Re: [PATCH v2] net: calxedaxgmac: rework transmit ring handling

[Rob Herring]

Eric Dumazet <eric.dumazet@xxxxxxxxx> wrote:

>On Fri, 2012-10-12 at 13:04 -0500, Rob Herring wrote:
>> From: Rob Herring <rob.herring@xxxxxxxxxxx>
>> 
>> 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 <rob.herring@xxxxxxxxxxx>
>> ---
>> 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 majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/