Data Collection and Restoration for
Heterogeneous Network Process Migration

Kasidit Chanchio,
Xian-He Sun,

Department of Computer Science
Louisiana State University
Baton Rouge, LA 70803-4020
sun@bit.csc.lsu.edu

Technical Reprot #97-17

Department of Computer Science
Louisiana State University
Baton Rouge, LA 70803-4020

Abstract

Network metacomputing requires efficient process migration. However, there is no known solution for efficient heterogeneous network process migration. In this study we propose a method for data collection, transformation, and restoration, so that high level code such as C programs can be migrated over a network of heterogeneous computers. We first introduce a logical data model to recognize complex data structures in the program address space. Then, we present the associated mechanisms for capturing program data structures and execution states, transferring this information via a network, and resuming the execution appropriately on the destination machine. A prototype of these mechanisms has been implemented to verify the proposed migration methodology. Pointer-intensive programs with function and recursion calls are tested. Performance comparison of array-based and pointer-intensive code is also presented. Experimental results confirm that the newly proposed design is feasible for heterogeneous network process migration.