From mboxrd@z Thu Jan 1 00:00:00 1970 From: mkl@pengutronix.de (Marc Kleine-Budde) Date: Mon, 23 May 2011 10:23:15 +0200 Subject: [PATCH v4 1/1] can: add pruss CAN driver. In-Reply-To: <4DD9FCFC.10803@hartkopp.net> References: <1303474267-6344-1-git-send-email-subhasish@mistralsolutions.com> <4DCB88A4.2010901@grandegger.com> <4DCBF1B6.6000104@hartkopp.net> <201105221230.56243.arnd@arndb.de> <4DD9FCFC.10803@hartkopp.net> Message-ID: <4DDA1973.4090309@pengutronix.de> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 05/23/2011 08:21 AM, Oliver Hartkopp wrote: [...] > In 'real world' CAN setups you'll never see 21.000 CAN frames per second (and > therefore 21.000 irqs/s) - you are usually designing CAN network traffic with > less than 60% busload. So interrupt rates somewhere below 1000 irqs/s can be > assumed. > > From what i've seen so far a 3-4 messages rx FIFO and NAPI support just make it. > > @Marc/Wolfgang: Would this be also your recommendation for a CAN controller > design that supports SocketCAN in the best way? If you have a rx FIFO NAPI is the way to go. For a single mailbox it adds overhead, if you can read the CAN frame in the interrupt handler. The error messages should probably generated from NAPI, too. Especially the I'm-the-only-CAN-node-on-the-net-and-get-no-ACK error message. However IIRC David said that every new driver should implement NAPI. > As the Linux network stack supports hardware timestamps too, this could be an > additional (optional!) feature. regards, Marc -- 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 | -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 262 bytes Desc: OpenPGP digital signature URL: