PXFS: A persistent storage model for extreme Scale
The continuing technological progress resulted in sustained increase in the number of transistors per chip as well as improved energy efficiency per FLOPS. This spurred a dramatic growth in aggregate computational performance of the largest supercomputing systems, yielding multiple Petascale impleme...
Saved in:
Published in | 2014 International Conference on Computing, Networking and Communications (ICNC) pp. 900 - 906 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.02.2014
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The continuing technological progress resulted in sustained increase in the number of transistors per chip as well as improved energy efficiency per FLOPS. This spurred a dramatic growth in aggregate computational performance of the largest supercomputing systems, yielding multiple Petascale implementations deployed in various locations over the world. Unfortunately, these advances did not translate to the required extent into accompanying I/O systems, which primarily saw the improvement in cumulative storage sizes required to match the ever expanding volume of scientific data sets, but little more in terms of architecture or effective access latency. Moreover, while new models of computations are formulated to handle the burden of efficiently structuring the parallel computations in anticipation of the arrival of Exascale systems, a meager progress is observed in the area of storage subsystems. New classes of algorithms developed for massively parallel applications, that gracefully handle the challenges of asynchrony, heavily multithreaded distributed codes, and message-driven computation, must be matched by similar advances in I/O methods and algorithms to produce a well performing and balanced supercomputing system. This paper discusses PXFS, a file system model for persistent objects inspired by the ParalleX model of execution that addresses many of these challenges. An early implementation of PXFS utilizing a well known Orange parallel file system as its back-end via asynchronous I/O layer is also described along with the preliminary performance data. The results show perfect scalability and 3× to 20× times speedup of I/O throughput performance comparing to OrangeFS user interface. Also the PXFS module on OrangeFS with 24 clients sees a 5× to 10× times more throughput than NFS. |
---|---|
AbstractList | The continuing technological progress resulted in sustained increase in the number of transistors per chip as well as improved energy efficiency per FLOPS. This spurred a dramatic growth in aggregate computational performance of the largest supercomputing systems, yielding multiple Petascale implementations deployed in various locations over the world. Unfortunately, these advances did not translate to the required extent into accompanying I/O systems, which primarily saw the improvement in cumulative storage sizes required to match the ever expanding volume of scientific data sets, but little more in terms of architecture or effective access latency. Moreover, while new models of computations are formulated to handle the burden of efficiently structuring the parallel computations in anticipation of the arrival of Exascale systems, a meager progress is observed in the area of storage subsystems. New classes of algorithms developed for massively parallel applications, that gracefully handle the challenges of asynchrony, heavily multithreaded distributed codes, and message-driven computation, must be matched by similar advances in I/O methods and algorithms to produce a well performing and balanced supercomputing system. This paper discusses PXFS, a file system model for persistent objects inspired by the ParalleX model of execution that addresses many of these challenges. An early implementation of PXFS utilizing a well known Orange parallel file system as its back-end via asynchronous I/O layer is also described along with the preliminary performance data. The results show perfect scalability and 3× to 20× times speedup of I/O throughput performance comparing to OrangeFS user interface. Also the PXFS module on OrangeFS with 24 clients sees a 5× to 10× times more throughput than NFS. |
Author | Ligon, Walter B. Brodowicz, Maciej Shuangyang Yang Kaiser, Hartmut |
Author_xml | – sequence: 1 surname: Shuangyang Yang fullname: Shuangyang Yang email: syang16@lsu.edu organization: Center for Comput. & Technol., Louisiana State Univ., Baton Rouge, LA, USA – sequence: 2 givenname: Maciej surname: Brodowicz fullname: Brodowicz, Maciej email: mbrodowi@indiana.edu organization: Center for Res. in Extreme Scale Technol., Indiana Univ., Bloomington, IN, USA – sequence: 3 givenname: Walter B. surname: Ligon fullname: Ligon, Walter B. email: walt@clemson.edu organization: Parallel Archit. Res. Lab., Clemson Univ., Clemson, SC, USA – sequence: 4 givenname: Hartmut surname: Kaiser fullname: Kaiser, Hartmut email: hkaiser@cct.lsu.edu organization: Center for Comput. & Technol., Louisiana State Univ., Baton Rouge, LA, USA |
BookMark | eNotj71OwzAURo1EByh9AVj8Agn-uY592SqLQqUKKrUDW-XENyhSfirHA7w9lej0TeccfffsdpxGYuxRilJKgc9b7z98qYSEsrLOgLE3bIXWSbCIShvn7pjaf20OL3zNz5Tmbs40Zj7nKYVv4sMUqeftlDj95EQD8UMTenpgizb0M62uu2THzevRvxe7z7etX--KDkUuWkVCNNHIhiyaCDUod2nXIKQQNWkkqxBBWxdji7ECSVCpCHSBZMCgl-zpX9sR0emcuiGk39P1iP4D8-1Aow |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/ICCNC.2014.6785457 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEL IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEL url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 9781479923588 1479923583 |
EndPage | 906 |
ExternalDocumentID | 6785457 |
Genre | orig-research |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-i90t-f2e00cd51ce795d4b428978b40100be39e72994378ddf9d641e462d4e0cd1a9a3 |
IEDL.DBID | RIE |
IngestDate | Thu Jun 29 18:38:25 EDT 2023 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i90t-f2e00cd51ce795d4b428978b40100be39e72994378ddf9d641e462d4e0cd1a9a3 |
PageCount | 7 |
ParticipantIDs | ieee_primary_6785457 |
PublicationCentury | 2000 |
PublicationDate | 2014-Feb. |
PublicationDateYYYYMMDD | 2014-02-01 |
PublicationDate_xml | – month: 02 year: 2014 text: 2014-Feb. |
PublicationDecade | 2010 |
PublicationTitle | 2014 International Conference on Computing, Networking and Communications (ICNC) |
PublicationTitleAbbrev | ICCNC |
PublicationYear | 2014 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.5663009 |
Snippet | The continuing technological progress resulted in sustained increase in the number of transistors per chip as well as improved energy efficiency per FLOPS.... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 900 |
SubjectTerms | Computational modeling Computer architecture Educational institutions Runtime Scalability Servers Throughput |
Title | PXFS: A persistent storage model for extreme Scale |
URI | https://ieeexplore.ieee.org/document/6785457 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFH9sO3lS2cRvcvBou6RNP-JNimMKG4NN2G00yQuI0A3pLv71vrTbRPHgLZSUNH3kfeX3ew_gTutUKRuZIBdCBdJknI5U6dloXLjMocid5w5Ppun4Vb4sk2UH7g9cGERswGcY-mFzl2_XZutTZUNSrGTwsy50cx61XK09D4ar4XNRTAsP1pLhbuKPjimNwRgdw2S_VIsTeQ-3tQ7N568qjP_9lhMYfFPz2OxgdE6hg1UfotlyNH9gj2zjs18kt6pmHvVIuoI1rW4YuaaM1LBPBrI5iQUHsBg9LYpxsGuGELwpXgcuQs6NTYTBTCVWagobKADUFB5xrjFWSF6yknGWW-uUTaVAmUZWIr0kSlXGZ9Cr1hWeA7MpL8mvSTOhuRRlmsfclM4oF8XW5om9gL7f7mrTlrtY7XZ6-ffjKzjyv7wFMl9Dr_7Y4g3Z6VrfNgL6AsEIk2Q |
link.rule.ids | 310,311,786,790,795,796,802,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NS8NAEB1qPehJpRW_3YNHk-4mm4_1JsXSalsKrdBbye5OQIS0SHrx1zubtBXFg7cQEjabYefNzL63A3CndayUDYyXCqE8aRJOSypzajQu8iRHkeZOOzwax_1X-TyP5g2432lhELEin6HvLqu9fLs0a1cq65BjJcBP9mCfcJ6rWq21VcJw1Rl0u-Ouo2tJf_Poj54pFWT0jmC0Haxmirz761L75vPXOYz__ZpjaH-L89hkBzsn0MCiBcFk3ps-sEe2cvUvslxRMsd7JG_BqmY3jIJTRo7YlQPZlAyDbZj1nmbdvrdph-C9KV56eYCcGxsJg4mKrNSUOFAKqClB4lxjqJDiZCXDJLU2VzaWAmUcWIn0kshUFp5Cs1gWeAbMxjyjyCZOhOZSZHEacpPlRuVBaG0a2XNouekuVvWBF4vNTC_-vn0LB_3ZaLgYDsYvl3Dofn9Na76CZvmxxmtC7VLfVMb6Arxblro |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2014+International+Conference+on+Computing%2C+Networking+and+Communications+%28ICNC%29&rft.atitle=PXFS%3A+A+persistent+storage+model+for+extreme+Scale&rft.au=Shuangyang+Yang&rft.au=Brodowicz%2C+Maciej&rft.au=Ligon%2C+Walter+B.&rft.au=Kaiser%2C+Hartmut&rft.date=2014-02-01&rft.pub=IEEE&rft.spage=900&rft.epage=906&rft_id=info:doi/10.1109%2FICCNC.2014.6785457&rft.externalDocID=6785457 |