Non-blocking Dynamic Unbounded Graphs with Wait-Free Snapshot

TL;DR

This paper introduces a novel lock-free, linearizable, and wait-free concurrent graph data structure with a snapshot algorithm, enabling efficient graph analytics like diameter and centrality calculations.

Contribution

First implementation of a wait-free snapshot algorithm for dynamic unbounded concurrent graphs, improving performance for graph analytics.

Findings

Outperforms existing graph implementations in benchmarks.

Enables efficient computation of diameter and centrality.

Demonstrates the versatility of the snapshot method for various analytics.

Abstract

Graphs are arguably one of the most fundamental data-structure used in many domains such as block-chain, networks etc. Theoretically and practically, improving Graph performance is one of the most studied and omnipresent research problems. In this paper, we have implemented a dynamic unbounded concurrent graph which can perform the add, delete or lookup operations on vertices and edges concurrently. All these methods are lock-free and linearizable. On top of this, we have also implemented the wait-free graph snapshot algorithm. To the best of knowledge this is first wait-free implementation of snapshot on concurrent graphs. We have used the snapshot of the algorithm to calculate the diameter and between centrality. We have compared our implementation with its counterparts and outperformed them by a good margin. This illustrates the efficiency of our snapshot method which is a generic method and can be used to perform other useful graph analytics operations.