{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:37:20Z","timestamp":1767141440803,"version":"build-2238731810"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Korea governmen","award":["RS-2024-00453929"],"award-info":[{"award-number":["RS-2024-00453929"]}]},{"name":"Korea governmen","award":["RS-2024-00453929"],"award-info":[{"award-number":["RS-2024-00453929"]}]},{"name":"Korea governmen","award":["RS-2024-00453929"],"award-info":[{"award-number":["RS-2024-00453929"]}]},{"name":"Korea governmen","award":["RS-2024-00453929"],"award-info":[{"award-number":["RS-2024-00453929"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10586-024-05000-6","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T12:26:23Z","timestamp":1753964783000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards an asynchronous commit in micro-batch streaming systems with log-structured merge-tree based key-value store"],"prefix":"10.1007","volume":"28","author":[{"given":"Kyuli","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongjae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeonwoo","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salim","family":"Hariri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungyong","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"key":"5000_CR1","doi-asserted-by":"crossref","unstructured":"Dai, Y., Yan, J., Tang, X., Zhao, H., Guo, M.: Online credit card fraud detection: a hybrid framework with big data technologies. In: 2016 IEEE Trustcom\/BigDataSE\/ISPA, pp.\u00a01644\u20131651 (2016)","DOI":"10.1109\/TrustCom.2016.0253"},{"key":"5000_CR2","doi-asserted-by":"crossref","unstructured":"Chang, G., Zhao, L., Liu, J., Li, P.: An anomaly detection method for stateful stream processing system. In: Proceedings of the 2017 2nd International Conference on Modelling, Simulation and Applied Mathematics (MSAM2017), pp.\u00a0196\u2013199 (2017)","DOI":"10.2991\/msam-17.2017.44"},{"key":"5000_CR3","doi-asserted-by":"publisher","first-page":"1634","DOI":"10.14778\/3137765.3137770","volume":"10","author":"SA Noghabi","year":"2017","unstructured":"Noghabi, S.A., Paramasivam, K., Pan, Y., Ramesh, N., Bringhurst, J., Gupta, I., Campbell, R.H.: Samza: stateful scalable stream processing at linkedin. Proc. VLDB Endow. 10, 1634\u20131645 (2017)","journal-title":"Proc. VLDB Endow."},{"issue":"8","key":"5000_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2022.102026","volume":"14","author":"H Hazem","year":"2023","unstructured":"Hazem, H., Awad, A., Yousef, A.H.: A distributed real-time recommender system for big data streams. Ain Shams Eng J 14(8), 102026 (2023)","journal-title":"Ain Shams Eng J"},{"key":"5000_CR5","doi-asserted-by":"crossref","unstructured":"Gupta, A., Birkner, R., Canini, M., Feamster, N., Mac-Stoker, C., Willinger, W.: Network monitoring as a streaming analytics problem. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks, pp.\u00a0106\u2013112 (2016)","DOI":"10.1145\/3005745.3005748"},{"key":"5000_CR6","unstructured":"Kolokasis, I.G., Papagiannis, A., Pratikakis, P., Bilas, A., Zakkak, F.: Say goodbye to off-heap caches! on-heap caches using memory-mapped i\/o. In: Proceedings of the 12th USENIX Conference on Hot Topics in Storage and File Systems, p.\u00a04 (2020)"},{"key":"5000_CR7","unstructured":"Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., Tzoumas, K.: Apache Flink\u2122: Stream and Batch Processing in a Single Engine. The Bulletin of the Technical Committee on Data Engineering. 38(4) (2015)"},{"issue":"11","key":"5000_CR8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M., Xin, R.S., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M.J., et al.: Apache spark: a unified engine for big data processing. Commun. ACM 59(11), 56\u201365 (2016)","journal-title":"Commun. ACM"},{"issue":"1","key":"5000_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.14445\/22312803\/IJCTT-V19P103","volume":"19","author":"MH Iqbal","year":"2015","unstructured":"Iqbal, M.H., Soomro, T.R., et al.: Big data analysis: Apache storm perspective. Int. J. Comput. Trends Technol. 19(1), 9\u201314 (2015)","journal-title":"Int. J. Comput. Trends Technol."},{"issue":"47","key":"5000_CR10","first-page":"9478","volume":"3","author":"KMM Thein","year":"2014","unstructured":"Thein, K.M.M.: Apache kafka: next generation distributed messaging system. Int. J. Sci. Eng. Technol. Res. 3(47), 9478\u20139483 (2014)","journal-title":"Int. J. Sci. Eng. Technol. Res."},{"key":"5000_CR11","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s002360050048","volume":"33","author":"P O\u2019Neil","year":"1996","unstructured":"O\u2019Neil, P., Cheng, E., Gawlick, D., O\u2019Neil, E.: The log-structured merge-tree (lsm-tree). Acta Informat. 33, 351\u2013385 (1996)","journal-title":"Acta Informat."},{"key":"5000_CR12","unstructured":"Facebook: Rocksdb: a persistent key-value store for fast storage environment (2012). https:\/\/rocksdb.org"},{"key":"5000_CR13","unstructured":"Google: Leveldb (2017). https:\/\/github.com\/google\/leveldb"},{"issue":"2","key":"5000_CR14","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1145\/1773912.1773922","volume":"44","author":"A Lakshman","year":"2010","unstructured":"Lakshman, A., Malik, P.: Cassandra: a decentralized structured storage system. ACM SIGOPS Oper. Syst. Rev. 44(2), 35\u201340 (2010)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"issue":"12","key":"5000_CR15","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.1109\/TPDS.2018.2846234","volume":"29","author":"D Cheng","year":"2018","unstructured":"Cheng, D., Zhou, X., Wang, Y., Jiang, C.: Adaptive scheduling parallel jobs with dynamic batching in spark streaming. IEEE Trans. Parallel Distrib. Syst. 29(12), 2672\u20132685 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"5","key":"5000_CR16","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1007\/s10586-022-03758-1","volume":"26","author":"S Lee","year":"2023","unstructured":"Lee, S., Jeong, Y., Park, K., Jung, G., Park, S.: zstream: towards a low latency micro-batch streaming system. Clust. Comput. 26(5), 2773\u20132787 (2023)","journal-title":"Clust. Comput."},{"key":"5000_CR17","unstructured":"databricks (2024). https:\/\/docs.databricks.com\/en\/structured-streaming\/async-checkpointing.html"},{"key":"5000_CR18","doi-asserted-by":"crossref","unstructured":"Armbrust, M., Das, T., Torres, J., Yavuz, B., Zhu, S., Xin, R., Ghodsi, A., Stoica, I., Zaharia, M.: Structured streaming: a declarative api for real-time applications in apache spark. In: Proceedings of the 2018 International Conference on Management of Data, pp.\u00a0601\u2013613 (2018)","DOI":"10.1145\/3183713.3190664"},{"key":"5000_CR19","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In: 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST), pp.\u00a01\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"5000_CR20","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.-T.: The google file system. In: Proceedings of the 19th ACM Symposium on Operating Systems Principles, pp.\u00a020\u201343. Bolton Landing, NY (2003)","DOI":"10.1145\/945445.945450"},{"key":"5000_CR21","unstructured":"Weil, S.A., Brandt, S.A., Miller, E.L., Long, D.D.E., Maltzahn, C.: Ceph: a scalable, high-performance distributed file system. In: 7th USENIX Symposium on Operating Systems Design and Implementation (OSDI 06). USENIX Association, Seattle, WA (2006)"},{"key":"5000_CR22","unstructured":"Gu, R., Yin, H., Zhong, W., Yuan, C., Huang, Y.: Meces: latency-efficient rescaling via prioritized state migration for stateful distributed stream processing systems. In: 2022 USENIX Annual Technical Conference (USENIX ATC 22), (Carlsbad, CA), pp.\u00a0539\u2013556. USENIX Association (2022)"},{"key":"5000_CR23","doi-asserted-by":"crossref","unstructured":"Del\u00a0Monte, B., Zeuch, S., Rabl, T., Markl, V.: Rhino: efficient management of very large distributed state for stream processing engines. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp.\u00a02471\u20132486 (2020)","DOI":"10.1145\/3318464.3389723"},{"key":"5000_CR24","doi-asserted-by":"crossref","unstructured":"Lee, G., Maeng, J., Park, J., Seo, J., Cho, H., Yang, Y., Um, T., Lee, J., Lee, J.W., Chun, B.-G.: Flowkv: a semantic-aware store for large-scale state management of stream processing engines. In: Proceedings of the 18th European Conference on Computer Systems, pp.\u00a0768\u2013783 (2023)","DOI":"10.1145\/3552326.3567493"},{"key":"5000_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wang, Q., Kanemasa, Y., Michaelis, J., Liu, J., Pu, C.: Shadowsync: latency long tail caused by hidden synchronization in real-time lsm-tree based stream processing systems. In: Proceedings of the 23rd ACM\/IFIP International Middleware Conference, pp.\u00a0281\u2013294 (2022)","DOI":"10.1145\/3528535.3565251"},{"key":"5000_CR26","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.future.2020.04.019","volume":"110","author":"S Jayasekara","year":"2020","unstructured":"Jayasekara, S., Harwood, A., Karunasekera, S.: A utilization model for optimization of checkpoint intervals in distributed stream processing systems. Futur. Gener. Comput. Syst. 110, 68\u201379 (2020)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"5000_CR27","doi-asserted-by":"crossref","unstructured":"Geldenhuys, M.K, Thamsen, L., Kao, O.: Chiron: optimizing fault tolerance in qos-aware distributed stream processing jobs. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 434\u2013440 (2020)","DOI":"10.1109\/BigData50022.2020.9378474"},{"key":"5000_CR28","unstructured":"Balmau, O., Dinu, F., Zwaenepoel, W., Gupta, K., Chandhiramoorthi, R., Didona, D.: SILK: preventing latency spikes in Log-Structured merge Key-Value stores. In: 2019 USENIX Annual Technical Conference (USENIX ATC 19), (Renton, WA), pp.\u00a0753\u2013766. USENIX Association (2019)"},{"key":"5000_CR29","unstructured":"Yu, J., Noh, S.H., Ri\u00a0Choi, Y., Xue, C.J.: ADOC: automatically harmonizing dataflow between components in Log-Structured Key-Value stores for improved performance. In: 21st USENIX Conference on File and Storage Technologies (FAST 23), (Santa Clara, CA), pp.\u00a065\u201380. USENIX Association (2023)"},{"key":"5000_CR30","doi-asserted-by":"crossref","unstructured":"Arasu, A., Cherniack, M., Galvez, E., Maier, D., Maskey, A.S., Ryvkina, E., Stonebraker, M., Tibbetts, R.: Linear road: a stream data management benchmark. In: Proceedings of the 13th International Conference on Very Large Data Bases, vol. 30, pp. 480\u2013491 (2004)","DOI":"10.1016\/B978-012088469-8\/50044-9"},{"key":"5000_CR31","doi-asserted-by":"crossref","unstructured":"Upadhyaya, P., Kwon, Y., Balazinska, M.: A latency and fault-tolerance optimizer for online parallel query plans. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp.\u00a0241\u2013252 (2011)","DOI":"10.1145\/1989323.1989350"},{"key":"5000_CR32","doi-asserted-by":"crossref","unstructured":"Sato, K., Mohror, K., Moody, A., Gamblin, T., Supinski, B.R.D., Maruyama, N., Matsuoka, S.: A user-level infiniband-based file system and checkpoint strategy for burst buffers. In: 2014 14th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp.\u00a021\u201330 (2014)","DOI":"10.1109\/CCGrid.2014.24"},{"key":"5000_CR33","doi-asserted-by":"crossref","unstructured":"Ni, X., Meneses, E., Kal\u00e9, L.\u00a0V.: Hiding checkpoint overhead in hpc applications with a semi-blocking algorithm. In: 2012 IEEE International Conference on Cluster Computing, pp.\u00a0364\u2013372 (2012)","DOI":"10.1109\/CLUSTER.2012.82"},{"key":"5000_CR34","doi-asserted-by":"crossref","unstructured":"Di, S., Bouguerra, M.S., Bautista-Gomez, L., Cappello, F.: Optimization of multi-level checkpoint model for large scale HPC applications. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp.\u00a01181\u20131190 (2014)","DOI":"10.1109\/IPDPS.2014.122"},{"key":"5000_CR35","unstructured":"Reiss, C., Wilkes, J., Hellerstein, J.L.: Google Cluster-Usage Traces: Format + Schema, vol.\u00a01, pp.\u00a01\u201314. Google Inc., White Paper (2011)"},{"key":"5000_CR36","doi-asserted-by":"crossref","unstructured":"Armbrust, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J., Ghodsi, A., et\u00a0al.: Spark sql: relational data processing in spark. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp.\u00a01383\u20131394 (2015)","DOI":"10.1145\/2723372.2742797"},{"key":"5000_CR37","unstructured":"Scala. https:\/\/www.scala-lang.org\/"},{"key":"5000_CR38","unstructured":"Scala-future. https:\/\/docs.scala-lang.org\/overviews\/core\/futures.html"}],"updated-by":[{"DOI":"10.1007\/s10586-025-05748-5","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000}}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-05000-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-024-05000-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-05000-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T05:31:58Z","timestamp":1761197518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-024-05000-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":38,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["5000"],"URL":"https:\/\/doi.org\/10.1007\/s10586-024-05000-6","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"10 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online of this article was revised: Some of the corrections were missed to incorporate in the article, the missing corrections have been now incorporated.","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2025","order":9,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":10,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":11,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s10586-025-05748-5","URL":"https:\/\/doi.org\/10.1007\/s10586-025-05748-5","order":12,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"420"}}