From mboxrd@z Thu Jan 1 00:00:00 1970 From: Phillip Susi Subject: Understanding staggered spinup Date: Tue, 24 Sep 2013 10:56:48 -0400 Message-ID: <5241A830.7030903@ubuntu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from cdptpa-omtalb.mail.rr.com ([75.180.132.120]:52929 "EHLO cdptpa-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753096Ab3IXRCN (ORCPT ); Tue, 24 Sep 2013 13:02:13 -0400 Received: from cdptpa-omtalb.mail.rr.com ([10.127.143.52]) by cdptpa-qmta02.mail.rr.com with ESMTP id <20130924145758514.QRAO28522@cdptpa-qmta02.mail.rr.com> for ; Tue, 24 Sep 2013 14:57:58 +0000 Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: linux-ide@vger.kernel.org -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 I was looking at the libata code that handles the ahci staggered spinup feature ( SSS ) and am confused as to how this feature can possibly work. Cross referencing the AHCI spec with the code, it seems that the feature simply delays sending COMRESET and initializing the sata link until we set the SUD bit rather than at power on. According to the ATA specs though, a drive that powers up in standby will remain there until given an explicit command ( either SET FEATURES or a command that requires media access ). In other words, COMRESET will not cause the drive to spin up. Does this feature not really work or am I missing something? -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.17 (MingW32) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iQEcBAEBAgAGBQJSQagwAAoJEJrBOlT6nu75M+wH/2s8N7HxNcnjNSmIAdotpVdS qeKzK2nVu6sTtizcBTcnfYx9FXDDx3E0rNeU3Tgyk+DI0qDSs/faDAHBzly/hs0x f88Nsr4c6DJkPqj+omDQ7dHLt0vAkLn9sfdCCUjm0WqINgklxcOZdmA1PKntPdNT DSpMAo0QoT4PZDxOA6D866JjoQUi/OgKeMwTGrrnptzUoQVpXkWDXK5aFUkO3HmM 6LAoSmXipy7Jwaln2KYmQdhMyd4Zh+8BSB5SzVjCxYoNf33cVqA4lQ2H7bRQZJll DEkEeSuexyJHce0TLiFDryG6aWenlqp5SnP/w0n95HQh5aD0cEZv3E6CAngBde8= =hjty -----END PGP SIGNATURE-----