Cell Relay Archive

Cell Relay Retreat>List Archive>month:1995-Apr> msg00413



[Date Prev][Date Next][Thread Prev][Thread Next]  
  [Date Index][Thread Index][Author Index][Subject Index]

Re: TCP window size

  • From: raj@cup.hp.com (Rick Jones)
  • Date: Wed, 26 Apr 1995 05:01:00 -0500, 26 Apr 1995 01:24:10 GMT

Fahad A Hoymany (fahad@cs.pitt.edu) wrote:
: Rick Jones (raj@cup.hp.com) wrote:
: : common TCP MSS (Ethenret's?) and it was relatively small. So basing
:   Ethernet's MTU is 1500 bytes which is relatively large.

I was speaking relative to FDDI (4096), ATM (~9KB), FibreChannel (up
to 64 KB). I will grant that "large" is a term open to interpretation.

:    I am not sure I undestand what you are trying to do here. The MSS
:    has nothing to do with the window size. It is used, though, for
:    the slow start window, but that's a different story.

This came-up after the mention of TCP_NODELAY and the question of it's
efficacy in improving performance. The window, the MSS, and the send
sizes all interoperate and can lead to a situation where sometimes one
is waiting for a standalone ACK - the Nagle algorithm for small packet
avoidance.

rick jones