[ltt-dev] [rp] [PATCH userspace-rcu 1/4] Provide pthread_atfork-friendly interfaces

[Mathieu Desnoyers]

* Paul E. McKenney (paulmck at linux.vnet.ibm.com) wrote:
> Provides call_rcu_before_fork() and call_rcu_after_fork_parent() to
> go with the existing call_rcu_after_fork_child().
> 
> Signed-off-by: Paul E. McKenney <paulmck at linux.vnet.ibm.com>
> ---
>  README          |    4 ++++
>  urcu-call-rcu.c |   29 ++++++++++++++++++++++++++++-
>  2 files changed, 32 insertions(+), 1 deletions(-)
> 
> diff --git a/README b/README
> index f7f0dec..56e98d7 100644
> --- a/README
> +++ b/README
> @@ -204,3 +204,7 @@ Interaction with fork()
>  	liburcu-bp, which is designed to handle fork() by calling
>  	rcu_bp_before_fork, rcu_bp_after_fork_parent and
>  	rcu_bp_after_fork_child.
> +
> +	Applications that use call_rcu() are required to invoke
> +	call_rcu_after_fork_child() from the child process after a
> +	successful fork() system call that is not followed by exec().
> diff --git a/urcu-call-rcu.c b/urcu-call-rcu.c
> index bb56dbb..665f20c 100644
> --- a/urcu-call-rcu.c
> +++ b/urcu-call-rcu.c
> @@ -566,13 +566,40 @@ void free_all_cpu_call_rcu_data(void)
>  }
>  
>  /*
> + * Acquire the call_rcu_mutex in order to ensure that the child sees
> + * all of the call_rcu() data structures in a consistent state.
> + * Suitable for pthread_atfork() and friends.
> + */
> +void call_rcu_before_fork(void)
> +{
> +	call_rcu_lock(&call_rcu_mutex);
> +}
> +
> +/*
> + * Clean up call_rcu data structures in the parent of a successful fork()
> + * that is not followed by exec() in the child.  Suitable for
> + * pthread_atfork() and friends.
> + */
> +void call_rcu_after_fork_parent(void)
> +{
> +	call_rcu_unlock(&call_rcu_mutex);
> +}
> +
> +/*
>   * Clean up call_rcu data structures in the child of a successful fork()
> - * that is not followed by exec().
> + * that is not followed by exec().  Suitable for pthread_atfork() and
> + * friends.
>   */
>  void call_rcu_after_fork_child(void)
>  {
>  	struct call_rcu_data *crdp;
>  
> +	/* Re-initialize the mutex. */
> +	if (pthread_mutex_init(&call_rcu_mutex, NULL) != 0) {
> +		perror("pthread_mutex_init");
> +		exit(-1);

Hi Paul,

I tried to turn UST from a scheme where "unlock" is executed in both the
parent and child processes (which works fine) to a scheme where we use
"pthread_mutex_init" in the child as you do here. For some reason, the
fork stress-test seems to hang when I do that. So I would be tempted to
turn all the "pthread_mutex_init" we do after fork in children processes
into a mutex. I'd like to understand better what is causing this trouble
though, but until then I would be tempted to turn these "re-init" into
"unlock".

Thoughts ?

Mathieu

> +	}
> +
>  	/*
>  	 * Allocate a new default call_rcu_data structure in order
>  	 * to get a working call_rcu thread to go with it.
> -- 
> 1.7.3.2
> 
> 
> _______________________________________________
> rp mailing list
> rp at svcs.cs.pdx.edu
> http://svcs.cs.pdx.edu/mailman/listinfo/rp

-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com