A Fast Lock-Free Internal Binary Search Tree

Abstract

We present a new lock-free algorithm for concurrent manipulation of a binary search tree in an asynchronous shared memory system that supports search, insert and delete operations. It combines ideas from two recently proposed lock-free algorithms: one of them provides good performance for a read-dominated workload and the other one for a write-dominated workload. Specifically, it uses internal representation of a search tree (as in the first one) and is based on marking edges instead of nodes (as in the second one). Our experiments indicate that our new lock-free algorithm outperforms other lock-free algorithms in most cases providing up to 35% improvement in some cases over the next best algorithm.