Filters








23 Hits in 2.9 sec

Isla Vista Heap Sizing: Using Feedback to Avoid Paging

Chris Grzegorczyk, Sunil Soman, Chandra Krintz, Rich Wolski
2007 International Symposium on Code Generation and Optimization (CGO'07)  
Managed runtime environments (MREs) employ garbage collection (GC) for automatic memory management.  ...  However, GC induces pressure on the virtual memory (VM) manager, since it may touch pages that are not related to the working set of the application.  ...  The works most similar to our own are the bookmarking garbage collector [17] and specialized VM support within Linux for GC runtimes in a system called CRAMM [32] .  ... 
doi:10.1109/cgo.2007.20 dblp:conf/cgo/GrzegorczykSKW07 fatcat:szbgyudigvc7pmokclzceofugy

Application level ballooning for efficient server consolidation

Tudor-Ioan Salomie, Gustavo Alonso, Timothy Roscoe, Kevin Elphinstone
2013 Proceedings of the 8th ACM European Conference on Computer Systems - EuroSys '13  
For example, a DB would stop accepting queries, wait for existing queries to complete, shut down, and restart with a larger memory pool.  ...  In virtualization scenarios (cloud computing, server consolidation), however, static peak provisioning of RAM to applications dramatically reduces the efficiency and cost-saving benefits of virtualization  ...  Ballooning creates memory pressure within the application itself forcing it to make more well-informed decisions on buffering I/O or garbage collection than either the OS or VMM can do on its behalf.  ... 
doi:10.1145/2465351.2465384 dblp:conf/eurosys/SalomieARE13 fatcat:iueaj6vgnfh23mh23zrui4yu6q

Waste not, want not

Matthew Hertz, Stephen Kane, Elizabeth Keudel, Tongxin Bai, Chen Ding, Xiaoming Gu, Jonathan E. Bard
2011 SIGPLAN notices  
We further show that this result is not specific to any garbage collection algorithm, but that this improvement is observed for every garbage collector on which we test it.  ...  To achieve optimal performance, garbage-collected applications must balance the sizes of their heaps dynamically.  ...  Acknowledgments We are grateful to IBM Research for making the Jikes RVM system available under open source terms and for the developers of the MMTk memory management toolkit.  ... 
doi:10.1145/2076022.1993487 fatcat:zozdr6riyjg2dftr6lkt6wnoaq

Waste not, want not

Matthew Hertz, Stephen Kane, Elizabeth Keudel, Tongxin Bai, Chen Ding, Xiaoming Gu, Jonathan E. Bard
2011 Proceedings of the international symposium on Memory management - ISMM '11  
We further show that this result is not specific to any garbage collection algorithm, but that this improvement is observed for every garbage collector on which we test it.  ...  To achieve optimal performance, garbage-collected applications must balance the sizes of their heaps dynamically.  ...  Acknowledgments We are grateful to IBM Research for making the Jikes RVM system available under open source terms and for the developers of the MMTk memory management toolkit.  ... 
doi:10.1145/1993478.1993487 dblp:conf/iwmm/HertzKKBDGB11 fatcat:mdg7af3oxzckherg6odgmsjux4

Efficiently and precisely locating memory leaks and bloat

Gene Novark, Emery D. Berger, Benjamin G. Zorn
2009 Proceedings of the 2009 ACM SIGPLAN conference on Programming language design and implementation - PLDI '09  
Previous tools for diagnosing memory inefficiencies-based on garbage collection, binary rewriting, or code sampling-impose high overheads (up to 100X) or generate many false alarms.  ...  Inefficient use of memory, including leaks and bloat, remain a significant challenge for C and C++ developers.  ...  Acknowledgments The authors would like to thank Ting Yang and Scott Kaplan for valuable discussions about Hound and Linux virtual memory management, Ted Hart for his feedback during the development of  ... 
doi:10.1145/1542476.1542521 dblp:conf/pldi/NovarkBZ09 fatcat:ixnysosw5beftclkpx4fd3sdky

Efficiently and precisely locating memory leaks and bloat

Gene Novark, Emery D. Berger, Benjamin G. Zorn
2009 SIGPLAN notices  
Previous tools for diagnosing memory inefficiencies-based on garbage collection, binary rewriting, or code sampling-impose high overheads (up to 100X) or generate many false alarms.  ...  Inefficient use of memory, including leaks and bloat, remain a significant challenge for C and C++ developers.  ...  Acknowledgments The authors would like to thank Ting Yang and Scott Kaplan for valuable discussions about Hound and Linux virtual memory management, Ted Hart for his feedback during the development of  ... 
doi:10.1145/1543135.1542521 fatcat:puhyk7bug5dbhk6e4gcml3lq3q

The mapping collector

Michal Wegiel, Chandra Krintz
2008 Proceedings of the 13th international conference on Architectural support for programming languages and operating systems - ASPLOS XIII  
We implement both stop-the-world and concurrent MC in a generational garbage collection framework within the open-source HotSpot Java Virtual Machine.  ...  Parallel and concurrent garbage collectors are increasingly employed by managed runtime environments (MREs) to maintain scalability, as multi-core architectures and multi-threaded applications become pervasive  ...  Acknowledgments We thank the anonymous reviewers for providing insightful comments on this paper. This work was funded in part by NSF grants CCF-0444412, CNS-0546737, and CNS-0627183.  ... 
doi:10.1145/1346281.1346294 dblp:conf/asplos/WegielK08 fatcat:aooimfd3gffrhmtw2d4t4sh6ke

The mapping collector

Michal Wegiel, Chandra Krintz
2008 SIGPLAN notices  
We implement both stop-the-world and concurrent MC in a generational garbage collection framework within the open-source HotSpot Java Virtual Machine.  ...  Parallel and concurrent garbage collectors are increasingly employed by managed runtime environments (MREs) to maintain scalability, as multi-core architectures and multi-threaded applications become pervasive  ...  Acknowledgments We thank the anonymous reviewers for providing insightful comments on this paper. This work was funded in part by NSF grants CCF-0444412, CNS-0546737, and CNS-0627183.  ... 
doi:10.1145/1353536.1346294 fatcat:kmd6gulx4va4pjtuddugv6nd6a

The mapping collector

Michal Wegiel, Chandra Krintz
2008 ACM SIGOPS Operating Systems Review  
We implement both stop-the-world and concurrent MC in a generational garbage collection framework within the open-source HotSpot Java Virtual Machine.  ...  Parallel and concurrent garbage collectors are increasingly employed by managed runtime environments (MREs) to maintain scalability, as multi-core architectures and multi-threaded applications become pervasive  ...  Acknowledgments We thank the anonymous reviewers for providing insightful comments on this paper. This work was funded in part by NSF grants CCF-0444412, CNS-0546737, and CNS-0627183.  ... 
doi:10.1145/1353535.1346294 fatcat:yrmruk2jhfchxmudkuqveehcey

The mapping collector

Michal Wegiel, Chandra Krintz
2008 SIGARCH Computer Architecture News  
We implement both stop-the-world and concurrent MC in a generational garbage collection framework within the open-source HotSpot Java Virtual Machine.  ...  Parallel and concurrent garbage collectors are increasingly employed by managed runtime environments (MREs) to maintain scalability, as multi-core architectures and multi-threaded applications become pervasive  ...  Acknowledgments We thank the anonymous reviewers for providing insightful comments on this paper. This work was funded in part by NSF grants CCF-0444412, CNS-0546737, and CNS-0627183.  ... 
doi:10.1145/1353534.1346294 fatcat:l3miimwxojgltf52zkqstxkciq

Automatic heap sizing

Ting Yang, Matthew Hertz, Emery D. Berger, Scott F. Kaplan, J. Eliot B. Moss
2004 Proceedings of the 4th international symposium on Memory management - ISMM '04  
Heap size has a huge impact on the performance of garbage collected applications.  ...  We present an automatic heap-sizing algorithm applicable to different garbage collectors with only modest changes.  ...  Finally, we are also developing new strategies for the VMM to select allocations intelligently for each process, especially those garbage collected process that can flexibly change their footprint in response  ... 
doi:10.1145/1029873.1029881 dblp:conf/iwmm/YangHBKM04 fatcat:b67m2ju2ynesdkbxq6ydjsqyoy

Dynamic prediction of collection yield for managed runtimes

Michal Wegiel, Chandra Krintz
2009 Proceeding of the 14th international conference on Architectural support for programming languages and operating systems - ASPLOS '09  
General-purpose MREs commonly implement parallel and/or concurrent garbage collection and employ compaction to eliminate heap fragmentation.  ...  To avoid such collections, we exploit the observation that dead objects tend to cluster together and form large, never-referenced, regions in the address space that correlate well with virtual pages that  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments. This work was funded in part by NSF grants CCF-0444412, CNS-CAREER-0546737, and CNS-0627183.  ... 
doi:10.1145/1508244.1508278 dblp:conf/asplos/WegielK09 fatcat:du432k527badfenscp4nm35rpu

Dynamic prediction of collection yield for managed runtimes

Michal Wegiel, Chandra Krintz
2009 SIGPLAN notices  
General-purpose MREs commonly implement parallel and/or concurrent garbage collection and employ compaction to eliminate heap fragmentation.  ...  To avoid such collections, we exploit the observation that dead objects tend to cluster together and form large, never-referenced, regions in the address space that correlate well with virtual pages that  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments. This work was funded in part by NSF grants CCF-0444412, CNS-CAREER-0546737, and CNS-0627183.  ... 
doi:10.1145/1508284.1508278 fatcat:qf245d7vgvbfpli2u5vukmrwde

Dynamic prediction of collection yield for managed runtimes

Michal Wegiel, Chandra Krintz
2009 SIGARCH Computer Architecture News  
General-purpose MREs commonly implement parallel and/or concurrent garbage collection and employ compaction to eliminate heap fragmentation.  ...  To avoid such collections, we exploit the observation that dead objects tend to cluster together and form large, never-referenced, regions in the address space that correlate well with virtual pages that  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments. This work was funded in part by NSF grants CCF-0444412, CNS-CAREER-0546737, and CNS-0627183.  ... 
doi:10.1145/2528521.1508278 fatcat:rl7ipnx2prefbnef3tnurekb4y

Marea: An Efficient Application-Level Object Graph Swapper

Mariano Martinez Peck, Noury Bouraqadi, Marcus Denker, Stéphane Ducasse, Luc Fabresse
2013 Journal of Object Technology  
Problems appear when objects are unused but cannot be garbage-collected because they are still referenced from other objects.  ...  We claim that relying on the operating system's (OS) virtual memory is not always enough since it cannot take into account the domain and structure of applications.  ...  Acknowledgments We thank Igor Stasenko for his help with the discussions and development of Marea, Martin Dias for his work on Fuel serializer and Esteban Lorenzano for his help with the experiments and  ... 
doi:10.5381/jot.2013.12.1.a2 fatcat:2hb2piaumffprpienbokn5tnzm
« Previous Showing results 1 — 15 out of 23 results