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! - : 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
