[Click] 1.6.0 release
Eddie Kohler
kohler at cs.ucla.edu
Tue Aug 28 14:39:35 EDT 2007
Hi Roman,
Many apologies for the delay, but I have finally looked at your ToDevice
patch for reducing packet drops.
On the one hand, this patch seems like a good idea. I agree with you
that ToDevice should not drop packets itself, that they should be
dropped upstream.
On the other hand, though, ToDevice is written expecting that the
network device _dev will SAY when it's going to reject a packet, by
stopping its input queue. I think this is the expected behavior from a
Linux device. I think we generally tried to engineer our devices and
configs so that ToDevice never rejected a packet.
Which device are you using that's rejecting packets even though its
queue is open? Or, alternatively, is it common for devices to reject
packets w/o stopping their queues first? If the problem is with the
device, it would seem better to fix that.
Eddie
rchertov at purdue.edu wrote:
> Hello Eddie,
> I would appreciate if you would take a look at my ToDevice email, regarding
> the packet dropping issue when sending the packets. (Sorry I can't forward it
> as I am in Russia with very limited access to my emails)
>
> Roman
>
> Quoting Eddie Kohler <kohler at cs.ucla.edu>:
>
>> Hi all,
>>
>> I am preparing for a 1.6.0 "stable" Click release. The anonymous CVS
>> has been updated with a NEWS file describing my take on the changes
>> since 1.5.0. In the coming days I will attempt to go through enqueued
>> Click mailing list mail and fix what I can. Please, if you really want
>> something fixed, or you have any complaints, now is the time to send them.
>>
>> A linked list template (one of the things I wanted to include) will not
>> make it into this release. Sorry Jason.
>>
>> Eddie
>> _______________________________________________
>> click mailing list
>> click at amsterdam.lcs.mit.edu
>> https://amsterdam.lcs.mit.edu/mailman/listinfo/click
>>
>
>
More information about the click
mailing list