Data Conversion for Process/Thread Migration and Checkpointing

Process/thread migration and checkpointing schemes support load balancing, load sharing and fault tolerance to improve application performance and system resource us-age on workstation clusters. To enable these schemes to work in heterogeneous environments, we have developed an application-level migration and checkpointing pack-age, MigThread, to abstract computation states at the lan-guage level for portability. To save and restore such states across different platforms, this paper proposes a novel “Re-ceiver Makes Right ” (RMR) data conversion method, called Coarse-Grain Tagged RMR (CGT-RMR), for efficient data marshalling and unmarshalling. Unlike common data rep-resentation standards, CGT-RMR does not require program-mers to analyze data types, flatten aggregate types, and en-code/decode scalar types explicitly within programs. With help from MigThread’s type system, CGT-RMR assigns a tag to each data type and converts non-scalar types as a whole. This speeds up the data conversion process and eases the programming task dramatically, especially for the large data trunks common to migration and checkpoint-ing. Armed with this “Plug-and-Play ” style data conver-sion scheme, MigThread has been ported to work in hetero-geneous environments. Some microbenchmarks and perfor-mance measurements within the SPLASH-2 suite are given to illustrate the efficiency of the data conversion process. 1