{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T15:05:33Z","timestamp":1783955133419,"version":"3.55.0"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2026,7,13]]},"abstract":"<jats:p>Increasing dataset sizes require larger application heaps. With recent technology limitations in DRAM scaling, modern datacenters resort to using the virtual memory mechanisms, i.e., the swapper (swap), to transparently extend application heaps over fast, block storage, such as NVMe SSDs or compressed DRAM. At the same time, larger heaps incur increased TLB miss and page fault handling CPU costs, necessitating the use of hugepages for their reduction, now viable given the advent of lower latency and higher throughput storage devices.<\/jats:p>\n                  <jats:p>However, the use of Transparent Hugepages (THP) combined with memory offloading in Linux currently has significant limitations. Hugepage utilization behaviour is overly aggressive in committing memory, and too coarse-grained for memory offloading purposes. Additionally, hugepage promotions lack the responsiveness and concurrency necessary to provide timely hugepage benefits to offloaded applications.<\/jats:p>\n                  <jats:p>To address these issues, we design xHeap, an alternative file-backed mmio path for the Linux kernel, which (a) decouples the use of memory for device-backed heaps from other functions in the kernel, (b) transparently supports regular pages and hugepages at fine granularity, and (c) provides concurrent, asynchronous promotions to adapt to runtime application behaviour.<\/jats:p>\n                  <jats:p>We implement xHeap as a loadable module in Linux to minimize kernel modifications, maintaining complete interoperability with the kernel memory management subsystem, and evaluate it with a variety of workloads. We find that xHeap reduces dTLB miss cycles by up to 15\u00d7, and improves performance by up to 76%, when offloading 15-25% of application memory, compared to swap with THP.<\/jats:p>","DOI":"10.1145\/3830422.3830432","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:20:01Z","timestamp":1783952401000},"page":"96-104","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<i>xHeap<\/i>\n                    : Transparent Hugepage Optimizations forMemory Offloading"],"prefix":"10.1145","volume":"60","author":[{"given":"Ioannis","family":"Malliotakis","sequence":"first","affiliation":[{"name":"FORTH-ICS,  , Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasios","family":"Papagiannis","sequence":"additional","affiliation":[{"name":"Isovalent,  , Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Marazakis","sequence":"additional","affiliation":[{"name":"FORTH-ICS,  , Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelos","family":"Bilas","sequence":"additional","affiliation":[{"name":"FORTH-ICS,  , Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Aorus gen5 12000 ssd 2tb specification. https:\/\/www.gigabyte.com\/S SD\/AORUS-Gen5-12000-SSD-2TB\/sp#sp."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304061"},{"key":"e_1_2_1_3_1","unstructured":"Aden Yi Wang. KDD Cup 2012 Track 2. https:\/\/kaggle.com\/competi tions\/kddcup2012-track2."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037706"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387522"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414630"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818973"},{"key":"e_1_2_1_8_1","first-page":"211","volume-title":"Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, NSDI'11","author":"Badam Anirudh","year":"2011","unstructured":"Anirudh Badam and Vivek S. Pai. Ssdalloc: Hybrid ssd\/ram memory management made easy. In Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, NSDI'11, page 211-224, USA, 2011. USENIX Association."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2012.87"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3154601.3154606"},{"key":"e_1_2_1_12_1","unstructured":"Corbet Jonathan. Memory Compaction. [Online]."},{"key":"e_1_2_1_13_1","volume-title":"Web graph release cc-main-2024-25-dec-jan-feb. https:\/\/data.commoncrawl.org\/projects\/hyperlinkgraph\/cc-main- 2024-25-dec-jan-feb\/index.html","author":"Crawl Common","year":"2025","unstructured":"Common Crawl. Web graph release cc-main-2024-25-dec-jan-feb. https:\/\/data.commoncrawl.org\/projects\/hyperlinkgraph\/cc-main- 2024-25-dec-jan-feb\/index.html, 2025. [Online]."},{"key":"e_1_2_1_14_1","unstructured":"Linux Kernel Documentation. Hugetlb pages. https:\/\/www.kernel.org \/doc\/html\/latest\/admin-guide\/mm\/hugetlbpage.html."},{"key":"e_1_2_1_15_1","unstructured":"Linux Kernel Documentation. Transparent hugepage support. https:\/\/ www.kernel.org\/doc\/html\/latest\/admin-guide\/mm\/transhuge.html."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901344"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582031"},{"key":"e_1_2_1_18_1","first-page":"395","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Feng Guanyu","year":"2022","unstructured":"Guanyu Feng, Huanqi Cao, Xiaowei Zhu, Bowen Yu, Yuanwei Wang, Zixuan Ma, Shengqi Chen, and Wenguang Chen. TriCache: A User- Transparent block cache enabling High-Performance Out-of-Core processing with In-Memory programs. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 395- 411, Carlsbad, CA, July 2022. USENIX Association."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624175"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375634.1375641"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24322-6_24"},{"key":"e_1_2_1_22_1","first-page":"287","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Gouk Donghyun","year":"2022","unstructured":"Donghyun Gouk, Sangwon Lee, Miryeong Kwon, and Myoungsoo Jung. Direct access, High-Performance memory disaggregation with DirectCXL. In 2022 USENIX Annual Technical Conference (USENIX ATC 22), pages 287-294, Carlsbad, CA, July 2022. USENIX Association."},{"key":"e_1_2_1_23_1","first-page":"649","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Gu Juncheng","year":"2017","unstructured":"Juncheng Gu, Youngmoon Lee, Yiwen Zhang, Mosharaf Chowdhury, and Kang G. Shin. Efficient memory disaggregation with infiniswap. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), pages 649-667, Boston, MA, March 2017. USENIX Association."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3036686"},{"key":"e_1_2_1_25_1","first-page":"257","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Hunter A.H.","year":"2021","unstructured":"A.H. Hunter, Chris Kennelly, Paul Turner, Darryl Gove, Tipp Moseley, and Parthasarathy Ranganathan. Beyond malloc efficiency to fleet efficiency: a hugepage-aware memory allocator. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21), pages 257-273. USENIX Association, July 2021."},{"key":"e_1_2_1_26_1","unstructured":"Jonathan Corbet. The final step for huge-page swapping. https: \/\/lwn.net\/Articles\/758677\/."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3538643.3539745"},{"key":"e_1_2_1_28_1","first-page":"715","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Kim Jonghyeon","year":"2021","unstructured":"Jonghyeon Kim, Wonkyo Choe, and Jeongseob Ahn. Exploring the design space of page management for Multi-Tiered memory systems. In 2021 USENIX Annual Technical Conference (USENIX ATC 21), pages 715-728. USENIX Association, July 2021."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026931"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304053"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.75"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613167"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588687"},{"key":"e_1_2_1_34_1","first-page":"999","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Li Chuandong","year":"2024","unstructured":"Chuandong Li, Sai Sha, Yangqing Zeng, Xiran Yang, Yingwei Luo, XiaolinWang, ZhenlinWang, and Diyu Zhou. Taming hot bloat under virtualization with HUGESCOPE. In 2024 USENIX Annual Technical Conference (USENIX ATC 24), pages 999-1012, Santa Clara, CA, July 2024. USENIX Association."},{"key":"e_1_2_1_35_1","unstructured":"Linux Kernel Documentation. Workqueue. https:\/\/www.kernel.org\/d oc\/html\/latest\/core-api\/workqueue.html."},{"key":"e_1_2_1_36_1","unstructured":"Linux Kernel Documentation. zram: Compressed RAM-based block devices. https:\/\/www.kernel.org\/doc\/html\/latest\/admin-guide\/blockd ev\/zram.html."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258257"},{"key":"e_1_2_1_38_1","first-page":"28","volume-title":"Proceedings of the 2021 ACM SIGPLAN International Symposium on Memory Management, ISMM 2021","author":"Maas Martin","year":"2021","unstructured":"Martin Maas, Chris Kennelly, Khanh Nguyen, Darryl Gove, Kathryn S. McKinley, and Paul Turner. Adaptive huge-page subrelease for nonmoving memory allocators in warehouse-scale computers. In Proceedings of the 2021 ACM SIGPLAN International Symposium on Memory Management, ISMM 2021, page 28-38, New York, NY, USA, 2021. Association for Computing Machinery."},{"key":"e_1_2_1_39_1","volume-title":"Characterizing physical memory fragmentation. arXiv preprint arXiv:2401.03523","author":"Mansi Mark","year":"2024","unstructured":"Mark Mansi and Michael M Swift. Characterizing physical memory fragmentation. arXiv preprint arXiv:2401.03523, 2024."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_2_1_41_1","first-page":"409","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Nair Alan","year":"2024","unstructured":"Alan Nair, Sandeep Kumar, Aravinda Prasad, Ying Huang, Andy Rudoff, and Sreenivas Subramoney. Telescope: Telemetry for gargantuan memory footprint applications. In 2024 USENIX Annual Technical Conference (USENIX ATC 24), pages 409-424, Santa Clara, CA, July 2024. USENIX Association."},{"key":"e_1_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Juan Navarro Sitaram Iyer Peter Druschel and Alan Cox. Practical transparent operating system support for superpages. In Proceedings of the 5th Symposium on Operating Systems Design and Implementation (Copyright Restrictions Prevent ACM from Being Able to Make the PDFs for This Conference Available for Downloading) OSDI '02 page 89-104 USA 2002. USENIX Association.","DOI":"10.1145\/1060289.1060299"},{"key":"e_1_2_1_43_1","unstructured":"Nitin Gupta. Proactive compaction for the kernel."},{"key":"e_1_2_1_44_1","volume-title":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '19","author":"Panwar Ashish","year":"2019","unstructured":"Ashish Panwar, Sorav Bansal, and K. Gopinath. Hawkeye: Efficient finegrained os support for huge pages. In Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '19, New York, NY, USA, 2019. Association for Computing Machinery."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173203"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456242"},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the 2020 USENIX Conference on Usenix Annual Technical Conference, USENIX ATC\u201920","author":"Papagiannis Anastasios","year":"2020","unstructured":"Anastasios Papagiannis, Giorgos Xanthakis, Giorgos Saloustros, Manolis Marazakis, and Angelos Bilas. Optimizing memory-mapped i\/o for fast storage devices. In Proceedings of the 2020 USENIX Conference on Usenix Annual Technical Conference, USENIX ATC\u201920, USA, 2020. USENIX Association."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531466"},{"key":"e_1_2_1_49_1","unstructured":"Shuyi Pei and Rekha Pitchumani. Cmm-h (cxl memory module - hybrid): Rethinking storage for the memory-centric computing era. https:\/\/semiconductor.samsung.com\/us\/news-events\/tech-blog\/ret"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3086302"},{"key":"e_1_2_1_51_1","unstructured":"Persistent Memory Development Kit (PMDK). Volatile persistent memory allocator. https:\/\/github.com\/pmem\/vmem\/."},{"key":"e_1_2_1_52_1","volume-title":"https:\/\/www. freebsd.org\/releases\/7.2R\/relnotes-detailed\/","author":"Project The","year":"2009","unstructured":"The FreeBSD Project. Freebsd 7.2-release release notes. https:\/\/www. freebsd.org\/releases\/7.2R\/relnotes-detailed\/, 2009."},{"key":"e_1_2_1_53_1","volume-title":"https:\/\/www. freebsd.org\/releases\/10.0R\/relnotes\/","author":"Project The","year":"2014","unstructured":"The FreeBSD Project. Freebsd 10.0-release release notes. https:\/\/www. freebsd.org\/releases\/10.0R\/relnotes\/, 2014."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00012"},{"key":"e_1_2_1_55_1","first-page":"181","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Qiao Yifan","year":"2023","unstructured":"Yifan Qiao, Chenxi Wang, Zhenyuan Ruan, Adam Belay, Qingda Lu, Yiying Zhang, Miryung Kim, and Guoqing Harry Xu. Hermit:{Low- Latency},{High-Throughput}, and transparent remote memory via {Feedback-Directed} asynchrony. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 181- 198, 2023."},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480062"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"e_1_2_1_58_1","first-page":"315","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Ruan Zhenyuan","year":"2020","unstructured":"Zhenyuan Ruan, Malte Schwarzkopf, Marcos K. Aguilera, and Adam Belay. AIFM: High-Performance, Application-Integrated far memory. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pages 315-332. USENIX Association, November 2020."},{"key":"e_1_2_1_59_1","unstructured":"Samsung Electronics Corporation. Samsung V-NAND SSD 970 EVO Plus 2021 Data Sheet. https:\/\/download.semiconductor.samsung.com \/resources\/data-sheet\/Samsung_NVMe_SSD_970_EVO_Plus_Data _Sheet_Rev.3.0_10129514051212.pdf."},{"key":"e_1_2_1_60_1","volume-title":"Efficient memory-mapped i\/o on fast storage device. ACM Trans. Storage, 12(4), may","author":"Song Nae Young","year":"2016","unstructured":"Nae Young Song, Yongseok Son, Hyuck Han, and Heon Young Yeom. Efficient memory-mapped i\/o on fast storage device. ACM Trans. Storage, 12(4), may 2016."},{"key":"e_1_2_1_61_1","volume-title":"Xsbench-the development and verification of a performance abstraction for monte carlo reactor analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR)","author":"Tramm John R","year":"2014","unstructured":"John R Tramm, Andrew R Siegel, Tanzima Islam, and Martin Schulz. Xsbench-the development and verification of a performance abstraction for monte carlo reactor analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR), 2014."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-013-0309-0"},{"key":"e_1_2_1_63_1","first-page":"161","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Chenxi","year":"2023","unstructured":"Chenxi Wang, Yifan Qiao, Haoran Ma, Shi Liu, Wenguang Chen, Ravi Netravali, Miryung Kim, and Guoqing Harry Xu. Canvas: Isolated and adaptive swapping for Multi-Applications on remote memory. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 161-179, Boston, MA, April 2023. USENIX Association."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507731"},{"key":"e_1_2_1_65_1","first-page":"601","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Yang Shao-Peng","year":"2023","unstructured":"Shao-Peng Yang, Minjae Kim, Sanghyun Nam, Juhyung Park, Jin yong Choi, Eyee Hyun Nam, Eunji Lee, Sungjin Lee, and Bryan S. Kim. Overcoming the memory wall with CXL-Enabled SSDs. In 2023 USENIX Annual Technical Conference (USENIX ATC 23), pages 601-617, Boston, MA, July 2023. USENIX Association."},{"key":"e_1_2_1_66_1","volume-title":"Part 1: System architecture, processes, threads, memory management, and more","author":"Yosifovich Pavel","year":"2017","unstructured":"Pavel Yosifovich, David A Solomon, and Alex Ionescu. Windows Internals, Part 1: System architecture, processes, threads, memory management, and more. Microsoft Press, 2017."},{"key":"e_1_2_1_67_1","first-page":"141","volume-title":"LinuxExpo Conference Proceedings","volume":"94","author":"Zadok Erez","year":"1999","unstructured":"Erez Zadok and Ion Badulescu. A stackable file system interface for linux. In LinuxExpo Conference Proceedings, volume 94, pages 141-151, 1999."},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589079"},{"key":"e_1_2_1_69_1","first-page":"45","volume-title":"13th USENIX Conference on File and Storage Technologies (FAST 15)","author":"Zheng Da","year":"2015","unstructured":"Da Zheng, Disa Mhembere, Randal Burns, Joshua Vogelstein, Carey E Priebe, and Alexander S Szalay. {FlashGraph}: Processing {Billion- Node} graphs on an array of commodity {SSDs}. In 13th USENIX Conference on File and Storage Technologies (FAST 15), pages 45-58, 2015."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/3489146.3489203"},{"key":"e_1_2_1_71_1","first-page":"375","volume-title":"2015 USENIX Annual Technical Conference (USENIX ATC 15)","author":"Zhu Xiaowei","year":"2015","unstructured":"Xiaowei Zhu, Wentao Han, and Wenguang Chen. {GridGraph}:{Large-Scale} graph processing on a single machine using 2-level hierarchical partitioning. In 2015 USENIX Annual Technical Conference (USENIX ATC 15), pages 375-386, 2015."}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3830422.3830432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:20:58Z","timestamp":1783952458000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3830422.3830432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":71,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,7,13]]}},"alternative-id":["10.1145\/3830422.3830432"],"URL":"https:\/\/doi.org\/10.1145\/3830422.3830432","relation":{},"ISSN":["0163-5980"],"issn-type":[{"value":"0163-5980","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}