Distributed Processor Allocation in Multicomputers

Current processor allocation techniques for multicomputers are based on centralized front-end based algorithms. As a result, the applied strategies are usually restricted to static, contiguous, structure preserving allocation, and suffer from low parallelism and weak fault tolerance. To lift these restrictions we are investigating a distributed approach to the processor allocation problem for mesh interconnected distributed memory machines. We conducted several experiments, some simulated and some running over a Simens hpcLine Primergy Server with 96 nodes, which showed that distributed allocation is feasible with current technologies. 1. The processor allocation problem Processor allocation involves the selection of a processor partition for a given parallel job, with the goal of maximizing throughput over a stream of many jobs. Because allocation operations have to be fast, allocation techniques usually restrict the feasible shapes of partitions to achieve some regularity, which facilitates their management. We call a partitioning scheme structure preserving if it generates partitions that are of the same topological graph family as the entire processor graph (subcube allocation in hypercubes and submesh allocation in meshes). In addition, many systems also require that the allocated processors are constrained to be physically adjacent (contiguous allocation) to reduce communication costs. 2. Distributed processor allocation Several approaches to deal with the processor allocation problem can be found in the literature [3]. In spite of the fact that they apply different policies in the resource management, all the schemes have one in common: the control of allocated resources is done with a global data structure localized mostly in a host machine. The main problems of such centralized management are lack of scalability, the incompatibility with adaptive processor allocation schemes (dynamic allocation), and its weak fault tolerance. Figure 1 shows a global view of the proposed distributed allocation [1] and the distributed Processor Managers involved in the allocation operation. The main differences to the centralized management are (i) the absence of a central data structure with information about the state of all processors, and (ii) the execution of allocation operations directly in the processor mesh in a distributed way, and not in a data structure localized in the host. The host machine is now only responsible for queuing the incoming requests and forwarding them to the processor mesh. Due to the distributed environment there is no restriction concerning the number of entry points in the mesh. Additional allocations Releases Allocation jobs Initial allocations Processor mesh Host machine PM