From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wols Lists Subject: Re: possible HighPoint RocketRAID 2720SGL failure Date: Sat, 23 Sep 2017 17:53:30 +0100 Message-ID: <59C6918A.6040609@youngman.org.uk> References: <73afd1f8-176a-07e9-1024-57692dc96904@eyal.emu.id.au> <20170921172019.2067e49b@natsu> <6c99402d-506c-32de-9673-22f5179df8d7@eyal.emu.id.au> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: Phil Turmel , Eyal Lebedinsky , list linux-raid List-Id: linux-raid.ids On 23/09/17 15:49, Phil Turmel wrote: > If thermal stress doesn't kill them, then dopant diffusion within the > semiconductors eventually will. This occurs even when turned off, but > proceeds much faster at elevated temperatures. Dopant concentrations > are engineered to not suffer from diffusion effects well beyond the > expected life of the components (at rated operating temps), but that > doesn't mean there aren't marginal production runs. Which can be hard > to discover before parts start failing years later. If that happens > after the warranty period, the manufacturer has dodged a big bullet. > With a bit of tarnish on their name, of course. And as manufacturers shrink their die sizes, dopant diffusion and quantum leakage become much bigger problems :-( If your transistor is only four or five atoms deep, it won't have many dopant atoms, and they only have to diffuse a short distance before your transistor is toast. Cheers, Wol