{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:58:09Z","timestamp":1781974689627,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2211302"],"award-info":[{"award-number":["2211302"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,20]]},"DOI":"10.1145\/3698038.3698554","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:32:43Z","timestamp":1731565963000},"page":"398-414","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["TailClipper: Reducing Tail Response Time of Distributed Services Through System-Wide Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8508-8124","authenticated-orcid":false,"given":"Nathan","family":"Ng","sequence":"first","affiliation":[{"name":"University of Massachusetts, Amherst"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6952-1195","authenticated-orcid":false,"given":"Abel","family":"Souza","sequence":"additional","affiliation":[{"name":"University of California Santa, Cruz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-9284","authenticated-orcid":false,"given":"Ahmed","family":"Ali-Eldin","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1722-4927","authenticated-orcid":false,"given":"David","family":"Irwin","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7808-7375","authenticated-orcid":false,"given":"Don","family":"Towsley","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5435-1901","authenticated-orcid":false,"given":"Prashant","family":"Shenoy","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2997641"},{"key":"e_1_3_2_1_2_1","unstructured":"Mike Belshe. 2010. More Bandwidth Doesn't Matter (Much). https:\/\/bit.ly\/3RUykxs."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291183"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Peter Bod\u00edk Ishai Menache Joseph (Seffi) Naor and Jonathan Yaniv. 2014. Brief Announcement: Deadline-Aware Scheduling of Big-Data Processing Jobs. In SPAA. https:\/\/www.microsoft.com\/en-us\/research\/publication\/brief-announcement-deadline-aware-scheduling-of-big-data-processing-jobs\/","DOI":"10.1145\/2612669.2612702"},{"key":"e_1_3_2_1_5_1","volume-title":"Trivedi","author":"Bolch Gunter","year":"1998","unstructured":"Gunter Bolch, Stefan Greiner, Hermann de Meer, and Kishor S. Trivedi. 1998. Queueing networks and Markov chains: modeling and performance evaluation with computer science applications. Wiley-Interscience, USA."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation","author":"Boutin Eric","year":"2014","unstructured":"Eric Boutin, Jaliya Ekanayake, Wei Lin, Bing Shi, Jingren Zhou, Zhengping Qian, Ming Wu, and Lidong Zhou. 2014. Apollo: scalable and coordinated scheduling for cloud-scale computing. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation (Broomfield, CO) (OSDI'14). USENIX Association, USA, 285--300."},{"key":"e_1_3_2_1_7_1","unstructured":"Gary Bradski Adrian Kaehler et al. 2000. OpenCV. Dr. Dobb's journal of software tools 3 2 (2000)."},{"key":"e_1_3_2_1_8_1","unstructured":"Gary Bradski Adrian Kaehler et al. 2024. OpenCV - Smoothing Images. https:\/\/docs.opencv.Org\/4.x\/d4\/d13\/tutorial_py_filtering.html."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465286"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1323293.1294281"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85778-5_11"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAC.2015.25"},{"key":"e_1_3_2_1_15_1","volume-title":"A Resourceful Coordination Approach for Multilevel Scheduling. arXiv preprint arXiv:2103.05809","author":"Eleliemy Ahmed","year":"2021","unstructured":"Ahmed Eleliemy and Florina M Ciorba. 2021. A Resourceful Coordination Approach for Multilevel Scheduling. arXiv preprint arXiv:2103.05809 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/224056.224076"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1012889.1012894"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488782"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-016-9485-y"},{"key":"e_1_3_2_1_20_1","unstructured":"Google. [n. d.]. GhOSt: Fast & Flexible User-Space Delegation of Linux Scheduling. https:\/\/github.com\/google\/ghost-userspace https:\/\/github.com\/google\/ghost-userspace."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694384"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123956"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483542"},{"key":"e_1_3_2_1_24_1","unstructured":"Yangqing Jia and Evan Shelhamer. 2024. Caffe Model Zoo. http:\/\/caffe.berkeleyvision.org\/model_zoo."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3323234.3323264"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391238"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541944"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494621.2494636"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488217"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592821"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670988"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3487003"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the Third Annual Web 2","author":"Mayer Marissa","year":"2006","unstructured":"Marissa Mayer. 2006. What Google Knows. Proceedings of the Third Annual Web 2 (2006)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2010.08.012"},{"key":"e_1_3_2_1_35_1","volume-title":"PieSlicer: Dynamically Improving Response Time for Cloud-based CNN Inference. In 12th ACM\/SPEC International Conference on Performance Engineering. Association for Computing Machinery (ACM).","author":"Ogden Samuel S.","year":"2021","unstructured":"Samuel S. Ogden, Xiangnan Kong, and Tian Guo. 2021. PieSlicer: Dynamically Improving Response Time for Cloud-based CNN Inference. In 12th ACM\/SPEC International Conference on Performance Engineering. Association for Computing Machinery (ACM)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3323234.3323265"},{"key":"e_1_3_2_1_37_1","volume-title":"Completely Fair Scheduler. Linux Magazine 184","author":"Pabla Chandandeep","year":"2009","unstructured":"Chandandeep Pabla. 2009. Completely Fair Scheduler. Linux Magazine 184 (2009)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812806"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132780"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291180"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3393691.3394179"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789770.2789806"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(91)90086-5"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2005.27"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830779"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2535372.2535392"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.13140\/2.1.1479.0402"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018443"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789770.2789808"},{"key":"e_1_3_2_1_50_1","volume-title":"StackMap: Low-Latency Networking with the OS Stack and Dedicated NICs. In 2016 USENIX Annual Technical Conference (USENIX ATC 16)","author":"Yasukata Kenichi","year":"2016","unstructured":"Kenichi Yasukata, Michio Honda, Douglas Santry, and Lars Eggert. 2016. StackMap: Low-Latency Networking with the OS Stack and Dedicated NICs. In 2016 USENIX Annual Technical Conference (USENIX ATC 16). 43--56."},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing","author":"Zaharia Matei","year":"2010","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 (Boston, MA) (HotCloud'10). USENIX Association, USA, 10."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8504-0"}],"event":{"name":"SoCC '24: ACM Symposium on Cloud Computing","location":"Redmond WA USA","acronym":"SoCC '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698554","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698038.3698554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:00:58Z","timestamp":1755889258000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":52,"alternative-id":["10.1145\/3698038.3698554","10.1145\/3698038"],"URL":"https:\/\/doi.org\/10.1145\/3698038.3698554","relation":{},"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}