Abstract. An algorithm for sorting on a mesh by alternately transforming the rows and columns is presented. The algorithm runs in a constant number of row-and column-transformation phases (sixteen phases), an improvement over the previous best upper bound of O(log log m) phases, m being the number of rows in the mesh. A corresponding lower bound of five phases is also shown.

The emergence of the cloud and advanced objectbased storage services provides opportunities to support novel models for long term preservation of digital assets. Among the benefits of this approach is leveraging the cloud's inherent scalability and redundancy to dynamically adapt to evolving needs of digital preservation. PDS Cloud is an OAIS-based preservation-aware storage service employing multiple heterogeneous cloud providers. It materializes the logical concept of a preservation information-object into physical cloud storage objects. Preserved information can be interpreted by deploying virtual appliances in the compute cloud provisioned with cloud storage data objects together with their designated rendering software. PDS Cloud has a hierarchical data model supporting independent tenants whose assets are organized in multiple aggregations based on content and value. Continuous changes to data objects, life-cycle activities, virtual appliances and cloud providers are applied in a manner transparent to the client. PDS Cloud is being developed as an infrastructure component of the European Union ENSURE project, where it is used for preservation of medical and financial data.

The methodology and design of a system that provides highly available data in a cluster is presented. A Highly Available Cluster consists of multiple machines interconnected by a common bus. Data is replicated at a primary and one or more backup machines. Data is accessed at the primary, using a location independent mechanism that ensures data integrity. If the primary COPY of the data fails, access is recovered by switching to a backup copy. Switchover is transparent to the application, hence called seamless switchover. The fault model is fail-stop. The entire cluster is resilient to at least single failures. Designating data as highly available is selective in scope, and the overhead of replication and recovery is incurred only by applications that access highly available data. An experimental prototype was implemented using IBMt AS/400f machines and a high-speed bus with fiber-optic links.

No abstract

The software and hardware available today for personal computers provides a broad range of support for personal productivity, business applications, research, programming, and other activities. If personal computers are connected in a local area network, they can form a system whose total resources are very great compared to those of each computer. With appropriate system mechanisms, users can share these resources.We describe the design and implementation of a resource sharing system for IBM Personal Computers. The system generalizes the traditional file and device server approach, allowing applications of any kind to be offered as services on the network. The system supports services by maintaining service definitions, queuing requests by priority, creating server processes, loading service programs, and combining services into larger distributed applications. A user may start several independent activities that proceed concurrently. Each activity can span several machines. The system is built upon an existing operating system, PC-DOS, extending the view it provides to users. Multitasking and enhanced memory management are provided. Interprocess communication is supported by a high-level service request protocol. The discussion emphasizes the problems encountered in building the system and the solutions devised.