File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Minimization of cloud task execution length with workload prediction errors

TitleMinimization of cloud task execution length with workload prediction errors
Authors
Issue Date2013
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000322
Citation
The 20th International Conference on High Performance Computing (HiPC 2013), Bengaluru (Bangalore), India, 18-21 December 2013. In Conference Proceedings, 2013, p. 1-10 How to Cite?
AbstractIn cloud systems, it is non-trivial to optimize task’s execution performance under user’s affordable budget, especially with possible workload prediction errors. Based on an optimal algorithm that can minimize cloud task’s execution length with predicted workload and budget, we theoretically derive the upper bound of the task execution length by taking into account the possible workload prediction errors. With such a state-of-the-art bound, the worst-case performance of a task execution with a certain workload prediction errors is predictable. On the other hand, we build a close-to-practice cloud prototype over a real cluster environment deployed with 56 virtual machines, and evaluate our solution with different resource contention degrees. Experiments show that task execution lengths under our solution with estimates of worst-case performance are close to their theoretical ideal values, in both non-competitive situation with adequate resources and the competitive situation with a certain limited available resources. We also observe a fair treatment on the resource allocation among all tasks.
Persistent Identifierhttp://hdl.handle.net/10722/191546

 

DC FieldValueLanguage
dc.contributor.authorDi, Sen_US
dc.contributor.authorKondo, Den_US
dc.contributor.authorWang, CLen_US
dc.date.accessioned2013-10-15T07:10:16Z-
dc.date.available2013-10-15T07:10:16Z-
dc.date.issued2013en_US
dc.identifier.citationThe 20th International Conference on High Performance Computing (HiPC 2013), Bengaluru (Bangalore), India, 18-21 December 2013. In Conference Proceedings, 2013, p. 1-10en_US
dc.identifier.urihttp://hdl.handle.net/10722/191546-
dc.description.abstractIn cloud systems, it is non-trivial to optimize task’s execution performance under user’s affordable budget, especially with possible workload prediction errors. Based on an optimal algorithm that can minimize cloud task’s execution length with predicted workload and budget, we theoretically derive the upper bound of the task execution length by taking into account the possible workload prediction errors. With such a state-of-the-art bound, the worst-case performance of a task execution with a certain workload prediction errors is predictable. On the other hand, we build a close-to-practice cloud prototype over a real cluster environment deployed with 56 virtual machines, and evaluate our solution with different resource contention degrees. Experiments show that task execution lengths under our solution with estimates of worst-case performance are close to their theoretical ideal values, in both non-competitive situation with adequate resources and the competitive situation with a certain limited available resources. We also observe a fair treatment on the resource allocation among all tasks.-
dc.languageengen_US
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000322-
dc.relation.ispartofInternational Conference on High Performance Computing Proceedingsen_US
dc.titleMinimization of cloud task execution length with workload prediction errorsen_US
dc.typeConference_Paperen_US
dc.identifier.emailDi, S: sdi@cs.hku.hken_US
dc.identifier.emailWang, CL: clwang@cs.hku.hk-
dc.identifier.authorityWang, CL=rp00183en_US
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/HiPC.2013.6799101-
dc.identifier.scopuseid_2-s2.0-84900334346-
dc.identifier.hkuros225319en_US
dc.identifier.spage1-
dc.identifier.epage10-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 140217-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats