Toddler: detecting performance problems via similar memory-access patterns
Performance bugs are programming errors that create significant performance degradation. While developers often use automated oracles for detecting functional bugs, detecting performance bugs usually requires time-consuming, manual analysis of execution profiles. The human effort for performance ana...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 571 |
|---|---|
| container_issue | |
| container_start_page | 562 |
| container_title | |
| container_volume | |
| creator | Nistor, Adrian Song, Linhai Marinov, Darko Lu, Shan |
| description | Performance bugs are programming errors that create significant performance degradation. While developers often use automated oracles for detecting functional bugs, detecting performance bugs usually requires time-consuming, manual analysis of execution profiles. The human effort for performance analysis limits the number of performance tests analyzed and enables performance bugs to easily escape to production. Unfortunately, while profilers can successfully localize slow executing code, profilers cannot be effectively used as automated oracles. This paper presents TODDLER, a novel automated oracle for performance bugs, which enables testing for performance bugs to use the well established and automated process of testing for functional bugs. TODDLER reports code loops whose computation has repetitive and partially similar memory-access patterns across loop iterations. Such repetitive work is likely unnecessary and can be done faster. We implement TODDLER for Java and evaluate it on 9 popular Java codebases. Our experiments with 11 previously known, real-world performance bugs show that TODDLER finds these bugs with a higher accuracy than the standard Java profiler. Using TODDLER, we also found 42 new bugs in six Java projects: Ant, Google Core Libraries, JUnit, Apache Collections, JDK, and JFreeChart. Based on our bug reports, developers so far fixed 10 bugs and confirmed 6 more as real bugs. |
| doi_str_mv | 10.5555/2486788.2486862 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>acm</sourceid><recordid>TN_cdi_acm_books_10_5555_2486788_2486862</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>acm_books_10_5555_2486788_2486862</sourcerecordid><originalsourceid>FETCH-LOGICAL-a157t-f82161ed37b65e2a7d05cad6c1aadb0835336a05c6ac459eda337d27dc63b9863</originalsourceid><addsrcrecordid>eNqNj01LxDAYhAMiqOuevebopTVpmo96k0VdZcHLeg5vkrdSbZuSFMF_bxf7AxwYBgZm4CHkhrNSLrqraqO0MeUpjarOyBWvlRaCacUuyDbnT8YY581ifUlejzGEHtM9DTijn7vxg06Y2pgGGD3SKUXX45Dpdwc0d0PXQ6IDDjH9FOA95kwnmGdMY74m5y30Gbdrbsj70-Nxty8Ob88vu4dDAVzquWhNxRXHILRTEivQgUkPQXkOEBwzQgqhYOkU-Fo2GEAIHSodvBKuMUpsSPn3C36wLsavbDmzJ3a7stuV3brUYbsMbv85EL97jlv5</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Toddler: detecting performance problems via similar memory-access patterns</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Nistor, Adrian ; Song, Linhai ; Marinov, Darko ; Lu, Shan</creator><creatorcontrib>Nistor, Adrian ; Song, Linhai ; Marinov, Darko ; Lu, Shan</creatorcontrib><description>Performance bugs are programming errors that create significant performance degradation. While developers often use automated oracles for detecting functional bugs, detecting performance bugs usually requires time-consuming, manual analysis of execution profiles. The human effort for performance analysis limits the number of performance tests analyzed and enables performance bugs to easily escape to production. Unfortunately, while profilers can successfully localize slow executing code, profilers cannot be effectively used as automated oracles. This paper presents TODDLER, a novel automated oracle for performance bugs, which enables testing for performance bugs to use the well established and automated process of testing for functional bugs. TODDLER reports code loops whose computation has repetitive and partially similar memory-access patterns across loop iterations. Such repetitive work is likely unnecessary and can be done faster. We implement TODDLER for Java and evaluate it on 9 popular Java codebases. Our experiments with 11 previously known, real-world performance bugs show that TODDLER finds these bugs with a higher accuracy than the standard Java profiler. Using TODDLER, we also found 42 new bugs in six Java projects: Ant, Google Core Libraries, JUnit, Apache Collections, JDK, and JFreeChart. Based on our bug reports, developers so far fixed 10 bugs and confirmed 6 more as real bugs.</description><identifier>ISBN: 1467330760</identifier><identifier>ISBN: 9781467330763</identifier><identifier>DOI: 10.5555/2486788.2486862</identifier><language>eng</language><publisher>Piscataway, NJ, USA: IEEE Press</publisher><subject>Computer systems organization -- Dependable and fault-tolerant systems and networks ; General and reference -- Cross-computing tools and techniques -- Metrics ; General and reference -- Cross-computing tools and techniques -- Performance ; Networks -- Network performance evaluation ; Social and professional topics -- Professional topics -- Management of computing and information systems -- Software management -- Software maintenance ; Software and its engineering -- Software creation and management -- Software post-development issues</subject><ispartof>Proceedings of the 2013 International Conference on Software Engineering, 2013, p.562-571</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,776,780,785,786,27902</link.rule.ids></links><search><creatorcontrib>Nistor, Adrian</creatorcontrib><creatorcontrib>Song, Linhai</creatorcontrib><creatorcontrib>Marinov, Darko</creatorcontrib><creatorcontrib>Lu, Shan</creatorcontrib><title>Toddler: detecting performance problems via similar memory-access patterns</title><title>Proceedings of the 2013 International Conference on Software Engineering</title><description>Performance bugs are programming errors that create significant performance degradation. While developers often use automated oracles for detecting functional bugs, detecting performance bugs usually requires time-consuming, manual analysis of execution profiles. The human effort for performance analysis limits the number of performance tests analyzed and enables performance bugs to easily escape to production. Unfortunately, while profilers can successfully localize slow executing code, profilers cannot be effectively used as automated oracles. This paper presents TODDLER, a novel automated oracle for performance bugs, which enables testing for performance bugs to use the well established and automated process of testing for functional bugs. TODDLER reports code loops whose computation has repetitive and partially similar memory-access patterns across loop iterations. Such repetitive work is likely unnecessary and can be done faster. We implement TODDLER for Java and evaluate it on 9 popular Java codebases. Our experiments with 11 previously known, real-world performance bugs show that TODDLER finds these bugs with a higher accuracy than the standard Java profiler. Using TODDLER, we also found 42 new bugs in six Java projects: Ant, Google Core Libraries, JUnit, Apache Collections, JDK, and JFreeChart. Based on our bug reports, developers so far fixed 10 bugs and confirmed 6 more as real bugs.</description><subject>Computer systems organization -- Dependable and fault-tolerant systems and networks</subject><subject>General and reference -- Cross-computing tools and techniques -- Metrics</subject><subject>General and reference -- Cross-computing tools and techniques -- Performance</subject><subject>Networks -- Network performance evaluation</subject><subject>Social and professional topics -- Professional topics -- Management of computing and information systems -- Software management -- Software maintenance</subject><subject>Software and its engineering -- Software creation and management -- Software post-development issues</subject><isbn>1467330760</isbn><isbn>9781467330763</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid/><recordid>eNqNj01LxDAYhAMiqOuevebopTVpmo96k0VdZcHLeg5vkrdSbZuSFMF_bxf7AxwYBgZm4CHkhrNSLrqraqO0MeUpjarOyBWvlRaCacUuyDbnT8YY581ifUlejzGEHtM9DTijn7vxg06Y2pgGGD3SKUXX45Dpdwc0d0PXQ6IDDjH9FOA95kwnmGdMY74m5y30Gbdrbsj70-Nxty8Ob88vu4dDAVzquWhNxRXHILRTEivQgUkPQXkOEBwzQgqhYOkU-Fo2GEAIHSodvBKuMUpsSPn3C36wLsavbDmzJ3a7stuV3brUYbsMbv85EL97jlv5</recordid><startdate>20130518</startdate><enddate>20130518</enddate><creator>Nistor, Adrian</creator><creator>Song, Linhai</creator><creator>Marinov, Darko</creator><creator>Lu, Shan</creator><general>IEEE Press</general><scope/></search><sort><creationdate>20130518</creationdate><title>Toddler: detecting performance problems via similar memory-access patterns</title><author>Nistor, Adrian ; Song, Linhai ; Marinov, Darko ; Lu, Shan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a157t-f82161ed37b65e2a7d05cad6c1aadb0835336a05c6ac459eda337d27dc63b9863</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Computer systems organization -- Dependable and fault-tolerant systems and networks</topic><topic>General and reference -- Cross-computing tools and techniques -- Metrics</topic><topic>General and reference -- Cross-computing tools and techniques -- Performance</topic><topic>Networks -- Network performance evaluation</topic><topic>Social and professional topics -- Professional topics -- Management of computing and information systems -- Software management -- Software maintenance</topic><topic>Software and its engineering -- Software creation and management -- Software post-development issues</topic><toplevel>online_resources</toplevel><creatorcontrib>Nistor, Adrian</creatorcontrib><creatorcontrib>Song, Linhai</creatorcontrib><creatorcontrib>Marinov, Darko</creatorcontrib><creatorcontrib>Lu, Shan</creatorcontrib></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nistor, Adrian</au><au>Song, Linhai</au><au>Marinov, Darko</au><au>Lu, Shan</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Toddler: detecting performance problems via similar memory-access patterns</atitle><btitle>Proceedings of the 2013 International Conference on Software Engineering</btitle><date>2013-05-18</date><risdate>2013</risdate><spage>562</spage><epage>571</epage><pages>562-571</pages><isbn>1467330760</isbn><isbn>9781467330763</isbn><abstract>Performance bugs are programming errors that create significant performance degradation. While developers often use automated oracles for detecting functional bugs, detecting performance bugs usually requires time-consuming, manual analysis of execution profiles. The human effort for performance analysis limits the number of performance tests analyzed and enables performance bugs to easily escape to production. Unfortunately, while profilers can successfully localize slow executing code, profilers cannot be effectively used as automated oracles. This paper presents TODDLER, a novel automated oracle for performance bugs, which enables testing for performance bugs to use the well established and automated process of testing for functional bugs. TODDLER reports code loops whose computation has repetitive and partially similar memory-access patterns across loop iterations. Such repetitive work is likely unnecessary and can be done faster. We implement TODDLER for Java and evaluate it on 9 popular Java codebases. Our experiments with 11 previously known, real-world performance bugs show that TODDLER finds these bugs with a higher accuracy than the standard Java profiler. Using TODDLER, we also found 42 new bugs in six Java projects: Ant, Google Core Libraries, JUnit, Apache Collections, JDK, and JFreeChart. Based on our bug reports, developers so far fixed 10 bugs and confirmed 6 more as real bugs.</abstract><cop>Piscataway, NJ, USA</cop><pub>IEEE Press</pub><doi>10.5555/2486788.2486862</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISBN: 1467330760 |
| ispartof | Proceedings of the 2013 International Conference on Software Engineering, 2013, p.562-571 |
| issn | |
| language | eng |
| recordid | cdi_acm_books_10_5555_2486788_2486862 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computer systems organization -- Dependable and fault-tolerant systems and networks General and reference -- Cross-computing tools and techniques -- Metrics General and reference -- Cross-computing tools and techniques -- Performance Networks -- Network performance evaluation Social and professional topics -- Professional topics -- Management of computing and information systems -- Software management -- Software maintenance Software and its engineering -- Software creation and management -- Software post-development issues |
| title | Toddler: detecting performance problems via similar memory-access patterns |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T04%3A59%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-acm&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Toddler:%20detecting%20performance%20problems%20via%20similar%20memory-access%20patterns&rft.btitle=Proceedings%20of%20the%202013%20International%20Conference%20on%20Software%20Engineering&rft.au=Nistor,%20Adrian&rft.date=2013-05-18&rft.spage=562&rft.epage=571&rft.pages=562-571&rft.isbn=1467330760&rft.isbn_list=9781467330763&rft_id=info:doi/10.5555/2486788.2486862&rft_dat=%3Cacm%3Eacm_books_10_5555_2486788_2486862%3C/acm%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |