HP3000-L Archives

December 2003, Week 5

HP3000-L@RAVEN.UTC.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Gavin Scott <[log in to unmask]>
Reply To:
Gavin Scott <[log in to unmask]>
Date:
Mon, 29 Dec 2003 10:11:31 -0800
Content-Type:
text/plain
Parts/Attachments:
text/plain (26 lines)
I just did a quick test across a T1-speed WAN, and found that FTP transfers
were about twice as fast as :DSCOPY.

Once again, it's my impression that :DSCOPY waits for an acknowledgement
after each block of data is sent, making it dependent on the latency of the
connection rather than the bandwidth (exactly what you don't want in a file
transfer process) whereas FTP simply streams the data out and relies on TCP
to do flow control and ensure that the data gets there reliably, and TCP is
very good at being independent of the latency of the connection thus
achieving full bandwidth utilization.

On a local LAN the difference might be less, but a quick local test *also*
showed FTP to be twice as fast as :DSCOPY.

The files used in the tests were :STORE-to-disk archives which are ordinary
MPE 128W BINARY files and one of the most likely file types that one would
be transferring between systems.

The tests were cone with moderately recent FTP versions (a year or two old)
and pairs of MPE/iX 6.0 and 6.5 systems.

G.

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

ATOM RSS1 RSS2