Re: Clock Tolerance and WAN PHY
Rich,
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
for FC.
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
Ethernet.
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 application.
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
PHY.
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,
Roy Bynum
At 04:38 AM 1/30/01 -0800, Rich Taborek wrote:
Roy,
Fibre Channel, contrary to what the minority may say, is a SAN
technology. The "S" stands for Storage. FC usage for LAN, MAN
and WAN
applications is minimal at best. SAN technology applications
generally
focus on high performance storage access. Prior to Fibre Channel,
these
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
technology.
The "L" stands for Local. Ethernet usage for SAN, MAN and
WAN
applications is minimal at best. Ethernet has essentially no
challenge
in the LAN and is slowly expanding into the MAN and WAN. I agree
with
Pat's statements with respect to Ethernet's relative performance to
Fibre Channel in support of SAN applications, it is currently
inferior.
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
appreciable
extent. Therefore, protocol conversion must occur in order to
transport
LAN and SAN information over the existing MAN and WAN
infrastructure.
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!!!
Best Regards,
Rich
--
Roy Bynum wrote:
>
> Pat,
>
> 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
protocol for
> all data services. Before that happens however, FC will need
to obsoleted
> the way that Token Ring was. Because P802.3ae has supported
the
> development of the next generation of FC through XAUI, that will not
happen
> anytime soon. The development of XAUI and the four lambda PHY
which will
> be used by FC, the market for the 10GbE LAN PHY was greatly
reduced.
>
> 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:
> >Roy,
> >
> >It would make our jobs easier (though less profitable) if we
could plan for
> >next year's network development based on what computer systems
do today.
> >Technology continues to evolve and there are some developments
in progress
> >that will impact system bandwidth needs.
> >
> >Today most large systems access their storage through Fibre
Channel links
> >and access the rest of the world through Ethernet links. The
Ethernet NICs
> >leave all or most of the TCP/IP handling to software which has
to touch
> >every packet. Therefore, pushing a Gigabit data rate takes a lot
of CPU
> >cycles. The Fibre Channel links do a lot of the packet
processing in
> >hardware. In an unerrored transfer case, the software above a
Fibre Channel
> >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
storage traffic
> >over Ethernet. In conjunction with that, there is also
development of
> >hardware that will provide hardware functionality for these
protocols
> >similar to that achieved by Fibre Channel. An Ethernet adapter
may then be
> >used to support Ethernet traffic plus storage traffic with
system
> >efficiency about that of FC.
> >
> >This development can increase the data rate needs/capability of
servers up
> >to the point where they need 10 Gbit.
> >
> >Regards,
> >Pat
> >
> >-----Original Message-----
> >From: Roy Bynum
[mailto:rabynum@xxxxxxxxxxxxxx]
> >Sent: Monday, January 29, 2001 5:06 AM
> >To: rtaborek@xxxxxxxxxxxxx; HSSG
> >
> >Rich,
> >
> >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
bandwidth
> >aggregation within privately owned campus fiber plant or a large
data
> >room. The 10GbE WAN PHY, is easily used extended LANs over
leased fiber;
> >MANs over privately owned or leased fiber and wavelengths; WANs
over DWDM
> >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
for a
> >"service provider" type of Ethernet is becoming a
major market
> >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
the WAN
> >PHY. The WAN PHY will be used because it has the
operational management
> >functionality required. If P802.3ae does not go ahead and
put the
> >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
proprietary
> >implementations will give 802.3 a "major black
eye".
> >
> >I tend to agree with Gary Nicholl in the need for a + 20
PPM
> >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
deleted>
-------------------------------------------------------
Richard Taborek
Sr.
Phone: 408-845-6102
Chief Technology
Officer
Cell: 408-832-3957
nSerial
Corporation
Fax: 408-845-6114
2500-5 Augustine Dr.
mailto:rtaborek@xxxxxxxxxxx
Santa Clara, CA
95054
http://www.nSerial.com