From nobody Sat May 21 16:14:43 2022 X-Original-To: questions@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 546921B3D25E for ; Sat, 21 May 2022 16:14:52 +0000 (UTC) (envelope-from merlyn@geeks.org) Received: from mail.geeks.org (mail.geeks.org [IPv6:2001:4980:3333:1::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4L57wC23f1z4fYq for ; Sat, 21 May 2022 16:14:51 +0000 (UTC) (envelope-from merlyn@geeks.org) Received: from mail.geeks.org (localhost [127.0.0.1]) by after-clamsmtpd.geeks.org (Postfix) with ESMTP id CADED414C9 for ; Sat, 21 May 2022 11:14:43 -0500 (CDT) Received: by mail.geeks.org (Postfix, from userid 1003) id B4078414C8; Sat, 21 May 2022 11:14:43 -0500 (CDT) Date: Sat, 21 May 2022 11:14:43 -0500 From: Doug McIntyre To: questions@freebsd.org Subject: Re: OT: Weird Hardware Problem Message-ID: References: <0a9f810d-7b4b-f4e6-4b7c-716044a9cf69@tundraware.com> <8b13e2f5-6ff4-ecc2-7036-c88cff0f5b6b@tundraware.com> <8732b894-0962-3546-4697-4c2ae0658cb8@kicp.uchicago.edu> <20200520182154.GA87305@neutralgood.org> <4287e288d0655880e1d6bb3598662eeb6a5a30e3.camel@adminart.net> <101c1ce69d461c329ce028753fb60a217b7e6906.camel@adminart.net> List-Id: User questions List-Archive: https://lists.freebsd.org/archives/freebsd-questions List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-questions@freebsd.org X-BeenThere: freebsd-questions@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <101c1ce69d461c329ce028753fb60a217b7e6906.camel@adminart.net> X-Virus-Scanned: ClamAV using ClamSMTP X-Rspamd-Queue-Id: 4L57wC23f1z4fYq X-Spamd-Bar: --- Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=pass (mx1.freebsd.org: domain of merlyn@geeks.org designates 2001:4980:3333:1::1 as permitted sender) smtp.mailfrom=merlyn@geeks.org X-Spamd-Result: default: False [-3.30 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; FROM_HAS_DN(0.00)[]; TO_MATCH_ENVRCPT_ALL(0.00)[]; R_SPF_ALLOW(-0.20)[+ptr]; MIME_GOOD(-0.10)[text/plain]; PREVIOUSLY_DELIVERED(0.00)[questions@freebsd.org]; TO_DN_NONE(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; NEURAL_HAM_LONG(-1.00)[-1.000]; RCVD_COUNT_THREE(0.00)[3]; DMARC_NA(0.00)[geeks.org]; NEURAL_HAM_SHORT(-1.00)[-1.000]; MLMMJ_DEST(0.00)[questions]; FROM_EQ_ENVFROM(0.00)[]; R_DKIM_NA(0.00)[]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:7753, ipnet:2001:4980::/32, country:US]; RCVD_TLS_LAST(0.00)[]; MID_RHS_MATCH_FROM(0.00)[] X-ThisMailContainsUnwantedMimeParts: N On Sat, May 21, 2022 at 11:52:12AM +0200, hw wrote: > On Fri, 2022-05-20 at 23:30 -0500, Doug McIntyre wrote: > > When you have a datacenter full of devices, you'll see alot more > > failures... > What would you say is the sample size and the rate of failure? > > I've seen only hundreds, not thousands of PSUs. Hmm, over the years? It would be in the range of thousands of machines (less than tens of thousands). Most of which have at least dual, if not 4-8 power supplies each. Plus storage which usually has many PSUs in each system. My past endevors usually drove the hardware as long as we could, so definately saw much more failure at the end of useful life. Current endevors have a much more reasonable hardware refresh cycle, so we would retire gear before the typical failure cycles kick in. Even so, I think the industry learned hard that cheaping out on components like electrolytic capacitors and saving those pennies per component was foolish when they had to spend lots of money RMAing them down the road when the cheap ones failed, and if they only spend a few more cents per cap, they'd cut down on their RMA budget significantly. So, gear made in certain years, when the cheap crap flooded the market really had a much larger failure pool than before then, or after the lesson was learned.