[c-nsp] TCP behavior under strict CAR rate-limiting

[Christopher Hunt]

Antonio,
  Thanks for the reply.  I understand that those values are not 
recommended and in fact i do not use them outside of the lab.  I am, 
however, struggling to understand how TCP reacts to very very low burst 
levels.  What mechanism is causing such low throughput as the 
tcp_receive_window values are not low?

Christopher Hunt




Antonio Querubin wrote:
> On Thu, 19 Jun 2008, Christopher Hunt wrote:
>
>> Sorry,
>> The rate-limit statement that results in 0.2mbps throughput is:
>> rate-limit input 10000000 5000 5000 conform-action transmit 
>> exceed-action drop
>
> Those burst values appear to be far below the recommended values for 
> most cases.  See the following:
>
> http://www.cisco.com/en/US/docs/ios/12_2/qos/command/reference/qrfcmd8.html 
>
>
> In your case, if your target rate-limit is 10000000, then 1875000 and 
> 3750000 are what you probably should be using for the burst.
>
>
> Antonio Querubin
> whois:  AQ7-ARIN