Re: Clock Tolerance and WAN PHY
I will donate some Cisco switches for the Earth to Moon Ethernet
One thing that we can predict, customers will deploy 10 GbE in
applications that the 10 GbE call for interest and study group did not
even dream about.
At 10:07 AM 1/30/01 -0600, Roy Bynum wrote:
I don't know which window to the world that you have been looking out of,
but you have had the blinds closed. The world has changed.
FC is now used for extended distance large frame data
storage applications and aggregated ESCON in several metropolitan US and
European markets. There is a service provider based out of Boston
that specializes in this market. SAN is not the only application
Ethernet is being used for extended distance (sometime very long
distances) "LAN extension" all over the world. There is
one service provider in Europe that is trying to build a national data
network with GbE over DWDM. LAN is not the only application for
As I have explained once before, there is not an application distance
limiting acknowledgement timer for 802.3 MAC frames, giving it almost
unlimited application distances. If I had a laser with enough
power, I could even bounce an "extended LAN" signal off of the
moon (NASA has a laser marker reflector on the moon). The only
distance issue is the speed of light latency within the upper layers of
The WAN market applications for 802.3 Ethernet are going to expand well
beyond the LAN market at higher, optical level, bandwidths.
The LAN market for Ethernet will continue to be dominated by the data
transfer limit of computers and servers. Granted the speed that
computers and servers will be increasing in performance, particularly in
the expensive high end systems. For the next several years, the
major market dominance for high bandwidth Ethernet will be the WAN.
The next generation of optical networking being developed, Automatic
Switched Optical Networking, will make extensive use of the 1300nm serial
I hope that you will have as much fun with all of the things that are
going on in this new space as I have been,
At 04:38 AM 1/30/01 -0800, Rich Taborek wrote:
Fibre Channel, contrary to what the minority may say, is a SAN
technology. The "S" stands for Storage. FC usage for LAN, MAN
applications is minimal at best. SAN technology applications
focus on high performance storage access. Prior to Fibre Channel,
applications were served by IBM's ESCON and equivalent proprietary
technologies on the high end and SCSI on the low end (of servers).
Ethernet, contrary to what the minority may say, is a LAN
The "L" stands for Local. Ethernet usage for SAN, MAN and
applications is minimal at best. Ethernet has essentially no
in the LAN and is slowly expanding into the MAN and WAN. I agree
Pat's statements with respect to Ethernet's relative performance to
Fibre Channel in support of SAN applications, it is currently
What's left out in the cold is SONET, ATM, the WAN PHY, etc. These
protocols will likely NEVER be supported by servers to any
extent. Therefore, protocol conversion must occur in order to
LAN and SAN information over the existing MAN and WAN
The way things are going to change seems pretty obvious to me.
What role does the 10GE LAN PHY play you ask? A HUGE ONE!!!
Roy Bynum wrote:
> From what you are telling me, only if 10GbE replaces FC will
there be a
> major computer/server market for the 10GbE LAN PHY?
> I personally would like to see a single ubiquitous data link
> all data services. Before that happens however, FC will need
> the way that Token Ring was. Because P802.3ae has supported
> development of the next generation of FC through XAUI, that will not
> anytime soon. The development of XAUI and the four lambda PHY
> be used by FC, the market for the 10GbE LAN PHY was greatly
> Since high bandwidth FC continues to be a major player in the
> computer/server market, what role does 10GbE LAN PHY play?
> Thank you,
> Roy Bynum
> At 02:03 PM 1/29/01 -0700, pat_thaler@xxxxxxxxxxx wrote:
> >It would make our jobs easier (though less profitable) if we
could plan for
> >next year's network development based on what computer systems
> >Technology continues to evolve and there are some developments
> >that will impact system bandwidth needs.
> >Today most large systems access their storage through Fibre
> >and access the rest of the world through Ethernet links. The
> >leave all or most of the TCP/IP handling to software which has
> >every packet. Therefore, pushing a Gigabit data rate takes a lot
> >cycles. The Fibre Channel links do a lot of the packet
> >hardware. In an unerrored transfer case, the software above a
> >card gets messages built from many packets. They get up to
Gigabit data rate
> >with much less system load.
> >People are developing iSCSI and iFCP protocols to support
> >over Ethernet. In conjunction with that, there is also
> >hardware that will provide hardware functionality for these
> >similar to that achieved by Fibre Channel. An Ethernet adapter
may then be
> >used to support Ethernet traffic plus storage traffic with
> >efficiency about that of FC.
> >This development can increase the data rate needs/capability of
> >to the point where they need 10 Gbit.
> >-----Original Message-----
> >From: Roy Bynum
> >Sent: Monday, January 29, 2001 5:06 AM
> >To: rtaborek@xxxxxxxxxxxxx; HSSG
> >I am not sure if anyone has done in technical or economic study
of how many
> >servers within the next two years will be able push close
to 10Gb of data
> >into a LAN PHY. From what I have been told, computer
systems today can not
> >even push enough to fill a GbE link, much less a 10GbE
link. Without a
> >computer/server market, the 10GbE LAN PHY will be relegated to
> >aggregation within privately owned campus fiber plant or a large
> >room. The 10GbE WAN PHY, is easily used extended LANs over
> >MANs over privately owned or leased fiber and wavelengths; WANs
> >wave lengths or leased fiber.
> >Given the amount of GbE that is being used by "legacy-free
carriers" in the
> >U.S.A. and Europe, and the expansion of the Internet, the need
> >"service provider" type of Ethernet is becoming a
> >issue. Combined with the other uses of the 10GE WAN PHY, I
believe that a
> >very high percentage (75%?) of 10GbE will be implemented using
> >PHY. The WAN PHY will be used because it has the
> >functionality required. If P802.3ae does not go ahead and
> >operational management functionality that is being recommended,
all of the
> >vendors will be implementing "proprietary" versions
that will have it. If
> >P802.3ae does not do it, then the need to do it in
> >implementations will give 802.3 a "major black
> >I tend to agree with Gary Nicholl in the need for a + 20
> >clock. Perhaps someone could give a relative cost to
implement a + 20 PPM
> >clock instead of a + 100 PPM clock.
> >Thank you,
> >Roy Bynum
> > <Previous emails in the string
2500-5 Augustine Dr.
Santa Clara, CA