Abstract
Spark is an efficient big data processing platform based on memory computing. However, the default task scheduling algorithm in Spark does not take into account the difference in capability and resource usage of nodes under the Spark cluster. Therefore, an uneven load on the nodes might be resulted with the high-capability node in idle state and the low-capability node in high-load state which will affect the work efficiency. To this end, we propose an adaptive task execution node allocation algorithm based on the ant colony-simulated annealing algorithm. The proposed algorithm optimizes the Spark cluster task execution node allocation method based on the resource usage of the node, which is used to achieve the purpose of load balancing. Experiments show that in comparison with the task scheduling algorithm of the Spark cluster, the task scheduling algorithm proposed in this paper has a significant improvement in cluster load balancing and task completion time.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
