From mboxrd@z Thu Jan 1 00:00:00 1970 From: Loic Dachary Subject: jerasure/gf-complete segmentation violation Date: Wed, 02 Apr 2014 19:35:35 +0200 Message-ID: <533C4A67.3070906@dachary.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="uwcT5lqwRge2wutBiwDd4nOgWBpfslacf" Return-path: Received: from smtp.dmail.dachary.org ([91.121.254.229]:34285 "EHLO smtp.dmail.dachary.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932527AbaDBRfo (ORCPT ); Wed, 2 Apr 2014 13:35:44 -0400 Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Kevin Greenan Cc: Ceph Development This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --uwcT5lqwRge2wutBiwDd4nOgWBpfslacf Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Hi Kevin, In the context of http://tracker.ceph.com/issues/7914 we're trying to fig= ure out why jerasure dumps core. We don't know how to reproduce it yet (r= an dozens of identical tests suites with no such crash in the past few da= ys, which is to be expected for rare bugs because the test suite introduc= es random errors / failures on purpose).=20 The full stack trace is at http://tracker.ceph.com/issues/7914#note-24 bu= t the relevant part is here: #0 0x00007f4756779b7b in raise (sig=3D) at ../nptl/sysdep= s/unix/sysv/linux/pt-raise.c:42 #1 0x0000000000981b4e in reraise_fatal (signum=3D11) at global/signal_ha= ndler.cc:59 #2 handle_fatal_signal (signum=3D11) at global/signal_handler.cc:105 #3 #4 0x0000000000000000 in ?? () #5 0x00007f47385ae6b1 in jerasure_matrix_dotprod (k=3D2, w=3D8, matrix_r= ow=3D0x31513a8, src_ids=3D0x0, dest_id=3D, data_ptrs=3D0x7= f4741ec7a00, coding_ptrs=3D0x7f4741ec7a10,=20 size=3D2048) at erasure-code/jerasure/jerasure/src/jerasure.c:607 #6 0x00007f47385ae7d6 in jerasure_matrix_encode (k=3D2, m=3D1, w=3D8, ma= trix=3D, data_ptrs=3D0x7f4741ec7a00, coding_ptrs=3D0x7f474= 1ec7a10, size=3D2048) at erasure-code/jerasure/jerasure/src/jerasure.c:310 =2E.. Note that this jerasure/gf-complete combination has been compiled with SS= E4.1, SSE4.2, PCLMUL, SSSE3, SSE3, SSE2, SSE flags activated. These are j= erasure v2 and gf-complete v1, only slightly modified as found in https:/= /github.com/ceph/jerasure/tree/v2-ceph and https://github.com/ceph/gf-com= plete/tree/v1-ceph (all commits there have a pending pull request under h= ttps://bitbucket.org/jimplank/gf-complete https://bitbucket.org/jimplank/= jerasure, nothing you've not seen before).=20 #5 is https://github.com/ceph/jerasure/blob/v2-ceph/src/jerasure.c#L607 and then it dives into gf-complete and most probably destroyed part of th= e stack when corrupting memory. I'll be chasing this tomorrow. If you hav= e a brilliant idea on why that happens, I'll take it ;-)=20 Cheers --=20 Lo=EFc Dachary, Artisan Logiciel Libre --uwcT5lqwRge2wutBiwDd4nOgWBpfslacf Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.20 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iEYEARECAAYFAlM8SmsACgkQ8dLMyEl6F23+2wCgs4Bt0TmIITCnqmu/uRjhzZL3 D6IAn2UIY/dd6XXlMNxF2WSqsO5Ok6gp =5L4Y -----END PGP SIGNATURE----- --uwcT5lqwRge2wutBiwDd4nOgWBpfslacf--