Date: 19 Apr 2016 22:05:30 -0000 From: "John Levine" <johnl@iecc.com> To: freebsd-questions@freebsd.org Cc: steve@sohara.org Subject: Re: Raid 1+0 Message-ID: <20160419220530.14065.qmail@ary.lan> In-Reply-To: <20160419180715.f788945fb67388a707c60ee7@sohara.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> Next Look at the curves for failure probability against age (or >total activity) and note that the classic bathtub shape and consider what >happens when your whole array is on the steep bit at the end and the first >drive failure happens. Drive makers, not being totally dim, try to design their drives so that they won't fail during the warranty period, but who cares after that. So it's not surprising that the failure rate goes up a lot shortly after the warranty expires. Also, if you buy a bunch of identical drives and slap them into a RAID, they're likely from the same production run and will have similar failure characteristics. I try to mix drives from different manufacturers, or at least with dates at least a month apart so they're not from the same production run. R's, John
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160419220530.14065.qmail>