Abstract
Recently, power has emerged as a critical factor in designing components of storage systems, especially for power-hungry data centers. While there is some research into power-aware storage stack components, there are no systematic studies evaluating each component's impact separately. Various factors like workloads, hardware configurations, and software configurations impact the performance and energy efficiency of the system. This article evaluates the file system's impact on energy consumption and performance. We studied several popular Linux file systems, with various mount and format options, using the FileBench workload generator to emulate four server workloads: Web, database, mail, and fileserver, on two different hardware configurations. The file system design, implementation, and available features have a significant effect on CPU/disk utilization, and hence on performance and power. We discovered that default file system options are often suboptimal, and even poor. In this article we show that a careful matching of expected workloads and hardware configuration to a single software configuration—the file system—can improve power-performance efficiency by a factor ranging from 1.05 to 9.4 times.
- }}Allalouf, M., Arbitman, Y., Factor, M., Kat, R. I., Meth, K., and Naor, D. 2009. Storage modeling for power estimation. In Proceedings of the Israeli Experimental Systems Conference (SYSTOR'09). ACM, New York. Google Scholar
Digital Library
- }}Almeida, J., Almeida, V., and Yates, D. 1996. Measuring the behavior of a world-wide web server. Tech. rep., Boston University, Boston, MA. Google Scholar
Digital Library
- }}Andersen, D. G., Franklin, J., Kaminsky, M., Phanishayee, A., Tan, L., and Vasudevan, V. 2009. FAWN: A fast array of wimpy nodes. In Proceedings of the 22nd ACM Symposium on Operating Systems Principles (SOSP'09). ACM, 1--14. Google Scholar
Digital Library
- }}Appleton, R. 1997. A non-technical look inside the ext2 file system. Linux J. Google Scholar
Digital Library
- }}Bisson, T., Brandt, S., and Long, D. 2007. A hybrid disk-aware spin-down algorithm with I/O subsystem support. In Proceedings of the IEEE Performance, Computing, and Communications Conference. IEEE, Los Alamitos, CA.Google Scholar
- }}Bryant, R., Forester, R., and Hawkes, J. 2002. Filesystem performance and scalability in Linux 2.4.17. In Proceedings of the Annual USENIX Technical Conference, FREENIX Track. USENIX Association, Monterey, CA, 259--274. Google Scholar
Digital Library
- }}Capps, D. 2008. IOzone Filesystem Benchmark. www.iozone.org/.Google Scholar
- }}Carrera, E., Pinheiro, E., and Bianchini, R. 2003. Conserving disk energy in network servers. In Proceedings of the 17th International Conference on Supercomputing. Google Scholar
Digital Library
- }}Colarelli, D. and Grunwald, D. 2002. Massive arrays of idle disks for storage archives. In Proceedings of the ACM/IEEE Conference on Supercomputing. 1--11. Google Scholar
Digital Library
- }}Craven, M. and Amer, A. 2005. Predictive reduction of power and latency (PuRPLe). In Proceedings of the 22nd IEEE/13th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST'05)., IEEE, Los Alamitos, CA, 237--244. Google Scholar
Digital Library
- }}Deng, Y. and Helian, F. 2008. EED: Energy efficient disk drive architecture. Inform. Sciences. Google Scholar
Digital Library
- }}Douglis, F., Krishnan, P., and Marsh, B. 1994. Thwarting the power-hungry disk. In Proceedings of the Winter USENIX Conference. 293--306. Google Scholar
Digital Library
- }}Electronic Educational Devices. Watts up? PRO ES power meter. www.wattsupmeters.com/secure/products.php.Google Scholar
- }}Elnozahy, E. N., Kistler, M., and Rajamony, R. 2002. Energy-efficient server clusters. In Proceedings of the 2nd Workshop on Power-Aware Computing Systems. 179--196. Google Scholar
Digital Library
- }}Ermolinskiy, A. and Tewari, R. 2009. C2Cfs: A collective caching architecture for distributed file access. Tech. rep. UCB/EECS-2009-40, University of California, Berkeley.Google Scholar
- }}Essary, D. and Amer, A. 2008. Predictive data grouping: Defining the bounds of energy and latency reduction through predictive data grouping and replication. ACM Trans. Storage 4, 1, 1--23. Google Scholar
Digital Library
- }}Gulati, A., Naik, M., and Tewari, R. 2007. Nache: Design and implementation of a caching proxy for NFSv4. In Proceedings of the 5th USENIX Conference on File and Storage Technologies (FAST'07). USENIX Association, Monterey, CA, 199--214. Google Scholar
Digital Library
- }}Gurumurthi, S., Zhang, J., Sivasubramaniam, A., Kandemir, M., Franke, H., Vijaykrishnan, N., and Irwin, M. J. 2003. Interplay of energy and performance for disk arrays running transaction processing workloads. In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, IEEE, Los Alamitos, CA, 123--132. Google Scholar
Digital Library
- }}Gurumurthi, S., Sivasubramaniam, A., Kandemir, M., and Franke, H. 2003. DRPM: Dynamic speed control for power management in server class disks. In Proceedings of the 30th Annual International Symposium on Computer Architecture. 169--181. Google Scholar
Digital Library
- }}Huang, H., Hung, W., and Shin, K. 2005. FS2: Dynamic data replication in free disk space for improving disk performance and energy consumption. In Proceedings of the 20th ACM Symposium on Operating Systems Principles (SOSP'05). ACM, New York, 263--276. Google Scholar
Digital Library
- }}Joukov, N. and Sipek, J. 2008. GreenFS: Making enterprise computers greener by protecting them better. In Proceedings of the 3rd ACM SIGOPS/EuroSys European Conference on Computer Systems (EuroSys'08). ACM, New York. Google Scholar
Digital Library
- }}Joukov, N., Traeger, A., Iyer, R., Wright, C. P., and Zadok, E. 2006. Operating system profiling via latency analysis. In Proceedings of the 7th Symposium on Operating Systems Design and Implementation (OSDI'06). ACM, 89--102. Google Scholar
Digital Library
- }}Katcher, J. 1997. PostMark: A new filesystem benchmark. Tech. rep. TR3022, Network Appliance. www.netapp.com/tech_library/3022.html.Google Scholar
- }}Kothiyal, R., Tarasov, V., Sehgal, P., and Zadok, E. 2009. Energy and performance evaluation of lossless file data compression on server systems. In Proceedings of the Israeli Experimental Systems Conference (ACM SYSTOR'09). ACM, New York. Google Scholar
Digital Library
- }}Leverich, J. and Kozyrakis, C. 2009. On the energy (in)efficiency of hadoop clusters. In Proceedings of the Workshop on Power Aware Computing and Systems (HotPower'09). ACM, New York.Google Scholar
- }}Li, D. 2006. High performance energy efficient file storage system. Ph.D. dissertation, Computer Science Department, University of Nebraska, Lincoln. Google Scholar
Digital Library
- }}Li, K., Kumpf, R., Horton, P., and Anderson, T. 1994. A quantitative analysis of disk drive power management in portable computers. In Proceedings of the Winter USENIX Conference. 279--291. Google Scholar
Digital Library
- }}Manzanares, A., Bellam, K., and Qin, X. 2008. A prefetching scheme for energy conservation in parallel disk systems. In Proceedings of the IEEE International Symposium on Parallel and Distributed Processing (IPDPS'08). IEEE, Los Alamitos, CA, 1--5.Google Scholar
- }}McDougall, R., Mauro, J., and Gregg, B. 2007. Solaris Performance and Tools. Prentice Hall, Englewood Cliffs, NJ.Google Scholar
- }}Narayanan, D., Donnelly, A., and Rowstron, A. 2008. Write off-loading: Practical power management for enterprise storage. In Proceedings of the 6th USENIX Conference on File and Storage Technologies (FAST'08). Google Scholar
Digital Library
- }}Nightingale, E. B. and Flinn, J. 2004. Energy-efficiency and storage flexibility in the blue file system. In Proceedings of the 6th Symposium on Operating Systems Design and Implementation (OSDI'04). ACM SIGOPS, 363--378. Google Scholar
Digital Library
- }}OSDIR mail archive. Message about XFS block size limit. http://osdir.com/ml/filesystems.xfs.general/200206/msg00071.html.Google Scholar
- }}Papathanasiou, A. E. and Scott, M. L. 2002. Increasing disk burstiness for energy efficiency. Tech. rep. 792, University of Rochester. Google Scholar
Digital Library
- }}Pinheiro, E. and Bianchini, R. 2004. Energy conservation techniques for disk array-based servers. In Proceedings of the 18th International Conference on Supercomputing (ICS'04). 68--78. Google Scholar
Digital Library
- }}Pinheiro, E., Bianchini, R., Carrera, E., and Heath, T. 2001. Load balancing and unbalancing for power and performance in cluster-based systems. In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques.Google Scholar
- }}Reiser, H. ReiserFS v.3 Whitepaper. http://web.archive.org/web/20031015041320/http://namesys.com/.Google Scholar
- }}Rivoire, S., Shah, M. A., Ranganathan, P., and Kozyrakis, C. 2007. JouleSort: A balanced energy-efficiency benchmark. In Proceedings of the ACM SIGMOD International Conference on Management of Data. ACM, New York. Google Scholar
Digital Library
- }}Seltzer, M. I. 1993. Transaction support in a log-structured file system. In Proceedings of the 9th International Conference on Data Engineering. 503--510. Google Scholar
Digital Library
- }}SGI. XFS Filesystem Structure. http://oss.sgi.com/projects/xfs/papers/xfsfilesystemstructure.pdf.Google Scholar
- }}Solaris Internals Wiki 2008. FileBench. www.solarisinternals.com/wiki/index.php/FileBench.Google Scholar
- }}SPEC. 2005. SPECweb99. www.spec.org/web99.Google Scholar
- }}SPEC. 2008a. SPECpower ssj2008 v1.01. www.spec.org/power_ssj2008/.Google Scholar
- }}SPEC. 2008b. SPECsfs2008. www.spec.org/sfs2008.Google Scholar
- }}The Standard Performance Evaluation Corporation. 2004. SPEC HPC Suite. www.spec.org/hpc2002/.Google Scholar
- }}Tweedie, S. 2000. Ext3, journaling filesystem. In Proceedings of the Ottawa Linux Symposium. http://olstrans.sourceforge.net/release/OLS2000-ext3/OLS2000-ext3.html.Google Scholar
- }}U.S. EPA. 2007. Report to Congress on Server and Data Center Energy Efficiency. Public Law 109--431.Google Scholar
- }}Wang, J., Zhu, H., and Li, D. 2008. eRAID: Conserving energy in conventional disk-based RAID system. IEEE Trans.Comput, 57, 3, 359--374. Google Scholar
Digital Library
- }}Washburn, D. 2008. More energy is consumed outside of the data center. www.forrester.com/Role/Research/Workbook/0,9126,47980,00.html.Google Scholar
- }}Weiser, M., Welch, B., Demers, A., and Shenker, S. 1994. Scheduling for reduced CPU energy. In Proceedings of the 1st USENIX Conference on Operating Systems Design and Implementation. Google Scholar
Digital Library
- }}Wikipedia. Ext3. http://en.wikipedia.org/wiki/Ext3.Google Scholar
- }}Wright, C. P., Joukov, N., Kulkarni, D., Miretskiy, Y., and Zadok, E. 2005. Auto-pilot: A platform for system software benchmarking. In Proceedings of the Annual USENIX Technical Conference, FREENIX Track. USENIX Association, Monterey, CA, 175--187. Google Scholar
Digital Library
- }}Zhu, Q., David, F. M., Devaraj, C. F., Li, Z., Zhou, Y., and Cao, P. 2004. Reducing energy consumption of disk storage using power-aware cache management. In Proceedings of the 10th International Symposium on High-Performance Computer Architecture. 118--129. Google Scholar
Digital Library
Index Terms
Optimizing energy and performance for server-class file system workloads
Recommendations
A multiple-file write scheme for improving write performance of small files in Fast File System
Fast File System (FFS) stores files to disk in separate disk writes, each of which incurs a disk positioning (seek + rotation) limiting the write performance for small files. We propose a new scheme called co-writing to accelerate small file writes in ...
A Novel Reordering Write Buffer to Improve Write Performance of Log-Structured File Systems
Abstract--This paper presents a novel reordering write buffer which improves the performance of Log-structured File Systems (LFS). While LFS has a good write performance, high garbage-collection overhead degrades its performance under high disk space ...
Evaluating performance and energy in file system server workloads
FAST'10: Proceedings of the 8th USENIX conference on File and storage technologiesRecently, power has emerged as a critical factor in designing components of storage systems, especially for power-hungry data centers. While there is some research into power-aware storage stack components, there are no systematic studies evaluating ...






Comments