{"id":"https://openalex.org/W133660033","doi":null,"title":"Towards High Availability for High-Performance Computing System Services: Accomplishments and Limitations","display_name":"Towards High Availability for High-Performance Computing System Services: Accomplishments and Limitations","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W133660033","mag":"133660033"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.5792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.5792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://xcr.cenit.latech.edu/hapcw2006/program/papers/engelmann06towards.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W133660033"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416","observed_orcids":["https://orcid.org/0000-0003-4365-6416"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":"https://orcid.org/0000-0003-4365-6416","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046213835","display_name":"Steven L. Scott","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven L. Scott","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066119931","display_name":"Leangsuksun Chokchai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leangsuksun Chokchai","raw_affiliation_strings":["Louisiana Tech University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana Tech University ,","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087956045","display_name":"Xubin He","orcid":"https://orcid.org/0000-0002-5071-2861","observed_orcids":["https://orcid.org/0000-0002-5071-2861","https://orcid.org/0000-0003-4220-7846"]},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xubin He","raw_affiliation_strings":["Tennessee Technological University"],"raw_orcid":"https://orcid.org/0000-0002-5071-2861","affiliations":[{"raw_affiliation_string":"Tennessee Technological University","institution_ids":["https://openalex.org/I63920570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1463,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84063298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9746000170707703,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9746000170707703,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.023000000044703484,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/high-availability","display_name":"high availability","score":0.9990000128746033},{"id":"https://openalex.org/keywords/high-performance-computing-systems","display_name":"high-performance computing systems","score":0.9139999747276306},{"id":"https://openalex.org/keywords/redundancy-strategies","display_name":"redundancy strategies","score":0.8309999704360962},{"id":"https://openalex.org/keywords/service-nodes","display_name":"service nodes","score":0.9649999737739563},{"id":"https://openalex.org/keywords/single-point-of-failure","display_name":"single point of failure","score":0.8569999933242798},{"id":"https://openalex.org/keywords/job-management","display_name":"job management","score":0.6990000009536743},{"id":"https://openalex.org/keywords/resource-management","display_name":"resource management","score":0.9959999918937683},{"id":"https://openalex.org/keywords/reliability-availability-and-serviceability","display_name":"reliability, availability, and serviceability","score":0.9369999766349792}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.720862865447998},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7093379497528076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6168893575668335},{"id":"https://openalex.org/C65813073","wikidata":"https://www.wikidata.org/wiki/Q1622420","display_name":"High availability","level":2,"score":0.5629715919494629},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4904153048992157},{"id":"https://openalex.org/C110245778","wikidata":"https://www.wikidata.org/wiki/Q2169658","display_name":"Serviceability (structure)","level":2,"score":0.4665237367153168},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4240246117115021},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.35896116495132446},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.287910521030426},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2873588800430298},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2621901035308838},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2507554292678833},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.5792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.5792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://xcr.cenit.latech.edu/hapcw2006/program/papers/engelmann06towards.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.610.7446","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.610.7446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.cct.lsu.edu/~estrabd/LACSI2006/workshops/workshop1/papers/engelmann06towards.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.9033","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.9033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csm.ornl.gov/~engelman/publications/engelmann06towards.pdf","raw_type":"text"},{"id":"mag:133660033","doi":null,"is_oa":false,"landing_page_url":"https://www.cct.lsu.edu/~estrabd/LACSI2006/workshops/workshop1/papers/engelmann06towards.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W119120648","https://openalex.org/W1504623286","https://openalex.org/W1595596071","https://openalex.org/W1596936080","https://openalex.org/W1990336866","https://openalex.org/W2030018523","https://openalex.org/W2077982907","https://openalex.org/W2081780581","https://openalex.org/W2148016597","https://openalex.org/W2156219632"],"related_works":["https://openalex.org/W2139199427","https://openalex.org/W2098740653","https://openalex.org/W2597895538","https://openalex.org/W2061441611","https://openalex.org/W79276452","https://openalex.org/W2148016597","https://openalex.org/W2135739350","https://openalex.org/W2944461282","https://openalex.org/W2083924499","https://openalex.org/W4283395245"],"abstract_inverted_index":{"During":[0],"the":[1,38],"last":[2],"several":[3],"years,":[4],"our":[5,76,99],"teams":[6],"at":[7],"Oak":[8],"Ridge":[9],"National":[10],"Laboratory,":[11],"Louisiana":[12],"Tech":[13],"University,":[14],"and":[15,26,56,59,65,84,93,105,109],"Tennessee":[16],"Technological":[17],"University":[18],"focused":[19],"on":[20],"efficient":[21],"redundancy":[22],"strategies":[23],"for":[24,40,67,87,123],"head":[25],"service":[27],"nodes":[28,47],"of":[29,63,75],"high-performance":[30],"computing":[31],"(HPC)":[32],"systems":[33,89],"in":[34,44],"order":[35],"to":[36,79,119],"pave":[37],"way":[39],"high":[41],"availability":[42],"(HA)":[43],"HPC.":[45],"These":[46],"typically":[48],"run":[49],"critical":[50],"HPC":[51,70,88,94],"system":[52],"services,":[53],"like":[54],"job":[55],"resource":[57],"management,":[58],"represent":[60],"sin-gle":[61],"points":[62],"failure":[64],"control":[66],"an":[68],"entire":[69],"sys-tem.":[71],"The":[72],"overarching":[73],"goal":[74],"research":[77],"is":[78],"pro-vide":[80],"high-level":[81],"reliability,":[82],"availability,":[83],"serviceabil-ity":[85],"(RAS)":[86],"by":[90],"combining":[91],"HA":[92],"technology.":[95],"This":[96],"paper":[97],"summarizes":[98],"accomplish-ments,":[100],"such":[101,113],"as":[102,114],"developed":[103],"concepts":[104],"implemented":[106],"proof-of-concept":[107],"prototypes,":[108],"describes":[110],"existing":[111],"lim-itations,":[112],"performance":[115],"issues,":[116],"which":[117],"need":[118],"be":[120],"dealt":[121],"with":[122],"production-type":[124],"deployment.":[125]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2016-06-24T00:00:00"}
