{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T07:10:21Z","timestamp":1734160221581,"version":"3.30.2"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1109\/mascots64422.2024.10786337","type":"proceedings-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T18:50:09Z","timestamp":1734115809000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Slicify: Fault Injection Testing for Network Partitions"],"prefix":"10.1109","author":[{"given":"Seba","family":"Khaleel","sequence":"first","affiliation":[{"name":"University of Waterloo,Waterloo,Canada"}]},{"given":"Sreeharsha","family":"Udayashankar","sequence":"additional","affiliation":[{"name":"University of Waterloo,Waterloo,Canada"}]},{"given":"Samer","family":"Al-Kiswany","sequence":"additional","affiliation":[{"name":"University of Waterloo,Waterloo,Canada"}]}],"member":"263","reference":[{"key":"ref1","first-page":"249","article-title":"Simple testing can prevent most critical failures: An analysis of production failures in distributed Data-Intensive systems","volume-title":"In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Yuan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2008.4630118"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3241062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1851275.1851220"},{"volume-title":"A Byzantine failure in the real world","year":"2020","key":"ref5"},{"volume-title":"Google Cloud Networking Incident #18003","year":"2019","key":"ref6"},{"volume-title":"Lyft Engineering: Operating Apache Kafka Clusters 24\/7 Without a Global Ops Team","year":"2019","author":"Falko","key":"ref7"},{"volume-title":"Learning from AWS Failure","year":"2013","key":"ref8"},{"key":"ref9","first-page":"51","article-title":"An analysis of network-partitioning failures in cloud systems","volume-title":"In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation, OSDI\u201918","author":"Alquraan"},{"key":"ref10","first-page":"351","article-title":"Toward a generic fault tolerance technique for partial network partitioning","volume-title":"In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Alfatafta"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3576192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS60354.2023.00017"},{"volume-title":"Kafka-8702: Kafka leader election doesn\u2019t happen when leader broker port is partitioned off the network","key":"ref13"},{"volume-title":"Hazelcast Documentation","key":"ref14"},{"volume-title":"Apache Flink Documentation","key":"ref15"},{"volume-title":"ActiveMQ Artemis Documentation","key":"ref16"},{"volume-title":"Artemis-4555: Activemq artemis can have two live brokers in one cluster at one time","key":"ref17"},{"volume-title":"Flink-34006: Flink terminates the execution of an application when there is a network problem between taskmanagers","key":"ref18"},{"volume-title":"Hazelcast-26208: Hazelcast fails some client requests when there is a split in the cluster","key":"ref19"},{"volume-title":"Slicify github repository","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934891"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2043164.2018477"},{"volume-title":"Bnx2 cards intermittantly going offline","author":"Mills","key":"ref23"},{"volume-title":"MySQL","year":"2013","author":"DuBois","key":"ref24"},{"key":"ref25","article-title":"Redis in action","author":"Carlson","year":"2013","journal-title":"Simon and Schuster"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/26.103043"},{"volume-title":"Wireshark User\u2019s Guide","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6198-6_16"},{"volume-title":"Pyshark Documentation","key":"ref29"},{"volume-title":"iptables(8) - Linux man page","key":"ref30"},{"volume-title":"Cloudlab hardware","key":"ref31"},{"key":"ref32","first-page":"1","article-title":"The design and operation of CloudLab","volume-title":"In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Duplyakin"},{"key":"ref33","first-page":"15","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for inmemory cluster computing","volume-title":"In Presented as part of the 9th {USENIX} Symposium on Networked Systems Design and Implementation ({NSDI} 12)","author":"Zaharia"},{"volume-title":"Apache Kafka","key":"ref34"},{"key":"ref35","first-page":"58","volume-title":"Mesos fundamentals","author":"Ignazio","year":"2018"},{"volume-title":"Apache ZooKeeper","key":"ref36"},{"key":"ref37","first-page":"305","article-title":"In search of an understandable consensus algorithm","volume-title":"In Proceedings of the 2014 USENIX Conference on USENIX Annual Technical Conference, USENIX ATC\u201914","author":"Ongaro"},{"volume-title":"Partial Network Partitions","key":"ref38"},{"volume-title":"Split-Brain Protection","key":"ref39"},{"volume-title":"Distributed Map","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/12.656094"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2003.1203468"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/RELDIS.2003.1238077"},{"key":"ref44","first-page":"536","article-title":"Cofi: Consistency-guided fault injection for cloud systems","volume-title":"In 2020 35th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2014.6915433"},{"volume-title":"Nagios: System and network monitoring","year":"2008","author":"Barth","key":"ref46"}],"event":{"name":"2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","start":{"date-parts":[[2024,10,21]]},"location":"Krakow, Poland","end":{"date-parts":[[2024,10,23]]}},"container-title":["2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10786488\/10786336\/10786337.pdf?arnumber=10786337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T06:33:59Z","timestamp":1734158039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10786337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/mascots64422.2024.10786337","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]}}}