An Interposed I/O Scheduling Framework for Latency and Throughput Guarantees

Quan Zhang; Dan Feng; Fang Wang; Yanwen Xie

doi:10.6180/jase.2014.17.2.10

An Interposed I/O Scheduling Framework for Latency and Throughput Guarantees

Computer Science and Information Engineering

Quan Zhang This email address is being protected from spambots. You need JavaScript enabled to view it.^1,2, Dan Feng^1,2, Fang Wang^1,2 and Yanwen Xie^1,2

¹WuHan National Laboratory for Optoelectronic, Wuhan 430074, P.R. China
²School of Computer, Huazhong University of Science and Technology, Wuhan 430074, P.R. China

Received: February 18, 2013
Accepted: April 19, 2014
Publication Date: June 1, 2014

Download Citation: ||https://doi.org/10.6180/jase.2014.17.2.10

ABSTRACT

Cloud storage system is becoming a trend in production environments for its economic benefits. With such architecture, storage resource is consolidated to provide multiplexing service for concurrent applications. Therefore, storage centers must be able to guarantee multi-dimensional Quality of Service for various applications. However, satisfying performance targets for each workload is challenging, because they compete for storage resource and have various performance targets in terms of throughput or latency. In this paper, we design and implement a novel scheduler, called Arbitrator, to maintain per-application performance no matter in terms of throughput or latency. In our scheduling framework, we introduce a factor to reflect how applications are sensitive to deadline missing. The scheduler employs a feedback mechanism to monitor latency guarantees and throughput allocation for each application, and compute how much applications deviate from their performance targets. Based on the estimation, Arbitrator makes the scheduling decision to achieve latency guarantee and proportional sharing of bandwidth. We implement Arbitrator in Linux kernel and evaluate its effectiveness, and the results show the scheduler has good ability to maintain satisfactory performance for applications.

Keywords: I/O Scheduling, Quality-of-Service, Shared Storage System, Performance Management

REFERENCES

[1] Lu, L., Varman, P. and Doshi, K., “Graduated QoS by Decomposing Bursts: Don’t Let the Tail Wag Your Server,” Proc. of the 29th Int. Conf. on Distributed Computing Systems, pp. 1221 (2009). doi: 10.1109/ ICDCS.2009.55
[2] Lumb, C. R., Merchant, A. and Alvarez, G. A., “Facade: Virtual Storage Devices with Performance Guarantees,” Proc. of the 2th USENIX Conf. on File and Storage Technologies, pp. 131144 (2003).
[3] Magnus, K., Christos, T. K. and Zhu, X., “Triage: Performance Differentiation for Storage Systems Using Adaptive Control,” ACM Transactions on Storage, Vol. 1, No. 4, pp. 457480 (2005). doi: 10.1145/ 1111609.1111612
[4] Ajay, G., Irfan, A. and Carl, A. W., “PARDA: Proportional Allocation of Resources for Distributed Storage Access,” Proc. of the 7th USENIX Conference on File and Storage Technologies, pp. 8598 (2009).
[5] Gulati, A., Merchant, A. and Varman, P. J., “mClock: Handling Throughput Variability for Hypervisor IO Scheduling,” Proc. of the 9th USENIX Symp. on Operating System Design and Implementation, pp. 437 450 (2010).
[6] Anna, P., Darren, S. and Scott, A. B., “Horizon: Efficient Deadline-Driven Disk I/O Management for Distributed Storage Systems,” Proc. of the 19th Int. Symp. on High Performance Distributed Computing, pp. 112 (2010). doi: 10.1145/1851476.1851478
[7] Chambliss, D., Alvarez, G., Pandey, P., Jadav, D., Xu, J., Menon, R. and Lee, T., “Performance Virtulization for Large-Scale Storage Systems,” Proc. of the 22nd Symposium on Reliable Distributed Systems, pp. 109 118 (2003). doi: 10.1109/RELDIS.2003.1238060
[8] Zhang, J., Anand, S., Qian W., Alma, R. and Erik, R., “Storage Performance Virtualization via Throughput and Latency Control,” ACM Transactions on Storage, Vol. 2, No. 3, pp. 283308 (2006). doi: 10.1145/ 1168910.1168913
[9] Abrahams, A., Gulati, A. M. and Varman, P., “Towards Multi-Objective Scheduling in Shared Storage Systems,” The 2th Int. Workshop on Storage Network Architecture and Parallel I/Os (2005).
[10] Arif, M., Mustafa, U. and Pradeep, P., “Maestro: Quality-of-Service in Large Disk Arrays,” The 8th Int. Conf. on Autonomic Computing, pp. 245254 (2011). doi: 10.1145/1998582.1998638
[11] Povzner, A., Kaldewey, T., Brandt, S., Golding, R., Wong, T. M. and Maltzahn, C., “Efficient Guaranteed Disk Request Scheduling with Fahrrad,” Proc. of EuroSys ’08, pp. 1325 (2008). doi: 10.1145/ 1352592.1352595
[12] Demers, A., Keshav, S. and Shenker, S., “Analysis and Simulation of a Fair Queuing Algorithm,” Journal of Internetworking Research and Experience, Vol. 1, No. 1, pp. 326 (1990). doi: 10.1145/75247.75248
[13] Goyal, P., Vin, H. M. and Cheng, H., “Start-Time Fair Queuing: A Scheduling Algorithm for Integrated Services Packet Switching Networks,” Technical Report CS-TR-96-02, UT Austin, January (1996). doi: 10. 1109/90.649569
[14] Wei, J., Jeffrey, S. C. and Jasleen, K., “Interposed Proportional Sharing for a Storage Service Utility,” Proc. of SIGMETRICS/Performance 2004, pp. 3748 (2004). doi: 10.1145/1012888.1005694
[15] Wang, Y. and Merchant, A., “Proportional-Share Scheduling for Distributed Storage Systems,” Proc. of the 5th USENIX Conf. on File and Storage Technologies, pp. 175188 (2007).
[16] Wachs, M., Abd-El-Malek, M., Thereska, E. and Ganger, G. R., “Argon: Performance Insulation for Shared Storage Servers,” Proc. of the 5th USENIX Conf. on File and Storage Technologies, pp. 6176 (2007).
[17] Gulati, A., Merchant, A. and Varman, P. J., “pClock: An Arrival Curve Based Approach for QoS Guarantees in shared Storage Systems,” Proc. 2007 Int. Conf. on Measurement and Modeling of Computer Systems, pp. 1324 (2007). doi: 10.1145/1254882.1254885
[18] Leana, G., Lui, J. C. S., Edmundo, S. S. and Gail, H. R., “Evaluation of Tradeoffs in Resource Management Techniques for Multimedia Stroage Severs,” IEEE Int. Conf. on Multimedia Computing and Systems, pp. 292296 (1999). doi: 10.1109/MMCS.1999.778387
[19] Reddy, A. L. N. and Wyllie, J., “Disk Scheduling in a Multimedia I/O System,” Proc. of the 1st ACM Int. Conf. on Multimedia, pp. 225233 (1993). doi: 10. 1145/166266.166292