{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T02:35:48Z","timestamp":1777775748490,"version":"3.51.4"},"reference-count":60,"publisher":"Emerald","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12,17]]},"abstract":"<jats:p>Distributed storage has been an active research area for decades. With the proliferation of cloud computing, there has been a rejuvenated interest in two perspectives. The first perspective is seen through the lenses of the cloud providers: how should we build global storage services for cloud hosted services and applications at scale with high reliability and availability guarantees, but also in a cost effective way? The second perspective is seen through the lenses of the service providers that utilize public clouds: how can we achieve high I\/O performance over cloud storage within a cost budget? In this manuscript, we first present various kinds of distributed storage systems, their operational characteristics and the key techniques to improve their performance. We then focus on cloud storage, exclusively. Cloud storage has massive scales with the promise to provide as much storage capacity as their tenants demand. Cloud providers also promise very high durability, availability, and I\/O performance. In this context, we cover the fundamental tradeoffs between storage efficiency and network bandwidth as well as I\/O throughput and latency. Erasure codes play an essential role in these tradeoffs and, thus, we also present their design and usage in the context of cloud storage broadly. We pay particular attention on various queuing models and the corresponding performance analysis in the presence of coded storage. We provide exact and approximate solutions under various settings and assumptions. We describe optimal or near-optimal scheduling and coding strategies that are established based on these analyses.<\/jats:p>","DOI":"10.1561\/1300000051","type":"journal-article","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T08:30:04Z","timestamp":1450341004000},"page":"219-315","source":"Crossref","is-referenced-by-count":1,"title":["Building Reliable Storage Clouds: Models, Fundamental Tradeoffs, and Solutions"],"prefix":"10.1108","volume":"9","author":[{"given":"Ulas C.","family":"Kozat","sequence":"first","affiliation":[{"name":"Huawei R&D"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanfeng","family":"Liang","sequence":"additional","affiliation":[{"name":"LinkedIn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2015,12,17]]},"reference":[{"issue":"4","key":"2026040606561660900_ref001","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1109\/18.850663","article-title":"Network information flow","volume":"46","author":"Ahlswede","year":"2000","journal-title":"IEEE Transactions on Information Theory"},{"issue":"6","key":"2026040606561660900_ref002","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1287\/opre.4.6.699","article-title":"The output of a queuing system","volume":"4","author":"Burke","year":"1956","journal-title":"Operations Research"},{"issue":"8","key":"2026040606561660900_ref003","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1109\/JSAC.2002.803996","article-title":"A digital fountain approach to asynchronous reliable multicast","volume":"20","author":"Byers","year":"2002","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"5","key":"2026040606561660900_ref004","doi-asserted-by":"crossref","first-page":"2974","DOI":"10.1109\/TIT.2013.2237752","article-title":"Asymptotic interference alignment for optimal repair of mds codes in distributed storage","volume":"59","author":"Cadambe","year":"2013","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026040606561660900_ref005","first-page":"1","article-title":"Load balancing and dynamic scaling of cache storage against zipfian workloads","author":"Cai","year":"2014"},{"issue":"2","key":"2026040606561660900_ref006","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1145\/1365815.1365816","article-title":"Bigtable: A distributed storage system for structured data","volume":"26","author":"Chang","year":"2008","journal-title":"ACM Transactions on Computer Systems (TOCS)"},{"issue":"2","key":"2026040606561660900_ref007","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1145\/176979.176981","article-title":"Raid: High-performance, reliable secondary storage","volume":"26","author":"Chen","year":"1994","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2026040606561660900_ref008","first-page":"1042","article-title":"When queueing meets coding: Optimal-latency data retrieving scheme in storage clouds","author":"Chen","year":"2014"},{"key":"2026040606561660900_ref009","first-page":"1","article-title":"Can network coding help in p2p networks?","author":"Chiu","year":"2006"},{"issue":"2","key":"2026040606561660900_ref010","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.14778\/1454159.1454167","article-title":"Pnuts: Yahoo!\u2019s hosted data serving platform","volume":"1","author":"Cooper","year":"2008","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"1","key":"2026040606561660900_ref011","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","article-title":"Mapreduce: Simplified data processing on large clusters","volume":"51","author":"Dean","year":"2008","journal-title":"Communications of the ACM"},{"key":"2026040606561660900_ref012","first-page":"205","article-title":"Dynamo: Amazon\u2019s highly available key-value store","author":"DeCandia","year":"2007"},{"issue":"9","key":"2026040606561660900_ref013","doi-asserted-by":"crossref","first-page":"4539","DOI":"10.1109\/TIT.2010.2054295","article-title":"Network coding for distributed storage systems","volume":"56","author":"Dimakis","year":"2010","journal-title":"IEEE Transactions on Information Theory"},{"issue":"3","key":"2026040606561660900_ref014","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1109\/JPROC.2010.2096170","article-title":"A survey on network codes for distributed storage","volume":"99","author":"Dimakis","year":"2011","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"2026040606561660900_ref015","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/s12083-009-0044-8","article-title":"Hierarchical codes: A flexible trade-off for erasure codes in peer-to-peer storage systems","volume":"3","author":"Duminuco","year":"2010","journal-title":"Peer-to-peer networking and applications"},{"key":"2026040606561660900_ref016","article-title":"Exact-regenerating codes between MBR and MSR points","author":"Ernvall","year":"2013","journal-title":"CoRR"},{"key":"2026040606561660900_ref017","first-page":"652","article-title":"Network coded storage with multi-resolution codes","author":"Ferner","year":"2013"},{"key":"2026040606561660900_ref018","article-title":"An Evaluation of Amazon\u2019s Grid Computing Services: EC2, S3 and SQS","author":"Garfinkel","year":"2007","journal-title":"Technical report"},{"key":"2026040606561660900_ref019","first-page":"2235","article-title":"Network coding for large scale content distribution","author":"Gkantsidis","year":"2005"},{"key":"2026040606561660900_ref020","article-title":"New codes and inner bounds for exact repair in distributed storage systems","author":"Goparaju","year":"2014","journal-title":"CoRR"},{"key":"2026040606561660900_ref021","first-page":"1","article-title":"Flat xor-based erasure codes in storage systems: Constructions, efficient recovery, and tradeoffs","author":"Greenan","year":"2010"},{"issue":"10","key":"2026040606561660900_ref022","doi-asserted-by":"crossref","first-page":"4413","DOI":"10.1109\/TIT.2006.881746","article-title":"A random linear network coding approach to multicast","volume":"52","author":"Ho","year":"2006","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026040606561660900_ref023","article-title":"Erasure coding in windows azure storage","author":"Huang","year":"2012"},{"key":"2026040606561660900_ref024","first-page":"2766","article-title":"Codes can reduce queueing delay in data centers","author":"Huang","year":"2012"},{"issue":"6","key":"2026040606561660900_ref025","doi-asserted-by":"crossref","first-page":"1973","DOI":"10.1109\/TIT.2005.847712","article-title":"Polynomial time algorithms for multicast network code construction","volume":"51","author":"Jaggi","year":"2005","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026040606561660900_ref026","first-page":"326","article-title":"Coding for Fast Content Download","author":"Joshi","year":"2012"},{"key":"2026040606561660900_ref027","article-title":"On the delay-storage tradeoff in content download from coded distributed storage systems","author":"Joshi","year":"2013","journal-title":"arXiv preprint"},{"issue":"5","key":"2026040606561660900_ref028","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1109\/JSAC.2014.140518","article-title":"On the Delay-Storage Trade-Off in Content Download from Coded Distributed Storage Systems","volume":"32","author":"Joshi","year":"2014","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"2026040606561660900_ref029","article-title":"Rethinking erasure codes for cloud file systems: Minimizing i\/o for recovery and degraded reads","author":"Khan","year":"2012"},{"issue":"2","key":"2026040606561660900_ref030","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/12.16501","article-title":"Analysis of the fork-join queue","volume":"38","author":"Kim","year":"1989","journal-title":"IEEE Transactions on Computers"},{"key":"2026040606561660900_ref031","first-page":"7:1","article-title":"Zyzzyva: Speculative Byzantine fault tolerance","volume":"27","author":"Kotla","year":"2010","journal-title":"ACM Transactions on Computer Systems"},{"key":"2026040606561660900_ref032","first-page":"3710","article-title":"On improving latency of geographically distributed key-value stores via load balancing with side information","author":"Kubo","year":"2013"},{"issue":"9","key":"2026040606561660900_ref033","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/LCOMM.2004.833807","article-title":"Systematic mds erasure codes based on vandermonde matrices","volume":"8","author":"Lacan","year":"2004","journal-title":"IEEE Communications Letters"},{"issue":"2","key":"2026040606561660900_ref034","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/1773912.1773922","article-title":"Cassandra: a decentralized structured storage system","volume":"44","author":"Lakshman","year":"2010","journal-title":"ACM SIGOPS Operating Systems Review"},{"key":"2026040606561660900_ref035","first-page":"826","article-title":"TOFEC: Achieving optimal throughput-delay trade-off of cloud storage using erasure codes","author":"Liang","year":"2014"},{"key":"2026040606561660900_ref036","doi-asserted-by":"crossref","DOI":"10.1109\/ALLERTON.2014.7028507","article-title":"Use of erasure code for low latency cloud storage","author":"Liang","year":"2014"},{"key":"2026040606561660900_ref037","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2289382","article-title":"FAST CLOUD: Pushing the Envelope on Delay Performance of Cloud Storage with Coding","author":"Liang","year":"2013","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"2026040606561660900_ref038","article-title":"On throughput-delay optimal access to storage clouds via load adaptive coding and chunking","author":"Liang","year":"2014","journal-title":"arXiv preprint"},{"key":"2026040606561660900_ref039","first-page":"1","article-title":"Uusee: large-scale operational on-demand streaming with random network coding","author":"Liu","year":"2010"},{"key":"2026040606561660900_ref040","first-page":"271","article-title":"LT codes","author":"Luby","year":"2002"},{"issue":"1","key":"2026040606561660900_ref041","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/TBC.2007.891703","article-title":"Reliable multimedia download delivery in cellular broadcast networks","volume":"53","author":"Luby","year":"2007","journal-title":"IEEE Transactions on Broadcasting"},{"key":"2026040606561660900_ref042","first-page":"2801","article-title":"Simple regenerating codes: Network coding for cloud storage","author":"Papailiopoulos","year":"2012"},{"issue":"3","key":"2026040606561660900_ref043","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/971701.50214","article-title":"A case for redundant arrays of inexpensive disks (raid)","volume":"17","author":"Patterson","year":"1988","journal-title":"SIGMOD Record"},{"key":"2026040606561660900_ref044","first-page":"367","article-title":"Modeling and performance analysis of bittorrent-like peer-to-peer networks","author":"Qiu","year":"2004"},{"key":"2026040606561660900_ref045","article-title":"Optimal exact-regenerating codes for distributed storage at the MSR and MBR points via a product-matrix construction","author":"Rashmi","year":"2010","journal-title":"CoRR"},{"key":"2026040606561660900_ref046","first-page":"329","article-title":"Pastry: Scalable, decentralized object location, and routing for large-scale peer-to-peer systems","author":"Rowstron","year":"2001"},{"key":"2026040606561660900_ref047","first-page":"325","article-title":"Xoring elephants: novel erasure codes for big data","author":"Sathiamoorthy","year":"2013"},{"key":"2026040606561660900_ref048","article-title":"Xoring elephants: Novel erasure codes for big data","author":"Sathiamoorthy","year":"2013","journal-title":"CoRR"},{"key":"2026040606561660900_ref049","first-page":"1","article-title":"Explicit codes minimizing repair bandwidth for distributed storage","author":"Shah","year":"2010"},{"issue":"3","key":"2026040606561660900_ref050","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.1109\/TIT.2011.2173792","article-title":"Distributed storage codes with repair-by-transfer and nonachievability of interior points on the storage-bandwidth tradeoff","volume":"58","author":"Shah","year":"2012","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026040606561660900_ref051","article-title":"The MDS queue: Analysing the latency performance of erasure codes","author":"Shah","year":"2013","journal-title":"arXiv preprint"},{"issue":"6","key":"2026040606561660900_ref052","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1109\/TIT.2006.874390","article-title":"Raptor codes","volume":"52","author":"Shokrollahi","year":"2006","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026040606561660900_ref053","first-page":"1","article-title":"The hadoop distributed file system","author":"Shvachko","year":"2010"},{"issue":"1","key":"2026040606561660900_ref054","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TNET.2002.808407","article-title":"Chord: A scalable peer-to-peer lookup protocol for internet applications","volume":"11","author":"Stoica","year":"2003","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"2026040606561660900_ref055","article-title":"Exact regeneration codes for distributed storage repair using interference alignment","author":"Suh","year":"2010","journal-title":"CoRR"},{"key":"2026040606561660900_ref056","article-title":"Layered, exact-repair regenerating codes via embedded error correction and block designs","author":"Tian","year":"2014","journal-title":"CoRR"},{"key":"2026040606561660900_ref057","article-title":"Deterministic regenerating codes for distributed storage","author":"Wu","year":"2007"},{"key":"2026040606561660900_ref058","article-title":"Joint latency and cost optimization for erasure-coded data center storage","author":"Xiang","year":"2014","journal-title":"arXiv preprint"},{"key":"2026040606561660900_ref059","article-title":"Does erasure coding have a role to play in my data center","volume":"52","author":"Zhang","year":"2010","journal-title":"Microsoft Research MSR-TR-2010"},{"issue":"1","key":"2026040606561660900_ref060","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/510726.510755","article-title":"Tapestry: A fault-tolerant wide-area application infrastructure","volume":"32","author":"Zhao","year":"2002","journal-title":"SIGCOMM Computer Communations Review"}],"container-title":["Foundations and Trends\u00ae in Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftnet\/article-pdf\/9\/4\/219\/11491550\/1300000051en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftnet\/article-pdf\/9\/4\/219\/11491550\/1300000051en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:13:49Z","timestamp":1777486429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftnet\/article\/9\/4\/219\/1330332\/Building-Reliable-Storage-Clouds-Models"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12,17]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,12,17]]}},"URL":"https:\/\/doi.org\/10.1561\/1300000051","relation":{},"ISSN":["1554-057X","1554-0588"],"issn-type":[{"value":"1554-057X","type":"print"},{"value":"1554-0588","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,12,17]]}}}