Date: Fri, 21 May 1999 12:05:02 -0400 From: Josip Loncaric <[EMAIL PROTECTED]> Linux TCP estimates of RTO are kept 200ms or longer, although for us 20ms is more Note, we clamp the RTO's so that we don't run into problems with BSD stacks. If you allow them to be smaller than the smallest timeout length in TCP timers under BSD you get real funnies without some clever hacks. I'm not saying this is whats happening here. BTW, if all of your analysis is second hand, can the person who does "know" that we are broken elaborate his analysis here so I can fix the problem? I believe we are doing delayed ACK and cwnd advancement correctly. Later, David S. Miller [EMAIL PROTECTED] - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] Please read the FAQ at http://www.tux.org/lkml/
- [patch] TCP/IP delacks disabled with MPI Andrea Arcangeli
- Re: [patch] TCP/IP delacks disabled with MPI Josip Loncaric
- Re: [patch] TCP/IP delacks disabled with MPI Andrea Arcangeli
- Re: [patch] TCP/IP delacks disabled with MPI Josip Loncaric
- Re: [patch] TCP/IP delacks disabled with... Andrea Arcangeli
- Re: [patch] TCP/IP delacks disabled... David S. Miller
- Re: [patch] TCP/IP delacks disa... Andrea Arcangeli
- Re: [patch] TCP/IP delacks disa... Josip Loncaric
- Re: [patch] TCP/IP delacks ... David S. Miller
- Re: [patch] TCP/IP delacks disabled... Josip Loncaric
- Re: [patch] TCP/IP delacks disabled with... David S. Miller
- Re: [patch] TCP/IP delacks disabled... Josip Loncaric
- Re: [patch] TCP/IP delacks disabled with MPI Andrea Arcangeli
- Re: [patch] TCP/IP delacks disabled with... Andi Kleen
- Re: [patch] TCP/IP delacks disabled... Andrea Arcangeli
- Re: [patch] TCP/IP delacks disa... Andi Kleen
- Re: [patch] TCP/IP delacks ... Andrea Arcangeli
- Re: [patch] TCP/IP delacks ... Andi Kleen
