{"id":"https://openalex.org/W2965448370","doi":"https://doi.org/10.1145/3332186.3332233","title":"Implementing a Flexible, Fault Tolerant Job Management System for Science Gateways","display_name":"Implementing a Flexible, Fault Tolerant Job Management System for Science Gateways","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965448370","doi":"https://doi.org/10.1145/3332186.3332233","mag":"2965448370"},"language":"en","primary_location":{"id":"doi:10.1145/3332186.3332233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3332186.3332233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3332186.3332233","source":{"id":"https://openalex.org/S4306524297","display_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3332186.3332233","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041614898","display_name":"Dimuthu Wannipurage","orcid":"https://orcid.org/0000-0001-6276-9059"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimuthu Wannipurage","raw_affiliation_strings":["Science Gateways Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateways Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037778136","display_name":"Suresh Marru","orcid":"https://orcid.org/0000-0002-6374-095X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Marru","raw_affiliation_strings":["Science Gateway Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateway Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081273814","display_name":"Marlon Piece","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marlon Piece","raw_affiliation_strings":["Science Gateway Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateway Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Eroma Abeysinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eroma Abeysinghe","raw_affiliation_strings":["Science Gateway Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateway Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038263103","display_name":"Sudhakar Pamidighantam","orcid":"https://orcid.org/0000-0002-6247-7504"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudhakar Pamidighantam","raw_affiliation_strings":["Science Gateway Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateway Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027985692","display_name":"Marcus Christie","orcid":"https://orcid.org/0000-0001-5458-9947"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcus Christie","raw_affiliation_strings":["Science Gateway Research Center, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Gateway Research Center, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026423768","display_name":"Gourav Shenoy","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gourav Shenoy","raw_affiliation_strings":["IBM Watson Health, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Health, Cambridge, MA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034682424","display_name":"Ajinkya Dhamnaskar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajinkya Dhamnaskar","raw_affiliation_strings":["Microsoft, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000928748","display_name":"Lahiru Jayathilaka","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Lahiru Jayathilaka","raw_affiliation_strings":["University of Moratuwa, Colombo, Srilanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Moratuwa, Colombo, Srilanka","institution_ids":["https://openalex.org/I195740183"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8868,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87755316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.7503030300140381},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5737625956535339},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5653409361839294},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5133101344108582},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5086618065834045},{"id":"https://openalex.org/keywords/system-administrator","display_name":"System administrator","score":0.49067556858062744},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4849543571472168},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.472595751285553},{"id":"https://openalex.org/keywords/high-availability","display_name":"High availability","score":0.4675922095775604},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.45085611939430237},{"id":"https://openalex.org/keywords/gateway","display_name":"Gateway (web page)","score":0.41315802931785583},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36956748366355896},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28378742933273315},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.19573920965194702},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12569475173950195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503030300140381},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5737625956535339},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5653409361839294},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5133101344108582},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5086618065834045},{"id":"https://openalex.org/C2780814629","wikidata":"https://www.wikidata.org/wiki/Q327353","display_name":"System administrator","level":2,"score":0.49067556858062744},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4849543571472168},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.472595751285553},{"id":"https://openalex.org/C65813073","wikidata":"https://www.wikidata.org/wiki/Q1622420","display_name":"High availability","level":2,"score":0.4675922095775604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.45085611939430237},{"id":"https://openalex.org/C2777710495","wikidata":"https://www.wikidata.org/wiki/Q5527195","display_name":"Gateway (web page)","level":2,"score":0.41315802931785583},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36956748366355896},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28378742933273315},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.19573920965194702},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12569475173950195},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3332186.3332233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3332186.3332233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3332186.3332233","source":{"id":"https://openalex.org/S4306524297","display_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3332186.3332233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3332186.3332233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3332186.3332233","source":{"id":"https://openalex.org/S4306524297","display_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G7726553634","display_name":null,"funder_award_id":"1339774","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965448370.pdf","grobid_xml":"https://content.openalex.org/works/W2965448370.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W882175666","https://openalex.org/W1529547272","https://openalex.org/W1899011294","https://openalex.org/W1976693239","https://openalex.org/W2028302194","https://openalex.org/W2059194600","https://openalex.org/W2069341504","https://openalex.org/W2070679139","https://openalex.org/W2123699854","https://openalex.org/W2129154270","https://openalex.org/W2167756108","https://openalex.org/W2180935464","https://openalex.org/W2290712622","https://openalex.org/W2309398411","https://openalex.org/W2509865457","https://openalex.org/W2600819636","https://openalex.org/W2609265534","https://openalex.org/W2725432521","https://openalex.org/W2857907774","https://openalex.org/W2913438032","https://openalex.org/W2917207851","https://openalex.org/W2917821888","https://openalex.org/W2948009782","https://openalex.org/W2979463162","https://openalex.org/W6696731696"],"related_works":["https://openalex.org/W3123141149","https://openalex.org/W2751414885","https://openalex.org/W2363040373","https://openalex.org/W2103295733","https://openalex.org/W2808531585","https://openalex.org/W4233801908","https://openalex.org/W1538240937","https://openalex.org/W1532689837","https://openalex.org/W2204165862","https://openalex.org/W1726064696"],"abstract_inverted_index":{"This":[0],"paper":[1],"summarizes":[2],"our":[3,26,29,85,99,153],"experiences":[4,33],"evaluating":[5],"and":[6,32,64,70,139,157,205],"deploying":[7],"a":[8,38],"new":[9,167],"task":[10],"execution":[11,211],"management":[12,103],"system":[13,104,168,180,197],"within":[14],"the":[15,60,81,94,178,182],"open":[16],"source":[17],"Apache":[18,78,106,116,137],"Airavata":[19,35,79,138],"framework":[20],"for":[21,42,83,119],"science":[22,163],"gateways.":[23],"We":[24,131],"base":[25],"choices":[27],"on":[28,77],"operational":[30,158],"requirements":[31],"running":[34],"software":[36],"as":[37,80,175,177],"multi-tenanted":[39],"production":[40],"service":[41],"multiple":[43,124],"gateway":[44,164],"clients.":[45,165],"Our":[46],"considerations":[47],"include":[48],"integrating":[49,67],"semi-independent":[50],"components,":[51],"making":[52],"major":[53],"upgrades":[54],"to":[55,98,122,171,193,203],"those":[56],"components":[57],"while":[58],"retaining":[59],"system's":[61],"overall":[62],"functionality,":[63],"choosing":[65],"between":[66],"third":[68],"party":[69],"in-house":[71,101,196],"developed":[72],"components.":[73],"While":[74],"we":[75,113,185],"focus":[76],"platform":[82],"evaluation,":[84],"results":[86],"should":[87],"be":[88,172],"of":[89,96,149],"general":[90],"interest.":[91],"After":[92],"considering":[93],"options":[95],"extensions":[97],"previous,":[100],"job":[102,210],"using":[105],"Kafka":[107],"or":[108],"replacing":[109],"it":[110],"with":[111,146,160,181],"Kubernetes,":[112],"ultimately":[114],"chose":[115],"Helix,":[117],"primarily":[118],"its":[120],"ability":[121],"execute":[123],"tasks":[125],"coupled":[126],"into":[127,136],"directed":[128],"acyclic":[129],"graphs.":[130],"have":[132,140,187],"integrated":[133],"this":[134],"approach":[135],"tested":[141],"extensively":[142],"over":[143],"several":[144],"months":[145],"many":[147],"thousands":[148],"jobs,":[150],"both":[151],"from":[152],"internal":[154],"throughput":[155],"testing":[156],"tests":[159],"early":[161],"adopter":[162],"The":[166],"has":[169],"proven":[170],"at":[173],"least":[174],"reliable":[176],"previous":[179],"advantages":[183],"that":[184,198],"now":[186],"simplified":[188],"maintenance,":[189],"do":[190],"not":[191],"need":[192],"support":[194,207],"an":[195],"required":[199],"extensive":[200],"developer":[201],"training":[202],"modify,":[204],"can":[206],"more":[208],"sophisticated":[209],"scenarios.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
