Optimizing server placement in hierarchical grid environments

Wang, Chien‐Min; Hsu, Chun-Chen; Liu, Pangfeng; Chen, Hsi-Min; Wu, Jan‐Jan

doi:10.1007/s11227-007-0118-4

Cited by 7 publications

(7 citation statements)

References 13 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure is more complex than the centralized one because there are three types of methods for constructing the network, i.e., randomly connected [17,18], hierarchically connected [6,16,[19][20][21], and fully connected [22].…”

Section: Network Structures For Schedulersmentioning

confidence: 99%

Liana: a decentralized load-dependent scheduler for performance-cost optimization of grid service

Liu

Cao

2008

J Supercomput

View full text Add to dashboard Cite

This paper addresses the scheduling problem in decentralized grid systems. Such problem focuses on computing a large set of arbitrary tasks to optimize the system performance while minimizing the average system costs. The mainstream solution flourished in recent literatures is to maximize the total system throughput by modeling such systems in either a network flow or a tree. However, most of them neglect the movements of tasks and load-dependent system costs which, in fact, are crucial to the system performance in real situations. In this paper, a Service-Oriented Overlay Network (SOON) is presented, in which the service nodes encapsulate both computation and communication resources and the links are used to track the movements of tasks instead of describing communication. An analytical Cost-Charge (C 2 ) model, in which both running cost and service charge are dependent on load, is proposed to describe the problem by incorporating degree-dependent task allocation into a closed queuing network model. The Infinitesimal Perturbation Analysis (IPA) is applied to solve C 2 theoretically. Following the theoretical analysis, a scalable decentralized scheduler named Liana (the movements of tasks in the proposed system like the growth and spread of evergreen liana, so we use Liana to name the proposed scheduler) is proposed. The major components of Liana are an autonomous scheduling algorithm and a Degree-Driven Protocol (DDP). Furthermore, trace based simulations on the test bed distributed widely across the world are implemented to compare the system performance by Liana with recent approaches. The proposed approach 128 D. Liu et al. shows promising results that the close-to-optimal service utilization is achieved when taking system cost into account.

show abstract

Section: Network Structures For Schedulersmentioning

confidence: 99%

Liana: a decentralized load-dependent scheduler for performance-cost optimization of grid service

Liu

Cao

2008

J Supercomput

View full text Add to dashboard Cite

show abstract

“…We next conduct the following experiments for the optimal service quality problem. We compare three algorithms: (1) the DP algorithm combined a binary search as described in Section 4, (2) the Greedy algorithm combined a binary search and (3) a waiting-time based(WTB) server placement algorithm described in [12]. Note that there is no guarantee of performance for the Greedy algorithm combined a binary search since the Greedy algorithm does not have the property of Corollary 1.…”

Section: Resultsmentioning

confidence: 99%

“…In this paper we use a hierarchical Grid model, one of the most common architectures in current use [7,9,10,11,12,13]. Consider Fig.…”

Section: The System Modelmentioning

confidence: 99%

“…Intermediate nodes can be either routers for network communications or I/O servers that store file replicas. We assume that, initially, only one copy (i.e., the master copy) of a file exists at the root site, as in [9,10,11,12,13]. Let T i be the sub-tree rooted at node i.…”

Section: The System Modelmentioning

confidence: 99%

“…This assumption omits one of the characteristics in grid computing infrastructure: the heterogeneity of its nature. In an early work by Wang [12], they considered the servers' capabilities when minimizing the number of servers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing Server Placement for QoS Requirements in Hierarchical Grid Environments

Wang

Hsu

Liu

et al.

Advances in Grid and Pervasive Computing

Self Cite

View full text Add to dashboard Cite

Abstract. This paper focuses on two problems related to QoS-aware I/O server placement in hierarchical Grid environments. Given a hierarchical network with requests from clients, the network latencies of links, constraints on servers' capabilities and the service quality requirement, the solution to the minimum server placement problem attempts to place the minimum number of servers that meet both the constrains on servers' capabilities and the service quality requirement. As our model considers both the different capabilities of servers and the network latencies, it is more general than similar works in the literatures. Instead of using a heuristic approach, we propose an optimal algorithm based on dynamic programming to solve the problem. We also consider the optimal service quality problem, which tries to place a given number of servers appropriately so that the maximum expected response time is minimized. We prove that an optimal server placement can be achieved by combining the dynamic programming algorithm with a binary search on the service quality requirement. The simulation results clearly show the improvement in the number of servers and the maximum expected response time.

show abstract

The research on a novel structure of two‐layer distributed controllers in software‐defined networking

et al. 2017

View full text Add to dashboard Cite

Summary Distributed controllers have been proposed for solving the scalability and reliability of the centralized controllers problems in software‐defined networking. This paper has presented a new two‐layer distributed controller structure Cacc with the features of overlap management and dynamic management. Cacc has advantages of load balancing and manageability. Furthermore, this paper has conducted the performance modeling of controller topologies and has proposed a new placement problem for Cacc: capacitated multi‐controller placement problem, in which one local controller is assigned to 2 or more root controllers with capacity limitation to achieve a high reliability. Both of the analysis and experiment results have verified the reliability advantages of capacitated multi‐controller placement problem.

show abstract

Optimizing server placement in hierarchical grid environments

Cited by 7 publications

References 13 publications

Liana: a decentralized load-dependent scheduler for performance-cost optimization of grid service

Liana: a decentralized load-dependent scheduler for performance-cost optimization of grid service

Optimizing Server Placement for QoS Requirements in Hierarchical Grid Environments

The research on a novel structure of two‐layer distributed controllers in software‐defined networking

Contact Info

Product

Resources

About