Abstract
Most of the schedulers in the virtualization platforms provide throughput-oriented policy. However, such throughput-oriented policy has disadvantage in performance for multi-threaded applications which require synchronization among the threads or CPU-intensive programs. To solve this problem, we propose dynamic VCPU pinning mechanism that fixes VCPU to specific physical CPU considering the program characteristics. We demonstrate that the proposed method guarantees improved performance compared to the default VCPU assigning mechanism of credit scheduler in Xen hypervisor.
Original language | English |
---|---|
Title of host publication | 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781479939428 |
DOIs | |
Publication status | Published - 2014 Sept 30 |
Event | 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Kota Kinabalu, Malaysia Duration: 2014 Jan 15 → 2014 Jan 18 |
Publication series
Name | 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings |
---|
Other
Other | 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 |
---|---|
Country/Territory | Malaysia |
City | Kota Kinabalu |
Period | 14/1/15 → 14/1/18 |
Bibliographical note
Publisher Copyright:© 2014 IEEE.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Electrical and Electronic Engineering