From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnd Bergmann Subject: Re: [RFC PATCHv2 1/2] Export SoC info through sysfs Date: Fri, 8 Apr 2011 05:35:02 +0200 Message-ID: <201104080535.02769.arnd@arndb.de> References: <1299846911-15782-1-git-send-email-maxime.coquelin-nonst@stericsson.com> <201104080119.11378.arnd@arndb.de> <20110407232959.GA29305@kroah.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20110407232959.GA29305@kroah.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: linux-arm-kernel-bounces@lists.infradead.org Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org To: Greg KH Cc: Nicolas Pitre , ext Nishanth Menon , ext Tony Lindgren , Peter De-Schrijver , Linus Walleij , Ambresh , Saravana Kannan , Andrei Warkentin , Lee Jones , Rabin VINCENT , Russell King , Jonas ABERG , ext Kevin Hilman , David Brown , Maxime Coquelin , "linux-arm-msm@vger.kernel.org" , Loic PALLARDY , Eduardo Valentin , maxime_coquelin@yahoo.fr, Ryan Mallon , Linux-OMAP List-Id: linux-arm-msm@vger.kernel.org On Friday 08 April 2011, Greg KH wrote: > Symlinks are a requirement as multiple cpus can be attached to a single > SoC. > > What about multiple cpus that are attached to multiple SoCs? Why even > try to describe this relationship, what would userspace get out of this > information? The only one I can think of is node affinity. I've worked with a system (IBM QS2x Cell blade) that had two SoCs with multiple CPUs each. There was a significant performance penalty when talking to devices on the remote SoC. In that case, we used the NUMA node information in /sys/ to deal with it, but we might not want to use the NUMA infrastructure on systems that only have RAM on one node. Arnd From mboxrd@z Thu Jan 1 00:00:00 1970 From: arnd@arndb.de (Arnd Bergmann) Date: Fri, 8 Apr 2011 05:35:02 +0200 Subject: [RFC PATCHv2 1/2] Export SoC info through sysfs In-Reply-To: <20110407232959.GA29305@kroah.com> References: <1299846911-15782-1-git-send-email-maxime.coquelin-nonst@stericsson.com> <201104080119.11378.arnd@arndb.de> <20110407232959.GA29305@kroah.com> Message-ID: <201104080535.02769.arnd@arndb.de> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Friday 08 April 2011, Greg KH wrote: > Symlinks are a requirement as multiple cpus can be attached to a single > SoC. > > What about multiple cpus that are attached to multiple SoCs? Why even > try to describe this relationship, what would userspace get out of this > information? The only one I can think of is node affinity. I've worked with a system (IBM QS2x Cell blade) that had two SoCs with multiple CPUs each. There was a significant performance penalty when talking to devices on the remote SoC. In that case, we used the NUMA node information in /sys/ to deal with it, but we might not want to use the NUMA infrastructure on systems that only have RAM on one node. Arnd