SSD Bandwidth Distributing I/O Scheduler Considering Garbage Collection

Main Article Content

Jung Kyu Park Jaeho Kim


There were scheduler studies for QoS(Quality of Service) or SLA(Service Level Agreement) of hard disks. The use of SSDs as storage has been increasing dramatically in recent systems due to their fast performance and low power usage. However, the studies to guarantee the SLA are based on the hard disk and do not consider SSD which is a ash storage device. In the SSD, GC(Garbae Collection) process copies data to an empty block and the corresponding block is removed by the GC. This causes SSD performance to degrade in a virtualized environment with many I/Os. We considered the Linux scheduler to take SSD characteristics into consideration and to improve I/O performance. In this paper, we propose a MTS-CFQ I/O scheduler that is implemented by modifying the existing Linux CFQ I/O scheduler. Our proposed method controls the time slice based on the I/O bandwidth for the current storage device. Real workload-driven simulation based experimental results have shown that MTS-CFQ can improve performance by up to 20% with an average of 5%, compared with the traditional CFQ I/O for the four workload considered.


Article Details

How to Cite
J. K. Park and J. Kim, “SSD Bandwidth Distributing I/O Scheduler Considering Garbage Collection”, ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 12, no. 1, pp. 1-6, Mar. 2018.


[1] X. Song, J. Yang and H. Chen, Architecting Flash-based Solid-State Drive for High-performance I/O Virtualization, Computer Architecture Letters, vol. 13, no. 2, pp. 61-64, July 2013.

[2] T. Luo, S. Ma, R. Lee, X. Zhang, D. Liu, and Li Zhou, S-CAVE: Effective SSD Caching to Improve Virtual Machine Storage Performance, In Proc. of International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 103-112, Sep. 2013.

[3] F. Meng, L. Zhou, X. Ma, S. Uttamchandani, and D. Liu, vCacheShare: Automated Server Flash Cache Space Management in a Virtualization Environment, In Proc. of USENIX Conference on USENIX Annual Technical Conference(ATC), pp.133-144, June 2014.

[4] Y. Yang and J. Zhu, Analytical modeling of garbage collection algorithms in hotness-aware ash-based solid state drives, 2014 30th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1-10, June 2014

[5] Q. Niu, J. Dinan, Q. Lu and P. Sadayappan, PARDA: A Fast Parallel Reuse Distance Analysis Algorithm, IEEE 26th International Parallel &
Distributed Processing Symposium (IPDPS), pp. 1284-1294, May 2012.

[6] D. Kang, C. Kim ; K. Kim and S. Jung, Proportional Disk I/O Bandwidth Management for Server Virtualization Environment, International Conference on Computer Science and Information
Technology(ICCSIT '08), pp. 647-652, Sept. 2008.

[7] S. Seelam, R. Romero, P. Teller and B. Buros, Enhancements to Linux I/O Scheduling, In Proc. of the Linux Symposium, pp. 175-192, Sept. 2014.

[8] Q. Deng, Y. Luo, and J. Ge, Dual threshold based unsupervised face image clustering, In Proc. of the 2nd International Conference on Industrial Mechatronics and Automation, pp. 436-439, May 2010.

[9] SIMGRID Project,

[10] iostat,

[11] lebench,

[12] ioreplay,

[13] W. Shin, M. Kim, K. Kim and H. Y. Yeom, Providing QoS through host controlled ash SSD garbage collection and multiple SSDs, In Proc. of 2015 International Conference on Big Data and Smart Computing (BigComp), Feb. 2015.

[14] H. Tan, C. Li, Z. He, K. Li and K. Hwang, VMCD: A Virtual Multi-Channel Disk I/O Scheduling Method for Virtual Machines, IEEE
Transactions on Services Computing, vol. 9, no.
6, pp. 982-995, May 2015.