The classification of various types of processes is an important factor in large-scale distributed systems such as, grid and cloud platforms. Moreover, the coordination and control of distributed processes are research challenges in presence of unpredictable network partitioning and distributed semaphores. The process classification is important in order to allocate and schedule distributed processes enhancing overall resource utilization and throughput. The schedulers employ patterns of resource affinities of concurrent processes in order to make scheduling decisions affecting overall resource utilization in a system, where resource affinity patterns of a process may not be static. This paper proposes an estimation model and a classifier algorithm to queuing processes based on respective resource affinities. The kernel-level software architecture is designed to control scheduling of distributed processes based on classification for enhanced throughput. The classifier algorithm tracks the resource affinities of processes based on execution traces and the control algorithm performs process scheduling. Experimental results indicate that the classifier algorithm successfully manages process queues based on resource affinities of processes and, the control algorithm successfully monitors scheduler activation for a set of processes. 相似文献
The Earth Simulator (ES) is a large scale, distributed memory, parallel computer system consisting of 640 processor nodes (PN) with shared memory vector multi-processors (64GFLOPS/PN, 5120 APs in total, AP: arithmetic processor). All the nodes are connected via a high speed (16GB/s) single-stage crossbar network called the Interconnection Network (IN).
The operating system for the Earth Simulator is based on SUPER-UX, the UNIX operating system for the SX series scientific supercomputers. In order to realize high-performance parallel processing on the highly parallel machine, the operating system is enhanced for scalability.
The Earth Simulator system is managed as a two-level cluster system called the Super Cluster System. In the Super Cluster System, the Earth Simulator system is divided into 40 clusters (16 PNs/cluster). A single controller called Super Cluster Control Station (SCCS) manages all these clusters. This management system provides Single System Image (SSI) operation, management and job control for the large scale multi-node system.
The Job Scheduler (JS) and NQS running on the SCCS control all jobs of the system. They schedule the resources such as processing nodes and files which have not usually been treated as scheduling resources. This allows efficient scheduling of large scale jobs.
The MPI library (MPI/ES) and the HPF compiler (HPF/ES) are available for distributed parallel programming on the Earth Simulator. MPI/ES conforms to the MPI 2.0 standard and is optimized to exploit the hardware features. HPF/ES conforms to the core part of HPF 2.0 and supports some features of the HPF 2.0 approved extensions and HPF/JA 1.0 extensions. HPF/ES suitably handles the 3-level parallelism of the Earth Simulator system, that is, vectorization, shared-memory parallelization, and distributed-memory parallelization. Moreover, HPF/ES extends the language to easily handle irregular problems. 相似文献
This paper presents the first IEEE 802.16m medium access control (MAC) protocol module embedded in the network simulator version 3 (ns-3). The designed module provides a validation tool for researchers to verify simulated results related to the IEEE 802.16m. This module supports the basic MAC functions which includes an initial ranging (IR) function; four types of bandwidth request (BR) procedures; five types of standard-specified quality-of-service (QoS); a QoS-based transmission scheduler; an adaptive modulation and coding (AMC) selection function; a physical (PHY) layer with a channel propagation model. The designed module provides modification flexibility to adapt to other simulation modules. Various scenarios are simulated to show the capacity of the implemented IEEE 802.16m module in details. Results of different types of traffic are tested with the path loss effect on transmission to visualize the numeric capability of the module. 相似文献
In multiprocessor system-on-chip, tasks and communications should be scheduled carefully since their execution order affects
the performance of the entire system. When we implement an MPSoC according to the scheduling result, we may find that the
scheduling result is not correct or timing constraints are not met unless it takes into account the delays of MPSoC architecture.
The unexpected scheduling results are mainly caused from inaccurate communication delays and or runtime scheduler’s overhead.
Due to the big complexity of scheduling problem, most previous work neglects the inter-processor communication, or just assumes
a fixed delay proportional to the communication volume, without taking into consideration subtle effects like the communication
congestion and synchronization delay, which may change dynamically throughout tasks execution. In this paper, we propose an
accurate scheduling model of hardware/software communication architecture to improve timing accuracy by taking into account
the effects of dynamic software synchronization and detailed hardware resource constraints such as communication congestion
and buffer sharing. We also propose a method for runtime scheduler implementation and consider its performance overhead in
scheduling. In particular, we introduce efficient hardware and software scheduler architectures. Furthermore, we address the
issue of centralized implementation versus distributed implementation of the schedulers. We investigate the pros and cons
of the two different scheduler implementations. Through experiments with significant demonstration examples, we show the effectiveness
of the proposed approach. 相似文献