Fast and Cost-Effective Online Load-Balancing in Distributed Range-Queriable Systems

Konstantinou, Ioannis; Tsoumakos, Dimitrios; Koziris, Nectarios

doi:10.1109/tpds.2010.200

Cited by 35 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the system requires randomly chosen partition boundaries as in P2P network (e.g., [46,43]), efficient load balancing technique needs O(log n) messages, where n is the number of nodes. Methods that use skip graphs like [18,29,11] need to have global load statistics to address the problem of data skew. Skip graphs are circular linked lists, where each node maintains roughly O(log n) skip pointers, to enable the list traversal.…”

Section: Discussion and Comparison With Existing Approachesmentioning

confidence: 99%

“…The work in [29] evaluates the performance in terms of bandwidth cost and convergence speed of balancing range query capable data structures using successive item exchanges and node migrations. This approach maintains load information using a skip graph.…”

Section: Related Workmentioning

confidence: 99%

“…Works in [18,29,11] use two universal load balancing primitives which are item exchange between neighbors and node migration from the most loaded area to the least loaded one. Despite the effectiveness of these approaches, their main drawback is the high cost of maintaining load statistics.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

OLAPS: Online load-balancing in range-partitioned main memory database with approximate partition statistics

2018

View full text Add to dashboard Cite

Modern database systems can achieve high throughput main-memory query execution by being aware of the dynamics of highly parallel hardware. In such systems, data is partitioned into smaller pieces to reach a better parallelism. Unfortunately, data skew is one of the main problems faced during parallel processing in a parallel main memory database. In some data-intensive applications, parallel range queries over a dynamic range partitioned system are important. Continuous insertions/deletions can lead to a very high degree of data skew and consequently a poor performance of parallel range queries. In this paper, we propose an approach for maintaining balanced loads over a set of nodes as in a system of communicating vessels, by migrating tuples between neighboring nodes. These frequent (or even continuous) data transfers inevitably involve dynamic changes in the partition statistics. To avoid the performance degradation typically associated with this dynamism, we provide a solution based on an approximate Partition Statistics Table. The basic idea behind this table is that both clients and nodes may have an imperfect knowledge about the effective load distribution. They can nevertheless locate any data with almost the same efficiency as using exact partition statistics. Furthermore, maintaining load distribution statistics do not require exchanging additional messages as opposed to the cost of efficient solutions from the state-of-art (which requires at least O(logn) messages). We show through intensive experiments that our proposal supports efficient range queries, while simultaneously guaranteeing storage balance even in the presence of numerous concurrent insertions/deletions generating a heavy skewed data distribution.

show abstract

Section: Discussion and Comparison With Existing Approachesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

OLAPS: Online load-balancing in range-partitioned main memory database with approximate partition statistics

2018

View full text Add to dashboard Cite

show abstract

“…It is performed by moving just one unit per iteration [23], [24], [25], [26], or a fixed number [27], [28]. Further, in [29] it's achieved by exchanging the load between neighbor nodes.…”

Section: Related Workmentioning

confidence: 99%

A Mobile Agent Team Works based on Load-Balancing Middleware for Distributed Computing Systems

Benchara¹,

Youssfi²

2019

IJACSA

View full text Add to dashboard Cite

The aim of this paper is to present a load balancing middleware for parallel and distributed systems. The great challenge is to balance the tasks between heterogeneous distributed nodes for parallel and distributed computing models based distributed systems, by the way to ensure HPC (High performance computing) of these models. Accordingly, the proposed middleware is based on mobile agent team work which implements an efficient method with two strategies: (i) Load balancing Strategy that determines the node tasks assignment based on node performance, and (ii) Rebalancing Strategy that detects the unbalanced nodes and enables tasks migration. The paper focuses on the proposed middleware and its cooperative mobile agent team work model strategies to dynamically balance the nodes, and scale up distributed computing systems. Indeed, some experimental results that highlight the performance and efficiency of the proposed middleware are presented.

show abstract

“…To do so, the excess loads are transferred to the under loaded nodes in their own domain, thus reducing communication overhead. In [11], the two following techniques are used to achieve load-balancing state, they are: iterative key redistribution between neighbors and node migration. The authors have proposed Load balancing algorithm based on aspect oriented approach 147 a hybrid method to achieve both fast and cost-effective load-balancing in distributed systems that support range queries.…”

Section: Introductionmentioning

confidence: 99%

Load balancing algorithm based on aspect oriented approach for a multi agent distributed system

Youssfi¹,

Bouattane²,

Daaif³

et al. 2016

ces

View full text Add to dashboard Cite

In this paper, we present a new load balancing system based on aspect oriented approach for multi agents distributed systems. The proposed model is based on using a dispatcher agent assigned to dynamically distribute tasks received in random requests coming from agent producers. We suppose that tasks are assigned to be executed by workers agents deployed over the nodes of the distributed system. To make the initial mechanism of task distribution balanced, we propose a separated aspect where we propose a load balancing procedure assigned to be affected to the dispatcher by an aspect weaving in compilation or run times. The load balancing aspect increases the performances of the dispatcher agent using code advices in different join points. The task distribution code advice is used to implement the load balancing algorithm which determines the under loaded worker agent who will be assigned to execute the current task Ti. In this algorithm, we take into account the heterogeneity of the processing performances, the communication latency, occupancy rate of each node and the complexity of the current task. In this model we can also use metadata of the tasks to estimate more accurately the required times to perform each task. This mechanism allows predicting the performance offered by the distributed system according to the selected computational model. To describe the proposed approach, some communication diagrams, the established mathematical model and an application example are presented to prove the effectiveness of the proposed model. 146 Mohamed Youssfi et al.

show abstract

Fast and Cost-Effective Online Load-Balancing in Distributed Range-Queriable Systems

Cited by 35 publications

References 33 publications

OLAPS: Online load-balancing in range-partitioned main memory database with approximate partition statistics

OLAPS: Online load-balancing in range-partitioned main memory database with approximate partition statistics

A Mobile Agent Team Works based on Load-Balancing Middleware for Distributed Computing Systems

Load balancing algorithm based on aspect oriented approach for a multi agent distributed system

Contact Info

Product

Resources

About