From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lin Ming Subject: Re: [PATCH 0/3] ata port runtime power management support Date: Thu, 03 Nov 2011 22:47:17 +0800 Message-ID: <1320331637.2813.84.camel@hp6530s> References: <1320214900-2112-1-git-send-email-ming.m.lin@intel.com> <20111102151711.GB12543@dhcp-172-17-108-109.mtv.corp.google.com> <1320330107.2813.73.camel@hp6530s> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: linux-ide-owner@vger.kernel.org To: Tejun Heo Cc: "linux-kernel@vger.kernel.org" , "linux-ide@vger.kernel.org" , "linux-scsi@vger.kernel.org" , "linux-pm@vger.kernel.org" , Alan Stern , Jeff Garzik , "Rafael J. Wysocki" , James Bottomley , "Huang, Ying" , "Zhang, Rui" List-Id: linux-scsi@vger.kernel.org On Thu, 2011-11-03 at 22:30 +0800, Tejun Heo wrote: > Hello, > > On Thu, Nov 3, 2011 at 7:21 AM, Lin Ming wrote: > >> * How much does this add on top of hardware timed auto spindown and > >> dynamic link power management? > > > > Sorry, I don't understand this question. > > What do you mean? > > I was curious about the amount of additional power saving on top of > the existing PM features. I'll measure the power saving. > > >> * Do the added benefits justify yet another runtime powersaving > >> mechanism? > > > > There will be ACPI firmware which supports ata port runtime D3Cold. > > To enable ata port runtime PM is the first step. > > libata can already turn off unused ports although it wouldn't go as > far as putting the whole controller into D3. At runtime? Could you point me which piece of code implement this? > > >> * Any way we can tie the other stuff with overall runtime PM? > > > > What's the other stuff? > > Do you mean tie disk/link/port/controller stuff with overall runtime PM? > > Hardware initiated spin-down (hdparm -S) and link power saving (look > for ata_lpm_*). It would be great if there's an overall design how > they interact before adding yet another PM vector. Yes. Need to think about it. Thanks.