Topic
Lock convoy
About: Lock convoy is a research topic. Over the lifetime, 101 publications have been published within this topic receiving 5277 citations.
Papers published on a yearly basis
Papers
TL;DR: The principal conclusion is that contention due to synchronization need not be a problemin large-scale shared-memory multiprocessors, and the existence of scalable algorithms greatly weakens the case for costly special-purpose hardware support for synchronization, and provides protection against so-called “dance hall” architectures.
Abstract: Busy-wait techniques are heavily used for mutual exclusion and barrier synchronization in shared-memory parallel programs. Unfortunately, typical implementations of busy-waiting tend to produce large amounts of memory and interconnect contention, introducing performance bottlenecks that become markedly more pronounced as applications scale. We argue that this problem is not fundamental, and that one can in fact construct busy-wait synchronization algorithms that induce no memory or interconnect contention. The key to these algorithms is for every processor to spin on separate locally-accessible flag variables, and for some other processor to terminate the spin with a single remote write operation at an appropriate time. Flag variables may be locally-accessible as a result of coherent caching, or by virtue of allocation in the local portion of physically distributed shared memory.We present a new scalable algorithm for spin locks that generates 0(1) remote references per lock acquisition, independent of the number of processors attempting to acquire the lock. Our algorithm provides reasonable latency in the absence of contention, requires only a constant amount of space per lock, and requires no hardware support other than a swap-with-memory instruction. We also present a new scalable barrier algorithm that generates 0(1) remote references per processor reaching the barrier, and observe that two previously-known barriers can likewise be cast in a form that spins only on locally-accessible flag variables. None of these barrier algorithms requires hardware support beyond the usual atomicity of memory reads and writes.We compare the performance of our scalable algorithms with other software approaches to busy-wait synchronization on both a Sequent Symmetry and a BBN Butterfly. Our principal conclusion is that contention due to synchronization need not be a problem in large-scale shared-memory multiprocessors. The existence of scalable algorithms greatly weakens the case for costly special-purpose hardware support for synchronization, and provides a case against so-called “dance hall” architectures, in which shared memory locations are equally far from all processors. —From the Authors' Abstract
1,290 citations
TL;DR: The author examines the questions of whether there are efficient algorithms for software spin-waiting given hardware support for atomic instructions, or whether more complex kinds of hardware support are needed for performance.
Abstract: The author examines the questions of whether there are efficient algorithms for software spin-waiting given hardware support for atomic instructions, or whether more complex kinds of hardware support are needed for performance. He considers the performance of a number of software spin-waiting algorithms. Arbitration for control of a lock is in many ways similar to arbitration for control of a network connecting a distributed system. He applies several of the static and dynamic arbitration methods originally developed for networks to spin locks. A novel method is proposed for explicitly queueing spinning processors in software by assigning each a unique number when it arrives at the lock. Control of the lock can then be passed to the next processor in line with minimal effect on other processors. >
726 citations
1 Apr 1994
TL;DR: A method to characterize the performance of proposed queue lock algorithms, and applies it to previously published algorithms conclude that the M lock is the best overall queue lock for the class of architectures studied.
Abstract: Large-scale shared-memory multiprocessors typically have long latencies for remote data accesses. A key issue for execution performance of many common applications is the synchronization cost. The communication scalability of synchronization has been improved by the introduction of queue-based spin-locks instead of Test&(Test&Set). For architectures with long access latencies for global data, attention should also be paid to the number of global accesses that are involved in synchronization. We present a method to characterize the performance of proposed queue lock algorithms, and apply it to previously published algorithms. We also present two new queue locks, the LH lock and the M lock. We compare the locks in terms of performance, memory requirements, code size and required hardware support. The LH lock is the simplest of all the locks, yet requires only an atomic swap operation. The M lock is superior in terms of global accesses needed to perform synchronization and still competitive in all other criteria. We conclude that the M lock is the best overall queue lock for the class of architectures studied. >
227 citations
Patent•
2 Jul 1996TL;DR: In this paper, a lock manager decomposes the single spin lock traditionally employed to protect shared, global Lock Manager structures into multiple spin locks, each protecting individual hash buckets or groups of hash buckets which index into particular members of those structures.
Abstract: Database system and methods are described for improving scalability of multi-user database systems by improving management of locks used in the system. The system provides multiple server engines, with each engine having a Parallel Lock Manager. More particularly, the Lock Manager decomposes the single spin lock traditionally employed to protect shared, global Lock Manager structures into multiple spin locks, each protecting individual hash buckets or groups of hash buckets which index into particular members of those structures. In this manner, contention for shared, global Lock Manager data structures is reduced, thereby improving the system's scalability. Further, improved "deadlock" searching methodology is provided. Specifically, the system provides a "deferred" mode of deadlock detection. Here, a task simply goes to sleep on a lock; it does not initiate a deadlock search. At a later point in time, the task is awakened to carry out the deadlock search. Often, however, a task can be awakened with the requested lock being granted. In this manner, the "deferred" mode of deadlock detection allows the system to avoid deadlock detection for locks which are soon granted.
169 citations
Patent•
31 Aug 1995TL;DR: An object lock management system for use in a parallel data processing system where objects are accessible by processing activities on computing nodes within the parallel system is described in this article, where lock information is selectively reported to a global deadlock detector which performs deadlock detection.
Abstract: An object lock management system for use in a parallel data processing system where objects are accessible by processing activities on computing nodes within the parallel system. The system includes local lock control elements, where each of the local lock control element coordinates the locking of a predetermined set of objects. In particular, each local lock control element grants locks or queues lock requests in response to lock requests. Lock information is selectively reported to a global deadlock detector which performs deadlock detection. The global deadlock detector instructs the local lock control elements to release selected locks and queued lock requests upon detecting a deadlock. Lock information is reported to the global deadlock detector periodically and only for queued lock requests that have timed-out, whereby message traffic and processing overhead is reduced in the parallel system.
149 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2017 | 3 |
| 2016 | 3 |
| 2015 | 5 |
| 2014 | 12 |
| 2013 | 6 |
| 2012 | 11 |