[dm-devel] [PATCH] DM-CRYPT: Scale to multiple CPUs
Mikulas Patocka
mpatocka at redhat.com
Tue Jun 1 02:39:37 UTC 2010
> > >> 2) Per volume threads and mempools were added to solve low memory
> > >> problems (exhausted mempools), isn't now possible deadlock here again?
> > >
> > > Increasing the number of parallel submitters does not increase deadlocks
> > > with mempool as long as they don't nest. They would just
> > > block each other, but eventually make progress as one finishes.
> >
> > I mean if they nest of course, sorry for confusion.
>
> No change to that, it's the same as it always worked.
>
> Anyways, Right now you would need to nest more than 16 times I think
> to exhaust the mempool (or 8, but the pages are less critical I think)
>
> For me that seems like a "don't do that if hurts" situation.
If the mempools are per-instance (they are), it can nest any number of
times, because each nested instance will get new mempools. It is not a
problem.
Mikulas
More information about the dm-devel
mailing list