Better I/O through byte-addressable, persistent memory

ABSTRACT

Modern computer systems have been built around the assumption that persistent storage is accessed via a slow, block-based interface. However, new byte-addressable, persistent memory technologies such as phase change memory (PCM) offer fast, fine-grained access to persistent storage.

In this paper, we present a file system and a hardware architecture that are designed around the properties of persistent, byteaddressable memory. Our file system, BPFS, uses a new technique called short-circuit shadow paging to provide atomic, fine-grained updates to persistent storage. As a result, BPFS provides strong reliability guarantees and offers better performance than traditional file systems, even when both are run on top of byte-addressable, persistent memory. Our hardware architecture enforces atomicity and ordering guarantees required by BPFS while still providing the performance benefits of the L1 and L2 caches.

Since these memory technologies are not yet widely available, we evaluate BPFS on DRAM against NTFS on both a RAM disk and a traditional disk. Then, we use microarchitectural simulations to estimate the performance of BPFS on PCM. Despite providing strong safety and consistency guarantees, BPFS on DRAM is typically twice as fast as NTFS on a RAM disk and 4-10 times faster than NTFS on disk. We also show that BPFS on PCM should be significantly faster than a traditional disk-based file system.

REFERENCES

• 1: Process integration, devices, and structures. In International Technology Roadmap for Semiconductors (2007).
• 2: BAILEY, D. ET AL. NAS parallel benchmarks. Tech. Rep. RNR-94-007, NASA Ames Research Center, 1994.
• 3: BEDESCHI, F. ET AL. An 8Mb demonstrator for high-density 1.8V phase-change memories. In VLSI Circuits (2004).
• 4: CHEN, P.M., NG, W.T., CHANDRA, S., AYCOCK, C., RAJAMANI, G., AND LOWELL, D. The Rio file cache: Surviving operating system crashes. In Architectural Support for Programming Languages and Operating Systems (ASPLOS) (1996).
• 5: FRASER, K., AND HARRIS, T. Concurrent programming without locks. Transactions on Computer Systems (TOCS) 25, 2 (2007).
• 6: HAGMANN, R. Reimplementing the Cedar file system using logging and group commit. In Symposium on Operating Systems Principles (SOSP) (1987).
• 7: HITZ, D., LAU, J., AND MALCOLM, M. File system design for an NFS file server appliance. In USENIX Winter Technical Conference (1994).
• 8: KATCHER, J. PostMark: A new file system benchmark. Tech. Rep. TR3022, Network Appliance, 1997.
• 9: LEE, B., IPEK, E., MUTLU, O., AND BURGER, D. Architecting phase change memory as a scalable DRAM alternative. In International Symposium on Computer Architecture (ISCA) (2009).
• 10: LOWELL, D.E., AND CHEN, P.M. Free transactions with Rio Vista. In Symposium on Operating Systems Principles (SOSP) (1997).
• 11: MICHELONI, R., MARELLI, A., AND RAVASIO, R. BCH hardware implementation in NAND Flash memories. In Error Correction Codes in Non-Volatile Memories. Springer Netherlands, 2008.
• 12: MOGUL, J.C., ARGOLLO, E., SHAH, M., AND FARABOSCHI, P. Operating system support for NVM+DRAM hybrid main memory. In Hot Topics in Operating Systems (HotOS) (2009).
• 13: MOHAN, C. Repeating history beyond ARIES. In Very Large Data Bases (VLDB) (1999).
• 14: MOHAN, C., HADERLE, D., LINDSAY, B., PIRAHESH, H., AND SCHWARZ, P. ARIES: A transaction recovery method supporting fine-granularity locking and partial rollbacks using write-ahead logging. Transactions on Database Systems (TODS) 17, 1 (1992).
• 15: NIGHTINGALE, E.B., VEERARAGHAVAN, K., CHEN, P.M., AND FLINN, J. Rethink the sync. In Operating Systems Design and Implementation (OSDI) (2006).
• 16: PANT, M.D., PANT, P., AND WILLS, D.S. On-chip decoupling capacitor optimization using architectural level prediction. Transactions on Very Large Scale Integration Systems (TVLSI) 10, 3 (2002).
• 17: PRABHAKARAN, V., BAIRAVASUNDARAM, L.N., AGRAWAL, N., GUNAWI, H.S., ARPACI-DUSSEAU, A.C., AND ARPACI-DUSSEAU, R.H. IRON file systems. In Symposium on Operating Systems Principles (SOSP) (2005).
• 18: QURESHI, M.K., SRINIVASAN, V., AND RIVERS, J.A. Scalable high performance main memory system using phase-change memory technology. In International Symposium on Computer Architecture (ISCA) (2009).
• 19: RAOUX, S. ET AL. Phase-change random access memory: A scalable technology. IBM Journal of Research and Development 52, 4 (2008).
• 20: RENAU, J., FRAGUELA, B., TUCK, J., LIU, W., PRVULOVIC, M., CEZE, L., SARANGI, S., SACK, P., STRAUSS, K., AND MONTESINOS, P. SESC simulator, 2005. htp:/sec.sourceforge.nt.
• 21: ROSENBLUM, M., AND OUSTERHOUT, J.K. The design and implementation of a log-structured file system. Transactions on Computer Systems (TOCS) 10, 1 (1992).
• 22: SMITH, L., ANDERSON, R., FOREHAND, D., PELC, T., AND ROY, T. Power distribution system design methodology and capacitor selection for modern CMOS technology. IEEE Transactions on Advanced Packaging 22, 3 (1999).
• 23: SUN MICROSYSTEMS. ZFS. htp:/w.opensolaris.org/oscomunity/zfs/.
• 24: WANG, A.-I. A., REIHER, P., POPEK, G.J., AND KUENNING, G.H. Conquest: Better performance through a disk/persistent-RAM hybrid file system. In USENIX Technical Conference (2002).
• 25: WOODHOUSE, D. JFFS: The journalling flash file system. In Ottawa Linux Symposium (2001), RedHat Inc.
• 26: WU, M., AND ZWAENEPOEL, W. eNVy: A non-volatile, main memory storage system. In Architectural Support for Programming Languages and Operating Systems (ASPLOS) (1994).
• 27: ZHOU, P., ZHAO, B., YANG, J., AND ZHANG, Y. A durable and energy efficient main memory using phase change memory technology. In International Symposium on Computer Architecture (ISCA) (2009).

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.3 File Systems Management

Additional Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.5 Reliability

General Terms:
Design, Performance, Reliability

Keywords:
file systems, performance, phase change memory