On Wed, Jul 13, 2016 at 10:57:12PM +0200, Peter Zijlstra wrote: > On Wed, Jul 13, 2016 at 01:52:11PM -0700, Paul E. McKenney wrote: > > Not a particularly real-time-friendly fix, but certainly a good check > > on our various assumptions. > > Not only RT, but also HPC and all the other RDMA userspace polling > freaks ;-)
If Tejun's lglock-like approach doesn't pan out, then it would quite
easy to make a boot parameter that selected expedited vs. non-expedited
behavior.
Thanx, Paul
