Re: Two other ways to do latched seqcounts

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Apr 13, 2015 at 05:26:05AM -0400, George Spelvin wrote:
> > I'm assuming you're writing to me because of the latched rb-tree;
> > because that's the most recent related thing I posted ;-)
> 
> Basically yes, although it was the documentation you added to the
> latched seqlock code in particular.
> 
> I haven't checked the users of your rb-tree code to see how large and
> frequently read the trees are, but if a read is expensive, then avoiding
> retries by incrementing the seqlock twice per update starts to become
> interesting.

Right, so I use it for modules, and updates are near non existent
under normal usage.