Gtimer: A Distributed System for Processing Temporal Graphs

Gtimer provides a general-purpose programming framework, which adopts Pregel's vertex-centric computing model to allow easy design of distributed graph algorithms.

Like Pregel, the Gtimer system automatically handles work distribution and fault tolerance so that programmers do not have to worry on the complicated details.

Apart from a general API as Pregel's, Gtimer also supports a set of fundamental operators for processing temporal graphs, which hide (from users) the low-level details of how operations specific to a temporal graph should be performed. We design new storage structure and indexes to support efficient and scalable operations on a large temporal graph.

Gtimer also supports efficient update maintenance as a temporal graph keeps updating over time. Our performance evaluation verifies that existing systems are not efficient for processing temporal graphs, while Gtimer is efficient and scalable on a wide range of operations on large temporal graphs from different domains.