From: Len Brown Subject: Re: cpuidle asymmetry (was Re: [RFC PATCH V4 5/5] cpuidle: cpuidle driver for apm) Date: Fri, 01 Apr 2011 00:09:25 -0400 (EDT) Message-ID: References: <20110322123208.28725.30945.stgit@tringupt.in.ibm.com> <20110322123336.28725.29810.stgit@tringupt.in.ibm.com> <20110323121458.ec7cdaf9.sfr@canb.auug.org.au> <4D89CA7D.8080108@linux.vnet.ibm.com> <4D8B550D.5000409@linux.vnet.ibm.com> <20110325180156.GC19214@dirshya.in.ibm.com> <1301577536.4859.249.camel@twins> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Return-path: In-reply-to: <1301577536.4859.249.camel@twins> Sender: linux-kernel-owner@vger.kernel.org To: Peter Zijlstra Cc: Vaidyanathan Srinivasan , Trinabh Gupta , arjan@linux.intel.com, Stephen Rothwell , suresh.b.siddha@intel.com, benh@kernel.crashing.org, venki@google.com, ak@linux.intel.com, linux-kernel@vger.kernel.org, xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org > > Moorestown is already an example of an asymmetric system, > > since its deepest c-state is available on cpu0, but not on cpu1. > > So it needs different tables for each cpu. > > wtf are these hardware guys smoking and how the heck are we supposed to > schedule on such a machine? Prefer to keep cpu1 busy while idling cpu0? they are smoking micro-amps:-) S0i3 on cpu0 can be entered only after cpu1 is already off-line, among other system hardware dependencies... So it makes no sense to export S0i3 as a c-state on cpu1. When cpu1 is online, the scheduler treats it as a normal SMP. cheers, -Len Brown, Intel Open Source Technology Center