Re: Sequence Number Validation Bug Fixes 0/2

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



> | 
> | What I'm noticing is that the DCCP sender doesn't update it's ack
> | numbers very often. In examining packet captures, it is typical for DCCP
> | to send 20-60 packets with the same ack number (If I increase the ack
> | and seq validity windows to 1000, I've seen 200 packets with the same
> | ack number).
> | 
> Depending on the type of link (duplex or half-duplex as in WiFi) and the 
> application sending rate, this might even be normal.

Good point. I hadn't thought of checking whether the network was running
duplex or half-duplex. It turns out that it was running half-duplex
because I had a dumb hub in the testbed setup. 

Once I adjusted the testbed setup to remove the hub, I was able to run
full duplex and DCCP started to work much better. I'm now seeing an
increase in the ack number with almost every packet(which is what I
would expect to see). 

Right now, I'm seeing speeds of 9.43Mbits/sec over a 10Mbit/sec link and
85Mbit/sec over a 100Mbit/sec link (TCP does 91Mbit/sec). Those speeds
seem very reasonable and are much better than anything I have seen yet
in working with DCCP. Is that about what I should expect to get out of
DCCP? Or is it typical to get better performance than that?

Samuel Jero
Internetworking Research Group
Ohio University

Attachment: signature.asc
Description: This is a digitally signed message part


[Index of Archives]     [Linux Kernel]     [IETF DCCP]     [Linux Networking]     [Git]     [Security]     [Linux Assembly]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux