An ATM clustering system is a kind of workstation clusters over an ATM network. Such a system can be used as a distributed database server which requires reliable data delivery. This paper proposes an error recovery scheme at the transport layer for reliable data transfers with high throughput in the ATM clustering system. For such data transfers, acknowledgments are sent periodically as well as at the detection of packet losses. To be eflcient, the periods of acknowledgments for the scheme are adaptively varied, depending on whether current transfer is either in errorfree phase or in an error recovery phase. The design andpelformance evaluation of the error recovery scheme is presented with a set of parameter values to achieve the best pelformance. The results show that the proposed scheme operates correctly and eficiently for the ATM clustering system. The throughput peforrnance of the proposed scheme is superior to the SSCOP (Service Specific Connection Oriented Protocol) regardless of packet loss rates. Some recent works have been devoted to build and evaluate workstation clusters over ATM networks. [5] has shown that among four different API’s a distributed program using the ATM API can obtain a better communication performance than the others. [SI have regarded a workstation cluster over an ATM network a platform of High Performance Distributed Computing(HPDC). An ATM clustering system is a kind of workstation clusters used as a distributed database server. The system consists of several nodes each of which is configured with a 155 Mbps adapter board. User data can be stored in each node by using either partitioned or replicated schemes [7]. In such a system, reliable delivery should be supported to achieve data integrity whatever the scheme
[1]
David Hung-Chang Du,et al.
Distributed network computing over local ATM networks
,
1994,
Supercomputing '94.
[2]
Josep Solé-Pareta,et al.
Network-based parallel computing over ATM using improved SSCOP protocol
,
1996,
Comput. Commun..
[3]
Harry Rudin,et al.
A survey of light-weight transport protocols for high-speed networks
,
1990,
IEEE Trans. Commun..
[4]
Patrick Valduriez,et al.
Principles of Distributed Database Systems
,
1990
.
[5]
Arun N. Netravali,et al.
Design and implementation of a high-speed transport protocol
,
1990,
IEEE Trans. Commun..
[6]
Arun N. Netravali,et al.
Error and flow control performance of a high speed protocol
,
1993,
IEEE Trans. Commun..