Messages in this thread | | | Date | Fri, 20 Jun 2014 14:24:23 -0700 | From | josh@joshtrip ... | Subject | Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression |
| |
On Fri, Jun 20, 2014 at 12:12:36PM -0700, Paul E. McKenney wrote: > o Make cond_resched() a no-op for PREEMPT=y. This might well turn > out to be a good thing, but it doesn't help give RCU the quiescent > states that it needs.
What about doing this, together with letting the fqs logic poke un-quiesced kernel code as needed? That way, rather than having cond_resched do any work, you have the fqs logic recognize that a particular CPU has gone too long without quiescing, without disturbing that CPU at all if it hasn't gone too long.
- Josh Triplett
| |