%0 Report %1 Harchol-Balter:1998:CTA:889010 %A Harchol-Balter, M. %A Crovella, M. E. %A Murta, C. %C Cambridge, MA, USA %D 1998 %I Massachusetts Institute of Technology %K assignment choosing distributed policy task %T On Choosing a Task Assignment Policy for a Distributed Server System %X We consider a distributed server system model and ask which policy should be used for assigning tasks to hosts. In our model each host processes tasks in First-Come-First-Serve order and the task''s service demand is known in advance. We consider four task assignment policies commonly proposed for such distributed server systems: Round-Robin, Random, Size-Based, in which all tasks within a give size range are assigned to a particular host, and Dynamic-Least-Work-Remaining, in which a task is assigned to the host with the least outstanding work. Our goal is to understand the influence of task size variability on the decision of which task assignment policy is best. We find that when the task sizes are not highly variable, the Dynamic policy is preferable. However when task sizes show the degree of variability more characteristic of empirically measured computer workloads, the Size-Based policy is the best choice. We use the resulting observations to argue in favor of a specific size-based policy, SITA-E, that can outperform the Dynamic policy by almost 2 orders of magnitude and can outperform other task assignment policies by many orders of magnitude, under a realistic task size distribution.

@techreport{Harchol-Balter:1998:CTA:889010, abstract = {We consider a distributed server system model and ask which policy should be used for assigning tasks to hosts. In our model each host processes tasks in First-Come-First-Serve order and the task''s service demand is known in advance. We consider four task assignment policies commonly proposed for such distributed server systems: Round-Robin, Random, Size-Based, in which all tasks within a give size range are assigned to a particular host, and Dynamic-Least-Work-Remaining, in which a task is assigned to the host with the least outstanding work. Our goal is to understand the influence of task size variability on the decision of which task assignment policy is best. We find that when the task sizes are not highly variable, the Dynamic policy is preferable. However when task sizes show the degree of variability more characteristic of empirically measured computer workloads, the Size-Based policy is the best choice. We use the resulting observations to argue in favor of a specific size-based policy, SITA-E, that can outperform the Dynamic policy by almost 2 orders of magnitude and can outperform other task assignment policies by many orders of magnitude, under a realistic task size distribution.}, added-at = {2014-04-25T10:06:38.000+0200}, address = {Cambridge, MA, USA}, author = {Harchol-Balter, M. and Crovella, M. E. and Murta, C.}, biburl = {https://www.bibsonomy.org/bibtex/286c3f15c5c406255e6773597a124b279/timfan3939}, description = {On Choosing a Task Assignment Policy for a Distributed Server System}, interhash = {64cc139530cffca94e3619972ec553ed}, intrahash = {86c3f15c5c406255e6773597a124b279}, keywords = {assignment choosing distributed policy task}, publisher = {Massachusetts Institute of Technology}, source = {http://www.ncstrl.org:8900/ncstrl/servlet/search?formname=detail\&id=oai%3Ancstrlh%3Amitai%3AMIT-LCS%2F%2FMIT%2FLCS%2FTR-757}, timestamp = {2014-04-25T10:06:38.000+0200}, title = {On Choosing a Task Assignment Policy for a Distributed Server System}, year = 1998 }