Date: Tue, 23 Jun 2015 06:06:53 -0400 From: Quartz <quartz@sneakertech.com> To: kpneal@pobox.com Cc: FreeBSD FS <freebsd-fs@freebsd.org> Subject: Re: ZFS raid write performance? Message-ID: <55892FBD.7030204@sneakertech.com> In-Reply-To: <20150623042234.GA66734@neutralgood.org> References: <5587C3FF.9070407@sneakertech.com> <5587C97F.2000407@delphij.net> <55887810.3080301@sneakertech.com> <20150622221422.GA71520@neutralgood.org> <55888E0D.6040704@sneakertech.com> <20150623002854.GB96928@neutralgood.org> <5588D291.4030806@sneakertech.com> <20150623042234.GA66734@neutralgood.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> I'd go with something similar to how the machine will be used in production. Hrmm, I was hoping for a quickie synthetic test just to gauge if the write speed was anywhere near as low as the network. > Also, ZFS has the ability to detect sequences of zeros and optimize the > writing of them. Yeah, I had a vague memory of something like that, which is why I asked. >Make sure the amount copied to the machine is, oh, say, at least > twice (or maybe thrice?) the amount of RAM in the server just to be sure > you've defeated any caching. That's... not going to be easy. I don't have that much data broken into files of that size kicking around yet. It won't necessarily be a "production" test either, given that most clients will be transferring only a few gigs over at a time.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?55892FBD.7030204>