{"_id":"RuaXiPZPmB4T6wnnc","bibbaseid":"dean-nguyen-gu-zhang-rhee-arora-jiang-perfscopepracticalonlineserverperformancebuginferenceinproductioncloudcomputinginfrastructures-2014","downloads":0,"creationDate":"2016-10-15T13:23:04.489Z","title":"PerfScope: Practical Online Server Performance Bug Inference in Production Cloud Computing Infrastructures","author_short":["Dean, D. J.","Nguyen, H.","Gu, X.","Zhang, H.","Rhee, J.","Arora, N.","Jiang, G."],"year":2014,"bibtype":"inproceedings","biburl":"http://bibbase.org/zotero/pentarious","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"PerfScope: Practical Online Server Performance Bug Inference in Production Cloud Computing Infrastructures","abstract":"Performance bugs which manifest in a production cloud computing infrastructure are notoriously difficult to diagnose because of both the difficulty of reproducing those bugs and the lack of debugging information. In this paper, we present PerfScope, a practical online performance bug inference tool to help the developer understand how a performance bug happened during the production run. PerfScope achieves online bug inference to obviate the need for offline bug reproduction. PerfScope does not require application source code or any runtime instrumentation to the production system. PerfScope is application-agnostic, which can support both interpreted and compiled programs running inside a cloud infrastructure. We have implemented PerfScope and tested it using real performance bugs on seven popular open source server systems (Hadoop, HDFS, Cassandra, Tomcat, Apache, Lighttpd, MySQL). The results show that PerfScope can narrow down the search scope of the bug-related functions to a small percentage (0.03-2.3%) and rank the real bug-related functions within top five candidates in the majority of cases. PerfScope only imposes on average 1.8% runtime overhead to the tested server applications.","booktitle":"Proc. of the ACM Symp. on Cloud Computing","author":[{"propositions":[],"lastnames":["Dean"],"firstnames":["Daniel","J."],"suffixes":[]},{"propositions":[],"lastnames":["Nguyen"],"firstnames":["Hiep"],"suffixes":[]},{"propositions":[],"lastnames":["Gu"],"firstnames":["Xiaohui"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Hui"],"suffixes":[]},{"propositions":[],"lastnames":["Rhee"],"firstnames":["Junghwan"],"suffixes":[]},{"propositions":[],"lastnames":["Arora"],"firstnames":["Nipun"],"suffixes":[]},{"propositions":[],"lastnames":["Jiang"],"firstnames":["Geoff"],"suffixes":[]}],"year":"2014","keywords":"performance, reliability, testing and debugging, veniok","bibtex":"@inproceedings{dean_perfscope:_2014,\n\ttitle = {{PerfScope}: {Practical} {Online} {Server} {Performance} {Bug} {Inference} in {Production} {Cloud} {Computing} {Infrastructures}},\n\tabstract = {Performance bugs which manifest in a production cloud computing infrastructure are notoriously difficult to diagnose because of both the difficulty of reproducing those bugs and the lack of debugging information. In this paper, we present PerfScope, a practical online performance bug inference tool to help the developer understand how a performance bug happened during the production run. PerfScope achieves online bug inference to obviate the need for offline bug reproduction. PerfScope does not require application source code or any runtime instrumentation to the production system. PerfScope is application-agnostic, which can support both interpreted and compiled programs running inside a cloud infrastructure. We have implemented PerfScope and tested it using real performance bugs on seven popular open source server systems (Hadoop, HDFS, Cassandra, Tomcat, Apache, Lighttpd, MySQL). The results show that PerfScope can narrow down the search scope of the bug-related functions to a small percentage (0.03-2.3\\%) and rank the real bug-related functions within top five candidates in the majority of cases. PerfScope only imposes on average 1.8\\% runtime overhead to the tested server applications.},\n\tbooktitle = {Proc. of the {ACM} {Symp}. on {Cloud} {Computing}},\n\tauthor = {Dean, Daniel J. and Nguyen, Hiep and Gu, Xiaohui and Zhang, Hui and Rhee, Junghwan and Arora, Nipun and Jiang, Geoff},\n\tyear = {2014},\n\tkeywords = {performance, reliability, testing and debugging, veniok}\n}\n\n","author_short":["Dean, D. J.","Nguyen, H.","Gu, X.","Zhang, H.","Rhee, J.","Arora, N.","Jiang, G."],"key":"dean_perfscope:_2014","id":"dean_perfscope:_2014","bibbaseid":"dean-nguyen-gu-zhang-rhee-arora-jiang-perfscopepracticalonlineserverperformancebuginferenceinproductioncloudcomputinginfrastructures-2014","role":"author","urls":{},"keyword":["performance","reliability","testing and debugging","veniok"],"downloads":0},"search_terms":["perfscope","practical","online","server","performance","bug","inference","production","cloud","computing","infrastructures","dean","nguyen","gu","zhang","rhee","arora","jiang"],"keywords":["performance","reliability","testing and debugging","veniok"],"authorIDs":[],"dataSources":["QiRZ7m7shEMvADZkd"]}