{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:04:57Z","timestamp":1762088697387,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["62025203"],"award-info":[{"award-number":["62025203"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1145\/3552326.3567484","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:33:02Z","timestamp":1683307982000},"page":"452-468","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["LogGrep: Fast and Cheap Cloud Log Storage by Exploiting both Static and Runtime Patterns"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0688-6370","authenticated-orcid":false,"given":"Junyu","family":"Wei","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3480-5902","authenticated-orcid":false,"given":"Guangyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6273-075X","authenticated-orcid":false,"given":"Junchao","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9721-4923","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9350-7625","authenticated-orcid":false,"given":"Weimin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3334-1309","authenticated-orcid":false,"given":"Tingtao","family":"Sun","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7417-5469","authenticated-orcid":false,"given":"Jiesheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0135-1932","authenticated-orcid":false,"given":"Jiangwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Daniel Abadi Peter Boncz Stavros Harizopoulos Stratos Idreos Samuel Madden et al. 2013. The design and implementation of modern column-oriented database systems. Foundations and Trends\u00ae in Databases 5 3 (2013) 197--280.","DOI":"10.1561\/1900000024"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142548"},{"key":"e_1_3_2_1_3_1","volume-title":"NSDI'15 Proceedings of the 12th USENIX Conference on Networked Systems Design and Implementation. 337--350","author":"Agarwal Rachit","year":"2015","unstructured":"Rachit Agarwal, Anurag Khandelwal, and Ion Stoica. 2015. Succinct: enabling queries on compressed data. In NSDI'15 Proceedings of the 12th USENIX Conference on Networked Systems Design and Implementation. 337--350."},{"volume-title":"Pattern and cluster mining on text data. In 2014 fourth international conference on communication systems and network technologies","author":"Agnihotri Deepak","key":"e_1_3_2_1_4_1","unstructured":"Deepak Agnihotri, Kesari Verma, and Priyanka Tripathi. 2014. Pattern and cluster mining on text data. In 2014 fourth international conference on communication systems and network technologies. IEEE, 428--432."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/359842.359859"},{"key":"e_1_3_2_1_6_1","unstructured":"Elasticsearch B.V. 2020. Elasticsearch 7.8.0. https:\/\/www.elastic.co\/downloads\/past-releases\/elasticsearch-7-8-0."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457565"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 217--231","author":"Chow Michael","year":"2014","unstructured":"Michael Chow, David Meisner, Jason Flinn, Daniel Peek, and Thomas F Wenisch. 2014. The mystery machine: End-to-end performance analysis of large-scale Internet services. In Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 217--231."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1108792.1108814"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096090"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/96749.98245"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903741"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Peter Deutsch. 1996. DEFLATE Compressed Data Format Specification version 1.3. https:\/\/tools.ietf.org\/html\/rfc1951.","DOI":"10.17487\/rfc1951"},{"key":"e_1_3_2_1_14_1","unstructured":"Linux developer community. 2020. Grep Manuel. https:\/\/linux.die.net\/man\/1\/grep."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134015"},{"volume-title":"Ways of Knowing in HCI","author":"Dumais Susan","key":"e_1_3_2_1_16_1","unstructured":"Susan Dumais, Robin Jeffries, Daniel M Russell, Diane Tang, and Jaime Teevan. 2014. Understanding user behavior through log data and analysis. In Ways of Knowing in HCI. Springer, 349--372."},{"key":"e_1_3_2_1_17_1","unstructured":"Facebook. 2021. z-standard compression tool. https:\/\/github.com\/facebook\/zstd."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2489657"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-017-0450-y"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom.2016.0215"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2790755.2790797"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0255(01)00098-6"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183746"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2384497"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2004.1311529"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539702402354"},{"key":"e_1_3_2_1_27_1","volume-title":"Elasticsearch: Bulk Inserting Examples. https:\/\/queirozf.com\/entries\/elasticsearch-bulk-inserting-examples.","author":"ElasticSearch","year":"2019","unstructured":"ElasticSearch group. 2019. Elasticsearch: Bulk Inserting Examples. https:\/\/queirozf.com\/entries\/elasticsearch-bulk-inserting-examples."},{"key":"e_1_3_2_1_28_1","unstructured":"Loghub group. 2019. Download link of public log dataset. https:\/\/zenodo.org\/record\/7056802#.Yxm2VexBwq2."},{"key":"e_1_3_2_1_29_1","unstructured":"LogArchive group. 2019. Open source code of LogArchive. https:\/\/github.com\/robertchristensen\/log_archive_v0."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983358"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2017.13"},{"key":"e_1_3_2_1_32_1","volume-title":"Lyu","author":"He Shilin","year":"2020","unstructured":"Shilin He, Jieming Zhu, Pinjia He, and Michael R. Lyu. 2020. Loghub: A Large Collection of System Log Datasets towards Automated Log Analytics. arXiv preprint arXiv:2008.06448 (2020)."},{"key":"e_1_3_2_1_33_1","unstructured":"Splunk Inc. 2020. Spunk Enterprise 8.0.3. https:\/\/www.splunk.com\/en_us\/download\/previous-releases.html."},{"key":"e_1_3_2_1_34_1","unstructured":"Scalyr Inc. 2021. Scalyr home page. https:\/\/www.scalyr.com\/."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3380750.3380761"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/QSIC.2008.50"},{"volume-title":"Proceedings DCC '98 Data Compression Conference (Cat. No.98TB100225)","author":"Kida T.","key":"e_1_3_2_1_37_1","unstructured":"T. Kida, M. Takeda, A. Shinohara, M. Miyazaki, and S. Arikawa. 1998. Multiple pattern matching in LZW compressed text. In Proceedings DCC '98 Data Compression Conference (Cat. No.98TB100225). 103--112."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-024X(199911)29:13<1149::AID-SPE274>3.0.CO;2-O"},{"key":"e_1_3_2_1_39_1","unstructured":"Grafana Labs. 2021. Loki Documentation. https:grafana.com\/docs\/loki\/latest\/."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882925"},{"key":"e_1_3_2_1_41_1","volume-title":"The unified logging infrastructure for data analytics at Twitter. arXiv preprint arXiv:1208.4171","author":"Lee George","year":"2012","unstructured":"George Lee, Jimmy Lin, Chuang Liu, Andrew Lorek, and Dmitriy Ryaboy. 2012. The unified logging infrastructure for data analytics at Twitter. arXiv preprint arXiv:1208.4171 (2012)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452829"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457277"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.45"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00085"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.138"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557154"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196340"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/SCC.2013.73"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.53"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2010.5463281"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/2228298.2228334"},{"volume-title":"Introduction to HPC with MPI for Data Science","author":"Nielsen Frank","key":"e_1_3_2_1_53_1","unstructured":"Frank Nielsen. 2016. Hierarchical clustering. In Introduction to HPC with MPI for Data Science. Springer, 195--211."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.14"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290962"},{"key":"e_1_3_2_1_56_1","first-page":"1","article-title":"Techniques for Inverted Index","volume":"53","author":"Pibiri Giulio Ermanno","year":"2020","unstructured":"Giulio Ermanno Pibiri and Rossano Venturini. 2020. Techniques for Inverted Index Compression. Comput. Surveys 53, 6 (2020), 1--36.","journal-title":"Compression. Comput. Surveys"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-51486-4_90"},{"key":"e_1_3_2_1_58_1","volume-title":"CLP: Efficient and Scalable Search on Compressed Text Logs. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI'21)","author":"Rodrigues Kirk","year":"2021","unstructured":"Kirk Rodrigues, Yu Luo, and Ding Yuan. 2021. CLP: Efficient and Scalable Search on Compressed Text Logs. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI'21). 183--198."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.5555\/545381.545410"},{"key":"e_1_3_2_1_60_1","unstructured":"Vijay Samuel. 2018. Monitoring Anything and Everything with Beats at eBay. (2018)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Khalid Sayood. 2017. Introduction to data compression. Morgan Kaufmann.","DOI":"10.1016\/B978-0-12-809474-7.00019-7"},{"key":"e_1_3_2_1_62_1","volume-title":"Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213","author":"Shima Keiichi","year":"2016","unstructured":"Keiichi Shima. 2016. Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213 (2016)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/3025111.3025123"},{"key":"e_1_3_2_1_64_1","unstructured":"LogGrep authors. 2022. Producition logs sample. https:\/\/github.com\/THUBear-wjy\/openSample."},{"key":"e_1_3_2_1_65_1","unstructured":"LogGrep authors. 2022. Source code of LogGrep. https:\/\/github.com\/THUBear-wjy\/LogGrep."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063690"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPOM.2003.1251233"},{"key":"e_1_3_2_1_68_1","volume-title":"Twitter mining for fine-grained syndromic surveillance. Artificial intelligence in medicine 61, 3","author":"Velardi Paola","year":"2014","unstructured":"Paola Velardi, Giovanni Stilo, Alberto E Tozzi, and Francesco Gesualdo. 2014. Twitter mining for fine-grained syndromic surveillance. Artificial intelligence in medicine 61, 3 (2014), 153--163."},{"key":"e_1_3_2_1_69_1","volume-title":"On the Feasibility of Parser-based Log Compression in Large-Scale Cloud Systems. In 19th USENIX Conference on File and Storage Technologies (FAST'21)","author":"Wei Junyu","year":"2021","unstructured":"Junyu Wei, Guangyan Zhang, Yang Wang, Zhiwei Liu, Zhanyang Zhu, Junchao Chen, Tingtao Sun, and Qi Zhou. 2021. On the Feasibility of Parser-based Log Compression in Large-Scale Cloud Systems. In 19th USENIX Conference on File and Storage Technologies (FAST'21). 249--262."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629587"},{"key":"e_1_3_2_1_71_1","unstructured":"YScope. 2021. clp-core. https:\/\/github.com\/y-scope\/clp-core."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736038"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00636-3"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2017.137"},{"key":"e_1_3_2_1_75_1","volume-title":"Effective pattern discovery for text mining","author":"Zhong Ning","year":"2010","unstructured":"Ning Zhong, Yuefeng Li, and Sheng-Tang Wu. 2010. Effective pattern discovery for text mining. IEEE transactions on knowledge and data engineering 24, 1 (2010), 30--44."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00021"},{"key":"e_1_3_2_1_77_1","unstructured":"7 zip developer group. 2019. 7-zip file achiever home page. https:\/\/www.7-zip.org\/."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"}],"event":{"name":"EuroSys '23: Eighteenth European Conference on Computer Systems","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Rome Italy","acronym":"EuroSys '23"},"container-title":["Proceedings of the Eighteenth European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3567484","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552326.3567484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:43:36Z","timestamp":1750272216000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3567484"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":78,"alternative-id":["10.1145\/3552326.3567484","10.1145\/3552326"],"URL":"https:\/\/doi.org\/10.1145\/3552326.3567484","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]},"assertion":[{"value":"2023-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}