TY - JOUR
T1 - Dynamic load balancing with group communication
AU - Dolev, Shlomi
AU - Segala, Roberto
AU - Shvartsman, Alexander
N1 - Funding Information:
A preliminary version of this works appears in the proceedings of the Sixth International Colloquium on Structural Information and Communication Complexity (SIROCCO’99), 1999, pp. 111–125. ∗Corresponding author. Department of Computer Science and Engineering, University of Connecticut, 371 Fairfield Rd., Unit 2155, Storrs, CT 06269, USA. E-mail addresses: [email protected] (S. Dolev), [email protected] (R. Segala), [email protected] (A. Shvartsman). 1Part of the research was done while visiting the Laboratory for Computer Science at MIT. 2 The work was supported by MIUR projects CoVer and AIDA. 3The work was supported in part by a NSF CAREER Award 9984778, by the NSF Grants 9988304, 0121277, and 0311368, the AFOSR Grant F49620-99-1-0244, and a grant from the GTE Laboratories.
PY - 2006/12/15
Y1 - 2006/12/15
N2 - This work considers the problem of efficiently performing a set of tasks using a network of processors in the setting where the network is subject to dynamic reconfigurations, including partitions and merges. A key challenge for this setting is the implementation of dynamic load balancing that reduces the number of tasks that are performed redundantly because of the reconfigurations. We explore new approaches for load balancing in dynamic networks that can be employed by applications using a group communication service (GCS). The GCS that we consider include a membership service (establishing new groups to reflect dynamic changes) but does not include maintenance of a primary component. For the n-processor, n-task load balancing problem defined in this work, the following specific results are obtained. For the case of fully dynamic changes including fragmentation and merges we show that the termination time of any on-line task assignment algorithm is greater than the termination time of an off-line task assignment algorithm by a factor greater than n / 12. We present a load balancing algorithm that guarantees completion of all tasks in all fragments caused by partitions with work O (n + f · n) in the presence of f fragmentation failures. We develop an effective scheduling strategy for minimizing the task execution redundancy and we prove that our strategy provides each of the n processors with a schedule of Θ (n1 / 3) tasks such that at most one task is performed redundantly by any two processors.
AB - This work considers the problem of efficiently performing a set of tasks using a network of processors in the setting where the network is subject to dynamic reconfigurations, including partitions and merges. A key challenge for this setting is the implementation of dynamic load balancing that reduces the number of tasks that are performed redundantly because of the reconfigurations. We explore new approaches for load balancing in dynamic networks that can be employed by applications using a group communication service (GCS). The GCS that we consider include a membership service (establishing new groups to reflect dynamic changes) but does not include maintenance of a primary component. For the n-processor, n-task load balancing problem defined in this work, the following specific results are obtained. For the case of fully dynamic changes including fragmentation and merges we show that the termination time of any on-line task assignment algorithm is greater than the termination time of an off-line task assignment algorithm by a factor greater than n / 12. We present a load balancing algorithm that guarantees completion of all tasks in all fragments caused by partitions with work O (n + f · n) in the presence of f fragmentation failures. We develop an effective scheduling strategy for minimizing the task execution redundancy and we prove that our strategy provides each of the n processors with a schedule of Θ (n1 / 3) tasks such that at most one task is performed redundantly by any two processors.
KW - Dynamic networks
KW - Group communications
KW - Load balancing
KW - Scheduling
UR - http://www.scopus.com/inward/record.url?scp=33751018568&partnerID=8YFLogxK
U2 - 10.1016/j.tcs.2006.09.020
DO - 10.1016/j.tcs.2006.09.020
M3 - Article
AN - SCOPUS:33751018568
SN - 0304-3975
VL - 369
SP - 348
EP - 360
JO - Theoretical Computer Science
JF - Theoretical Computer Science
IS - 1-3
ER -