From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnaldo Carvalho de Melo Subject: Re: [RFC] perf top and deleted binaries Date: Mon, 9 May 2011 17:58:49 -0300 Message-ID: <20110509205849.GA26156@ghostprotocols.net> References: <20110509182822.GA23798@dev1756.snc6.facebook.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from bombadil.infradead.org ([18.85.46.34]:59024 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753247Ab1EIU6y (ORCPT ); Mon, 9 May 2011 16:58:54 -0400 Content-Disposition: inline In-Reply-To: <20110509182822.GA23798@dev1756.snc6.facebook.com> Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: Arun Sharma Cc: linux-perf-users@vger.kernel.org Em Mon, May 09, 2011 at 11:28:23AM -0700, Arun Sharma escreveu: > > For long running binaries which may have been replaced or deleted, today > perf top spits out a warning and doesn't show anything. For eg: > > test.c: > > main() > { > while(1); > } > > gcc -O2 test.c -o test > ./test & > gcc -O2 test.c -o test # overwrite the binary > perf top -p > > shows nothing. It could instead show: > > 100% test > > like perf record/report would show for the same test case. Comments? Agreed :-) When/if we get build-id as first class citizen, stashing it in some kernel data structure at DSO load time, we'll be able to use it for content based DSO lookup in the cache. - Arnaldo