Re: [PATCH 3/3] memcg: simplify mem_cgroup_reclaim_iter

[Tejun Heo <tj@kernel.org>]

Yo,

On Wed, Jun 05, 2013 at 05:17:04PM -0400, Johannes Weiner wrote:
> That could be an advantage, yes.  But keep in mind that every
> destruction has to perform this invalidation operation against the
> global root_mem_cgroup's nr_node * nr_zone * nr_priority_levels
> iterators, so you can't muck around forever, while possibly holding a
> lock at this level.  It's not a hot path, but you don't want to turn
> it into one, either.

nr_node tends to be pretty low in most cases, so it shouldn't be a
problem there but yeah with high enough nodes and high enough rate of
cgroup destruction, I guess it could be an issue in extreme cases.

> The upshot for me is this: whether you do long-term pinning or greedy
> iterator invalidation, the cost of cgroup destruction increases.
> Either in terms of memory usage or in terms of compute time.  I would
> have loved to see something as simple as the long-term pinning work
> out in practice, because it truly would have been simpler.  But at
> this point, I don't really care much because the projected margins of
> reduction in complexity and increase of cost from your proposal are
> too small for me to feel strongly about one solution or the other, or
> go ahead and write the code.  I'll look at your patches, though ;-)

I don't know.  I've developed this deep-seated distrust of any code
which makes creative use of barriers and object lifetimes.  We get
them wrong too often, it makes other devs a lot more reluctant to
review and dive into the code, and it's hellish to track down when
something actually goes wrong.  I'd happily pay a bit of computation
or memory overhead for more conventional construct.  In extremely hot
paths, sure, we just bite and do it but I don't think this reaches
that level.

> Either way, I'll prepare the patch set that includes the barrier fix
> and a small cleanup to make the weak pointer management more
> palatable.  I'm still open to code proposals, so don't let it distract
> you, but we might as well make it a bit more readable in the meantime.

Sure thing.  We need to get it fixed for -stable anyway.

Thanks.

-- 
tejun

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>