Messages in this thread | | | From | (Alan Cox) | Subject | Re: my broken TCP is faster on broken networks | Date | Mon, 14 Sep 1998 16:39:41 +0100 (BST) |
| |
> What about going from exponential to a linearly increasing > timeout? Ie. timeouts of 1, 2, 3, 4 etc... Since most > 'timeouts' will be because of dropped packets, and since
A linear timeout can cause a congestive collapse of the entire network. TCP is actually as aggressive as it is safe to be.
> a lot of links are a _lot_ of hops, this algorithm might > approach reality a lot better. The upper bound should probably > be at 4 or 8 times RTT.
And the RTT is an estimated variable, not always available and constantly behind the truth.
Alan
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/faq.html
| |