Processor hardware counter statistics as a first-class system resource

ABSTRACT

Today's processors provide a rich source of statistical information on program execution characteristics through hardware counters. However, traditionally, operating system (OS) support for and utilization of the hardware counter statistics has been limited and ad hoc. In this paper, we make the case for direct OS management of hardware counter statistics. First, we show the utility of processor counter statistics in CPU scheduling (for improved performance and fairness) and in online workload modeling, both of which require online continuous statistics (as opposed to ad hoc infrequent uses). Second, we show that simultaneous system and user use of hardware counters is possible via time-division multiplexing. Finally, we highlight potential counter misuses to indicate that the OS should address potential security issues in utilizing processor counter statistics.

REFERENCES

• 1: Jennifer M. Anderson , Lance M. Berc , Jeffrey Dean , Sanjay Ghemawat , Monika R. Henzinger , Shun-Tak A. Leung , Richard L. Sites , Mark T. Vandevoorde , Carl A. Waldspurger , William E. Weihl, Continuous profiling: where have all the cycles gone?, ACM Transactions on Computer Systems (TOCS), v.15 n.4, p.357-390, Nov. 1997 [doi>10.1145/265924.265925]
• 2: [2] C.D. Antonopoulos, D.S. Nikolopoulos, and T.S. Papatheodorou. Scheduling algorithms with bus bandwidth considerations for SMPs. In Proc. of the 32nd Int'l Conf. on Parallel Processing, October 2003.
• 3: [3] M. Arlitt and T. Jin. Workload Characterization of the 1998 World Cup Web Site. Technical Report HPL-1999-35, HP Laboratories Palo Alto, 1999.
• 4: Paul Barham , Austin Donnelly , Rebecca Isaacs , Richard Mortier, Using magpie for request extraction and workload modelling, Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation, p.18-18, December 06-08, 2004, San Francisco, CA
• 5: S. Browne , J. Dongarra , N. Garner , K. London , P. Mucci, A scalable cross-platform infrastructure for application performance tuning using hardware counters, Proceedings of the 2000 ACM/IEEE conference on Supercomputing (CDROM), p.42-es, November 04-10, 2000, Dallas, Texas, United States
• 6: James R. Bulpin , Ian A. Pratt, Hyper-threading aware process scheduling heuristics, Proceedings of the annual conference on USENIX Annual Technical Conference, p.27-27, April 10-15, 2005, Anaheim, CA
• 7: Ira Cohen , Moises Goldszmidt , Terence Kelly , Julie Symons , Jeffrey S. Chase, Correlating instrumentation data to system states: a building block for automated diagnosis and control, Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation, p.16-16, December 06-08, 2004, San Francisco, CA
• 8: Matthew Curtis-Maury , James Dzierwa , Christos D. Antonopoulos , Dimitrios S. Nikolopoulos, Online power-performance adaptation of multithreaded programs using hardware event-based prediction, Proceedings of the 20th annual international conference on Supercomputing, June 28-July 01, 2006, Cairns, Queensland, Australia [doi>10.1145/1183401.1183426]
• 9: Evelyn Duesterwald , Calin Cascaval , Sandhya Dwarkadas, Characterizing and Predicting Program Behavior and its Variability, Proceedings of the 12th International Conference on Parallel Architectures and Compilation Techniques, p.220, September 27-October 01, 2003
• 10: Alexandra Fedorova , Margo Seltzer , Christoper Small , Daniel Nussbaum, Performance of multithreaded chip multiprocessors and implications for operating system design, Proceedings of the annual conference on USENIX Annual Technical Conference, p.26-26, April 10-15, 2005, Anaheim, CA
• 11: Alexandra Fedorova , Christopher Small , Daniel Nussbaum , Margo Seltzer, Chip multithreading systems need a new operating system scheduler, Proceedings of the 11th workshop on ACM SIGOPS European workshop, September 19-22, 2004, Leuven, Belgium [doi>10.1145/1133572.1133597]
• 12: [12] J. Kelsey, B. Schneier, D. Wagner, and C. Hall. Side channel cryptanalysis of product ciphers. Journal of Computer Security, 8(2-3):141-158, 2000.
• 13: Butler W. Lampson, A note on the confinement problem, Communications of the ACM, v.16 n.10, p.613-615, Oct. 1973 [doi>10.1145/362375.362389]
• 14: [14] OpenSSL: The open source toolkit for SSL/TLS. http://www.openssl.org.
• 15: [15] S. Parekh, S. Eggers, and H. Levy. Thread-sensitive scheduling for SMT processors. Technical report, Department of Computer Science and Engineering, University of Washington, May 2000.
• 16: [16] C. Percival. Cache missing for fun and profit. In BSDCan 2005, Ottawa, Canada, May 2005. http://www .daemonology.net/papers/htt.pdf.
• 17: [17] M. Pettersson. Linux performance counters driver. http://sourceforge.net/projects/perfctr/.
• 18: Allan Snavely , Dean M. Tullsen, Symbiotic jobscheduling for a simultaneous multithreaded processor, Proceedings of the ninth international conference on Architectural support for programming languages and operating systems, p.234-244, November 2000, Cambridge, Massachusetts, United States
• 19: Peter F. Sweeney , Matthias Hauswirth , Brendon Cahoon , Perry Cheng , Amer Diwan , David Grove , Michael Hind, Using hardware performance monitors to understand the behavior of java applications, Proceedings of the 3rd conference on Virtual Machine Research And Technology Symposium, p.5-5, May 06-07, 2004, San Jose, California
• 20: [20] Intel VTune™ performance analyzers. http://www .intel.com/software/products/vtune.

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.1 Process Management

Additional Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.6 Security and Protection
          Subjects: Information flow controls
      D.4.8 Performance
          Subjects: Operational analysis

General Terms:
Design, Management, Security