From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751564AbcFYQaU (ORCPT ); Sat, 25 Jun 2016 12:30:20 -0400 Received: from mx1.HRZ.tu-dortmund.de ([129.217.128.51]:32818 "EHLO unimail.uni-dortmund.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750872AbcFYQaT (ORCPT ); Sat, 25 Jun 2016 12:30:19 -0400 X-Greylist: delayed 2600 seconds by postgrey-1.27 at vger.kernel.org; Sat, 25 Jun 2016 12:30:18 EDT From: Alexander Lochmann Subject: [RFC] perf record: missing buildid for callstack modules -- again To: linux-kernel@vger.kernel.org Message-ID: <576EA76F.8040509@tu-dortmund.de> Date: Sat, 25 Jun 2016 17:46:55 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.8.0 MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="43sTn8clmDeexrGnVdSi8SVM94SBLxElN" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --43sTn8clmDeexrGnVdSi8SVM94SBLxElN Content-Type: multipart/mixed; boundary="ThEo8dMKNWl55LeMDDCj4tWmwI7LPBoR3" From: Alexander Lochmann To: linux-kernel@vger.kernel.org Message-ID: <576EA76F.8040509@tu-dortmund.de> Subject: [RFC] perf record: missing buildid for callstack modules -- again --ThEo8dMKNWl55LeMDDCj4tWmwI7LPBoR3 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Hi folks! As mentioned by this discussion https://lkml.org/lkml/2016/1/7/661, perf does not record the build id for modules, which are hit on the way down the callstack. Sadly that issue is not completely fixed by the cmd argument --buildid-al= l. In my case, I have my own kernel module starting a kernel thread. It does some stuff, and calls schedule from time to time. If I start perf like this perf record -e sched:sched_stat_sleep -e sched:sched_switch -a -g -o perf.data.raw -p -- sleep 10 , it records the callstacks for those three events. Afterwards I want to do some post processing to generate a cold graph: perf inject -v -s -i perf.data.raw -o perf.data That step fails ('failed to write feature 2') due to the lack of a build-id for my module, which isn't included in perf.data.raw. Can anyone confirm that this is a bug? Does anyone have a workaround for it? Thanks in advance! Cheers, Alex P.S.: Pls put me in CC, because I'm not subscribed to the mailinglist. --=20 Technische Universit=C3=A4t Dortmund Alexander Lochmann PGP key: 0xBC3EF6FD Otto-Hahn-Str. 16 phone: +49.231.7556141 D-44227 Dortmund fax: +49.231.7556116 http://ess.cs.tu-dortmund.de/Staff/al --ThEo8dMKNWl55LeMDDCj4tWmwI7LPBoR3-- --43sTn8clmDeexrGnVdSi8SVM94SBLxElN Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAEBCAAGBQJXbqdwAAoJEFk+7QW8Pvb9jckP/2+vX1qOjYqfpc7QQ0atCW8m XY+iK+y7pDs+5jrv7zaZmisf9VLLCaSNrmLvDjTt87LVIeQYg6nxEUMQXbkUkkB9 lBJbw5S1uMGmLn30E1mwYvQZ6W6UiCfj1u2xWTdEKdjh4rDfinyieFU6YWs2ou/l WS8K27uoJJ+tweJqfrc8sunlxu/KrZ8cEEygEOJzyswhRQntT6Ig6h1x2iO0z3O3 rVIY5Kqyst+G8ndocwQ8I7em2lCaA94crp1XyaEa5vSnB2IuQJdHsAtqe4Pw0Rfn MfRuhbkGo4yZqdwdOglf6eLpHJPHRYgKA9CuSx8YpfBcNHfyPo4XoJXqSNcedudn GCsX4gfyx+jlA6TJJTZk0TVHvRxI4gdf3JdOaqDZStaNjW0qzCGxALkp4POla1aH o9S711uPRNmV/Tn6g7T9uA0cenCLqp6ocEI+UXQ/sD5omY1X5+YdcKi8AfM67mtj TUxgSGCVVVSpJ8VAt9/GlGdTfdXZO3C3Vv1BIroz3z2y9/2AN9XMWYKA32lIT5WC jsNEEQFs1zh/raIYQxusasN+bRTFiS3+vCYTEy04iHY0OItwOcbZoepYXqTXifaR 0d5tvHwLfTlTKNy6JZWIDkqHadyoSZUzpCerluLCF7+gMcL9JgeZENOMqBlAwLKE uOqY7QIW0//vRO/GnhbF =fCTY -----END PGP SIGNATURE----- --43sTn8clmDeexrGnVdSi8SVM94SBLxElN--