Re: [PATCH] rfc: threaded epoll_wait thundering herd

[Davide Libenzi]

On Mon, 7 May 2007, Ulrich Drepper wrote:

> On 5/7/07, Davi Arnaut <davi@xxxxxxxxxxxxx> wrote:
> > See Linus's message on this same thread.
> 
> No.  I'm talking about the userlevel side, not kernel side.
> 
> If a thread is canceled *after* it returns from the syscall but before
> it reports the event to the call (i.e., while still in the syscall
> wrapper, thread cancellation rules require a check there) the event is
> lost.

read(2) is a cancellation point too. So if the fine userspace code issues 
a random pthread_cancel() to a thread handling that, data is lost together 
with the session that thread was handling. Hmm, I wonder how the world 
could have functioned so far.
Bottom line is, if you really want to throw random cancels to your worker 
threads, you better wrap them into pthread_cleanup_push(). Because 
otherwise, no matter where your cancel hits, you end up with a broken 
system.



- Davide


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/