Exploiting fine-grained idle periods in networks of workstations
Studies have shown that for a significant fraction of the time, workstations are idle. In this paper, we present a new scheduling policy called Linger-Longer that exploits the fine-grained availability of workstations to run sequential and parallel jobs. We present a two-level workload characterizat...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on parallel and distributed systems 2000-07, Vol.11 (7), p.683-698 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 698 |
|---|---|
| container_issue | 7 |
| container_start_page | 683 |
| container_title | IEEE transactions on parallel and distributed systems |
| container_volume | 11 |
| creator | Kyung Dong Ryu Hollingsworth, J.K. |
| description | Studies have shown that for a significant fraction of the time, workstations are idle. In this paper, we present a new scheduling policy called Linger-Longer that exploits the fine-grained availability of workstations to run sequential and parallel jobs. We present a two-level workload characterization study and use it to simulate a cluster of workstations running our new policy. We compare two variations of our policy to two previous policies: Immediate-Eviction and Pause-and-Migrate. Our study shows that the Linger-Longer policy can improve the throughput of foreign jobs on a cluster by 60 percent with only a 0.5 percent slowdown of local jobs. For parallel computing, we show that the Linger-Longer policy outperforms reconfiguration strategies when the processor utilization by the local process is 20 percent or less in both synthetic bulk synchronous and real data-parallel applications. |
| doi_str_mv | 10.1109/71.877793 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_71_877793</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>877793</ieee_id><sourcerecordid>2582273311</sourcerecordid><originalsourceid>FETCH-LOGICAL-c402t-c1d461d530276e0e8b1da1ba6ecf67238cd59747e933021de15bbe7f1d97e5203</originalsourceid><addsrcrecordid>eNqF0T1LxEAQBuBFFDxPC1urYKFY5NzZ7GenHOcHHNhoHZLs5Ngzl427OdR_bzRiYaHVvDAPA8NLyDHQGQA1lwpmWillsh0yASF0ykBnu0OmXKSGgdknBzGuKQUuKJ-Qq8Vb13jXu3aV1K7FdBWKYdjE2QaTDoPzNiauTVrsX314jomvk6_QF73zbTwke3XRRDz6nlPydLN4nN-ly4fb-_n1Mq04ZX1ageUSrMgoUxIp6hJsAWUhsaqlYpmurDCKKzTZQMAiiLJEVYM1CgWj2ZScj3e74F-2GPt842KFTVO06LcxN8BlpjVngzz7UzKtBJOM_w-lZKAUDPD0F1z7bWiHd3PDqKLSMD2gixFVwccYsM674DZFeM-B5p_d5ArysZvBnozWIeKP-15-AABqh98</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>920706928</pqid></control><display><type>article</type><title>Exploiting fine-grained idle periods in networks of workstations</title><source>IEEE Electronic Library (IEL)</source><creator>Kyung Dong Ryu ; Hollingsworth, J.K.</creator><creatorcontrib>Kyung Dong Ryu ; Hollingsworth, J.K.</creatorcontrib><description>Studies have shown that for a significant fraction of the time, workstations are idle. In this paper, we present a new scheduling policy called Linger-Longer that exploits the fine-grained availability of workstations to run sequential and parallel jobs. We present a two-level workload characterization study and use it to simulate a cluster of workstations running our new policy. We compare two variations of our policy to two previous policies: Immediate-Eviction and Pause-and-Migrate. Our study shows that the Linger-Longer policy can improve the throughput of foreign jobs on a cluster by 60 percent with only a 0.5 percent slowdown of local jobs. For parallel computing, we show that the Linger-Longer policy outperforms reconfiguration strategies when the processor utilization by the local process is 20 percent or less in both synthetic bulk synchronous and real data-parallel applications.</description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/71.877793</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Availability ; Clusters ; Computer networks ; Concurrent computing ; Contracts ; Delay ; Intelligent networks ; Parallel processing ; Policies ; Predictive models ; Resumes ; Running ; Strategy ; Synchronous ; Throughput ; Workload ; Workstations</subject><ispartof>IEEE transactions on parallel and distributed systems, 2000-07, Vol.11 (7), p.683-698</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2000</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c402t-c1d461d530276e0e8b1da1ba6ecf67238cd59747e933021de15bbe7f1d97e5203</citedby><cites>FETCH-LOGICAL-c402t-c1d461d530276e0e8b1da1ba6ecf67238cd59747e933021de15bbe7f1d97e5203</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/877793$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/877793$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kyung Dong Ryu</creatorcontrib><creatorcontrib>Hollingsworth, J.K.</creatorcontrib><title>Exploiting fine-grained idle periods in networks of workstations</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>Studies have shown that for a significant fraction of the time, workstations are idle. In this paper, we present a new scheduling policy called Linger-Longer that exploits the fine-grained availability of workstations to run sequential and parallel jobs. We present a two-level workload characterization study and use it to simulate a cluster of workstations running our new policy. We compare two variations of our policy to two previous policies: Immediate-Eviction and Pause-and-Migrate. Our study shows that the Linger-Longer policy can improve the throughput of foreign jobs on a cluster by 60 percent with only a 0.5 percent slowdown of local jobs. For parallel computing, we show that the Linger-Longer policy outperforms reconfiguration strategies when the processor utilization by the local process is 20 percent or less in both synthetic bulk synchronous and real data-parallel applications.</description><subject>Availability</subject><subject>Clusters</subject><subject>Computer networks</subject><subject>Concurrent computing</subject><subject>Contracts</subject><subject>Delay</subject><subject>Intelligent networks</subject><subject>Parallel processing</subject><subject>Policies</subject><subject>Predictive models</subject><subject>Resumes</subject><subject>Running</subject><subject>Strategy</subject><subject>Synchronous</subject><subject>Throughput</subject><subject>Workload</subject><subject>Workstations</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2000</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqF0T1LxEAQBuBFFDxPC1urYKFY5NzZ7GenHOcHHNhoHZLs5Ngzl427OdR_bzRiYaHVvDAPA8NLyDHQGQA1lwpmWillsh0yASF0ykBnu0OmXKSGgdknBzGuKQUuKJ-Qq8Vb13jXu3aV1K7FdBWKYdjE2QaTDoPzNiauTVrsX314jomvk6_QF73zbTwke3XRRDz6nlPydLN4nN-ly4fb-_n1Mq04ZX1ageUSrMgoUxIp6hJsAWUhsaqlYpmurDCKKzTZQMAiiLJEVYM1CgWj2ZScj3e74F-2GPt842KFTVO06LcxN8BlpjVngzz7UzKtBJOM_w-lZKAUDPD0F1z7bWiHd3PDqKLSMD2gixFVwccYsM674DZFeM-B5p_d5ArysZvBnozWIeKP-15-AABqh98</recordid><startdate>20000701</startdate><enddate>20000701</enddate><creator>Kyung Dong Ryu</creator><creator>Hollingsworth, J.K.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20000701</creationdate><title>Exploiting fine-grained idle periods in networks of workstations</title><author>Kyung Dong Ryu ; Hollingsworth, J.K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c402t-c1d461d530276e0e8b1da1ba6ecf67238cd59747e933021de15bbe7f1d97e5203</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Availability</topic><topic>Clusters</topic><topic>Computer networks</topic><topic>Concurrent computing</topic><topic>Contracts</topic><topic>Delay</topic><topic>Intelligent networks</topic><topic>Parallel processing</topic><topic>Policies</topic><topic>Predictive models</topic><topic>Resumes</topic><topic>Running</topic><topic>Strategy</topic><topic>Synchronous</topic><topic>Throughput</topic><topic>Workload</topic><topic>Workstations</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kyung Dong Ryu</creatorcontrib><creatorcontrib>Hollingsworth, J.K.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kyung Dong Ryu</au><au>Hollingsworth, J.K.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Exploiting fine-grained idle periods in networks of workstations</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>2000-07-01</date><risdate>2000</risdate><volume>11</volume><issue>7</issue><spage>683</spage><epage>698</epage><pages>683-698</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>Studies have shown that for a significant fraction of the time, workstations are idle. In this paper, we present a new scheduling policy called Linger-Longer that exploits the fine-grained availability of workstations to run sequential and parallel jobs. We present a two-level workload characterization study and use it to simulate a cluster of workstations running our new policy. We compare two variations of our policy to two previous policies: Immediate-Eviction and Pause-and-Migrate. Our study shows that the Linger-Longer policy can improve the throughput of foreign jobs on a cluster by 60 percent with only a 0.5 percent slowdown of local jobs. For parallel computing, we show that the Linger-Longer policy outperforms reconfiguration strategies when the processor utilization by the local process is 20 percent or less in both synthetic bulk synchronous and real data-parallel applications.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/71.877793</doi><tpages>16</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1045-9219 |
| ispartof | IEEE transactions on parallel and distributed systems, 2000-07, Vol.11 (7), p.683-698 |
| issn | 1045-9219 1558-2183 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_71_877793 |
| source | IEEE Electronic Library (IEL) |
| subjects | Availability Clusters Computer networks Concurrent computing Contracts Delay Intelligent networks Parallel processing Policies Predictive models Resumes Running Strategy Synchronous Throughput Workload Workstations |
| title | Exploiting fine-grained idle periods in networks of workstations |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T06%3A58%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Exploiting%20fine-grained%20idle%20periods%20in%20networks%20of%20workstations&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Kyung%20Dong%20Ryu&rft.date=2000-07-01&rft.volume=11&rft.issue=7&rft.spage=683&rft.epage=698&rft.pages=683-698&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/71.877793&rft_dat=%3Cproquest_RIE%3E2582273311%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=920706928&rft_id=info:pmid/&rft_ieee_id=877793&rfr_iscdi=true |