Ziping Liu

Novel low-overhead roll-forward recovery scheme for distributed systems

An efficient roll-forward checkpointing/recovery scheme for distributed systems has been presented. This work is an improvement of our earlier work. The use of the concept of forced checkpoints helps to design a single phase non-blocking algorithm to find consistent global checkpoints. It offers the main advantages of both the synchronous and the asynchronous approaches, that is simple recovery and simple way to create checkpoints. The algorithm produces reduced number of checkpoints. Since each process independently takes its decision whether to take a forced checkpoint or not, it makes the algorithm simple, fast and efficient. The proposed work offers better performance than some noted existing works. Besides, the advantages stated above also ensure that the algorithm can work efficiently in mobile computing environment.

Hierarchical pruning to improve bandwidth utilization of RPF-based broadcasting

Some of the attractive features of using Reverse Path Forwarding (RPF) method for broadcasting include reasonably low amount of memory necessary for storing the data structures in a router required by the protocol and ease of its implementation as it does not look for shortest path delivery. However, it generates quite a large number of duplicate packets resulting in poor bandwidth utilization. In this paper we have introduced a novel hierarchical pruning mechanism to improve bandwidth utilization for broadcasting using the RPF method. Experimental results support our theoretical findings of achieving very high reduction in the number of the duplicate packets generated.

A highly efficient RPF-based broadcast protocol using a new two-level pruning mechanism

Abstract Reverse path forwarding (RPF) based data communication is one of the widely used data communication protocols in networks. The most attractive feature of RPF is that reasonably low amount of memory is needed per router for storing the routing information (DVR table). However, it generates quite a large number of duplicate packets resulting in poor bandwidth utilization. We have observed that if the location of the broadcast source is considered while forwarding a packet, considerable improvement of the bandwidth utilization can be achieved from the viewpoint of less number of duplicate packets generated. In this paper we have used this location aspect in the design of a novel hierarchical pruning mechanism to improve bandwidth utilization for broadcasting based on RPF mechanism for data communication. Experimental results support our theoretical findings and hence guarantee improvement of bandwidth utilization.

NPR - A new QoS-based routing protocol for mobile ad-hoc networks

Ad-hoc on-demand networks have received a significant interest in the literature. Many routing schemes for such networks focus on finding an optimal path. In this paper, however, we consider the routing problem from the viewpoint of sustaining QoS (quality of service) requirement. Some algorithms such as MP-DSR already have considered this problem in terms of the end-to-end reliability requirement. While the Multi-Path Dynamic Source Routing (MP-DSR) algorithm is capable of resolving the issue to a certain extent, it only considers disjoint paths between a pair of source and destination nodes. In reality due to mobility of nodes there may not exist such disjoint paths. In this paper the proposed approach is independent of the nature of the paths, and yet it achieves the required reliability to satisfy QoS requirement.

A Low-Overhead Non-Block Check Pointing and Recovery Approach for Mobile Computing Environment

Check pointing/rollback-recovery strategy is used for providing fault-tolerance to distributed applications (Y.M. Wang, 1997; M. Singhal & N. G. Shivaratri, 1994; R. E. Strom and S. Yemini 1985; R. Koo & S. Toueg, 1987; S. Venkatesan et al.,1997; G. Cao & M. Singhal, 1998; D. Manivannan & M. Singhal, 1999). A checkpoint is a snapshot of the local state of a process, saved on local nonvolatile storage to survive process failures. A global checkpoint of an n-process distributed system consists of n checkpoints (local) such that each of these n checkpoints corresponds uniquely to one of the n processes. A global checkpoint M is defined as a consistent global checkpoint if no message is sent after a checkpoint of M and received before another checkpoint of M (Y.M. Wang, 1997). The checkpoints belonging to a consistent global checkpoint are called globally consistent checkpoints (GCCs). The set of such checkpoints is also known as recovery line.