Eric Dumazet <[email protected]> wrote: >On Fri, 2012-10-12 at 13:04 -0500, Rob Herring wrote: >> From: Rob Herring <[email protected]> >> >> Only generate tx interrupts on every ring size / 4 descriptors. Move >the >> netif_stop_queue call to the end of the xmit function rather than >> checking at the beginning. >> >> Signed-off-by: Rob Herring <[email protected]> >> --- >> v2: >> - Add missed enabling of the descriptor tx interrupt > >Seems to be net-next material to me. >
Perhaps, but the series as a whole is what I've been testing. This one has the least performance impact. >Furthermore, your changelog is a bit terse for such a patch, that could >easily break upper layers. > >You need to tell us how long TX completion for a packet might be >deferred. The prior behavior was only interrupting when done with all buffers. It now will interrupt before completely emptying the ring. Rob -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
