{"id":73584,"updated":"2025-01-20T06:25:44.173428+00:00","links":{},"created":"2025-01-18T23:31:27.806797+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00073584","sets":["934:1119:6347:6373"]},"path":["6373"],"owner":"11","recid":"73584","title":["マルチコアCPUの電力消費特性を考慮した仮想CPUスケジューラ"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-03-10"},"_buckets":{"deposit":"eacdaa09-05f9-442d-aa14-062ed9971aa6"},"_deposit":{"id":"73584","pid":{"type":"depid","value":"73584","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"マルチコアCPUの電力消費特性を考慮した仮想CPUスケジューラ","author_link":["363071","363073","363070","363074","363075","363077","363072","363069","363076","363068"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"マルチコアCPUの電力消費特性を考慮した仮想CPUスケジューラ"},{"subitem_title":"Considering Power Consumption Characteristics of Multicore CPUs for Energy Efficient Virtual CPU Scheduling","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"省電力方式（優秀論文賞受賞）","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2011-03-10","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"慶應義塾大学"},{"subitem_text_value":"慶應義塾大学／科学技術振興機構CREST"},{"subitem_text_value":"東京大学"},{"subitem_text_value":"慶應義塾大学／科学技術振興機構CREST"},{"subitem_text_value":"東京大学"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Keio University","subitem_text_language":"en"},{"subitem_text_value":"Keio University / CREST, Japan Science and Technology Agency","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Keio University / CREST, Japan Science and Technology Agency","subitem_text_language":"en"},{"subitem_text_value":"The University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/73584/files/IPSJ-TACS0402005.pdf","label":"IPSJ-TACS0402005"},"date":[{"dateType":"Available","dateValue":"2013-03-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TACS0402005.pdf","filesize":[{"value":"1.8 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"16"},{"tax":["include_tax"],"price":"0","billingrole":"11"},{"tax":["include_tax"],"price":"0","billingrole":"14"},{"tax":["include_tax"],"price":"0","billingrole":"15"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2a9194b5-7b92-4b43-8b0a-89c0ccb3cda1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"吉田, 哲也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山田, 浩史"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"佐々木, 広"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河野, 健二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村, 宏"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tetsuya, Yoshida","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Yamada","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Sasaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kenji, Kono","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Nakamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11833852","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7829","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"クラウド環境を提供する仮想化データセンタにおける消費エネルギーを削減するために，Dynamic Voltage and Frequency Scaling（DVFS） を利用した CPU の電力制御が行われている．ここで，既存のマルチコア CPU には，すべてのコアの周波数を揃えて下げないと消費エネルギーの削減効果が小さいという特性がある．ところが，既存の VM 環境はこの性質を考慮していないため，効率良く消費エネルギーを削減できていない．本論文では，VM 環境において，先にあげたマルチコア CPU の電力消費特性を考慮した仮想 CPU（VCPU） スケジューラである Accele スケジューラを提案する．Accele スケジューラは，すべてのコアに同周波数の VCPU がスケジューリングされる時間を長くすることで，すべてのコアの周波数が揃って下がる時間を長くし，DVFS による消費エネルギー削減を大きくする．また，クラウド環境で一般的に行われている work-conserving なプロポーショナルシェアリングを行う．SysBench と SPEC CPU2006 を用いて実験を行った結果，Xen のスケジューラである Credit スケジューラと比べ，消費エネルギーを最大 22.8% 小さくすることができた．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Dynamic voltage and frequency scaling (DVFS) is performed to reduce energy consumption in virtualized data centers used as a platform of cloud computing. However, DVFS provides inefficient energy savings in existing VM environments, because of the characteristic of multicore CPUs that DVFS cannot save significant amount of energy unless the frequencies of all cores are lowered. In this paper, we propose an energy-conscious Virtual CPU (VCPU) scheduler that takes the above characteristic of multicore CPUs into account. Our scheduler, named Accele scheduler, schedules VCPUs by considering the frequency of them to increase the probability that all cores run the same frequency VCPUs simultaneously. As a result, the frequencies of all cores are lowered simultaneously with high probability, and therefore we can gain higher energy savings with DVFS. In addition, Accele scheduler performs work-conserving and proportional-share scheduling, which is common in the cloud computing environments. We evaluate  Accele scheduler with SysBench and SPEC CPU2006. The evaluation showed that  Accele scheduler reduced the energy consumption of the CPU by up to 22.8% compared with Xen's Credit scheduler.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"39","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌コンピューティングシステム（ACS）"}],"bibliographicPageStart":"25","bibliographicIssueDates":{"bibliographicIssueDate":"2011-03-10","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"4"}]},"relation_version_is_last":true,"weko_creator_id":"11"}}