Cloud computing aims to give users virtually unlimited pay-per-use computing resources without the burden of managing the underlying infrastructure. We present a new job execution environment Flextic that exploits scal- able static scheduling techniques to provide the user with a flexible pricing model, such as a tradeoff between dif- ferent degrees of execution speed and execution price, and at the same time, reduce scheduling overhead for the cloud provider. We have evaluated a prototype of Flextic on Amazon EC2 and compared it against Hadoop. For various data parallel jobs from machine learning, im- age processing, and gene sequencing that we considered, Flextic has low scheduling overhead and reduces job du- ration by up to 15% compared to Hadoop, a dynamic cloud scheduler.
1 - 6
HotCloud: Workshop on Hot Topics in Cloud Computing
2011-06-14 – 2011-06-15
Henzinger TA, Singh A, Singh V, Wies T, Zufferey D. Static scheduling in clouds. In: USENIX; 2011:1-6.
Henzinger, T. A., Singh, A., Singh, V., Wies, T., & Zufferey, D. (2011). Static scheduling in clouds (pp. 1–6). Presented at the HotCloud: Workshop on Hot Topics in Cloud Computing, USENIX.
Henzinger, Thomas A, Anmol Singh, Vasu Singh, Thomas Wies, and Damien Zufferey. “Static Scheduling in Clouds,” 1–6. USENIX, 2011.
T. A. Henzinger, A. Singh, V. Singh, T. Wies, and D. Zufferey, “Static scheduling in clouds,” presented at the HotCloud: Workshop on Hot Topics in Cloud Computing, 2011, pp. 1–6.
Henzinger TA, Singh A, Singh V, Wies T, Zufferey D. 2011. Static scheduling in clouds. HotCloud: Workshop on Hot Topics in Cloud Computing 1–6.
Henzinger, Thomas A., et al. Static Scheduling in Clouds. USENIX, 2011, pp. 1–6.