Re: [PATCH RFC] sched: introduce add_wait_queue_exclusive_head

["Dilger, Andreas" <andreas.dilger@intel.com>]

On 2014/03/19, 11:33 AM, "Oleg Nesterov" <oleg@redhat.com> wrote:
>On 03/19, Peng Tao wrote:
>>
>> On Wed, Mar 19, 2014 at 12:23 AM, Oleg Nesterov <oleg@redhat.com> wrote:
>> >
>> > Firtsly, cfs_block_sigs/cfs_block_sigsinv/etc are not exactly right,
>> > they need set_current_blocked(). And you can read "old" lockless.
>> >
>> It seems that set_current_blocked() is not exported. Can we ask to
>>export it?
>
>Why not. If you are going to change this code to use
>set_current_blocked(), I'd suggest you to send the "export
>set_current_blocked" patch in series. Otherwise, if it is sent
> separately, your change will depend on another tree.
>
>Or you can use sigprocmask(). Actually it should die, but this won't
>happen soon and it is already exported.
>
>> And looking at other similar places like coda_block_signals(),
>
>Yes, it can have much more users.
>
>But note that set_current_blocked() can't help you to really block
>SIGKILL anyway.
>
>Could you explain why __l_wait_event() can't use TASK_UNINTERRUPTIBLE
>instead of cfs_block_sigsinv(0) ?

The original reason for l_wait_event() not using TASK_UNINTERRUPTIBLE
is to avoid the load on the server continually being "num_service_threads"
regardless of whether they are actually doing something or not.  We
added various cases for periodic wakeups and such afterward.

l_wait_event() was originally developed for 2.4 kernels, so there may
well be better primitives to use today.

I'd be happy to move toward replacing l_wait_event() with kernel
primitives if possible, but we need to ensure that this is tested
sufficiently since it can otherwise be a source of hard-to-find bugs.

Cheers, Andreas
-- 
Andreas Dilger

Lustre Software Architect
Intel High Performance Data Division