Exploiting process lifetime distributions for dynamic load balancing
We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resol...
Gespeichert in:
| Veröffentlicht in: | ACM transactions on computer systems 1997-08, Vol.15 (3), p.253-285 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 285 |
|---|---|
| container_issue | 3 |
| container_start_page | 253 |
| container_title | ACM transactions on computer systems |
| container_volume | 15 |
| creator | Harchol-Balter, Mor Downey, Allen B. |
| description | We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We show how to apply this distribution to derive a preemptive migration policy that requires no hand-tuned parameters. We used a trace-driven simulation to show that our preemptive migration strategy is far more effective than remote execution, even when the memory transfer cost is high. |
| doi_str_mv | 10.1145/263326.263344 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_29097663</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A20553664</galeid><sourcerecordid>A20553664</sourcerecordid><originalsourceid>FETCH-LOGICAL-a551t-d1fbde68a2c74265bd4e7b6325d7372206acc1589539849863fdd56745c1a52c3</originalsourceid><addsrcrecordid>eNqFkctLAzEQxoMoWB9HD94WEU-u5p3do2h9QMGLnkM2jxJJNzXZgv3vTdmiHkSZw8DMb4b55gPgBMErhCi7xpwQzK82idIdMEGMiVoQQnbBBApCawwF2gcHOb9BCEsdT8Dd9GMZoh98P6-WKWqbcxW8s4Nf2Mr4PCTfrQYf-1y5mCqz7tXC6ypEZapOBdXrMnkE9pwK2R5v8yF4vZ--3D7Ws-eHp9ubWa0YQ0NtkOuM5Y3CWlDMWWeoFR0nmBlBBMaQK60Ra1pG2oa2DSfOGMYFZRophjU5BBfj3nLp-8rmQS581jaUM2xcZYlb2Ape5P8LokKJFhfwbATnKljpexeHpPQGljcYMkY4pwW6_AWa294mFWJvnS_ln3j9C17C2PK6P3idYs7JOrlMfqHSWiIoN8bK0Vg5Glv48604lbUKLm1MyF9D5Y1cQFSw0xErer6b44pP4aunog</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>21663792</pqid></control><display><type>article</type><title>Exploiting process lifetime distributions for dynamic load balancing</title><source>ACM Digital Library Complete</source><creator>Harchol-Balter, Mor ; Downey, Allen B.</creator><creatorcontrib>Harchol-Balter, Mor ; Downey, Allen B.</creatorcontrib><description>We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We show how to apply this distribution to derive a preemptive migration policy that requires no hand-tuned parameters. We used a trace-driven simulation to show that our preemptive migration strategy is far more effective than remote execution, even when the memory transfer cost is high.</description><identifier>ISSN: 0734-2071</identifier><identifier>EISSN: 1557-7333</identifier><identifier>DOI: 10.1145/263326.263344</identifier><identifier>CODEN: ACSYEC</identifier><language>eng</language><publisher>New York, NY, USA: ACM</publisher><subject>Applied computing ; Applied sciences ; Architectures ; Computer networks ; Computer science; control theory; systems ; Computer systems organization ; Computer systems performance. Reliability ; Computers in other domains ; Computing methodologies ; Cross-computing tools and techniques ; Dependable and fault-tolerant systems and networks ; Design and construction ; Distributed architectures ; Distributed systems organizing principles ; Exact sciences and technology ; General and reference ; Information networks ; Mathematical analysis ; Mathematics of computing ; Microcomputers ; Modeling and simulation ; Network management ; Network monitoring ; Network operating systems ; Network performance evaluation ; Network services ; Networks ; Numerical analysis ; Personal computers and PC applications ; Probability and statistics ; Software ; Software and its engineering ; Software organization and properties ; Software system structures</subject><ispartof>ACM transactions on computer systems, 1997-08, Vol.15 (3), p.253-285</ispartof><rights>ACM</rights><rights>1998 INIST-CNRS</rights><rights>COPYRIGHT 1997 Association for Computing Machinery, Inc.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a551t-d1fbde68a2c74265bd4e7b6325d7372206acc1589539849863fdd56745c1a52c3</citedby><cites>FETCH-LOGICAL-a551t-d1fbde68a2c74265bd4e7b6325d7372206acc1589539849863fdd56745c1a52c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://dl.acm.org/doi/pdf/10.1145/263326.263344$$EPDF$$P50$$Gacm$$H</linktopdf><link.rule.ids>314,780,784,2280,27923,27924,40195,75999</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2066701$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Harchol-Balter, Mor</creatorcontrib><creatorcontrib>Downey, Allen B.</creatorcontrib><title>Exploiting process lifetime distributions for dynamic load balancing</title><title>ACM transactions on computer systems</title><addtitle>ACM TOCS</addtitle><description>We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We show how to apply this distribution to derive a preemptive migration policy that requires no hand-tuned parameters. We used a trace-driven simulation to show that our preemptive migration strategy is far more effective than remote execution, even when the memory transfer cost is high.</description><subject>Applied computing</subject><subject>Applied sciences</subject><subject>Architectures</subject><subject>Computer networks</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems organization</subject><subject>Computer systems performance. Reliability</subject><subject>Computers in other domains</subject><subject>Computing methodologies</subject><subject>Cross-computing tools and techniques</subject><subject>Dependable and fault-tolerant systems and networks</subject><subject>Design and construction</subject><subject>Distributed architectures</subject><subject>Distributed systems organizing principles</subject><subject>Exact sciences and technology</subject><subject>General and reference</subject><subject>Information networks</subject><subject>Mathematical analysis</subject><subject>Mathematics of computing</subject><subject>Microcomputers</subject><subject>Modeling and simulation</subject><subject>Network management</subject><subject>Network monitoring</subject><subject>Network operating systems</subject><subject>Network performance evaluation</subject><subject>Network services</subject><subject>Networks</subject><subject>Numerical analysis</subject><subject>Personal computers and PC applications</subject><subject>Probability and statistics</subject><subject>Software</subject><subject>Software and its engineering</subject><subject>Software organization and properties</subject><subject>Software system structures</subject><issn>0734-2071</issn><issn>1557-7333</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1997</creationdate><recordtype>article</recordtype><recordid>eNqFkctLAzEQxoMoWB9HD94WEU-u5p3do2h9QMGLnkM2jxJJNzXZgv3vTdmiHkSZw8DMb4b55gPgBMErhCi7xpwQzK82idIdMEGMiVoQQnbBBApCawwF2gcHOb9BCEsdT8Dd9GMZoh98P6-WKWqbcxW8s4Nf2Mr4PCTfrQYf-1y5mCqz7tXC6ypEZapOBdXrMnkE9pwK2R5v8yF4vZ--3D7Ws-eHp9ubWa0YQ0NtkOuM5Y3CWlDMWWeoFR0nmBlBBMaQK60Ra1pG2oa2DSfOGMYFZRophjU5BBfj3nLp-8rmQS581jaUM2xcZYlb2Ape5P8LokKJFhfwbATnKljpexeHpPQGljcYMkY4pwW6_AWa294mFWJvnS_ln3j9C17C2PK6P3idYs7JOrlMfqHSWiIoN8bK0Vg5Glv48604lbUKLm1MyF9D5Y1cQFSw0xErer6b44pP4aunog</recordid><startdate>19970801</startdate><enddate>19970801</enddate><creator>Harchol-Balter, Mor</creator><creator>Downey, Allen B.</creator><general>ACM</general><general>Association for Computing Machinery</general><general>Association for Computing Machinery, Inc</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19970801</creationdate><title>Exploiting process lifetime distributions for dynamic load balancing</title><author>Harchol-Balter, Mor ; Downey, Allen B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a551t-d1fbde68a2c74265bd4e7b6325d7372206acc1589539849863fdd56745c1a52c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Applied computing</topic><topic>Applied sciences</topic><topic>Architectures</topic><topic>Computer networks</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems organization</topic><topic>Computer systems performance. Reliability</topic><topic>Computers in other domains</topic><topic>Computing methodologies</topic><topic>Cross-computing tools and techniques</topic><topic>Dependable and fault-tolerant systems and networks</topic><topic>Design and construction</topic><topic>Distributed architectures</topic><topic>Distributed systems organizing principles</topic><topic>Exact sciences and technology</topic><topic>General and reference</topic><topic>Information networks</topic><topic>Mathematical analysis</topic><topic>Mathematics of computing</topic><topic>Microcomputers</topic><topic>Modeling and simulation</topic><topic>Network management</topic><topic>Network monitoring</topic><topic>Network operating systems</topic><topic>Network performance evaluation</topic><topic>Network services</topic><topic>Networks</topic><topic>Numerical analysis</topic><topic>Personal computers and PC applications</topic><topic>Probability and statistics</topic><topic>Software</topic><topic>Software and its engineering</topic><topic>Software organization and properties</topic><topic>Software system structures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Harchol-Balter, Mor</creatorcontrib><creatorcontrib>Downey, Allen B.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems 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><jtitle>ACM transactions on computer systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Harchol-Balter, Mor</au><au>Downey, Allen B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Exploiting process lifetime distributions for dynamic load balancing</atitle><jtitle>ACM transactions on computer systems</jtitle><stitle>ACM TOCS</stitle><date>1997-08-01</date><risdate>1997</risdate><volume>15</volume><issue>3</issue><spage>253</spage><epage>285</epage><pages>253-285</pages><issn>0734-2071</issn><eissn>1557-7333</eissn><coden>ACSYEC</coden><abstract>We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We show how to apply this distribution to derive a preemptive migration policy that requires no hand-tuned parameters. We used a trace-driven simulation to show that our preemptive migration strategy is far more effective than remote execution, even when the memory transfer cost is high.</abstract><cop>New York, NY, USA</cop><pub>ACM</pub><doi>10.1145/263326.263344</doi><tpages>33</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0734-2071 |
| ispartof | ACM transactions on computer systems, 1997-08, Vol.15 (3), p.253-285 |
| issn | 0734-2071 1557-7333 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_29097663 |
| source | ACM Digital Library Complete |
| subjects | Applied computing Applied sciences Architectures Computer networks Computer science control theory systems Computer systems organization Computer systems performance. Reliability Computers in other domains Computing methodologies Cross-computing tools and techniques Dependable and fault-tolerant systems and networks Design and construction Distributed architectures Distributed systems organizing principles Exact sciences and technology General and reference Information networks Mathematical analysis Mathematics of computing Microcomputers Modeling and simulation Network management Network monitoring Network operating systems Network performance evaluation Network services Networks Numerical analysis Personal computers and PC applications Probability and statistics Software Software and its engineering Software organization and properties Software system structures |
| title | Exploiting process lifetime distributions for dynamic load balancing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T00%3A00%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Exploiting%20process%20lifetime%20distributions%20for%20dynamic%20load%20balancing&rft.jtitle=ACM%20transactions%20on%20computer%20systems&rft.au=Harchol-Balter,%20Mor&rft.date=1997-08-01&rft.volume=15&rft.issue=3&rft.spage=253&rft.epage=285&rft.pages=253-285&rft.issn=0734-2071&rft.eissn=1557-7333&rft.coden=ACSYEC&rft_id=info:doi/10.1145/263326.263344&rft_dat=%3Cgale_proqu%3EA20553664%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=21663792&rft_id=info:pmid/&rft_galeid=A20553664&rfr_iscdi=true |