Re: Fwd: [dccp] CCID2/RFC 2988 RTT computation

[Ian McDonald <iam4 at cs.waikato.ac.nz>]

> 
> 
> The concern in RFC 2988 is not with the system clock, but the clock 
> for dealing with TCP interrupts.  My memory is that current
> clock granularities for computing TCP RTT measurements are often 
> on the order of tens of ms, but I would be wrong.
> 
You are correct by default here. On the Linux DCCP implementation I have
changed as much as possible to use microseconds as I found that on low
latency networks (e.g. two PCs on the same switch) that the transmit
rate was being lowered artificially by being 10 ms as a minimum. Once I
did this it raised the rate usable by an order of magnitude.

Regards,

Ian