This document presents research on improving the energy efficiency of secure disk systems without altering existing security mechanisms. The study explores various approaches to enhance energy efficiency while implementing various encryption algorithms, highlighting bottlenecks in CPU and network data transmission rates. The authors also note limitations in their testbed environment and the representativeness of workloads analyzed.

1. Can We Improve Energy Efficiency of Secure Disk Systems without Modifying Security Mechanisms? Xiaojun Ruan, Adam Manzanares , Shu Yin and Xiao Qin Auburn University http://www.eng.auburn.edu/~xqin [email_address]

2. Introduction 02/28/11

3. Introduction 02/28/11

4. Introduction 02/28/11

5. Proposed Architecture Write requests Read requests Data movement Power Management Disk 1 Disk 2 Disk 3 Disk 4 Disk 5 Buffer Disks RAM Buffer Buffer Disk Controller Disk Requests

6. Security vs. Power Consumption ACM Transactions on Information and System Security, Vol. 9, No. 2, May 2006. R. CHANDRAMOULI et. al

7. Improve both Energy Efficiency and Security: Approach 1 To improve the energy efficiency of security mechanisms in disk systems Security Mechanisms Improve Energy Efficiency

8. Improve both Energy Efficiency and Security: Approach 2 To integrate conventional security services with energy-efficient disk architectures. Security Mechanisms Energy Conservation Schemes

9. Table 1 System Parameters of the Testbed CPU Speed Pentium 4 2.4 GHZ Memory 512 MB Operating System Ubuntu 7.10 USB 1.1 12 Mb/s HD Bus IDE

10. Xyssl Implements many popular encryption algorithms Provides sample programs Allowed us to develop software based on the sample programs

11. Conky Lightweight system monitor Highly configurable Simple text configuration file

12. Conky

13. Testbed Information Encryption Algorithms 3DES AES Hash Functions MD5 SHA-1 SHA-256 RSA Signature Verification

14. Possible Bottlenecks Receive Encrypt or Verify Store Flash Drive (Network) CPU Hard Disk

15. Experiment Results MD5 Verification

16. Experiment Results MD5 Verification

17. Experiment Results SHA-1 Verification

18. Experiment Results SHA-1 Verification

19. Experiment Results RSA Verification

20. Experiment Results RSA Verification

21. Experiment Results Advanced Encryption Standard

22. Experiment Results Advanced Encryption Standard

23. Experiment Results 3DES

24. Experiment Results 3DES

25. A Sample Table CPU Load Read Load Write Load Save Energy for Reads? Save Energy for Writes? MD5 M H M Unlikely Yes SHA1 M VH M Unlikely Yes SHA2 M VH M Unlikely Yes RSA M VH M No Yes AES VH VH M No Yes 3DES EH M L Yes Yes

26. Conclusion For MD5, SHA-1, SHA-2 and RSA, the bottleneck is the reading speed due to the network data transmitting rate. For 3DES, bottleneck is CPU, because 3DES algorithm’s workload is very high. There is no space to save energy for Bottleneck components

27. Major drawbacks of this research Workload was not representative Dedicated I/O workload. Did not consider access patterns of a single user / multiple users Test bed was not representative An emulated network environment. Only evaluated a single disk rather than parallel disks

28. Download the presentation slides http://www.slideshare.net/xqin74 Google: slideshare Xiao Qin

29. Download our paper Google: Xiao Qin X.-J. Ruan, A. Manzanares, S. Yin, M. Nijim, and X. Qin, “Can We Improve Energy Efficiency of Secure Disk Systems without Modifying Security Mechanisms?” Proc. 4th IEEE Int'l Conf. Networking, Architecture, and Storage, July 2009. http://www.eng.auburn.edu/~xqin/pubs/nas09.pdf Abstract: http:// ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber =5197358

30. Questions ?