home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.protocols.nfs:2334 comp.protocols.tcp-ip.ibmpc:5259 comp.dcom.lans.ethernet:1917
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!sdd.hp.com!swrinde!elroy.jpl.nasa.gov!ames!Mongo-Jr.Empirical.COM!karl
- From: karl@empirical.com (Karl Auerbach)
- Newsgroups: comp.protocols.nfs,comp.protocols.tcp-ip.ibmpc,comp.dcom.lans.ethernet
- Subject: Re: Sun <=> PC Transfer Rate (Summary)
- Message-ID: <karl.25.716588913@empirical.com>
- Date: 15 Sep 92 20:28:33 GMT
- References: <1992Sep4.173931.24033@pixel.kodak.com> <karl.23.716089551@empirical.com> <1992Sep15.065528.3162@medtron.medtronic.com>
- Sender: usenet@news.arc.nasa.gov
- Organization: Empirical Tools and Technologies
- Lines: 25
-
- >In article <karl.23.716089551@empirical.com> karl@empirical.com (Karl
- Auerbach) writes:>>>Two SPARCstation 2's are apparently capable of data
- rates of 800 to 1000>>>kilobytes per second memory-to-memory transfer on a
- dedicated Ethernet.>>
- >>Sun's can do *much* better than that.
- >
- >No they cannot. 1000 kByte/s = 8 Mbit/s, which already comes close to the
- >10 Mbit/s of the Ethernet...
-
- Ahhh...you must be using the old low voltage Ethenet option. The new 1500
- volt, 3 amp transceivers really speed things up.
-
- Joking aside...
-
- I had read kilobytes as kilo *bits*. And 1000 k *bits* is slow but
- 1000 k *bytes* certainly isn't.
-
- An interesting twist I've seen to all of this is the use of LZV compression
- of a file as it passes through FTP. This can substantially improve the
- apparent throughput. The technique is perhaps somewhat less effective for
- independent-block mode transfers (such as NFS) as opposed to full file
- transfers (FTP.) I'm also not sure of the legal situation regarding LZV
- patents.
-
- --karl--
-