GeoRep - Resilient Storage for Wide Area Networks

Artikel i vetenskaplig tidskrift, 2022

Embedded systems typically have limited processing and storage capabilities, and may only
intermittently be powered on. After sending data from its sensors upstream, the system must therefore be able
to trust that the data, once acknowledged, is not lost. The purpose of this work is to propose a novel solution
for replicating data between the upstream nodes in such systems, with a minimal effect on the software
architecture. On the assumption that there is no relative order between replicated data tuples, we designed
a new replication protocol based on partial replication. Our protocol uses only 2 communication steps per
data tuple, instead of the 3 to 12 used by other solutions. We verified its failover mechanism in a proof-of-
concept implementation of the protocol using simulated network failures, and evaluated the implementation
on throughput and latency in several controlled experiments using up to 7 nodes in up to 5 geographically
separated areas, with up to 1000 data producers per node. The recorded system throughput increased linearly
relative to both the number of nodes and the number of data producers. For comparison, Paxos showed a
performance similar to our protocol when using 3 nodes, but got slower as more nodes were added. The lack
of a relative order, in combination with partial replication, enables our system to continue working during
network partitions, not only in the part containing the majority of the nodes, but also in any sufficiently large
minority partitions.