Total views : 253

Performance Evaluation and Scalability of IP-based and Heuristic-based Job Scheduling Algorithm Backup Systems


  • School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran, Islamic Republic of


Background/Objectives: One of the most important factors in the design of enterprise computer networks is data storage method. Increase the volume, recovery and security of stored information is the biggest challenge. Using backup systems is a perfect solution to solve these challenges. Traditional methods can be used to perform backups, but new methods and new backup systems are more efficient. Methods/Statistical Analysis: To analyze and compare overall backup session time, backup session processing time, overhead, fragmentation of large data and efficiency of the IP-based schedule and the heuristic-based job scheduling algorithm. Findings: My analysis show that the simple heuristic-based job scheduling algorithm with adaptive number of active DAs is close to optimal while having no additional computing overhead compared to the compute expensive IP-based solution. The simulator-based on heuristic-based job scheduling algorithm enables the analysis to minimize the number of actively used backup servers while meeting backup window constraints and data restore satisfying rates. Applications/Improvements: This algorithm is close to the results that reduce backup time by 60 percent without additional computing overhead and fragmentation of large data processing compared to IP-based methods. As well as, the algorithm can simulate the analysis of a backup system will help. The proposed approach significantly increases the performance, reliability and quality of implemented solutions.


Algorithm, Backup, Performance, Scalability, Schedulin.

Full Text:

 |  (PDF views: 199)


  • Eizadpanah E, Koroupi F. timing of resources in cloud computing by using multi-purpose particles congestion algorithm. Indian Journal of Science and Technology. 2015; 8(Suppl 8):474-83.
  • Four tips for optimizing continuous data protection, [Online]. Available: 2278838. 19/05/2008.
  • Cherkasova L, Zhang A, Li X. DP+IP=Design of efficient backup scheduling. Proceedings of 6th International Conference on Network and Service Management; Niagara Falls, ON. 2010. p. 118-25.
  • Cherkasova L, Lau R, Burose H, Kalambur SV, Kappler B, Veeranan K. Run-time performance optimization and job management in a data protection solution. Proceeding of 11th IFIP/IEEE Symposium on Integrated Management (IM); Dublin. 2011. p. 65-72.
  • CPLEX, [Online]. Available from: wiki/CPLEX
  • Graham RL. Bounds on multiprocessing timing anomalies. SIAM Journal on Applied Mathematics.1969; 17(2):416-29.
  • Yoo SM, Youn HY. Largest job first scan all scheduling policy for 2D mesh-connected systems. Proceedings of 6th Symposium on the Frontiers of Massively Parallel Computation; Annapolis, MD.1996. p. 118-25.
  • Preston W. Backup and Recovery. USA: O’Reily; 2006.
  • The Automated Maryland Automatic Network Disk Archiver, [Online]. Available: 20/01/2016.
  • EMC Backup Advisor [Online]. Available from: http:// htm
  • IBM Tivoli Continuous Data Protection for Files [Online]. Available from: wss?uid=swg24031940
  • Lifka DA. The ANL/IBM SP scheduling system. Proceedings of Job Scheduling Strategies for Parallel Processing; Heidelberg: Springer Berlin; 1995. p. 295-303.
  • Heymann E, Senar MA, Luque E, Livny M. Adaptive scheduling for master-worker applications on the computational grid. Proceedings of 1st IEEE/ACM International Workshop on Grid Computing, LNCS 1971; 2000. p. 214-27.
  • Tan L, Tari Z. Dynamic task assignment in server farms: Better performance by task grouping. Proceedings of the ISCC; 2002. p. 175.
  • Vrable M, Savage S, Voelker G. Cumulus: Filesystem backup to the cloud. Proceedings of the FAST; 2009.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.