{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:32Z","timestamp":1750309472651,"version":"3.41.0"},"reference-count":25,"publisher":"Association for Computing Machinery (ACM)","issue":"05","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:p>Memory disaggregation architecture physically separates CPU and memory into independent components, which are connected via high-speed networks (for example, RDMA), greatly improving resource utilization of datacenter systems. However, such an architecture poses unique challenges to data indexing due to limited memory access semantics and near-zero computation power at memory side. Existing indexes supporting disaggregated memory either suffer from low write performance or require hardware modification.<\/jats:p>\n          <jats:p>\n            We present\n            <jats:sc>Sherman<\/jats:sc>\n            , a write-optimized\n            <jats:inline-formula>\n              <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\">\n                <mml:mrow>\n                  <mml:msup>\n                    <mml:mi mathvariant=\"normal\">B<\/mml:mi>\n                    <mml:mo>+<\/mml:mo>\n                  <\/mml:msup>\n                  <mml:mi>Tree<\/mml:mi>\n                <\/mml:mrow>\n              <\/mml:math>\n            <\/jats:inline-formula>\n            index on RDMA-enabled disaggregated memory.\n            <jats:sc>Sherman<\/jats:sc>\n            combines RDMA hardware features and RDMA-friendly software techniques to boost index write performance from three angles. First, to reduce round trips,\n            <jats:sc>Sherman<\/jats:sc>\n            coalesces dependent RDMA commands by leveraging in-order delivery property of RDMA. Second, to accelerate concurrent accesses,\n            <jats:sc>Sherman<\/jats:sc>\n            introduces a hierarchical lock that exploits on-chip memory of RDMA NICs. Finally, to mitigate write amplification,\n            <jats:sc>Sherman<\/jats:sc>\n            tailors the data structure layout of\n            <jats:inline-formula>\n              <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\">\n                <mml:mrow>\n                  <mml:msup>\n                    <mml:mi mathvariant=\"normal\">B<\/mml:mi>\n                    <mml:mo>+<\/mml:mo>\n                  <\/mml:msup>\n                  <mml:mi>Tree<\/mml:mi>\n                <\/mml:mrow>\n              <\/mml:math>\n            <\/jats:inline-formula>\n            with a two-level version mechanism. Our evaluation shows that\u00a0\n            <jats:sc>Sherman<\/jats:sc>\n            is one order of magnitude faster compared with state-of-the-art designs in terms of both throughput and 99\n            <jats:sup>th<\/jats:sup>\n            percentile latency on typical write-intensive workloads.\n          <\/jats:p>","DOI":"10.1145\/3709647","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T16:59:00Z","timestamp":1744736340000},"page":"92-100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Designing an Efficient Tree Index on Disaggregated Memory"],"prefix":"10.1145","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5526-7154","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6214-5390","authenticated-orcid":false,"given":"Youyou","family":"Lu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7362-2789","authenticated-orcid":false,"given":"Jiwu","family":"Shu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321433"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446713"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"e_1_3_1_5_2","first-page":"401","volume-title":"Proceedings of NSDI\u201914","author":"Dragojevi\u0107 A.","year":"2014","unstructured":"Dragojevi\u0107, A., Narayanan, D., Hodson, O., and Castro, M. Fast remote memory. In Proceedings of NSDI\u201914. USENIX Association, USA, (2014), 401\u2013414."},{"key":"e_1_3_1_6_2","first-page":"249","volume-title":"Proceedings of OSDI\u201916","author":"Gao P.X.","year":"2016","unstructured":"Gao, P.X. et al. Network requirements for resource disaggregation. In Proceedings of OSDI\u201916. USENIX Association, USA, (2016), 249\u2013264."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329074"},{"key":"e_1_3_1_8_2","unstructured":"InfiniBandTM Architecture Specification Volume 1 Release 1.3 (General Specifications) InfiniBand Trade Association\u00a0(2015)."},{"key":"e_1_3_1_9_2","first-page":"437","volume-title":"Proceedings of ATC\u201916","author":"Kalia A.","year":"2016","unstructured":"Kalia, A., Kaminsky, M., and Andersen, D.G. Design guidelines for high-performance RDMA systems. In Proceedings of ATC\u201916. USENIX Association, USA, (2016), 437\u2013450."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2768405.2768406"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555789"},{"key":"e_1_3_1_13_2","first-page":"451","volume-title":"Proceedings of ATC\u201916","author":"Mitchell C.","year":"2016","unstructured":"Mitchell, C. et al. Balancing CPU and network in the cell distributed B-Tree store. In Proceedings of ATC\u201916. USENIX Association, USA, (2016), 451\u2013464."},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Pinto C. et al. Thymesisflow: A software-defined HW\/SW co-designed interconnect stack for rack-scale memory disaggregation. In MICRO\u201920 (2020) 868\u2013880.","DOI":"10.1109\/MICRO50266.2020.00075"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300069"},{"key":"e_1_3_1_16_2","first-page":"69","volume-title":"Proceedings of OSDI\u201918","author":"Shan Y.","year":"2018","unstructured":"Shan, Y., Huang, Y., Chen, Y., and Zhang, Y. LegoOS: A disseminated, distributed OS for hardware resource disaggregation. In Proceedings of OSDI\u201918. USENIX Association, USA, (2018), 69\u201387."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387519"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387517"},{"key":"e_1_3_1_19_2","first-page":"33","volume-title":"Proceedings of ATC\u201920","author":"Tsai S.-Y.","year":"2020","unstructured":"Tsai, S.-Y., Shan, Y., and Zhang, Y. Disaggregating persistent memory and controlling them remotely: An exploration of passive disaggregated key-value stores. In Proceedings of ATC\u201920. USENIX Association, USA, (2020), 33\u201348."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696062"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517824"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342639"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397249"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467877"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589276"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300081"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709647","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:20Z","timestamp":1750295840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":25,"journal-issue":{"issue":"05","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1145\/3709647"],"URL":"https:\/\/doi.org\/10.1145\/3709647","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"type":"print","value":"0001-0782"},{"type":"electronic","value":"1557-7317"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"assertion":[{"value":"2025-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}