Searched hist:"3 dfe682f55250bfe5309902ec217fea71b50c7bb" (Results 1 – 3 of 3) sorted by relevance
| /haiku/headers/posix/ |
| H A D | semaphore.h | 3dfe682f55250bfe5309902ec217fea71b50c7bb Thu May 08 01:39:49 UTC 2008 Ingo Weinhold <ingo_weinhold@gmx.de> * Added some padding to the sem_t structure.
* Changed the semantics of unnamed semaphores. Before parent and child
of a fork() would always share an earlier created semaphore. Now we do
that only, if the "shared" parameter of sem_init() was true. That's
still not quite the behavior Linux and Solaris have, but should be
perfectly fine with how reasonable code would use the API.
* There's a global table for shared unnamed semaphores now. ATM a
semaphore is leaked when no one explicitly destroys it (just as with
named sems).
* Enforce per-team and global semaphore number limits.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25362 a95241bf-73f2-0310-859d-f6bbb57e9c96
|
| /haiku/src/system/kernel/posix/ |
| H A D | realtime_sem.cpp | 3dfe682f55250bfe5309902ec217fea71b50c7bb Thu May 08 01:39:49 UTC 2008 Ingo Weinhold <ingo_weinhold@gmx.de> * Added some padding to the sem_t structure.
* Changed the semantics of unnamed semaphores. Before parent and child
of a fork() would always share an earlier created semaphore. Now we do
that only, if the "shared" parameter of sem_init() was true. That's
still not quite the behavior Linux and Solaris have, but should be
perfectly fine with how reasonable code would use the API.
* There's a global table for shared unnamed semaphores now. ATM a
semaphore is leaked when no one explicitly destroys it (just as with
named sems).
* Enforce per-team and global semaphore number limits.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25362 a95241bf-73f2-0310-859d-f6bbb57e9c96
|
| /haiku/src/system/libroot/posix/ |
| H A D | semaphore.cpp | 3dfe682f55250bfe5309902ec217fea71b50c7bb Thu May 08 01:39:49 UTC 2008 Ingo Weinhold <ingo_weinhold@gmx.de> * Added some padding to the sem_t structure.
* Changed the semantics of unnamed semaphores. Before parent and child
of a fork() would always share an earlier created semaphore. Now we do
that only, if the "shared" parameter of sem_init() was true. That's
still not quite the behavior Linux and Solaris have, but should be
perfectly fine with how reasonable code would use the API.
* There's a global table for shared unnamed semaphores now. ATM a
semaphore is leaked when no one explicitly destroys it (just as with
named sems).
* Enforce per-team and global semaphore number limits.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25362 a95241bf-73f2-0310-859d-f6bbb57e9c96
|