From mboxrd@z Thu Jan 1 00:00:00 1970 From: Brendan Gregg Subject: Re: Weird instruction profiling Date: Fri, 20 Feb 2015 11:04:59 -0800 Message-ID: References: <87zj8bvzqn.fsf@tassilo.jf.intel.com> <54E5214B.5060408@gmail.com> <20150218233836.GB823@two.firstfloor.org> <54E52451.4030303@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Return-path: Received: from mail-ie0-f171.google.com ([209.85.223.171]:46796 "EHLO mail-ie0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755172AbbBTTFU (ORCPT ); Fri, 20 Feb 2015 14:05:20 -0500 Received: by iecvy18 with SMTP id vy18so10037917iec.13 for ; Fri, 20 Feb 2015 11:05:19 -0800 (PST) In-Reply-To: <54E52451.4030303@gmail.com> Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: David Ahern Cc: Andi Kleen , "linux-perf-use." On Wed, Feb 18, 2015 at 3:46 PM, David Ahern wrote: > On 2/18/15 4:38 PM, Andi Kleen wrote: >> >> On Wed, Feb 18, 2015 at 04:33:31PM -0700, David Ahern wrote: >>> >>> On 2/18/15 11:30 AM, Andi Kleen wrote: >>> >>>>> I think Andi mentioned this to me last year -- that instruction >>>>> profiling was no longer reliable. >>>> >>>> >>>> It never was. >>> >>> >>> Why is that? What about profiling with other hardware counters? >> >> >> Practically all profiling has skid of some form. > > > ok, so you meant that only in the context of skid meaning the hit > instruction is off a few (ie., squint backwards at the annotate output). > Thanks Andi and David, There's skid, but I was noticing what I thought was a different artifact in the profile: where only every 4th instruction is seen. Wouldn't this effect be more due to the IP pointing to the next instruction while a group of 4 are executed in parallel? Then there's skid on top of that.... Brendan