Glacier: highly durable, decentralized storage despite massive correlated failures

By Andreas Haeberlen, Alan Mislove, Peter Druschel. Symposium on Networked Systems Design and Implementation, 2005

320 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Depot: Cloud Storage with Minimal Trust (2010, background): “Glacier [Haeberlen et al. 2005] can tolerate a high threshold, but still no more than this threshold, of faulty nodes, and it stores only immutable objects.”
Erasure Coding in Windows Azure Storage (2012, background): “Erasure Coding in Storage Systems: Erasure coding has been applied in many large-scale distributed storage systems, including storage systems at Facebook and Google [3, 4, 5, 8, 9, 10].”
Want to scale in centralized systems? Think P2P (2015, background): “…and routing overlay) is complemented with a number of additional protocols to handle nodes joining and leaving (either graciously, or through failures, including catastrophic ones [16]), and load-balancing (in case of a skewed distribution of keys in the hash space, or particularly popular keys).”
PeerReview: practical accountability for distributed systems (2007, background): “The DHT is replicated for availability and durability [26], and it can adapt to node failures and churn.”
A Secure Erasure Code-Based Cloud Storage System with Secure Data Forwarding (2012, unknown): “over storage servers [1], [2], [3], [4], [5].”
f4: Facebook's Warm BLOB Storage System (2014, unknown): “Other systems include Glacier [23] and Ursa Minor [1].”