Re: TCP NewReno and single retransmit

[Marcelo Ricardo Leitner <mleitner@redhat.com>]

On 30-10-2014 00:03, Neal Cardwell wrote:
> On Mon, Oct 27, 2014 at 2:49 PM, Marcelo Ricardo Leitner
> <mleitner@redhat.com> wrote:
>> Hi,
>>
>> We have a report from a customer saying that on a very calm connection, like
>> having only a single data packet within some minutes, if this packet gets to
>> be re-transmitted, retrans_stamp is only cleared when the next acked packet
>> is received. But this may make we abort the connection too soon if this next
>> packet also gets lost, because the reference for the initial loss is still
>> for a big while ago..
> ...
>> @@ -2382,31 +2382,32 @@ static inline bool tcp_may_undo(const struct
>> tcp_sock *tp)
>>   static bool tcp_try_undo_recovery(struct sock *sk)
> ...
>>          if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
>>                  /* Hold old state until something *above* high_seq
>>                   * is ACKed. For Reno it is MUST to prevent false
>>                   * fast retransmits (RFC2582). SACK TCP is safe. */
>>                  tcp_moderate_cwnd(tp);
>> +               tp->retrans_stamp = 0;
>>                  return true;
>>          }
>>          tcp_set_ca_state(sk, TCP_CA_Open);
>>          return false;
>>   }
>>
>> We would still hold state, at least part of it.. WDYT?
>
> This approach sounds OK to me as long as we include a check of
> tcp_any_retrans_done(), as we do in the similar code paths (for
> motivation, see the comment above tcp_any_retrans_done()).

Yes, okay. I thought that this would be taken care of already by then but 
reading the code again now after your comment, I can see what you're saying. 
Thanks.

> So it sounds fine to me if you change that one new line to the following 2:
>
> +  if (!tcp_any_retrans_done(sk))
> +    tp->retrans_stamp = 0;

Will do.

> Nice catch!

A good part of it (including the diagram) was done by customer. :)
I'll post the patch as soon as we sync with them (credits).

Marcelo