Skip to Main content Skip to Navigation
Reports

Efficient locking for multicore architectures

Jean-Pierre Lozi 1, 2 Gaël Thomas 2, 1, 3 Julia L. Lawall 2, 1 Gilles Muller 2, 1, 3 
Abstract : The scalability of multithreaded applications on current multicore systems is hampered by the performance of critical sections, due in particular to the costs of access contention and cache misses. In this paper, we propose a new locking technique, Remote Core Locking (RCL) that aims to improve the performance of critical sections in legacy applications on multicore architectures. The idea of RCL is to replace lock acquisitions by optimized remote procedure calls to a dedicated server core. RCL limits the performance collapse observed with regular locks when many threads try to acquire a lock concurrently and removes the need to transfer lock-protected shared data to the core acquiring the lock: such data can typically remain in the server core's cache. Our microbenchmark shows that under high contention, RCL is always more efficient than the other state-of-the-art lock mechanisms, and a preliminary macrobenchmark evaluation shows performance gains on SPLASH-2 benchmarks (speedup up to 4.85) and on the Web cacheapplication memcached (speedup up to 2.62).
Document type :
Reports
Complete list of metadata

Cited literature [2 references]  Display  Hide  Download

https://hal.inria.fr/hal-00641252
Contributor : Gilles Muller Connect in order to contact the contributor
Submitted on : Tuesday, November 15, 2011 - 11:32:43 AM
Last modification on : Friday, January 21, 2022 - 3:22:03 AM
Long-term archiving on: : Friday, November 16, 2012 - 10:55:09 AM

File

rr7779.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00641252, version 1

Citation

Jean-Pierre Lozi, Gaël Thomas, Julia L. Lawall, Gilles Muller. Efficient locking for multicore architectures. [Research Report] RR-7779, INRIA. 2011, pp.30. ⟨hal-00641252⟩

Share

Metrics

Record views

258

Files downloads

290