxxx>
References: <CAAxjCEzh3+doupD=LmgqSbCeYWzn9Ru-vE4T8tOJmoud+28FDQ@xxxxxxxxxxxxxx> <4F9AA43A.1060509@xxxxxxxxxxxxxxxxx> <CAAxjCEzzMk0TFKy23cAA_cAxbUFLS6cOCjgRBQocDUNtJO2UnA@xxxxxxxxxxxxxx> <CAAxjCEyMEtyDXdPN50HmV_k3vUPxCtYN1k5_AD=gZqu8-1wXqg@xxxxxxxxxxxxxx> <4FC6C9AE.1070808@xxxxxxxxxxxxxxxxx>
> You now have persistent write cache.  Did you test with XFS barriers
> disabled?  If not you should.  You'll likely see a decent, possibly
> outstanding, performance improvement with your huge metadata
> modification workload, as XFS will no longer flush the cache frequently
> when writing to the journal log.

I've already done that test with the previous controller. It had a
BBWC, so it was persistent as well. And it was easy to enable or
disable it. Yes, everything was always done with barrier=0. And yes,
the cache made a big difference (about 3x).

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