summaryrefslogtreecommitdiff
path: root/lib/libthr/thread/thr_init.c
Commit message (Expand)AuthorAgeFilesLines
* - Reduce function call overhead for uncontended case.David Xu2008-05-291-2/+1
* _vfork is not in libthr, remove the reference.David Xu2008-04-161-1/+0
* Use cpuset defined in pthread_attr for newly created thread, for now,David Xu2008-03-051-1/+1
* implement pthread_attr_getaffinity_np and pthread_attr_setaffinity_np.David Xu2008-03-041-1/+3
* Add my recent work of adaptive spin mutex code. Use two environments variableDavid Xu2007-10-301-1/+9
* backout experimental adaptive spinning mutex for product use.David Xu2007-05-091-7/+0
* get LIBPTHREAD_ADAPTIVE_SPIN early, so it can be used for some globalDavid Xu2006-12-201-2/+5
* Check environment variable PTHREAD_ADAPTIVE_SPIN, if it is set, useDavid Xu2006-12-201-0/+4
* - Remove variable _thr_scope_system, all threads are system scope.David Xu2006-12-151-12/+4
* Eliminate atomic operations in thread cancellation functions, it shouldDavid Xu2006-11-241-1/+2
* use rtprio_thread system call to get or set thread priority.David Xu2006-09-211-2/+2
* Replace internal usage of struct umtx with umutex which can supportsDavid Xu2006-09-061-13/+13
* Use umutex APIs to implement pthread_mutex, member pp_mutexq is addedDavid Xu2006-08-281-0/+1
* Get number of CPUs and ignore spin count on single processor machine.David Xu2006-08-081-0/+3
* 1. Don't override underscore version of aio_suspend(), system(),David Xu2006-07-251-17/+17
* Caching scheduling policy and priority in userland, a critical but baddlyDavid Xu2006-07-131-0/+6
* Use kernel facilities to support real-time scheduling.David Xu2006-07-121-14/+4
* - Use same priority range returned by kernel's sched_get_priority_min()David Xu2006-04-271-5/+13
* WARNS level 4 cleanup.David Xu2006-04-041-25/+7
* Remove priority mutex code because it does not work correctly,David Xu2006-03-271-2/+1
* Set default contention scope to system.David Xu2006-03-201-1/+1
* Add some more pthread stubs so that librt can use them.Daniel Eischen2006-03-051-4/+35
* Rework last change of pthread_once, create a function _thr_once_init toDavid Xu2006-02-151-2/+1
* After fork(), reinitialize internal locks for pthread_once().David Xu2006-02-151-0/+2
* Now, thread name is stored in kernel, userland no longer has to keep it.David Xu2006-02-051-2/+1
* Use macro STATIC_LIB_REQUIRE to declare a symbol should be linked intoDavid Xu2006-01-101-95/+68
* 1. Retire macro SCLASS, instead simply use language keyword andDavid Xu2005-12-211-0/+52
* Add code to handle timer_delete(). The timer wrapper code is completelyDavid Xu2005-11-011-0/+1
* Conditionally report initial thread event.David Xu2005-04-121-1/+2
* Add debugger event reporting support, current only TD_CREATE and TD_DEATHDavid Xu2005-04-121-0/+2
* Remove unique id field which is no longer used by debugger.David Xu2005-04-061-1/+0
* Import my recent 1:1 threading working. some features improved includes:David Xu2005-04-021-161/+214
* Increase the default stacksizes:Joe Marcus Clarke2005-03-061-6/+16
* Don't include sys/user.h merely for its side-effect of recursivelyDavid Schultz2004-11-271-1/+0
* Implement pthread_atfork in libthr. This is mostly from deichen'sMike Makonnen2004-06-271-0/+4
* In the case that the global thread list is being re-initialized afterMike Makonnen2004-06-271-4/+4
* Make libthr async-signal-safe without costly signal masking. The guidlines IMike Makonnen2004-05-201-18/+3
* o Remove more references to SIGTHRMike Makonnen2004-03-291-51/+0
* Remove the garbage collector thread. All resources are freedMike Makonnen2004-03-281-4/+2
* Move the initialization of thread priority to a common function.Mike Makonnen2004-02-181-5/+3
* Preparations to make libthr work in multi-threaded fork()ing applications.Mike Makonnen2003-12-261-39/+78
* When _PTHREADSINVARIANTS is defined SIGABRT is not includedMike Makonnen2003-07-081-0/+3
* Make _thread_suspend work with both the old broken sigtimedwaitJohn Polstra2003-06-291-0/+26
* Make C applications statically compiled with libthr work. Previously,Mike Makonnen2003-06-041-0/+6
* Return gracefully, rather than aborting, when the maximum concurrentMike Makonnen2003-05-251-1/+2
* Start locking up the active and dead threads lists. The active threadsMike Makonnen2003-05-251-1/+1
* Make WARNS2 clean. The fixes mostly included:Mike Makonnen2003-05-231-2/+1
* The thread id was being set *before* zeroing out the thread. ReverseMike Makonnen2003-05-211-2/+3
* - Pass a ucontext_t to _set_curthread. If non-NULL the new thread is setJake Burkholder2003-04-031-1/+1
* - Define curthread as _get_curthread() and remove all direct calls toJeff Roberson2003-04-021-16/+0