[Cluster-devel] [Upstream patch] DLM: Convert rsb data from linked list to rb_tree

[David Teigland <teigland@redhat.com>]

On Mon, Oct 10, 2011 at 08:00:07PM +0100, Steven Whitehouse wrote:
> > The fact remains that caching "as much as possible" tends to be harmful,
> > and some careful limiting would be a good investment.
> > 
> There is a limit. The point is that the limit is dynamic and depends on
> memory pressure. 

the "as possible" part of "as much as possible".

> The VM requests a reduction in the number of cached
> objects when it wants to reduce the size of what we have cached. So the
> larger the amount of RAM, the more inodes may be potentially cached.
> 
> I don't agree that caching as much as possible (given the constraints
> just mentioned) is bad. 

the "tends to" part meant that it can be good or bad, depending.

> The more we cache, the more disk I/O is avoided so the better the
> performance will be.

You don't need to argue that more caching can be good.  My point is it's
not universally true in practice, as Bob's tests show.