Re: [RFC 2/3] mm/vmalloc: add support for __GFP_NOFAIL

[Uladzislau Rezki]

> > > > Is this really required to be part of the initial support?
> > >
> > > No.... I was just thinking out-loud.
> > >
> > alloc_vmap_area() has an retry path, basically if it fails the code
> > will try to "purge"
> > areas and repeat it one more time. So we do not need to purge outside some where
> > else.
>
> I think that Neil was not concerned about the need for purging something
> but rather a waiting event the retry loop could hook into. So that the
> sleep wouldn't have to be a random timeout but something that is
> actually actionable - like somebody freeing an area.
>
I see this point. But sometimes it is not as straightforward as it could be. If
we have lack of vmap space within a specific range, it might be not about
reclaiming(nobody frees to that area and no outstanding areas) thus we
can do nothing.

-- 
Uladzislau Rezki