Re: [Boost-bugs] [Boost C++ Libraries] #11798: Implementation of boost::shared_mutex on POSIX is suboptimal

Subject: Re: [Boost-bugs] [Boost C++ Libraries] #11798: Implementation of boost::shared_mutex on POSIX is suboptimal
From: Boost C++ Libraries (noreply_at_[hidden])
Date: 2016-05-18 17:16:17

#11798: Implementation of boost::shared_mutex on POSIX is suboptimal
-------------------------+-------------------------------------------------
  Reporter:  alex@…      |      Owner:  viboes
      Type:  Tasks       |     Status:  assigned
 Milestone:  To Be       |  Component:  thread
  Determined             |   Severity:  Optimization
   Version:  Boost       |   Keywords:  pthread shared_mutex performance
  1.59.0                 |  concurrency spinlock
Resolution:              |
-------------------------+-------------------------------------------------

Comment (by Max <silverhammermba@…>):

 I think I just ran into this bug with this repo:
 https://github.com/silverhammermba/sanity


 Basically I'm timing how long it takes a bunch of threads to do concurrent
 reads on a std::unordered_map. In one case the reads are protected by
 std::lock_guard<std::mutex>, so each thread has to wait its turn. In the
 other case, the reads are protected by
 boost::shared_lock<boost::shared_mutex>, so other than checking in with
 the shared_mutex the reads should be concurrent.

 One would think this is the ideal use-case for a shared lock: lots of
 reads, no writes. But on my Arch Linux box the shared_lock version is
 '''almost twice as slow''' as a naive mutex. My friend compiled the same
 code on Windows and saw the exact opposite, with shared_lock being almost
 twice as fast (as we would hope).

 This is not just a matter of optimization, '''this makes
 boost::shared_mutex completely useless on Linux'''. Please upgrade the
 severity of this report.

-- 
Ticket URL: <https://svn.boost.org/trac/boost/ticket/11798#comment:8>
Boost C++ Libraries <http://www.boost.org/>
Boost provides free peer-reviewed portable C++ source libraries.