otp.git - Mirror of Erlang/OTP repository.

Age	Commit message (Collapse)	Author
2014-12-10	Use the new 64-bit atomic ops API	Rickard Green

2013-06-12	Update copyright years	Björn-Egil Dahlberg

2013-04-03	Be less eager requesting wakeup for cleanup jobs	Rickard Green

2012-12-07	Implement true asynchronous signaling between processes and ports	Rickard Green

2012-12-03	Implement functionality for delaying thread progress from unmanaged threads	Rickard Green

2012-08-02	Use thread progress instead of scheduling misc aux work were possible	Rickard Green
	Functionality for scheduling operations at thread progress later has been introduced. Deallocation of ETS table structures were previously done by scheduling misc aux work. Deallocation of process structures (not released yet) was also implemented this way. Instead of using the misc aux work functionality these implementation now use the newly introduced functionality for scheduling operations at thread progress later. By using this new functionaliy we reduce the amount of memory allocation/deallocation operations needed.
2012-06-18	Fix faulty use of thread progress in handle_aux_work()	Rickard Green
	As an optimization old thread progress data was kept and used in handle_aux_work() in erl_process.c. This could cause memory to be deallocated at a later time than intended, which is quite harmless. This has, however, now been fixed.
2012-03-12	Remove newly introduced excessive barrier in erts_thr_progress_later()	Rickard Green

2012-02-19	Misc memory barrier fixes	Rickard Green
	- Document barrier semantics - Introduce ddrb suffix on atomic ops - Barrier macros for both non-SMP and SMP case - Make the thread progress API a bit more intuitive
2011-11-13	Replace system block with thread progress block	Rickard Green
	The ERTS internal system block functionality has been replaced by new functionality for blocking the system. The old system block functionality had contention issues and complexity issues. The new functionality piggy-backs on thread progress tracking functionality needed by newly introduced lock-free synchronization in the runtime system. When the functionality for blocking the system isn't used there is more or less no overhead at all. This since the functionality for tracking thread progress is there and needed anyway.
2011-11-13	Optimize memory allocation	Rickard Green
	A number of memory allocation optimizations have been implemented. Most optimizations reduce contention caused by synchronization between threads during allocation and deallocation of memory. Most notably: * Synchronization of memory management in scheduler specific allocator instances has been rewritten to use lock-free synchronization. * Synchronization of memory management in scheduler specific pre-allocators has been rewritten to use lock-free synchronization. * The 'mseg_alloc' memory segment allocator now use scheduler specific instances instead of one instance. Apart from reducing contention this also ensures that memory allocators always create memory segments on the local NUMA node on a NUMA system.