Re: [PATCH v3] ummunotify: Userspace support for MMU notifications

[Brice Goglin]

Roland Dreier wrote:
> I suspect that MPI workloads will hit the overflow case in practice,
> since they probably want to run as close to out-of-memory as possible,
> and the application may not enter the MPI library often enough to keep
> the queue of ummunotify events short -- I can imagine some codes that do
> a lot of memory management, enter MPI infrequently, and end up
> overflowing the queue and flushing all registrations over and over.
> Having userspace register ranges means I can preallocate a landing area
> for each event and make the MMU notifier hook pretty simple.
>   

Thanks, I see.

> Second, it turns out that having the filter does cut down quite a bit on
> the events.  From running some Open MPI tests that Jeff provided, I saw
> that there were often several times as many MMU notifier events
> delivered in the kernel than ended up being reported to userspace.
>   

So maybe multiple invalidate_page are gathered into the same range
event? If so, maybe it'd make sense to cache the last used rb_node in
ummunotify_handle_notify()? (and if multiple ranges were invalidated at
once, just don't cache anything, it shouldn't happen often anyway)

>  > 2) What happens in case of fork? If father+child keep reading from the
>  > previously-open /dev/ummunotify, each event will be delivered only to
>  > the first reader, right? Fork is always a mess in HPC, but maybe there's
>  > something to do here.
>
> It works just like any other file where fork results in two file
> descriptors in two processes... as you point out the two processes can
> step on each other.  (And in the ummunotify case the file remains
> associated with the original mm)  However this is the case for simpler
> stuff like sockets etc too, and I think uniformity of interface and
> least surprise say that ummunotify should follow the same model.
>   

I was wondering if adding a special event such as "COWED" could help
user-space. But maybe fork already invalidates all COW'ed ranges in
copy_page_range() anyway?

Brice

--
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/