2026-08-07T04:53:40Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:19505 2024-03-06T11:04:10Z ddc:004 open_access

Nova: Safe Off-Heap Memory Allocation and Reclamation Fakhoury, Ramy Braginsky, Anastasia Keidar, Idit Zuriel, Yoav memory reclamation concurrency performance off-heap allocation In recent years, we begin to see Java-based systems embrace off-heap allocation for their big data demands. As of today, these system rely on simple ad-hoc garbage-collection solutions, which restrict the usage of off-heap data. This paper introduces the abstraction of safe off-heap memory allocation and reclamation (SOMAR), a thread-safe memory allocation and reclamation scheme for off-heap data in otherwise managed environments. SOMAR allows multi-threaded Java programs to use off-heap memory seamlessly. To realize this abstraction, we present Nova, Novel Off-heap Versioned Allocator, a lock-free SOMAR implementation. Our experiments show that Nova can be used to store off-heap data in Java data structures with better performance than ones managed by Java’s automatic GC. We further integrate Nova into the open-source Oak concurrent map library, which allows Oak to reclaim keys while the data structure is being accessed. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Ramy Fakhoury and Anastasia Braginsky and Idit Keidar and Yoav Zuriel 2024 Is Part Of LIPIcs, Volume 286, 27th International Conference on Principles of Distributed Systems (OPODIS 2023) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.OPODIS.2023.15 urn:nbn:de:0030-drops-195052 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.OPODIS.2023.15 eng https://creativecommons.org/licenses/by/4.0/legalcode