A General Technique for Non-blocking Trees

TL;DR

This paper introduces a general method for creating correct, non-blocking tree data structures using multi-word primitives, demonstrated through a non-blocking chromatic tree with competitive performance.

Contribution

The authors present a novel, general technique for non-blocking tree implementations using LLX, SCX, and VLX primitives, applicable to various tree structures.

Findings

Non-blocking chromatic tree implementation with O(c + log n) height.

Java implementation outperforms other concurrent dictionaries.

Technique applicable to a broad class of tree data structures.

Abstract

We describe a general technique for obtaining provably correct, non-blocking implementations of a large class of tree data structures where pointers are directed from parents to children. Updates are permitted to modify any contiguous portion of the tree atomically. Our non-blocking algorithms make use of the LLX, SCX and VLX primitives, which are multi-word generalizations of the standard LL, SC and VL primitives and have been implemented from single-word CAS. To illustrate our technique, we describe how it can be used in a fairly straightforward way to obtain a non-blocking implementation of a chromatic tree, which is a relaxed variant of a red-black tree. The height of the tree at any time is $O(c+ \log n)$, where $n$ is the number of keys and $c$ is the number of updates in progress. We provide an experimental performance analysis which demonstrates that our Java implementation of a chromatic tree rivals, and often significantly outperforms, other leading concurrent dictionaries.