glibc/nptl/TODO

32 lines
1007 B
Plaintext

- we should probably extend pthread_mutexattr_t with a field to create a
single linked list of all instances. This requires changing the
pthread_mutexattr_* functions.
- a new attribute for mutexes: number of times we spin before calling
sys_futex
- for adaptive mutexes: when releasing, determine whether somebody spins.
If yes, for a short time release lock. If someone else locks no wakeup
syscall needed.
- test with threaded process terminating and semadj (?) being applied
only after all threads are gone
- semaphore changes:
- sem_post should only wake one thread and only when the state of
the semaphore changed from 0 to 1
this also requires that sem_wait and sem_timedwait don't drop the
post if they get canceled.
- possibly add counter field. This requires reviving the
differences between old and new semaphose funtions. The old ones
stay as they are now. The new once can use an additional field
wich is the counter for the number of waiters