On 10/13/2010 11:46 AM, Wolfgang Grandegger wrote: >>> I'm following the discussion and realized that it will not work for >>> devices doing the local loopback in hardware, like the flexcan >>> controller. >> >> What is actually the advantage of using hardware loopback? One can >> always quit using it and use Tx interrupt for self reception ...
...from my other mail: I think we (the socketcan people) originally thought it's a better solution to loop the CAN frames back in hardware (if available), as it represents what's happening on the wire far better than software loopback. > Hey, we care about overhead ;-). CAN can cause high interrupt loads, > especially at 1 MB/s. On the flexcan, we use (currently) the hardware loopback. So a TX'ed CAN frame generates a TX-complete interrupt, which we need for the netif_wake_queue(). And it also generates a RX-interrupt due to the hardware loopback. If the replace hardware loopback by software loopback we can actually save the RX interrupt. cheers, 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 |
signature.asc
Description: OpenPGP digital signature
_______________________________________________ Socketcan-users mailing list [email protected] https://lists.berlios.de/mailman/listinfo/socketcan-users
