The Credit Net ATM Project
This is the World Wide Web home page of the
ARPA-funded Credit Net (VC Nectar) project in the
School of Computer Science at
Carnegie Mellon University.
This page is still being improved.
Project Overview
The Credit Net project is a joint project with Harvard, BNR and Intel, and
involves the development of a 622 Mbit/second flow-controlled ATM network.
As in its predecessor project,
Gigabit Nectar,
the research is focused on building a system that
supports applications effectively.
Credit Net is a prototype network, with switches built by Bell Northern
Research and PCI host adapters built by Intel Architecture Labs, designed in cooperation with
Harvard and CMU, respectively. Its features include
- High speed: the 622 megabits per second of a Credit Net link are four
times as fast as commercial ATM LAN products.
- Flow control: the Credit Net switches and adapters incorporate
sophisticated flow control algorithms that prevent congestion collapse of
the network under any possible load.
- Multicast: the Credit Net switches include hardware support for
efficient multicast.
- Standards compliance: Credit Net uses standard SONET links at OC-3 and
OC-12 speeds, and complies with national and international data formats and
protocols.
In the context of CreditNet Intel and CMU are developing a
622 megabits per second host interface for the PCI bus. The main
components on the board are an ASIC that supports standard ATM cell
processing and management of host buffers, and a 960 microcontroler
that supports the more experimental features of the network such as
flow control.
Status and Plans
Credit Net networks are currently operational at both CMU and Harvard, and
the results of early credit-based flow control experiments are summarized
below. Most links are currently OC3; they will be upgraded to OC12 in
August/September 1995. The CMU network will grow to include two switches
and some 25 high-end personal computers in the same time frame. Research
topics on our agenda include:
- Low overhead protocols
- Multimedia applications
- Support for compiled distributed programs
- Heterogeneous quality of service
- Programming interfaces for network-aware applications
Early credit results
Credit-based flow control has been implemented in both the Credit Net
switches and hosts.
In February 1995 we demonstrated that credit-based flow control can
eliminate the cell loss, and resulting drop in performance, on congested
links inside an ATM network. The results are summarized below, and more
details can be found
here .
The basic result is that without flow control, cells get lost resulting
in very poor performance, as measured using ttcp. This is illustrated by the
traces shown below (traces on left): packets are lost, resulting in
tcp timeouts and loss of throughput. As is shown in the traces on the
right, with credit-based flow control we achieve good throughput
(the sum of the throughput of the links equals the OC3 link bandwidth) and
fair sharing of the bandwidth. If tcp is competing
with a traffic stream without backoff, e.g. a video stream, throughput
drops to close to 0.
More recently we implemented an all-software credit implementation on the host.
The host interprets incoming credit cells and schedules packets based on the
availability of credit; no hardware support on the adapter is needed. No flow
control is used for the incoming data stream under the assumption that the host
should should have enough buffer space to store incoming data. The results are
summarized below. The nodes used in the test are 90 MHz Pentium PCs.
Related Projects
The Credit Net group works closely with several other research projects at CMU,
including
the
iWarp project,
the
Fx parallel FORTRAN compiler project,
Dome,
Scotch parallel storage, the
Environmental modeling NSF grand challenge application ,
and the
multicomputer project.
People
Allan Fisher
and
Peter Steenkiste
lead the project at CMU.
David Eckhardt,
Corey Kosak,
and
Todd Mummert
form the rest of the inner circle.
H. T. Kung
leads the
Harvard
team.
prs@cs.cmu.edu