From mboxrd@z Thu Jan 1 00:00:00 1970 From: CrashPlan Pro Subject: Re: Disk spin-up optimization during system resume Date: Mon, 20 Jan 2014 13:38:15 +0100 Message-ID: <52DD18B7.7030303@crashplan.pro> References: <20140116220409.GA1183@linux.intel.com> <52D9976C.2010009@ubuntu.com> <52D9F27F.8060705@ubuntu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from slow1-d.mail.gandi.net ([217.70.178.86]:57500 "EHLO slow1-d.mail.gandi.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753355AbaATM4m (ORCPT ); Mon, 20 Jan 2014 07:56:42 -0500 Received: from relay6-d.mail.gandi.net (relay6-d.mail.gandi.net [217.70.183.198]) by slow1-d.mail.gandi.net (Postfix) with ESMTP id 74D3947AFC6 for ; Mon, 20 Jan 2014 13:38:25 +0100 (CET) In-Reply-To: Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org Cc: Todd E Brandt , Aaron Lu , Phillip Susi , SCSI development list Dan Williams wrote at 18-01-14 05:09: > Larger systems are less likely to ever sleep. I have to agree with this. There is almost no storage server that will be suspended to sleep. Users of storage servers rather see an improvement at reboot time. For example by not re-enumerating all 40 / 80 / 100 attached PuiS ATA drives or not spinning the drive while enumerating. Only the boot drive needs to be spin up. Currently the reboot proces does wake each drive that was previously spun down. At a rate of 1 concurrent drive that takes approximately 6 seconds to spin up, the re-enumeration part takes around 8 minutes during reboot.