{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T23:07:50Z","timestamp":1784934470999,"version":"3.55.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:p>It is challenging for cloud-native relational databases to meet the ever-increasing needs of scaling compute and memory resources independently and elastically. The recent emergence of memory disaggregation architecture, relying on high-speed RDMA network, offers opportunities to build cost-effective and elastic cloud-native databases. There exist proposals to let unmodified applications run transparently on disaggregated systems. However, running relational database kernel atop such proposals experiences notable performance degradation and time-consuming failure recovery, offsetting the benefits of disaggregation.<\/jats:p>\n          <jats:p>To address these challenges, in this paper, we propose a novel database architecture called LegoBase, which explores the co-design of database kernel and memory disaggregation. It pushes the memory management back to the database layer for bypassing the Linux I\/O stack and re-using or designing (remote) memory access optimizations with an understanding of data access patterns. LegoBase further splits the conventional ARIES fault tolerance protocol to independently handle the local and remote memory failures for fast recovery of compute instances. We implemented LegoBase atop MySQL. We compare LegoBase against MySQL running on a standalone machine and the state-of-the-art disaggregation proposal Infiniswap. Our evaluation shows that even with a large fraction of data placed on the remote memory, LegoBase's system performance in terms of throughput (up to 9.41% drop) and P99 latency (up to 11.58% increase) is comparable to the monolithic MySQL setup, and significantly outperforms (1.99x-2.33x, respectively) the deployment of MySQL over Infiniswap. Meanwhile, LegoBase introduces an up to 3.87x and 5.48x speedup of the recovery and warm-up time, respectively, over the monolithic MySQL and MySQL over Infiniswap, when handling failures or planned re-configurations.<\/jats:p>","DOI":"10.14778\/3467861.3467877","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T16:17:12Z","timestamp":1635265032000},"page":"1900-1912","source":"Crossref","is-referenced-by-count":44,"title":["Towards cost-effective and elastic cloud database deployment via memory disaggregation"],"prefix":"10.14778","volume":"14","author":[{"given":"Yingqiang","family":"Zhang","sequence":"first","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyi","family":"Ruan","sequence":"additional","affiliation":[{"name":"Alibaba Group and University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjun","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feifei","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Fang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingze","family":"Huo","sequence":"additional","affiliation":[{"name":"Alibaba Group and University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Bi","sequence":"additional","affiliation":[{"name":"Alibaba Group and University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,26]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3277355.3277430"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3489146.3489204"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3485849.3485864"},{"key":"e_1_2_1_4_1","volume-title":"Firebox: A hardware building block for 2020 warehouse-scale computers.","author":"Asanovi\u0107 Krste","year":"2014","unstructured":"Krste Asanovi\u0107 . 2014 . Firebox: A hardware building block for 2020 warehouse-scale computers. (2014). Krste Asanovi\u0107. 2014. Firebox: A hardware building block for 2020 warehouse-scale computers. (2014)."},{"key":"e_1_2_1_5_1","unstructured":"TPC Benchmark. 2020. TPC-C. http:\/\/www.tpc.org\/tpcc\/. \"[accessed-Dec-2020]\".  TPC Benchmark. 2020. TPC-C. http:\/\/www.tpc.org\/tpcc\/. \"[accessed-Dec-2020]\"."},{"key":"e_1_2_1_6_1","unstructured":"TPC Benchmark. 2020. TPC-H. http:\/\/www.tpc.org\/tpch\/. \"[accessed-Dec-2020]\".  TPC Benchmark. 2020. TPC-H. http:\/\/www.tpc.org\/tpch\/. \"[accessed-Dec-2020]\"."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378504"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236209"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3386691.3386695"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229872"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622518"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3149457.3149466"},{"key":"e_1_2_1_13_1","volume-title":"The Machine: A New Kind of Computer. https:\/\/www.hpl.hp.com\/research\/systems-research\/themachine\/. \"[accessed-Oct-2020]\".","author":"Development Company HP","year":"2020","unstructured":"HP Development Company . 2020 . The Machine: A New Kind of Computer. https:\/\/www.hpl.hp.com\/research\/systems-research\/themachine\/. \"[accessed-Oct-2020]\". HP Development Company. 2020. The Machine: A New Kind of Computer. https:\/\/www.hpl.hp.com\/research\/systems-research\/themachine\/. \"[accessed-Oct-2020]\"."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491245"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314035"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2616448.2616486"},{"key":"e_1_2_1_17_1","unstructured":"Facebook. 2013. Future rack technology. https:\/\/newsroom.intel.com\/news-releases\/intel-facebook-collaborate-on-future-data-center-rack-technologies\/. \"[accessed-Oct-2020]\".  Facebook. 2013. Future rack technology. https:\/\/newsroom.intel.com\/news-releases\/intel-facebook-collaborate-on-future-data-center-rack-technologies\/. \"[accessed-Oct-2020]\"."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2831090.2831107"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026897"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"e_1_2_1_21_1","unstructured":"The PostgreSQL Global Development Group. 2021. PostgreSQL. https:\/\/www.postgresql.org\/. \"[accessed-April-2021]\".  The PostgreSQL Global Development Group. 2021. PostgreSQL. https:\/\/www.postgresql.org\/. \"[accessed-April-2021]\"."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3154630.3154683"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2342821.2342823"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415535"},{"key":"e_1_2_1_25_1","unstructured":"Docker Inc. 2020. Docker. https:\/\/www.docker.com\/. \"[accessed-Dec-2020]\".  Docker Inc. 2020. Docker. https:\/\/www.docker.com\/. \"[accessed-Dec-2020]\"."},{"key":"e_1_2_1_26_1","unstructured":"Intel. 2020. Rack Scale Architecture. https:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/rack-scale-design-overview.html. \"[accessed-Oct-2020]\".  Intel. 2020. Rack Scale Architecture. https:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/rack-scale-design-overview.html. \"[accessed-Oct-2020]\"."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2971808.2971968"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/365628.365655"},{"key":"e_1_2_1_29_1","volume-title":"Sysbench manual. MySQL AB","author":"Kopytov Alexey","year":"2012","unstructured":"Alexey Kopytov . 2012. Sysbench manual. MySQL AB ( 2012 ), 2--3. Alexey Kopytov. 2012. Sysbench manual. MySQL AB (2012), 2--3."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806845"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352141"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2011.87"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/128765.128770"},{"key":"e_1_2_1_34_1","unstructured":"MySQL. 2015. MySQL Buffer Pool LRU Algorithm. https:\/\/dev.mysql.com\/doc\/refman\/5.7\/en\/innodb-buffer-pool.html. \"[accessed-Dec-2020]\".  MySQL. 2015. MySQL Buffer Pool LRU Algorithm. https:\/\/dev.mysql.com\/doc\/refman\/5.7\/en\/innodb-buffer-pool.html. \"[accessed-Dec-2020]\"."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2813767.2813789"},{"key":"e_1_2_1_36_1","volume-title":"Auto-Scaling Cloud-Based Memory-Intensive Applications. In 2020 IEEE 13th International Conference on Cloud Computing (CLOUD). IEEE, 229--237","author":"Novak Joe","year":"2020","unstructured":"Joe Novak , Sneha Kumar Kasera , and Ryan Stutsman . 2020 . Auto-Scaling Cloud-Based Memory-Intensive Applications. In 2020 IEEE 13th International Conference on Cloud Computing (CLOUD). IEEE, 229--237 . Joe Novak, Sneha Kumar Kasera, and Ryan Stutsman. 2020. Auto-Scaling Cloud-Based Memory-Intensive Applications. In 2020 IEEE 13th International Conference on Cloud Computing (CLOUD). IEEE, 229--237."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/264359.264360"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3148149"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1137\/0108018"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291175"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352123"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056101"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/1298455.1298485"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397249"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3467861.3467877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T10:37:20Z","timestamp":1672223840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3467861.3467877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["10.14778\/3467861.3467877"],"URL":"https:\/\/doi.org\/10.14778\/3467861.3467877","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}