{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:46:53Z","timestamp":1750308413519,"version":"3.41.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,6,8]],"date-time":"2024-06-08T00:00:00Z","timestamp":1717804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4500302"],"award-info":[{"award-number":["2022YFB4500302"]}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"crossref","award":["2022JJ30667"],"award-info":[{"award-number":["2022JJ30667"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Parallel Comput."],"published-print":{"date-parts":[[2024,6,30]]},"abstract":"<jats:p>\n            For latency-sensitive data processing applications in the cloud, concurrent data-parallel tasks need to be scheduled and processed quickly. A data-parallel task usually consists of a set of sub-tasks, generating a set of flows that are collectively referred to as\n            <jats:italic>coflows<\/jats:italic>\n            . The state-of-the-art schedulers collect coflow information in the cloud to optimize coflow-level performance. However, most of the coflows, classified as\n            <jats:italic>small coflows<\/jats:italic>\n            because they consist of only short flows, have been largely overlooked. This article presents\n            <jats:sc>OptaX<\/jats:sc>\n            , a decentralized network scheduling service that collaboratively schedules data-parallel tasks\u2019 small coflows.\n            <jats:sc>OptaX<\/jats:sc>\n            adopts a cross-layer, commercial off-the-shelf switch-compatible design that leverages the\n            <jats:monospace>sendbuffer<\/jats:monospace>\n            information in the kernel to adaptively optimize flow scheduling in the network. Specifically,\n            <jats:sc>OptaX<\/jats:sc>\n            (i) monitors the system calls (syscalls) in the hosts to obtain their\n            <jats:monospace>sendbuffer<\/jats:monospace>\n            footprints, and (ii) recognizes small coflows and assigns high priorities to their flows.\n            <jats:sc>OptaX<\/jats:sc>\n            transfers these flows in a FIFO manner by adjusting TCP\u2019s two attributes: window size and round-trip time. We have implemented\n            <jats:sc>OptaX<\/jats:sc>\n            as a Linux kernel module. The evaluation shows that\n            <jats:sc>OptaX<\/jats:sc>\n            is at least 2.2\u00d7 faster than fair sharing and 1.2\u00d7 faster than only assigning small coflows with the highest priority. We further apply\n            <jats:sc>OptaX<\/jats:sc>\n            to improve the small I\/O performance of\n            <jats:sc>Ursa<\/jats:sc>\n            , a distributed block storage system that provides virtual disks where small I\/O is dominant.\n            <jats:sc>Ursa<\/jats:sc>\n            with\n            <jats:sc>OptaX<\/jats:sc>\n            achieves significant improvement compared to the original\n            <jats:sc>Ursa<\/jats:sc>\n            for small I\/O latency.\n          <\/jats:p>","DOI":"10.1145\/3651858","type":"journal-article","created":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T11:20:56Z","timestamp":1710588056000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Scheduling for Data-Parallel Tasks in the Cloud"],"prefix":"10.1145","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8600-8420","authenticated-orcid":false,"given":"Ziyang","family":"Li","sequence":"first","affiliation":[{"name":"NICE XLab, XMU, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9743-2034","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"NUDT, Changsha China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8171-1861","authenticated-orcid":false,"given":"Yingwen","family":"Chen","sequence":"additional","affiliation":[{"name":"NUDT, Changsha China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"SING Lab, HKUST, Hong Kong China and XMU, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-8485","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"NICE XLab, XMU, Xiamen China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,8]]},"reference":[{"key":"e_1_3_3_2_2","volume-title":"Proceedings of the 7th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud \u201915)","author":"Agache Alexandru","year":"2015","unstructured":"Alexandru Agache and Costin Raiciu. 2015. Oh flow, are thou happy? TCP sendbuffer advertising for make benefit of clouds and tenants. In Proceedings of the 7th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud \u201915). https:\/\/www.usenix.org\/conference\/hotcloud15\/workshop-program\/presentation\/agache"},{"key":"e_1_3_3_3_2","first-page":"19","volume-title":"Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation (NSDI \u201910)","author":"Al-Fares Mohammad","year":"2010","unstructured":"Mohammad Al-Fares, Sivasankar Radhakrishnan, Barath Raghavan, Nelson Huang, and Amin Vahdat. 2010. Hedera: Dynamic flow scheduling for data center networks. In Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation (NSDI \u201910). 19. http:\/\/dl.acm.org\/citation.cfm?id=1855711.1855730"},{"key":"e_1_3_3_4_2","first-page":"253","volume-title":"Proceedings of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201912)","author":"Alizadeh Mohammad","year":"2012","unstructured":"Mohammad Alizadeh, Abdul Kabbani, Tom Edsall, Balaji Prabhakar, Amin Vahdat, and Masato Yasuda. 2012. Less is more: Trading a little bandwidth for ultra-low latency in the data center. In Proceedings of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201912). 253\u2013266. https:\/\/www.usenix.org\/conference\/nsdi12\/technical-sessions\/presentation\/alizadeh"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486031"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2014.62"},{"key":"e_1_3_3_7_2","first-page":"455","volume-title":"Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915)","author":"Bai Wei","year":"2015","unstructured":"Wei Bai, Li Chen, Kai Chen, Dongsu Han, Chen Tian, and Hao Wang. 2015. Information-agnostic flow scheduling for commodity data centers. In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915). 455\u2013468. https:\/\/www.usenix.org\/conference\/nsdi15\/technical-sessions\/presentation\/bai"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2079296.2079304"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1592681.1592692"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934888"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524525"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3323165.3323179"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2390231.2390237"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787480"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018448"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626322"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSCloud.2015.38"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511241"},{"key":"e_1_3_3_20_2","first-page":"1","volume-title":"Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915)","author":"Grosvenor Matthew P.","year":"2015","unstructured":"Matthew P. Grosvenor, Malte Schwarzkopf, Ionel Gog, Robert N. M. Watson, Andrew W. Moore, Steven Hand, and Jon Crowcroft. 2015. Queues don\u2019t matter when you can JUMP them! In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915). 1\u201314. https:\/\/www.usenix.org\/conference\/nsdi15\/technical-sessions\/presentation\/grosvenor"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342389"},{"key":"e_1_3_3_22_2","first-page":"15","volume-title":"Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915)","author":"Hu Shuihai","year":"2015","unstructured":"Shuihai Hu, Kai Chen, Haitao Wu, Wei Bai, Chang Lan, Hao Wang, Hongze Zhao, and Chuanxiong Guo. 2015. Explicit path control in commodity data centers: Design and applications. In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915). 15\u201328. https:\/\/www.usenix.org\/conference\/nsdi15\/technical-sessions\/presentation\/hu"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999592"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2016.7568579"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2935764.2935809"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303967"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2942358.2942367"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.82"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511251"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2525767"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511249"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626305"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934890"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6847920"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626309"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2755573.2755592"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2755573.2755592"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2845852"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2016.7784423"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2015.43"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1921168.1921186"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7842029"},{"key":"e_1_3_3_43_2","unstructured":"Matei Zaharia Mosharaf Chowdhury Michael J. Franklin Scott Shenker and Ion Stoica. 2010. Spark: Cluster computing with working sets. In Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing. 10."},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934880"},{"key":"e_1_3_3_45_2","first-page":"529","volume-title":"Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915)","author":"Zhang Yiming","year":"2015","unstructured":"Yiming Zhang, Chuanxiong Guo, Dongsheng Li, Rui Chu, Haitao Wu, and Yongqiang Xiong. 2015. CubicRing: Enabling one-hop failure detection and recovery for distributed in-memory storage systems. In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201915). 529\u2013542. https:\/\/www.usenix.org\/conference\/nsdi15\/technical-sessions\/presentation\/zhang"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218408"}],"container-title":["ACM Transactions on Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651858","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:12Z","timestamp":1750268952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651858"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,8]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6,30]]}},"alternative-id":["10.1145\/3651858"],"URL":"https:\/\/doi.org\/10.1145\/3651858","relation":{},"ISSN":["2329-4949","2329-4957"],"issn-type":[{"type":"print","value":"2329-4949"},{"type":"electronic","value":"2329-4957"}],"subject":[],"published":{"date-parts":[[2024,6,8]]},"assertion":[{"value":"2023-03-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-28","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}