{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:02:27Z","timestamp":1779062547033,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF","award":["1846158, 1822933"],"award-info":[{"award-number":["1846158, 1822933"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517845","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"617-630","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Tastes Great! Less Filling! High Performance and Accurate Training Data Collection for Self-Driving Database Management Systems"],"prefix":"10.1145","author":[{"given":"Matthew","family":"Butrovich","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wan Shen","family":"Lim","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Rollinson","sequence":"additional","affiliation":[{"name":"Army Cyber Institute, West Point, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Xia","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Pavlo","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497466"},{"key":"e_1_3_2_1_2_1","unstructured":"Amazon Web Services Inc. 2021. Amazon RDS Performance Insights. https:\/\/aws.amazon.com\/rds\/performance-insights\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Chris Andrews. 2017. chrisa\/libusdt: Create DTrace probes at runtime. https:\/\/github.com\/chrisa\/libusdt ."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362704"},{"key":"e_1_3_2_1_6_1","unstructured":"BenchBase. 2013. GitHub - cmu-db\/benchbase: Multi-DBMS SQL Benchmarking Framework via JDBC. https:\/\/github.com\/cmu-db\/benchbase ."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2008 International Conference on Management of Data (SIGMOD '08)","author":"Cahill Michael J.","unstructured":"Michael J. Cahill, Uwe R\u00f6 hm, and Alan D. Fekete. 2008. Serializable isolation for snapshot databases. In Proceedings of the 2008 International Conference on Management of Data (SIGMOD '08). 729--738."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1988842.1988850"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314035"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732240.2732246"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687767"},{"key":"e_1_3_2_1_13_1","unstructured":"Facebook. 2021. folly\/tracing: Utility for User-level Statically Defined Tracing. https:\/\/github.com\/facebook\/folly\/tree\/master\/folly\/tracing ."},{"key":"e_1_3_2_1_14_1","volume-title":"X-Trace: A Pervasive Network Tracing Framework. In 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07)","author":"Fonseca Rodrigo","year":"2007","unstructured":"Rodrigo Fonseca, George Porter, Randy H. Katz, and Scott Shenker. 2007. X-Trace: A Pervasive Network Tracing Framework. In 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07) ."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304004"},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"Volcano","volume":"6","author":"Graefe G.","year":"1994","unstructured":"G. Graefe. 1994. Volcano: An Extensible and Parallel Query Evaluation System., Vol. 6, 1 (Feb. 1994), 120--135.","journal-title":"An Extensible and Parallel Query Evaluation System."},{"key":"e_1_3_2_1_17_1","volume-title":"BPF Performance Tools: Linux System and Application Observability","author":"Gregg Brendan","unstructured":"Brendan Gregg. 2019. BPF Performance Tools: Linux System and Application Observability 1st ed.). Addison-Wesley Professional.","edition":"1"},{"key":"e_1_3_2_1_18_1","volume-title":"Capturing and Enhancing In Situ System Observability for Failure Detection. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI '18)","author":"Huang Peng","year":"2018","unstructured":"Peng Huang, Chuanxiong Guo, Jacob R. Lorch, Lidong Zhou, and Yingnong Dang. 2018. Capturing and Enhancing In Situ System Observability for Failure Detection. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI '18). 1--16."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3456859.3456863"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320218"},{"key":"e_1_3_2_1_21_1","volume-title":"Sagedb: A learned database system. In CIDR .","author":"Kraska Tim","year":"2019","unstructured":"Tim Kraska, Mohammad Alizadeh, Alex Beutel, H Chi, Ani Kristo, Guillaume Leclerc, Samuel Madden, Hongzi Mao, and Vikram Nathan. 2019. Sagedb: A learned database system. In CIDR ."},{"key":"e_1_3_2_1_22_1","unstructured":"Cockroach Labs. 2021. EXPLAIN ANALYZE | CockroachDB Docs. https:\/\/www.cockroachlabs.com\/docs\/stable\/explain-analyze.html ."},{"key":"e_1_3_2_1_23_1","volume-title":"2020 IEEE 9th International Conference on Cloud Networking (CloudNet). 1--8.","author":"Levin Joshua","unstructured":"Joshua Levin and Theophilus A. Benson. 2020. ViperProbe: Rethinking Microservice Observability with eBPF. In 2020 IEEE 9th International Conference on Cloud Networking (CloudNet). 1--8."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352129"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476380"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/3436905.3436913"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 2018 International Conference on Management of Data (SIGMOD '18)","author":"Ma Lin","unstructured":"Lin Ma, Dana Van Aken, Ahmed Hefny, Gustavo Mezerhane, Andrew Pavlo, and Geoffrey J. Gordon. 2018. Query-based Workload Forecasting for Self-Driving Database Management Systems. In Proceedings of the 2018 International Conference on Management of Data (SIGMOD '18). 631--645."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457276"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342646"},{"key":"e_1_3_2_1_30_1","unstructured":"MariaDB. 2021. MariaDB Enterprise Documentation. https:\/\/mariadb.com\/docs\/reference\/mdb\/system-variables\/join_buffer_size\/."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2018.00034"},{"key":"e_1_3_2_1_32_1","first-page":"1","article-title":"RCU Usage In the Linux Kernel","volume":"54","author":"McKenney Paul E.","year":"2020","unstructured":"Paul E. McKenney, Joel Fernandes, Silas Boyd-Wickizer, and Jonathan Walpole. 2020. RCU Usage In the Linux Kernel: Eighteen Years Later. SIGOPS Oper. Syst. Rev., Vol. 54, 1 (Aug. 2020), 47--63.","journal-title":"Eighteen Years Later. SIGOPS Oper. Syst. Rev."},{"key":"e_1_3_2_1_33_1","unstructured":"MongoDB Inc. 2019. mongodb\/mongo: usdt.h. https:\/\/github.com\/mongodb\/mongo\/blob\/master\/src\/mongo\/platform\/usdt.h ."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2467800"},{"key":"e_1_3_2_1_35_1","unstructured":"MySQL. 2007. mysql\/mysql-server: sql_profile.cc. https:\/\/github.com\/mysql\/mysql-server\/blob\/8.0\/sql\/sql_profile.cc ."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/2002938.2002940"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749436"},{"key":"e_1_3_2_1_38_1","unstructured":"Oracle. 2021. Self-Driving Database | Autonomous Database Oracle 19c. https:\/\/oracle.com\/database\/autonomous-database\/."},{"key":"e_1_3_2_1_39_1","unstructured":"Oracle Corporation. 2015. MySQL 5.7 Reference Manual :: 5.8.4 Tracing mysqld Using DTrace. https:\/\/dev.mysql.com\/doc\/refman\/5.7\/en\/dba-dtrace-server.html ."},{"key":"e_1_3_2_1_40_1","volume-title":"Ziqi Wang, Yingjun Wu, Ran Xian, and Tieying Zhang.","author":"Pavlo Andrew","year":"2017","unstructured":"Andrew Pavlo, Gustavo Angulo, Joy Arulraj, Haibin Lin, Jiexi Lin, Lin Ma, Prashanth Menon, Todd Mowry, Matthew Perron, Ian Quah, Siddharth Santurkar, Anthony Tomasic, Skye Toor, Dana Van Aken, Ziqi Wang, Yingjun Wu, Ran Xian, and Tieying Zhang. 2017. Self-Driving Database Management Systems. In CIDR ."},{"key":"e_1_3_2_1_41_1","volume-title":"Lisa Lee, and Ruslan Salakhutdinov.","author":"Pavlo Andrew","year":"2019","unstructured":"Andrew Pavlo, Matthew Butrovich, Ananya Joshi, Lin Ma, Prashanth Menon, Dana Van Aken, Lisa Lee, and Ruslan Salakhutdinov. 2019. External vs. Internal: An Essay on Machine Learning Agents for Autonomous Database Management Systems. IEEE Data Engineering Bulletin (June 2019), 32--46."},{"key":"e_1_3_2_1_42_1","unstructured":"PostgreSQL. 2002. postgres\/postgres: getrusage.c. https:\/\/github.com\/postgres\/postgres\/blob\/master\/src\/port\/getrusage.c ."},{"key":"e_1_3_2_1_43_1","unstructured":"PostgreSQL. 2006 a. postgres\/postgres: probes.d. https:\/\/github.com\/postgres\/postgres\/blob\/master\/src\/backend\/utils\/probes.d ."},{"key":"e_1_3_2_1_44_1","unstructured":"PostgreSQL. 2006 b. PostgreSQL: Documentation: 14: EXPLAIN. https:\/\/www.postgresql.org\/docs\/current\/sql-explain.html ."},{"key":"e_1_3_2_1_45_1","unstructured":"SolarWinds. 2021. Database Performance Monitor (DPM) | SolarWinds. https:\/\/vividcortex.com\/."},{"key":"e_1_3_2_1_46_1","volume-title":"LKML: Alexei Starovoitov [PATCH net-next] extended BPF. https:\/\/lkml.org\/lkml\/2013\/9\/30\/627 .","author":"Starovoitov Alexei","year":"2013","unstructured":"Alexei Starovoitov. 2013. LKML: Alexei Starovoitov [PATCH net-next] extended BPF. https:\/\/lkml.org\/lkml\/2013\/9\/30\/627 ."},{"key":"e_1_3_2_1_47_1","unstructured":"Sthima. 2017. sthima\/libstapsdt: Create Systemtap's USDT probes at runtime. https:\/\/github.com\/sthima\/libstapsdt ."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135977"},{"key":"e_1_3_2_1_49_1","unstructured":"The Transaction Processing Council. 2007. TPC-C Benchmark (Revision 5.9.0). http:\/\/www.tpc.org\/tpcc\/spec\/tpcc_current.pdf ."},{"key":"e_1_3_2_1_50_1","unstructured":"Linus Torvalds. 2012. kernel\/git\/torvalds\/linux.git - Linux kernel source tree. https:\/\/git.kernel.org\/pub\/scm\/linux\/kernel\/git\/torvalds\/linux.git\/commit\/?id=654443e20dfc0617231f28a07c96a979ee1a0239 ."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064029"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452754"},{"key":"e_1_3_2_1_53_1","unstructured":"Vince Weaver. 2013. The Unofficial Linux Perf Events Web-Page. http:\/\/web.eece.maine.edu\/ vweaver\/projects\/perf_events\/."},{"key":"e_1_3_2_1_54_1","unstructured":"Antoni Wolski. 2009. TATP Benchmark Description (Version 1.0). http:\/\/tatpbenchmark.sourceforge.net ."},{"key":"e_1_3_2_1_55_1","volume-title":"MicroRCA: Root Cause Localization of PerformanceIssues in Microservices. In IEEE\/IFIP Network Operations and Management Symposium (NOMS '20)","author":"Wu Li","year":"2020","unstructured":"Li Wu, Johan Tordsson, Erik Elmroth, and Odej Kao. 2020. MicroRCA: Root Cause Localization of PerformanceIssues in Microservices. In IEEE\/IFIP Network Operations and Management Symposium (NOMS '20). IEEE, 1--9."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300085"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397238"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517845","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:35Z","timestamp":1750188635000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":57,"alternative-id":["10.1145\/3514221.3517845","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517845","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}