urcu rfc: privatize urcu/futex.h
A message that is not in the archive (sent off-list or not yet received): [email protected]
Hi Lai,
Quoted 8 lines · * Lai Jiangshan ([email protected]) wrote:
futex.his in urcu/, it means it can be used by users out of the library.But
If the user's system has futex, he should use #include <
linux/futex.h>. If the user's system don't have futex, it is not good that if the user use thiscompat_futex.
Quoted 5 lines
Because the compat_futex_async()'s behavior is different from the futex in linux. If the caller don't change the value of @uaddr, the
futex(FUTEX_WAKE)in linux can also wake a thread, butcompat_futex_async()don't. (I guess no one use this behavior, but if there are someone, we give them a wrong thing)
Hrm, passing a NULL uaddr parameter is really not the targeted use-case. We could probably just document that uaddr should not be NULL when using compat_futex ?
Quoted 1 line
So I suggest
urcu/futex.hbecomes a private thing for urcu.
Well, if possible, I'd like to keep it public, since it allows us to do wait/wakeup schemes across many OSes.
Do you have a use-case where you want to wake up all threads, even those which are not waiting on a specific uaddr ?
Quoted 7 lines
Alternative
implements(only describe the alternative FUTEX_WAIT):
1) Likecompat_futex_noasync(), but usemutex_lock_signal_save()+pthread_cond_wait().
Problem: the thread can't handle the signal when waiting onpthread_cond_wait(). (*mutex_lock_signal_save()is implemented incompat_arch_x86.c)
The culprit of the problem here is not really on the "wait" side, but rather on the "wake" side. The wakeup, in urcu, is issued by rcu_read_unlock() to wake up synchronize_rcu() (if there is one waiting).
However, we don't want to disable signals and take a mutex each time we do a rcu_read_unlock, because it would tremendously impact performance. AFAIK, pthread_cond_signal() is not signal-safe, so it could not be used without lock+signal save.
Another site where the wait/wakeup is used: in call_rcu, waking up the worker threads. We also don't want to take a mutex there, to ensure that call_rcu is wait-free as far as userspace code is concerned.
Quoted 4 lines
2) Like the linux kernel, use use
mutex_lock_signal_save()+ hash table
+ sleeping (usepoll()+ restore signal mask)
Problem: very complex
Would this solution require a lock+signal save on the wake up site too ?
Quoted 7 lines
Thanks,
Lai.(today I found a old patchset in my private tree, tried to rebase it and suddenly notice this
urcu/futex.hbut the patchset has nothing related withurcu/futex.h).
I look forward to see that work!
Thanks!
Mathieu
Signature · 4 lines
Mathieu Desnoyers Operating System Efficiency R&D Consultant EfficiOS Inc. http://www.efficios.com
A message that is not in the archive (sent off-list or not yet received): 20120807140616.GA29280@Krystal
Quoted 17 lines · Mathieu Desnoyers
Hi Lai,
Quoted 8 lines · * Lai Jiangshan ([email protected]) wrote:
futex.his in urcu/, it means it can be used by users out of the library.But
If the user's system has futex, he should use #include <
linux/futex.h>. If the user's system don't have futex, it is not good that if the user use thiscompat_futex.Quoted 5 lines
Because the compat_futex_async()'s behavior is different from the futex in linux. If the caller don't change the value of @uaddr, the
futex(FUTEX_WAKE)in linux can also wake a thread, butcompat_futex_async()don't. (I guess no one use this behavior, but if there are someone, we give them a wrong thing)
Quoted 3 lines
Hrm, passing a NULL uaddr parameter is really not the targeted use-case. We could probably just document that uaddr should not be NULL when using
compat_futex?
Sorry, I wanted to show you such un-normal behavior:
/* keep the value of *uaddr unchanged, wake up a thread to do something */ futex(FUTEX_WAKE, uaddr, ...).
This can't not wake up any thread for current compat_futex_async() implement. But the sys_futex() can.
A message that is not in the archive (sent off-list or not yet received): [email protected]
(Added a CC email address)
Quoted 22 lines · Lai Jiangshan
Quoted 17 lines · Mathieu Desnoyers
Hi Lai,
Quoted 8 lines · * Lai Jiangshan ([email protected]) wrote:
futex.his in urcu/, it means it can be used by users out of the library.But
If the user's system has futex, he should use #include <
linux/futex.h>. If the user's system don't have futex, it is not good that if the user use thiscompat_futex.Quoted 5 lines
Because the compat_futex_async()'s behavior is different from the futex in linux. If the caller don't change the value of @uaddr, the
futex(FUTEX_WAKE)in linux can also wake a thread, butcompat_futex_async()don't. (I guess no one use this behavior, but if there are someone, we give them a wrong thing)Quoted 3 lines
Hrm, passing a NULL uaddr parameter is really not the targeted use-case. We could probably just document that uaddr should not be NULL when using
compat_futex?
Quoted 9 lines
Sorry, I wanted to show you such un-normal behavior:
/* keep the value of *uaddr unchanged, wake up a thread to do something */
futex(FUTEX_WAKE, uaddr, ...).This can't not wake up any thread for current
compat_futex_async()implement. But thesys_futex()can.
It is hard to implement compat_futex_async() to make its behavior compatible with sys_futex().(I don't like the two alternatives too, I just wrote what I have thought) so I sent rfc email to suggest to privatize urcu/futex.h.
Thanks,
Lai
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 35 lines · * Lai Jiangshan ([email protected]) wrote:
(Added a CC email address)
Quoted 22 lines · Lai Jiangshan
Quoted 17 lines · Mathieu Desnoyers
Hi Lai,
Quoted 8 lines · * Lai Jiangshan ([email protected]) wrote:
futex.his in urcu/, it means it can be used by users out of the library.But
If the user's system has futex, he should use #include <
linux/futex.h>. If the user's system don't have futex, it is not good that if the user use thiscompat_futex.Quoted 5 lines
Because the compat_futex_async()'s behavior is different from the futex in linux. If the caller don't change the value of @uaddr, the
futex(FUTEX_WAKE)in linux can also wake a thread, butcompat_futex_async()don't. (I guess no one use this behavior, but if there are someone, we give them a wrong thing)Quoted 3 lines
Hrm, passing a NULL uaddr parameter is really not the targeted use-case. We could probably just document that uaddr should not be NULL when using
compat_futex?Quoted 9 lines
Sorry, I wanted to show you such un-normal behavior:
/* keep the value of *uaddr unchanged, wake up a thread to do something */
futex(FUTEX_WAKE, uaddr, ...).This can't not wake up any thread for current
compat_futex_async()implement. But thesys_futex()can.
Quoted 4 lines
It is hard to implement
compat_futex_async()to make its behavior compatible with sys_futex().(I don't like the two alternatives too, I just wrote what I have thought) so I sent rfc email to suggest to privatizeurcu/futex.h.
I don't think this issue has been taken care of, am I correct ?
Thanks,
Mathieu
Signature · 3 lines
Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com