Scalable Lock-Free Vector with Combining
Paper i proceeding, 2017

Dynamic vectors are among the most commonly used data structures in programming. They provide constant time random access and resizable data storage. Additionally, they provide constant time insertion (pushback) and deletion (popback) at the end of the sequence. However, in a multithreaded system, concurrent pushback and popback operations attempt to update the same shared object, creating a synchronization bottleneck. In this paper, we present a lock-free vector design that efficiently addresses the synchronization bottlenecks by utilizing a combining technique on pushback operations. Typical combining techniques come with the price of blocking. Our design introduces combining without sacrificing lock-freedom. We evaluate the performance of our design on a dual socket NUMA Intel server. The results show that our design performs comparably at low loads, and out-performs prior concurrent blocking and non-blocking vector implementations at high contention, by as much as 2.7x.

scalability

lock free

combining

dynamic resizable arrays

vectors

backoff

concurrent data structure

Författare

Ivan Walulya

Chalmers, Data- och informationsteknik, Nätverk och system

Philippas Tsigas

Chalmers, Data- och informationsteknik, Nätverk och system

Proceedings - 2017 IEEE 31st International Parallel and Distributed Processing Symposium, IPDPS 2017

917-926
9781538639146 (ISBN)

Ämneskategorier

Data- och informationsvetenskap

DOI

10.1109/IPDPS.2017.73

ISBN

9781538639146

Mer information

Skapat

2017-10-07