Toward replication in grids for digital libraries with freshness and correctness guarantees

Abstract

SUMMARYBuilding digital libraries (DLs) on top of data grids while facilitating data access and minimizing access overheads is challenging. To achieve this, replication in a Grid has to provide dedicated features that are only partly supported by existing Grid environments. First, it must provide transparent and consistent access to distributed data. Second, it must dynamically control the creation and maintenance of replicas. Third, it should allow higher replication granularities, i.e. beyond individual files. Fourth, users should be able to specify their freshness demands, i.e. whether they need most recent data or are satisfied with slightly outdated data. Finally, all these tasks must be performed efficiently. This paper presents an approach that will finally allow one to build a fully integrated and self-managing replication subsystem for data grids that will provide all the above features. Our approach is to start with an accepted replication protocol for database clusters, namely PDBREP, and to adapt it to the grid.

Partially Eager Update Propagation and Freshness-Based Read Relaxation for Replicated Internet Services

“…Commonly, the freshness of a replicated data set D is defined as the difference between D and the original data set D. Various freshness metrics can be used, such as version difference or the amount of modified data [5], [12] and the time difference [1], [16]. High freshness means that replicated data are close to the original data, and thus the replication service is reliable to a certain degree.…”

Boosting Database Replication Scalability through Partial Replication and 1-Copy-Snapshot-Isolation

“…Full database replication has been heavily studied [2,5,21,6,19,1,9]. The traditional correctness criterion for data replication is one-copy-serializability (1CS) [4].…”

“…For instance, let us assume that there are three sites {s 1 1 and s 2 use their entire processing capacity for local work (R i = 0, L i = C at both sites). The amount of remote work at s 3 is R 3 = (C + C) * 0.75 = 1.5C.…”

DTR: Distributed Transaction Routing in a Large Scale Network

“…Many solutions have been proposed in distributed systems for managing replicas [13], [11], [9], [8], [5] and [12]. Some of them include freshness control [15], [7], [10] and [1]. We base our work on the Leg@net approach [7], since it offers update anywhere and freshness control features and does not require any modification of the underlying DBMS nor of the application source code.…”