Enabling Work Migration in CoMD to Study Dynamic Load Imbalance Solutions

Infrastructure-As-A-Service (IAAS) provides an environmental setup under any type of cloud. In Distributed file system (DFS), nodes are simultaneously serve computing and storage functions; that is parallel Data Processing and storage in cloud. Here, file is considered as a data or load. That file is partitioned into a number of File chunks (FC) allocated in distinct nodes so that Map Reduce tasks can be performed in parallel over the nodes. Files and Nodes can be dynamically created, deleted, and added. This results in load imbalance in a distributed file system; that is, the file chunks are not distributed as uniformly as possible among the Chunk Servers (CS). Emerging distributed file systems in production systems strongly depend on a central node for chunk reallocation or Distributed node to maintain global knowledge of all chunks. This dependence is clearly inadequate in a large-scale, failure-prone environment because the central load balancer is put under considerable workload that is linearly scaled with the system size, it may thus become the performance bottleneck and the single point of failure and memory wastage in distributed nodes. So, we have to enhance the Client side module with server side module to create, delete and update the file chunks in Client Module. And manage the overall private cloud and apply dynamic load balancing algorithm to perform auto scaling options in private cloud. In this project, a fully distributed load rebalancing algorithm is presented to cope with the load imbalance problem.

Download Full-text

A New Approach to Load Balance for Parallel/Compositional Simulation Based on Reservoir-Model Overdecomposition

SPE Journal ◽

10.2118/163585-pa ◽

2013 ◽

Vol 19 (02) ◽

pp. 304-315 ◽

Cited By ~ 7

Author(s):

Yuhe Wang ◽

John E. Killough

Keyword(s):

Dynamic Load ◽

Execution Time ◽

Static Load ◽

Computational Cost ◽

Hydrocarbon Composition ◽

Reservoir Model ◽

Compositional Simulation ◽

New Approach ◽

Load Imbalance ◽

Load Balancer

Summary The quest for efficient and scalable parallel reservoir simulators has been evolving with the advancement of high-performance computing architectures. Among the various challenges of efficiency and scalability, load imbalance is a major obstacle that has not been fully addressed and solved. The causes of load imbalance in parallel reservoir simulation are both static and dynamic. Robust graph-partitioning algorithms are capable of handling static load imbalance by decomposing the underlying reservoir geometry to distribute a roughly equal load to each processor. However, these loads that are determined by a static load balancer seldom remain unchanged as the simulation proceeds in time. This so-called dynamic imbalance can be exacerbated further in parallel compositional simulations. The flash calculations for equations of state (EOSs) in complex compositional simulations not only can consume more than half of the total execution time but also are difficult to balance merely by a static load balancer. The computational cost of flash calculations in each gridblock heavily depends on the dynamic data such as pressure, temperature, and hydrocarbon composition. Thus, any static assignment of gridblocks may lead to dynamic load imbalance in unpredictable manners. A dynamic load balancer can often provide solutions for this difficulty. However, traditional techniques are inflexible and tedious to implement in legacy reservoir simulators. In this paper, we present a new approach to address dynamic load imbalance in parallel compositional simulation. It overdecomposes the reservoir model to assign each processor a bundle of subdomains. Processors treat these bundles of subdomains as virtual processes or user-level migratable threads that can be dynamically migrated across processors in the run-time system. This technique is shown to be capable of achieving better overlap between computation and communication for cache efficiency. We use this approach in a legacy reservoir simulator and demonstrate a reduction in the execution time of parallel compositional simulations while requiring minimal changes to the source code. Finally, it is shown that domain overdecomposition, together with a load balancer, can improve speedup from 29.27 to 62.38 on 64 physical processors for a realistic simulation problem.

Download Full-text

Exploring dynamic load imbalance solutions with the CoMD proxy application

Future Generation Computer Systems ◽

10.1016/j.future.2017.12.010 ◽

2019 ◽

Vol 92 ◽

pp. 920-932 ◽

Cited By ~ 1

Author(s):

Olga Pearce ◽

Hadia Ahmed ◽

Rasmus W. Larsen ◽

Peter Pirkelbauer ◽

David F. Richards

Keyword(s):

Dynamic Load ◽

Load Imbalance

Download Full-text

A New Approach of Dynamic Load Balancing Scheduling Algorithm for Homogeneous Multiprocessor System

International Journal of Applied Evolutionary Computation ◽

10.4018/ijaec.2016040104 ◽

2016 ◽

Vol 7 (2) ◽

pp. 61-75 ◽

Cited By ~ 5

Author(s):

Mahfooz Alam ◽

Ankur Kumar Varshney

Keyword(s):

Load Balancing ◽

Dynamic Load ◽

Execution Time ◽

Interconnection Network ◽

Scheduling Algorithm ◽

Heterogeneous Systems ◽

Dynamic Load Balancing ◽

Multiprocessor System ◽

Load Imbalance ◽

Crossed Cube

Load balancing of parallel tasks in homogeneous as well as heterogeneous systems are major trouble for researches of both industry and academia. Load balancing were broadly classified into two categories namely static load balancing and dynamic load balancing. Nowadays, numerous of researches focus towards dynamic load balancing schemes for multiprocessor system. In this paper, the authors propose a dynamic load balancing strategy for homogeneous multiprocessor system and apply on cube based interconnection network named as Folded Crossed Cube network. The performance of folded crossed cube network gives better result in terms of diameter. Experimental results show that lesser load imbalance factor has been achieved along with execution time. By this algorithm, parallel jobs are solved with largest number of tasks. The merit of this algorithm is that when the number of tasks increases, the execution time decreases with lesser load imbalance factor.

Download Full-text

Multilevel averaging weight method for dynamic load imbalance problems∗

International Journal of Computer Mathematics ◽

10.1080/00207160108805040 ◽

2001 ◽

Vol 76 (4) ◽

pp. 463-477 ◽

Cited By ~ 4

Author(s):

Mo Zeyao ◽

Zhang Baolin

Keyword(s):

Dynamic Load ◽

Load Imbalance ◽

Weight Method

Download Full-text

ON TUNING THE DYNAMIC LOAD BALANCING FEM FRAMEWORK

Acta Polytechnica CTU Proceedings ◽

10.14311/app.2020.26.0007 ◽

2020 ◽

Vol 26 ◽

pp. 7-12

Author(s):

Michal Bošanský ◽

Bořek Patzák

Keyword(s):

Load Balancing ◽

Dynamic Load ◽

Current Trend ◽

Dynamic Load Balancing ◽

Computer Hardware ◽

Memory Model ◽

Finite Element Software ◽

Load Imbalance ◽

Improved Technique ◽

Multiple Processing

Developments in computer hardware are currently bringing new opportunities for numerical modelling. The current trend in technology is parallel processing making use of multiple processing units simultaneously to solve a given problem. This paper deals with exploring the parallel dynamic load balancing framework implemented in the finite element software. This framework is based on a domain decomposition paradigm for distributed memory model. The paper describes the improved technique to determine the actual processor weights related to performance of individual processing units. The load recovery consisting in mesh (re)partitioning is based on actual processor weights. The (re)partitioning process has to be performed during the simulation and whenever the load imbalance is significant. The performance of the proposed technique is tested on the benchmark problem and discussed.

Download Full-text