[LARTC] Problems with HTB (ceil being overpassed)

[Gerardo Arceri]

>
> It seems you have hit timer innacuracy issues:
> http://www.docum.org/stef.coene/qos/faq/cache/40.html
>

Recompiled the kernel with the PSCHED_CPU modification and now
tc -s -d class show dev eth1 shows that the server is capped exactly at 
312Kpbs (2500Kbit).
BUT... read below quote..

>>  From my limited experience i would say that somehow my mrtg is 
>> measuring
>> traffic well before it passes thru htb (which seems imposible from what
>> i've read). i take the measurement on the
>> iptables FORWARD chain:
>>
>> iptables -N $server_ip-in
>> iptables -N $server_ip-out
>> iptables -A $server_ip-in -j RETURN
>> iptables -A $server_ip-out -j RETURN
>> iptables -A FORWARD -s $server_ip -j $server_ip-out
>> iptables -A FORWARD -d $server_ip -j $server_ip-in
>>
>> and to make the actual measurement:
>> iptables -nvxL $server_ip-in
>> iptables -nvxL $server_ip-out
>>


That mrtg measurement still shows 412 Kbps, how could it be. doesn't seem 
plausible that iptables reads the packets before the packet scheduler, 
since it works at a lower level closer to actual hardware.
What's the explanation for this ?
Thanks in advance.!


Using M2, Opera's revolutionary e-mail client: http://www.opera.com/m2/