{"id":"https://openalex.org/W4399730231","doi":"https://doi.org/10.31274/td-20240617-18","title":"Enhancing I/O observability and storage reliability in high-performance computing systems","display_name":"Enhancing I/O observability and storage reliability in high-performance computing systems","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399730231","doi":"https://doi.org/10.31274/td-20240617-18"},"language":"en","primary_location":{"id":"doi:10.31274/td-20240617-18","is_oa":true,"landing_page_url":"http://dx.doi.org/10.31274/td-20240617-18","pdf_url":"https://dr.lib.iastate.edu/bitstreams/c4681a5e-a7b4-492e-a645-484c5002562c/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dr.lib.iastate.edu/bitstreams/c4681a5e-a7b4-492e-a645-484c5002562c/download","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050327643","display_name":"Runzhou Han","orcid":"https://orcid.org/0000-0003-1440-7568"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Runzhou Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5050327643"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9991999864578247,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.761813759803772},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7576138377189636},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5940960049629211},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5717442035675049},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.560158908367157},{"id":"https://openalex.org/keywords/lustre","display_name":"Lustre (file system)","score":0.5463011264801025},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.544849157333374},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.46017590165138245},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4452360272407532},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41255858540534973},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3984875977039337},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3951054811477661},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34787002205848694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23338642716407776},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22158828377723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761813759803772},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7576138377189636},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5940960049629211},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5717442035675049},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.560158908367157},{"id":"https://openalex.org/C180699724","wikidata":"https://www.wikidata.org/wiki/Q1877782","display_name":"Lustre (file system)","level":3,"score":0.5463011264801025},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.544849157333374},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.46017590165138245},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4452360272407532},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41255858540534973},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3984875977039337},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3951054811477661},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34787002205848694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23338642716407776},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22158828377723694},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31274/td-20240617-18","is_oa":true,"landing_page_url":"http://dx.doi.org/10.31274/td-20240617-18","pdf_url":"https://dr.lib.iastate.edu/bitstreams/c4681a5e-a7b4-492e-a645-484c5002562c/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/3wxa4Kov","is_oa":false,"landing_page_url":"https://doi.org/10.31274/td-20240617-18","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dissertation"}],"best_oa_location":{"id":"doi:10.31274/td-20240617-18","is_oa":true,"landing_page_url":"http://dx.doi.org/10.31274/td-20240617-18","pdf_url":"https://dr.lib.iastate.edu/bitstreams/c4681a5e-a7b4-492e-a645-484c5002562c/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399730231.pdf","grobid_xml":"https://content.openalex.org/works/W4399730231.grobid-xml"},"referenced_works_count":163,"referenced_works":["https://openalex.org/W130792636","https://openalex.org/W154253821","https://openalex.org/W168132470","https://openalex.org/W188037868","https://openalex.org/W1412006679","https://openalex.org/W1423003888","https://openalex.org/W1444906800","https://openalex.org/W1444959585","https://openalex.org/W1486776102","https://openalex.org/W1548849615","https://openalex.org/W1550594210","https://openalex.org/W1552694902","https://openalex.org/W1559528097","https://openalex.org/W1765271930","https://openalex.org/W1834470623","https://openalex.org/W1838389500","https://openalex.org/W1847696060","https://openalex.org/W1858703999","https://openalex.org/W1865515598","https://openalex.org/W1905719725","https://openalex.org/W1927072723","https://openalex.org/W1964889439","https://openalex.org/W1983178058","https://openalex.org/W1993830711","https://openalex.org/W1994326726","https://openalex.org/W1995626000","https://openalex.org/W1997044393","https://openalex.org/W2002934700","https://openalex.org/W2003131282","https://openalex.org/W2019371364","https://openalex.org/W2023718005","https://openalex.org/W2032756564","https://openalex.org/W2039157918","https://openalex.org/W2043719859","https://openalex.org/W2046793036","https://openalex.org/W2056826630","https://openalex.org/W2063564815","https://openalex.org/W2067182386","https://openalex.org/W2069028640","https://openalex.org/W2069260454","https://openalex.org/W2073742357","https://openalex.org/W2079267582","https://openalex.org/W2096761130","https://openalex.org/W2099837838","https://openalex.org/W2100307454","https://openalex.org/W2103315535","https://openalex.org/W2105185344","https://openalex.org/W2105605904","https://openalex.org/W2106930560","https://openalex.org/W2119738171","https://openalex.org/W2128268793","https://openalex.org/W2135797505","https://openalex.org/W2138555106","https://openalex.org/W2144992723","https://openalex.org/W2146141344","https://openalex.org/W2147504831","https://openalex.org/W2148575324","https://openalex.org/W2154376164","https://openalex.org/W2161234420","https://openalex.org/W2161718902","https://openalex.org/W2166756349","https://openalex.org/W2168544140","https://openalex.org/W2171989756","https://openalex.org/W2277915713","https://openalex.org/W2293030740","https://openalex.org/W2295075181","https://openalex.org/W2302501749","https://openalex.org/W2548592627","https://openalex.org/W2605350375","https://openalex.org/W2738916082","https://openalex.org/W2768462553","https://openalex.org/W2788656564","https://openalex.org/W2789234353","https://openalex.org/W2791059415","https://openalex.org/W2791793074","https://openalex.org/W2887081378","https://openalex.org/W2896457183","https://openalex.org/W2899050079","https://openalex.org/W2903092728","https://openalex.org/W2907009609","https://openalex.org/W2912709745","https://openalex.org/W2914636073","https://openalex.org/W2916105680","https://openalex.org/W2927543040","https://openalex.org/W2933883078","https://openalex.org/W2944852720","https://openalex.org/W2949033485","https://openalex.org/W2949443561","https://openalex.org/W2950279944","https://openalex.org/W2973727699","https://openalex.org/W2979357014","https://openalex.org/W2980099728","https://openalex.org/W2981689050","https://openalex.org/W2982400926","https://openalex.org/W2982421692","https://openalex.org/W3000668449","https://openalex.org/W3005153041","https://openalex.org/W3005884080","https://openalex.org/W3011096584","https://openalex.org/W3011718251","https://openalex.org/W3012373689","https://openalex.org/W3016185124","https://openalex.org/W3037470707","https://openalex.org/W3042938130","https://openalex.org/W3046192195","https://openalex.org/W3046671719","https://openalex.org/W3047947484","https://openalex.org/W3087735676","https://openalex.org/W3101360223","https://openalex.org/W3107331477","https://openalex.org/W3121569598","https://openalex.org/W3124737070","https://openalex.org/W3187255235","https://openalex.org/W4200414623","https://openalex.org/W4220730878","https://openalex.org/W4233128776","https://openalex.org/W4239248483","https://openalex.org/W4242749428","https://openalex.org/W4248578633","https://openalex.org/W4288089799","https://openalex.org/W4298422451","https://openalex.org/W4313305673","https://openalex.org/W4385245566","https://openalex.org/W4387377969","https://openalex.org/W6606324823","https://openalex.org/W6628249541","https://openalex.org/W6628432071","https://openalex.org/W6638870186","https://openalex.org/W6639074551","https://openalex.org/W6640091283","https://openalex.org/W6641543129","https://openalex.org/W6643663680","https://openalex.org/W6646101001","https://openalex.org/W6648740326","https://openalex.org/W6648822029","https://openalex.org/W6649546340","https://openalex.org/W6650963013","https://openalex.org/W6656603005","https://openalex.org/W6661872208","https://openalex.org/W6668078709","https://openalex.org/W6670398541","https://openalex.org/W6675458958","https://openalex.org/W6675976239","https://openalex.org/W6677216421","https://openalex.org/W6677660805","https://openalex.org/W6678205474","https://openalex.org/W6680447750","https://openalex.org/W6681722003","https://openalex.org/W6684501114","https://openalex.org/W6727099177","https://openalex.org/W6729316162","https://openalex.org/W6731187400","https://openalex.org/W6739901393","https://openalex.org/W6748437547","https://openalex.org/W6748769447","https://openalex.org/W6760419517","https://openalex.org/W6760507315","https://openalex.org/W6769352828","https://openalex.org/W6776143864","https://openalex.org/W6781625084","https://openalex.org/W6804898078","https://openalex.org/W6868564194","https://openalex.org/W6931760132"],"related_works":["https://openalex.org/W2133280212","https://openalex.org/W4311545198","https://openalex.org/W2140836923","https://openalex.org/W2113098103","https://openalex.org/W2164036813","https://openalex.org/W2994238052","https://openalex.org/W2151392458","https://openalex.org/W2163726882","https://openalex.org/W3097895792","https://openalex.org/W2768462553"],"abstract_inverted_index":{"High-performance":[0],"computing":[1],"(HPC)":[2],"plays":[3,290],"an":[4,106],"essential":[5],"role":[6,293],"in":[7,62,198,225,228,239,278,284,294,316,319],"scientific":[8,63,112],"research,":[9],"engineering,":[10],"and":[11,23,30,59,77,89,117,147,175,189,191,208,230,235,258,270,334,361],"business.":[12],"Due":[13],"to":[14,32,42,74,85,109,172,213,265],"the":[15,33,51,96,129,144,177,204,221,226,232,248,295,311,329,343,349,353],"complexity":[16],"of":[17,20,45,54,132,143,150,160,179,206,237,241,250,261,298,314,351,355],"HPC,":[18],"analysis":[19,210],"HPC":[21,24,46,66,87],"workload":[22],"system":[25,78],"is":[26],"a":[27,38,101,157,168,214,291],"both":[28],"critical":[29],"challenging":[31],"community.":[34],"We":[35,80,166,181,201],"first":[36],"introduce":[37,140,337],"data-centric":[39],"provenance":[40,49,69,92,102,130],"solution":[41],"enhance":[43],"observability":[44],"workloads.":[47],"Data":[48],"captures":[50],"life":[52],"cycle":[53],"data,":[55,113],"including":[56],"its":[57],"origins":[58],"usage":[60],"patterns":[61,234],"workflows":[64,88,123],"on":[65,95,183,306],"systems.":[67,287],"Existing":[68],"solutions":[70],"are":[71,156],"inadequate":[72],"due":[73],"incompatible":[75],"models":[76],"implementations.":[79],"collaborate":[81],"with":[82,121,135,253],"domain":[83,133],"scientists":[84,134],"survey":[86],"identify":[90,231,259],"specific":[91],"requirements.":[93],"Based":[94],"survey,":[97],"we":[98,139,219,245,274,309],"propose":[99,167],"PROV-IO+,":[100],"framework":[103],"that":[104,125,325],"incorporates":[105],"I/O-centric":[107],"model":[108],"precisely":[110],"describe":[111],"associated":[114],"I/O":[115],"operations,":[116],"environments.":[118],"Our":[119,322,346],"experiments":[120,227],"real-world":[122],"demonstrate":[124],"PROV-IO+":[126],"effectively":[127],"meets":[128],"needs":[131],"reasonable":[136],"performance.":[137],"Then,":[138],"our":[141,209,276],"study":[142,247,310],"failure":[145,242],"recovery":[146,331],"logging":[148],"mechanisms":[149],"parallel":[151],"file":[152],"systems":[153,164],"(PFSes)":[154],"which":[155],"major":[158],"subset":[159],"high-performance":[161,285,300],"distributed":[162],"storage":[163,286,307],"(DSSes).":[165],"tool":[169],"called":[170],"PFault":[171],"simulate":[173],"failures":[174],"analyze":[176],"behavior":[178,263],"PFSes.":[180],"focus":[182],"two":[184],"widely":[185],"used":[186],"PFSes":[187,238],"(Lustre":[188],"BeeGFS)":[190],"find":[192],"areas":[193],"where":[194],"they":[195],"can":[196],"improve":[197],"handling":[199],"failures.":[200],"also":[202],"investigate":[203],"causes":[205],"abnormalities,":[207],"has":[211],"led":[212],"patch":[215],"for":[216,358],"Lustre.":[217],"Additionally,":[218],"characterize":[220],"extensive":[222],"logs":[223],"generated":[224],"details":[229],"unique":[233],"limitations":[236],"terms":[240],"logging.":[243],"Moreover,":[244],"further":[246],"capabilities":[249],"PFS":[251],"checkers":[252],"more":[254],"fine-gained":[255],"fault":[256,296],"injection":[257],"instances":[260],"sub-optimal":[262],"leading":[264],"issues":[266],"like":[267],"kernel":[268],"panics":[269],"incorrect":[271],"repairs.":[272],"Finally,":[273],"present":[275],"effort":[277],"studying":[279],"erasure":[280],"coding":[281,289],"(EC)":[282],"performance":[283],"Erasure":[288],"crucial":[292],"tolerance":[297],"modern":[299],"DSSes.":[301],"Inspired":[302],"by":[303],"recent":[304],"research":[305,360],"configuration,":[308],"configuration":[312],"sensitivity":[313],"EC":[315,330,335,359],"real":[317,356],"DSS":[318,357],"this":[320],"work.":[321],"results":[323],"show":[324],"configurations":[326],"may":[327,336],"affect":[328],"time":[332],"significantly,":[333],"extra":[338],"write":[339],"amplification":[340],"(WA)":[341],"than":[342],"theoretical":[344],"expectation.":[345],"work":[347],"suggests":[348],"importance":[350],"considering":[352],"context":[354],"implementation.":[362]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}