[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-net
Subject:    Re: A TCP monitoring /proc/net file
From:       Federico David Sacerdoti <fds () cs ! ucsd ! edu>
Date:       2001-08-20 18:06:06
[Download RAW message or body]

Paolo Castagna wrote:

>
> Ciao,
> dal tuo cognome suppongo che tu parli Italiano!? ;)

Si, un poco. My father is from Milano, but I have lived in the states my whole
life, and  my italian is not as good as it should be...

About the additions, you're right in that they would be usefull.

* sk->tp_pinfo.af_tcp.snd_cwnd

The sender congestion-control window size (in packets). Gives an indication of
how "freely" packets are going from sender to receiver; starts at 1 and
increaces for every sucessfully received ACK. Indicates how many packets can be
"in flight" (not acknowledged) on any connection. Closes by half whenever a
packet is lost. But its not much use at the receiver side since most of the
sending is happening at the server. It would however be useful on webservers,
and maybe that's value enough.

* sk->tp_pinfo.af_tcp.rcv_wnd

The current receiver window size. Indicates how much data the receiver has room
to receive. Does not change dynamically when congestion is detected, and
usually is quite large.

* sk->tp_pinfo.af_tcp.snd_ssthresh

The slow start threshhold. The maximum value of cwnd?

It would be easy to add these values into tcphealth. The only question is how
usefull they are to us. Let me know and I'll make the changes.

Dave

> Anyway... many thanks for your great job... but,
> why not include some usefull variables as cwnd, rwnd,
> ssthresh, and so on, in your tcphealh?

> Bye, bye!

-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[prev in list] [next in list] [prev in thread] [next in thread]