Modern information networks often require maintaining multiple copies of the same data items for the purpose of coping with failures, robustness to errors, and fast access. The traditional approach for the design of data multiplication protocols relies on replication. A more recent powerful tool that facilitates low storage costs, as well as low communication costs, is erasure codes that transform a message of k symbols into a code-word with n symbols such that the original message can be recovered from a subset of the n symbols.
In this talk, we will discuss several challenges concerning data multiplication in the context of Content Delivery Networks (CDN) and large scale Distributed Storage Systems (DSS). Following that, we will present a replication based protocol that minimizes the delivery and storage costs for Video on Demand (VoD) in CDNs. Then, we will present a Storage-Optimized Data-Atomic protocol for DSSs that employs erasure codes in a novel sophisticated manner.
The talk will be self-contained.
Erez Kantor, Distributed Systems group, CSAIL MIT