{"id":"https://openalex.org/W2035085763","doi":"https://doi.org/10.1109/mascot.2009.5366158","title":"Efficient tracing and performance analysis for large distributed systems","display_name":"Efficient tracing and performance analysis for large distributed systems","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2035085763","doi":"https://doi.org/10.1109/mascot.2009.5366158","mag":"2035085763"},"language":"en","primary_location":{"id":"doi:10.1109/mascot.2009.5366158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascot.2009.5366158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041677248","display_name":"Eric Anderson","orcid":"https://orcid.org/0000-0001-9688-4135"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric Anderson","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113477896","display_name":"Christopher Hoover","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Hoover","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693397","display_name":"Xiaozhou Li","orcid":"https://orcid.org/0000-0002-6904-9393"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhou Li","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023021993","display_name":"Joseph Tucek","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Tucek","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA 94304 USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041677248"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":1.3714,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81960356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.9148155450820923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8298367857933044},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7687286138534546},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6853971481323242},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6381773352622986},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.631432056427002},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5910523533821106},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4208299219608307},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4014616012573242},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20426374673843384},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09631180763244629},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09442269802093506}],"concepts":[{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.9148155450820923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8298367857933044},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7687286138534546},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6853971481323242},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6381773352622986},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.631432056427002},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5910523533821106},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4208299219608307},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4014616012573242},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20426374673843384},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09631180763244629},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09442269802093506},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mascot.2009.5366158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascot.2009.5366158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W148956775","https://openalex.org/W1537198022","https://openalex.org/W1578335245","https://openalex.org/W2028660080","https://openalex.org/W2035562244","https://openalex.org/W2077967211","https://openalex.org/W2114716229","https://openalex.org/W2116435752","https://openalex.org/W2117020308","https://openalex.org/W2123536775","https://openalex.org/W2130843735","https://openalex.org/W2143229717","https://openalex.org/W2148451663","https://openalex.org/W2150542153","https://openalex.org/W2162870748","https://openalex.org/W2165202235","https://openalex.org/W2171369888","https://openalex.org/W2283715726","https://openalex.org/W2314485382","https://openalex.org/W2990299855","https://openalex.org/W3137220996","https://openalex.org/W3208940722","https://openalex.org/W4234891628","https://openalex.org/W4238807847","https://openalex.org/W4238860748","https://openalex.org/W6606033369","https://openalex.org/W6632104034","https://openalex.org/W6669897081","https://openalex.org/W6677690934","https://openalex.org/W7001507273"],"related_works":["https://openalex.org/W138412134","https://openalex.org/W3147005146","https://openalex.org/W2108078705","https://openalex.org/W2543101158","https://openalex.org/W2062141481","https://openalex.org/W1836768014","https://openalex.org/W1569638199","https://openalex.org/W2115308562","https://openalex.org/W2789571330","https://openalex.org/W4299652732"],"abstract_inverted_index":{"Distributed":[0],"systems":[1,18,27,37,100,154],"are":[2,233],"notoriously":[3],"difficult":[4],"to":[5,57,179,183,212,235],"implement":[6],"and":[7,188,220,225],"debug.":[8],"One":[9],"important":[10],"tool":[11],"for":[12,24,65,168,186],"understanding":[13],"the":[14,77],"behavior":[15,158],"of":[16,61,79,105,114,116,152,200],"distributed":[17,26,36,99,214,222,237],"is":[19],"tracing.":[20],"Unfortunately,":[21],"effective":[22,130],"tracing":[23,49,60,131,147,151],"modern":[25],"faces":[28],"several":[29],"challenges.":[30,140],"First,":[31],"many":[32],"interesting":[33],"behaviors":[34],"in":[35,55,72,111],"only":[38],"occur":[39],"rarely,":[40],"or":[41,159],"at":[42],"full":[43],"production":[44,62],"scale.":[45],"Hence":[46],"we":[47,229],"need":[48],"mechanisms":[50],"which":[51,149,194],"impose":[52],"minimal":[53],"overhead,":[54],"order":[56],"allow":[58],"always-on":[59],"instances.":[63],"Second,":[64],"high-speed":[66],"systems,":[67,215],"messages":[68],"can":[69,121],"be":[70],"delivered":[71],"significantly":[73],"less":[74],"time":[75,81,87,91,172],"than":[76],"error":[78],"traditional":[80],"synchronization":[82,173],"techniques":[83,93,135,193,211,232],"such":[84],"as":[85],"network":[86],"protocol":[88],"(NTP),":[89],"necessitating":[90],"adjustment":[92],"with":[94],"much":[95],"higher":[96],"precision.":[97],"Third,":[98],"today":[101],"may":[102],"generate":[103],"millions":[104],"events":[106],"per":[107],"second":[108],"systemwide,":[109],"resulting":[110],"traces":[112,120,197],"consisting":[113],"billions":[115,199],"events.":[117],"Such":[118],"large":[119,153],"overwhelm":[122],"existing":[123],"trace":[124,201],"analysis":[125],"tools.":[126],"These":[127],"challenges":[128],"make":[129],"difficult.":[132],"We":[133,206],"present":[134],"that":[136],"address":[137],"these":[138,210],"three":[139],"Our":[141],"contributions":[142],"include":[143],"(1)":[144],"a":[145,164,216,221],"low-overhead":[146],"mechanism,":[148],"allows":[150],"without":[155],"impacting":[156],"their":[157],"performance":[160],"(0.14":[161],"\u00bfs/event),":[162],"(2)":[163],"post":[165],"hoc":[166],"technique":[167],"producing":[169],"highly":[170],"accurate":[171],"across":[174],"hosts":[175],"(within":[176],"10/ts,":[177],"compared":[178],"between":[180],"100":[181],"\u00bfs":[182],"2":[184],"ms":[185],"NTP),":[187],"(3)":[189],"incremental":[190],"data":[191],"processing":[192],"facilitate":[195],"analyzing":[196],"containing":[198],"points":[202],"on":[203],"desktop":[204],"systems.":[205,238],"have":[207],"successfully":[208],"applied":[209],"two":[213],"cooperative":[217],"caching":[218],"system":[219],"storage":[223],"system,":[224],"from":[226],"our":[227,231],"experience,":[228],"believe":[230],"applicable":[234],"other":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}