Messages in this thread | | | Date | Wed, 06 Aug 2008 07:30:13 +0200 | From | Manfred Spraul <> | Subject | Re: [PATCH tip/core/rcu] classic RCU locking and memory-barrier cleanups |
| |
Hi Paul,
Paul E. McKenney wrote: > This patch is in preparation for moving to a hierarchical > algorithm to allow the very large SMP machines -- requested by some > people at OLS, and there seem to have been a few recent patches in the > 4096-CPU direction as well.
I thought about hierarchical RCU, but I never found the time to implement it. Do you have a concept in mind?
Right now, I try to understand the current code first - and some of it doesn't make much sense.
There are three per-cpu lists: ->nxt ->cur ->done.
Obviously, there must be a quiescent state between cur and done. But why does the code require a quiescent state between nxt and cur? I think that's superflous. The only thing that is required is that all cpus have moved their callbacks from nxt to cur. That doesn't need a quiescent state, this operation could be done in hard interrupt as well.
Thus I think this should work:
1) A callback is inserted into ->nxt. 2) As soon as too many objects are sitting in the ->nxt lists, a new rcu cycle is started. 3) As soon as a cpu sees that a new rcu cycle is started, it moves it's callbacks from ->nxt to ->cur. No checks for hard_irq_count & friends necessary. Especially: same rule for _bh and normal. 4) As soon as all cpus have moved their lists from ->nxt to ->cur, the real grace period is started. 5) As soon as all cpus passed a quiescent state (i.e.: now with tests for hard_irq_count, different rules for _bh and normal), the list is moved from ->cur to ->completed. Once in completed, they can be destroyed by performing the callbacks.
What do you think? would that work? It doesn't make much sense that step 3) tests for a quiescent state.
Step 2) could depend memory pressure. Step 3) and 4) could be accelerated by force_quiescent_state(), if the memory pressure is too high.
-- Manfred -> nxt
| |