From owner-freebsd-arm@freebsd.org Sun Jan 22 02:53:55 2017 Return-Path: Delivered-To: freebsd-arm@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 3933BCB0B2C for ; Sun, 22 Jan 2017 02:53:55 +0000 (UTC) (envelope-from freebsd-rwg@pdx.rh.CN85.dnsmgr.net) Received: from pdx.rh.CN85.dnsmgr.net (br1.CN84in.dnsmgr.net [69.59.192.140]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id DF8FEC56 for ; Sun, 22 Jan 2017 02:53:54 +0000 (UTC) (envelope-from freebsd-rwg@pdx.rh.CN85.dnsmgr.net) Received: from pdx.rh.CN85.dnsmgr.net (localhost [127.0.0.1]) by pdx.rh.CN85.dnsmgr.net (8.13.3/8.13.3) with ESMTP id v0M2rknr095914; Sat, 21 Jan 2017 18:53:46 -0800 (PST) (envelope-from freebsd-rwg@pdx.rh.CN85.dnsmgr.net) Received: (from freebsd-rwg@localhost) by pdx.rh.CN85.dnsmgr.net (8.13.3/8.13.3/Submit) id v0M2rkrl095913; Sat, 21 Jan 2017 18:53:46 -0800 (PST) (envelope-from freebsd-rwg) From: "Rodney W. Grimes" Message-Id: <201701220253.v0M2rkrl095913@pdx.rh.CN85.dnsmgr.net> Subject: Re: how to measure microsd wear In-Reply-To: <8C5C59C9-9AF3-4596-9B36-A792EDE05768@icloud.com> To: Jordan Hubbard Date: Sat, 21 Jan 2017 18:53:46 -0800 (PST) CC: Karl Denninger , freebsd-arm@freebsd.org X-Mailer: ELM [version 2.4ME+ PL121h (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-BeenThere: freebsd-arm@freebsd.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: "Porting FreeBSD to ARM processors." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 22 Jan 2017 02:53:55 -0000 > > > On Jan 21, 2017, at 3:40 PM, Karl Denninger wrote: > > [ SD cards can fail ] > > I have to second the assertion that even the comparatively pricy SanDisk Ultra SD cards can fail in production scenarios all the time, nor do they even need to be used in a more advanced filesystem role. I go through a lot of those cards just using them to shoot a lot of GoPro footage (video and still photos) and I usually get a few weeks out of each card, filling it almost entirely with footage several times a day, before it write locks and is ready for the bin. This is why I also shoot a lot of redundant footage with multiple GoPros, and anyone using these cards extensively for digital photograph or video will tell you the same. > I think I can add some light as to the higher failure rate in your digital video photography usage of the SD cards, your actually likely to write every single block of the device at a pretty regular rate, where as a file system is going to have hot spots of data that gets updated often, but at no where near the over all block write rate your doing in digital photography. I suspect using one as a drive in a security DVR would make for a good write cycle life counter. Probably wearing them out at the rate Jordan is seeing in the GoPro's. In either case the manufactures of flash devices have made it very clear that these things DO have a write cycle life time, and that your going to see a failure eventually if you write enough data to them. -- Rod Grimes rgrimes@freebsd.org