From mboxrd@z Thu Jan 1 00:00:00 1970 From: Clark Williams Subject: Re: [PATCH v2] rt-tests: Add option to force timeout to pmqtest Date: Thu, 1 Apr 2010 12:41:40 -0500 Message-ID: <20100401124140.49f4cfa1@torg> References: <4BB0C273.2040606@osadl.org> <4BB209ED.80602@osadl.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/8c=1TweY0d+0l.B1gxKNtR/"; protocol="application/pgp-signature" Cc: Thomas Gleixner , RT-Users To: Carsten Emde Return-path: Received: from mx1.redhat.com ([209.132.183.28]:53884 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754234Ab0DARlz (ORCPT ); Thu, 1 Apr 2010 13:41:55 -0400 In-Reply-To: <4BB209ED.80602@osadl.org> Sender: linux-rt-users-owner@vger.kernel.org List-ID: --Sig_/8c=1TweY0d+0l.B1gxKNtR/ Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable On Tue, 30 Mar 2010 16:25:49 +0200 Carsten Emde wrote: > On 03/29/2010 05:08 PM, Carsten Emde wrote: > > This patch adds the program pmqtest to the rt-tests suite. > > The test mechanism is the same as in ptsematest, svsematest > > and friends, but it uses message queues to synchronize the > > test threads. To test the - now hopefully fixed - kernel > > problem that occurred when a timeout was specified, the > > -T option is available. > This patch adds the option -f to force a timeout condition of > mq_timedreceive() to pmqtest - only meaningful along with -T. >=20 > The call > # pmqtest -Sp99 -i100 -d0 -T1 -f2 >=20 > will display >=20 > #0: ID17791, P99, CPU0, I100; #1: ID17792, P99, CPU0, Cycles 8 > #2: ID17793, P99, CPU1, I100; #3: ID17794, P99, CPU1, Cycles 8 > #4: ID17795, P99, CPU2, I100; #5: ID17796, P99, CPU2, Cycles 8 > #6: ID17797, P99, CPU3, I100; #7: ID17798, P99, CPU3, Cycles 8 > #8: ID17799, P99, CPU4, I100; #9: ID17800, P99, CPU4, Cycles 8 > #10: ID17801, P99, CPU5, I100; #11: ID17802, P99, CPU5, Cycles 8 > #12: ID17803, P99, CPU6, I100; #13: ID17804, P99, CPU6, Cycles 8 > #14: ID17805, P99, CPU7, I100; #15: ID17806, P99, CPU7, Cycles 8 > #1 -> #0, Min 16, Cur 22, Avg 18, Max 24 > #3 -> #2, Min 13, Cur 14, Avg 14, Max 16 > #5 -> #4, Min 14, Cur 20, Avg 16, Max 20 > #7 -> #6, Min 13, Cur 14, Avg 14, Max 15 > #9 -> #8, Min 14, Cur 14, Avg 15, Max 19 > #11 -> #10, Min 13, Cur 13, Avg 16, Max 20 > #13 -> #12, Min 13, Cur 14, Avg 15, Max 19 > #15 -> #14, Min 13, Cur 14, Avg 15, Max 19 > etc. >=20 > but the next cycle will only continue when the timeout of 2 seconds is > elapsed. >=20 > Signed-off-by: Carsten Emde Carsten,=20 Not ignoring you, just took a while for your task to get scheduled (I'm an old uni-processor :)).=20 I'll pull these in and spin a new rt-tests tonight. Clark --Sig_/8c=1TweY0d+0l.B1gxKNtR/ Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.13 (GNU/Linux) iEYEARECAAYFAku02tcACgkQHyuj/+TTEp2hKQCeIu3qB3xx++pG5VVA0tNzjHHX VjgAoKZRZo59cSCRGNTfKzCh/qJ3MEeF =KxSR -----END PGP SIGNATURE----- --Sig_/8c=1TweY0d+0l.B1gxKNtR/--