Cliff Click
ABSTRACT
Modern transactional response-time sensitive applications have run into practical limits on the size of garbage collected heaps. The heap can only grow until GC pauses exceed the response-time limits. Sustainable, scalable concurrent collection has become a feature worth paying for.Azul Systems has built a custom system (CPU, chip, board, and OS) specifically to run garbage collected virtual machines. The custom CPU includes a read barrier instruction. The read barrier enables a highly concurrent (no stop-the-world phases), parallel and compacting GC algorithm. The Pauseless algorithm is designed for uninterrupted application execution and consistent mutator throughput in every GC phase.Beyond the basic requirement of collecting faster than the allocation rate, the Pauseless collector is never in a "rush" to complete any GC phase. No phase places an undue burden on the mutators nor do phases race to complete before the mutators produce more work. Portions of the Pauseless algorithm also feature a "self-healing" behavior which limits mutator overhead and reduces mutator sensitivity to the current GC state.We present the Pauseless GC algorithm, the supporting hardware features that enable it, and data on the overhead, efficiency, and pause times when running a sustained workload.
- Agesen, O. GC Points in a Threaded Environment. SMLI TR-98-70. Sun Microsystems, Palo Alto, CA. December 1998. Google Scholar
Digital Library
- Appel, A., Ellis, J., Li, K., Real-time concurrent collection on stock multiprocessors. In 1988 Conference on Programming Language Design and Implementation (PLDI), June 1988. Google ScholarDigital Library
- Appel, A., Li, K., Virtual Memory Primitives for User Programs. In 1991 Conference on Architectural Support for Programming Languages and Operating System, April 1991. Google ScholarDigital Library
- Bacon, D., Cheng, P., Rajan, V. The Metronome: A simpler approach to garbage collection in real-time systems. In Proceedings of the OTM Workshops: Workshop on Java Technologies for Real-Time and Embedded Systems, Catania, Sicily, Nov. 2003.Google ScholarCross Ref
- Baker, H., List processing in real time on a serial computer, Communications of the ACM, Vol. 21, 4, (April 1978),.280--294 Google ScholarDigital Library
- Barth, J. Shifting garbage collection overhead to compile time. Communications of the ACM, Vol. 20, 7 (July 1977), 513--518 Google ScholarDigital Library
- BEA Systems. 2003. BEA JRockit: Java for the Enterprise. White paper. BEA Systems, San Jose, CA.Google Scholar
- Blackburn, S., McKinley, K., In or Out? Putting Write Barriers in Their Place. In Proceedings of the 2002 International Symposium on Memory Management, Berlin, Germany, 2002. Google ScholarDigital Library
- Blackburn, S., Hosking, A., Barriers: Friend or Foe? In Proceedings of the 2004 International Symposium on Memory Management, Vancouver, Canada, 2004. Google ScholarDigital Library
- Brooks, R. Trading data space for reduced time and code space in real-time garbage collection on stock hardware. In 1984 ACM Symposium on Lisp and Functional Programming. (Aug. 1984) 256--262 Google ScholarDigital Library
- Cheney, C. A Nonrecursive List Compacting Algorithm. Communications of the ACM, Vol. 13, 11 (Nov. 1970), 677--678 Google ScholarDigital Library
- Cheng, P., Blelloch, G., A parallel, real-Time garbage collection. In Conference on Programming Languages Design and Implementation (PLDI '01). Snowbird, Utah, June 2001 Google ScholarDigital Library
- Collins, G., A method for overlapping and erasure of lists. Communications of the ACM, Vol. 3, 12 (Nov. 1960), 655--657 Google ScholarDigital Library
- Detlefs, D., Flood, C., Heller, S., Printezis, T. Garbage-first garbage collection. In Proceedings of the 2004 International Symposium on Memory Management, Vancouver, Canada, 2004 Google ScholarDigital Library
- Deutcsh, P., Bobrow, D. An Efficient, Incremental, Automatic Garbage Collector. Communications of the ACM, Vol. 19, 9 (Sept. 1976), 522--527 Google ScholarDigital Library
- Fenichel, R., Yochelson, J. A LISP Garbage-Collector for Virtual Memory Systems. Communications of the ACM, Vol. 12, 11 (Nov. 1969), 611--612. Google ScholarDigital Library
- Flood, C., Detlefs, D., Shavit, N., Zhang, C. Parallel Garbage Collection for Shared Memory Multiprocessors. In 2001 USENIX Java Virtual Machine Research and Technology Symposium (JVM '01). Monterey, CA, April 2001 Google ScholarDigital Library
- Goa, H., Nilsen, K. The real-time behavior of dynamic memory management in C++. In Proceedings of the Real-Time Technology and Applications Symposium. Chicago, IL, 1995 Google ScholarDigital Library
- Gosling, J., Bollela, G. The Real-Time Specification for Java. Addison-Wesley, Boston MA, 2000. Google ScholarDigital Library
- Heil, T., Smith, J. Concurrent garbage collection using hardware-assisted profiling. In Proceedings of the 2nd International Symposium on Memory Management, Minneapolis, MN, 2000 Google ScholarDigital Library
- Hosking, A., Moss, E., Stefanovic, D., A comparative performance evaluation of write barrier implementations. In Conference on Object Oriented Programming Systems, Languages, and Applications (OOPSLA '92). Vancouver, Canada, Oct. 1992 Google ScholarDigital Library
- McCarthy, J., Recursive functions of symbolic expressions and their computation by machine. Communications of the ACM, Vol. 3, 4 (April 1960), 184--195 Google ScholarDigital Library
- Moon, D. Garbage Collection in a Large LISP System. 1984 ACM Symposium on LISP and Functional Programming. (Aug. 1984) 235--246 Google ScholarDigital Library
- Nilsen, K., Schmidt, W. Cost-effective object space management for hardware-assisted real-time garbage collection. ACM Letters on Programming Languages and Systems (LOPLAS), Vol. 1, 4 (Dec. 1992) Google ScholarDigital Library
- Ossia, Y., Ben-Yitzhak, O., Segal, M., Mostly concurrent compaction for mark-sweep GC. In Proceedings of the 2004 International Symposium on Memory Management, Vancouver, Canada, 2004. Google ScholarDigital Library
- Steele, G. Multiprocessing compactifying garbage collection. Communications of the ACM, Vol. 18, 9 (Sept. 1975), 495--508 Google ScholarDigital Library
- Suganuma, T., Ogasawara, T., Takeuchi, M., Yasue, T., Kawahito, M., Ishizaki, K., Komatsd, H., and Nakatani, T. Overview of the IBM Java Just-in-Time Compiler, IBM Systems Journal, 39(1), 2000. Google ScholarDigital Library
- Sun Microsystems. 2001. The Java HotSpot virtual machine. White paper. Sun Microsystems, Santa Clara, CA.Google Scholar
- Williams, I., Wolczko, M. An Object-Based Memory Architecture. In Implementing Persistent Object Bases: Proceedings of the Fourth International Workshop on Persistent Object Systems, pages 114-130. Morgan Kaufmann Publishers, Inc., 1991.Google Scholar
- Wilson, P. Uniprocessor Garbage Collection Techniques. In 1992 Proceedings of the International Workshop on Memory Management (IWMM 92). Saint-Malo (France), 1992 Google ScholarDigital Library
- Wilson, P., Johnstone, M., Neely, M., Boles, D., Dynamic Storage Allocation: A Survey and Critical Review. In Proceedings of the International Workshop on Memory Management (IWMM 95), 1995 Google ScholarDigital Library
Index Terms
- The pauseless GC algorithm
Recommendations
Controlling garbage collection and heap growth to reduce the execution time of Java applications
In systems that support garbage collection, a tension exists between collecting garbage too frequently and not collecting it frequently enough. Garbage collection that occurs too frequently may introduce unnecessary overheads at the risk of not ...
Towards an Efficient Pauseless Java GC with Selective HTM-Based Access Barriers
ManLang 2017: Proceedings of the 14th International Conference on Managed Languages and RuntimesThe garbage collector (GC) is a critical component of any managed runtime environment (MRE), such as the Java virtual machine. While the main goal of the GC is to simplify and automate memory management, it may have a negative impact on the application ...
Yama: A Scalable Generational Garbage Collector for Java in Multiprocessor Systems
The current state-of-the-art generational garbage collector pauses all the program threads when it performs young and old generation garbage collection. As the number of program threads increases, the delay due to garbage collection also increases, thus ...
Comments