Performance Prediction for Coarse-Grained Locking

TL;DR

This paper introduces a simple stochastic model to predict the throughput of coarse-grained lock-based algorithms in concurrent data structures, demonstrating its effectiveness for CLH locks and potential applicability to other lock types.

Contribution

The paper presents a novel, simple model for predicting throughput of coarse-grained locking algorithms, validated on CLH lock and extendable to other lock designs.

Findings

Model accurately predicts CLH lock throughput

Potential applicability to TTAS and MCS locks

Supports stochastic analysis for concurrent performance prediction

Abstract

A standard design pattern found in many concurrent data structures, such as hash tables or ordered containers, is an alternation of parallelizable sections that incur no data conflicts and critical sections that must run sequentially and are protected with locks. A lock can be viewed as a queue that arbitrates the order in which the critical sections are executed, and a natural question is whether we can use stochastic analysis to predict the resulting throughput. As a preliminary evidence to the affirmative, we describe a simple model that can be used to predict the throughput of coarse-grained lock-based algorithms. We show that our model works well for CLH lock, and we expect it to work for other popular lock designs such as TTAS, MCS, etc.