On Wed, May 28, 2014 at 03:28:59PM +0000, Dave Goodell (dgoodell) wrote:
> On May 13, 2014, at 4:01 PM, Nathan Hjelm <hjelmn_at_[hidden]> wrote:
> > While tracking down memory leaks in components I ran into an interesting
> > issue. osc/rdma uses an opal_free_list_t (not an ompi_free_list_t) for
> > buffer fragments. The fragment class allocates a buffer as part in the
> > constructor and frees the buffer in the destructor. The problem is that
> > the item constructor is called but the destructor is never called.
> > I looked into the issue and I see what is happening. When growing the free
> > list we call the constructor for each item we allocate (see
> > opal_free_list.c:113) but the free list destructor does not invoke the
> > destructor. This is different from ompi_free_list_t which does invoke
> > the destructor on each constructed item.
> > The question is. Is this difference intentional? It seems a little odd
> > that the free list does not call the item destructor given that it
> > calls the constructor. If this is intentional is there a reason for this
> > behavior? If not I plan on "fixing" the opal_free_list_t destructor to
> > call the item destructor.
> The difference is not intentional, AFAIK. I fixed the "ompi_" version back in r29096 (https://svn.open-mpi.org/trac/ompi/changeset/29096), August 2013. I was probably unaware of the "opal_" version at the time, hence the lack of a corresponding fix.
Excellent. That was the answer I was looking for. We already made the
equivalent fix and it has been applied to 1.8.2.
- application/pgp-signature attachment: stored