{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:50Z","timestamp":1782798290939,"version":"3.54.5"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571395","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Vedrfolnir: RDMA Network Performance Anomalies Diagnosis in Collective Communications"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Chen","sequence":"first","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangzheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Laboratory of Internet Architecture"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxun","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shicheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Laboratory of Internet Architecture"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunming","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University,School of Software"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"InfiniBand Architecture Specification Release 1.4 Annex A17: RoCEv2","year":"2020"},{"key":"ref2","first-page":"519","article-title":"When cloud storage meets RDMA","author":"Gao","year":"2021","journal-title":"NSDI 2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"ref4","first-page":"49","article-title":"Empowering azure storage with RDMA","author":"Bai","journal-title":"NSDI 23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"ref8","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","author":"Jiang","year":"2020","journal-title":"OSDI 20"},{"key":"ref9","first-page":"745","article-title":"MegaScale: Scaling large language model training to more than 10,000 GPUs","author":"Jiang","year":"2024","journal-title":"NSDI 2024"},{"key":"ref10","first-page":"739","article-title":"TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs","author":"Wang","year":"2023","journal-title":"NSDI 23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303975"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"ref13","article-title":"IEEE 802.1 Qbb - Priority-based Flow Control","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787484"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406591"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3672202.3673711"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750490"},{"key":"ref18","article-title":"Closed-loop network performance monitoring and diagnosis with SpiderMon","author":"Wang","year":"2022","journal-title":"USENIX NSDI 2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230555"},{"key":"ref20","article-title":"Scaling hardware accelerated network monitoring to concurrent and dynamic queries with *flow","author":"Sonchack","year":"2018","journal-title":"USENIX ATC 2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref22","article-title":"I know what your packet did last hop: using packet histories to troubleshoot networks","author":"Handigol","year":"2014","journal-title":"USENIX NSDI 2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405894"},{"key":"ref24","article-title":"Vedrfolnir: Rdma network performance anomalies diagnosis in collective communication","year":"2025"},{"key":"ref25","article-title":"Flowradar: a better netflow for data centers","author":"Li","year":"2016","journal-title":"USENIX NSDI 2016"},{"key":"ref26","article-title":"Distributed network monitoring and debugging with switchpointer","author":"Tammana","year":"2018","journal-title":"USENIX NSDI 2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3050228"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787496"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934879"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544257"},{"key":"ref31","article-title":"007: democratically finding the cause of packet drops","author":"Arzani","year":"2018","journal-title":"USENIX NSDI 2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3359989.3365408"},{"key":"ref33","article-title":"Zeno: diagnosing performance prob- lems with temporal provenance","author":"Wu","year":"2024","journal-title":"USENIX NSDI 2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2025.3592688"},{"key":"ref35","first-page":"15","article-title":"Hostping: Diagnosing intra-host network bottlenecks in {RDMA} servers","author":"Liu","year":"2023","journal-title":"USENIX NSDI 2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672264"},{"key":"ref37","article-title":"Holmes: Localizing irregularities in llm training with mega-scale gpu clusters","author":"Yao","year":"2025","journal-title":"USENIX NSDI 2025"},{"key":"ref38","article-title":"Evolution of aegis: Fault diagnosis for ai model training service in production","author":"Dong","year":"2025","journal-title":"USENIX NSDI 2025"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571395.pdf?arnumber=11571395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:16:31Z","timestamp":1782796591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571395","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}