From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: One drive which perform frequent head unloads under Linux Date: Tue, 30 Sep 2008 23:17:29 +0900 Message-ID: <48E234F9.9050509@kernel.org> References: <1222334079.13537.2.camel@frattaglia> <48E09581.8010504@kernel.org> <1222690726.26716.11.camel@frattaglia> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Return-path: Received: from hera.kernel.org ([140.211.167.34]:50118 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752966AbYI3OSz (ORCPT ); Tue, 30 Sep 2008 10:18:55 -0400 In-Reply-To: <1222690726.26716.11.camel@frattaglia> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Vincenzo Ciancia Cc: linux-ide@vger.kernel.org Vincenzo Ciancia wrote: > On lun, 2008-09-29 at 17:44 +0900, Tejun Heo wrote: >> Vincenzo Ciancia wrote: >>> Hi, I own a toshiba m400 and I already had to replace a disk in less >>> than one year (luckily, it was covered by warranty). I noticed that >>> Load_Cycle_Count was indeed increasing. Using hdparm -B 255 fixes it, >>> but also 254 seems to fix it (and I guess it is better to have some >>> power management than none at all?). >>> >>> I am not subscribed to the list so if you need more information just ask >>> me. I followed instructions at >>> >>> http://ata.wiki.kernel.org/index.php/Known_issues#How_to_determine_whether_a_machine_has_this_problem >> I just updated the page. Can you please read the updated part (which is >> in bold) and post how much the load cycle count increases per hour >> without any adjustment? > > The problem is that now I don't know what is the default (I also found > no way to read the -B setting with hdparm). I tried with hdparm -B 128 > which seems adviced by many for laptops, and I get 130 cycles per hour. APM setting is not persistent and BIOS probably programs it during boot, so just removing any script you added and doing a cold reboot should give you the default configuration. -- tejun