Re: FACK

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

 



According the paper by Matthew Mathis and Jamshid Mahdavi, "Forward
Acknowledgement: Redefining TCP Congestion Control", it seems to me that
the two new state variables that are needed to implement FACK are snd.fack
and retran_data, where snd.fack is the highest sequence number known to
have been received and retran_data is the quantity of outstanding
retransmitted data in the network. Using the above variables the fast
retransmit/ recovery is changed as follows
while ((snd.nxt-snd.fack+retran_data) < cwnd)
	send_something();

and

if ((snd.fack - snd.una) > 3*MSS) || (dupacks == 3))
	do retransmit


I'm not able to get the relation between the above mentioned 2 variables
and tp->fackets_out and fack_count. I tried searching for other papers on
FACK but i couldnt find one. It would be great if you could explain me
how the FACK algorithm is implemented in the kernel ?

Thanks,
Rajkumar


On Thu, 17 Oct 2002, David S. Miller wrote:

>
> They are two pieces of state necessary to implement the
> FACK algorithms.  Read the papers on FACK, you'll understand
> what the variables keep track of after reading them.
>

-
: 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

[Index of Archives]     [Netdev]     [Ethernet Bridging]     [Linux 802.1Q VLAN]     [Linux Wireless]     [Kernel Newbies]     [Security]     [Linux for Hams]     [Netfilter]     [Git]     [Bugtraq]     [Yosemite News and Information]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux PCI]     [Linux Admin]     [Samba]

  Powered by Linux