From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marc Kleine-Budde Subject: Re: [RESEND] [PATCH] net: CAN: at91_can.c: decrease likelyhood of RX overruns Date: Mon, 06 Oct 2014 14:52:33 +0200 Message-ID: <54329091.2040409@pengutronix.de> References: <1403775686-19352-1-git-send-email-david@protonic.nl> <5282990.80afdvE4aW@ws-stein> <20141006112644.672440b2@archvile> <2417882.RxeThGvgsF@ws-stein> <20141006133942.0f1c820b@archvile> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="jL0b0DDbPRjLQLSxd0qlndX0xraE8mndu" Return-path: Received: from metis.ext.pengutronix.de ([92.198.50.35]:59741 "EHLO metis.ext.pengutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752465AbaJFMwp (ORCPT ); Mon, 6 Oct 2014 08:52:45 -0400 In-Reply-To: <20141006133942.0f1c820b@archvile> Sender: linux-can-owner@vger.kernel.org List-ID: To: David Jander , Alexander Stein Cc: linux-can@vger.kernel.org, Wolfgang Grandegger , Oliver Hartkopp , "Hans J. Koch" This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --jL0b0DDbPRjLQLSxd0qlndX0xraE8mndu Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 10/06/2014 01:39 PM, David Jander wrote: [...] >>>> And the same with 500kBit/s: >>>> plain: 0, 0, lockup >>>> your patch: 0, 0, 0 >>>> rx-fifo: 0, 0, 0 >>> >>> This is weird. Either you were lucky, your embedded devices aren't ab= le to >>> send back-to-back at that rate specifically, or the situation regardi= ng >>> load and latency spikes changed somehow. The results don't make sense= to >>> me. >> >> Well, I guess this will change if I would run more than 3 times, but a= s >> overruns already occured at 250kBit/s there _is_ still a problem in rx= -fifo, >> independently from 1MBit/s drops due to heavy load. >=20 > Well, I now think that rx-fifo was never intended to improve the driver= > performance (correct me if I'm wrong, Marc), but only to build a common= > subsystem around the same concept that seems to be re-invented in at91_= can, > flexcan and ti_hecc. It does fix the lockup-bug in at91_can though. Exactly. It's supposed to abstract the make-a-fifo code from the hardware and move it into the CAN driver core. Marc --=20 Pengutronix e.K. | Marc Kleine-Budde | Industrial Linux Solutions | Phone: +49-231-2826-924 | Vertretung West/Dortmund | Fax: +49-5121-206917-5555 | Amtsgericht Hildesheim, HRA 2686 | http://www.pengutronix.de | --jL0b0DDbPRjLQLSxd0qlndX0xraE8mndu Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iEYEARECAAYFAlQykJEACgkQjTAFq1RaXHOk4gCeKe/ChsacwZCtgYwHYLh7DE+D gPgAnA6Q3H+7YBe/9e+HEAsPc2l/p+Cv =zvUe -----END PGP SIGNATURE----- --jL0b0DDbPRjLQLSxd0qlndX0xraE8mndu--