TWA – Ticket Locks Augmented with a Waiting Array

• Published in: Euro-Par 2019: Parallel Processing Vol. 11725; pp. 334 - 345
• Main Authors: Dice, Dave, Kogan, Alex
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Concurrency control; Locks; Mutexes; Mutual exclusion; Synchronization
• ISBN: 3030293998; 9783030293994
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-29400-7_24

The classic ticket lock is simple and compact, consisting of ticket and grant fields. Arriving threads atomically fetch-and-increment ticket to obtain an assigned ticket value, and then wait for grant to become equal to that value, at which point the thread holds the lock. The corresponding unlock operation simply increments grant. This simple design has short code paths and fast handover (transfer of ownership) under light contention, but may suffer degraded scalability under high contention when multiple threads busy wait on the grant field – so-called global spinning. We propose a variation on ticket locks where long-term waiting threads – those with an assigned ticket value far larger than grant – wait on locations in a waiting array instead of busy waiting on the grant field. The single waiting array is shared among all locks. Short-term waiting is accomplished in the usual manner on the grant field. The resulting algorithm, TWA, improves on ticket locks by limiting the number of threads spinning on the grant field at any given time, reducing the number of remote caches requiring invalidation from the store that releases the lock. In turn, this accelerates handover, and since the lock is held throughout the handover operation, scalability improves. Under light or no contention, TWA yields performance comparable to the classic ticket lock. Under high contention, TWA is substantially more scalable than the classic ticket lock, and provides performance on par or beyond that of scalable queue-based locks such as MCS by avoiding the complexity and additional accesses incurred by the MCS handover operation while also obviating the need for maintaining queue elements. We provide an empirical evaluation, comparing TWA against ticket locks and MCS for various user-space applications, and within the Linux kernel.