From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Molnar Subject: Re: [PATCH 2/2] Markers Implementation for Preempt RCU Boost Tracing Date: Wed, 2 Jan 2008 18:01:57 +0100 Message-ID: <20080102170157.GA11161@elte.hu> References: <20071231060911.GB6461@in.ibm.com> <20071231102045.GB30380@elte.hu> <20080102124734.GC11208@elte.hu> <20080102163309.GC11496@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "K. Prasad" , linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org, dipankar@in.ibm.com, ego@in.ibm.com, mathieu.desnoyers@polymtl.ca, paulmck@linux.vnet.ibm.com, Andrew Morton , Linus Torvalds To: "Frank Ch. Eigler" Return-path: Received: from mx2.mail.elte.hu ([157.181.151.9]:60052 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754596AbYABRC3 (ORCPT ); Wed, 2 Jan 2008 12:02:29 -0500 Content-Disposition: inline In-Reply-To: <20080102163309.GC11496@redhat.com> Sender: linux-rt-users-owner@vger.kernel.org List-ID: * Frank Ch. Eigler wrote: > > [...] this is a general policy matter. It is _so much easier_ to add > > markers if they _can_ have near-zero overhead (as in 1-2 > > instructions). Otherwise we'll keep arguing about it, especially if > > any is added to performance-critical codepath. (where we are > > counting instructions) > > The effect of the immediate-values patch, combined with gcc > CFLAGS+=-freorder-blocks, *is* to keep the overhead at 1-2 > dcache-impact-free instructions. The register saves, parameter > evaluation, the function call, can all be moved out of line. well, -freorder-blocks seems to be default-enabled at -O2 on gcc 4.2, so we should already be getting that, right? There's one thing that would make out-of-line tracepoints have a lot less objectionable to me: right now the 'out of line' area is put to the end of functions. That splinters the kernel image with inactive, rarely taken areas of code - blowing up its icache footprint considerably. For example sched.o has ~100 functions, with the average function size being 200 bytes. At 64 bytes L1 cacheline size that's a 10-20% icache waste already. It's true that keeping the off-site code within the function keeps total codesize slightly smaller, because the offsets (and hence the conditional jumps) are thus 8 bit - but that's below 1% and the cache-blow-up aspect is more severe in practice at 10-20%. So it would be nice if we could collect all this offline code and stuff it away into another portion of the kernel image. (or, into another portion of the object file - which would still be good enough in practice) Ingo