Messages in this thread | | | Date | Tue, 31 Jan 2012 15:47:18 +0200 | From | Avi Kivity <> | Subject | Re: [RFC][PATCH] srcu: Implement call_srcu() |
| |
On 01/31/2012 03:32 PM, Peter Zijlstra wrote: > Subject: srcu: Implement call_srcu() > From: Peter Zijlstra <a.p.zijlstra@chello.nl> > Date: Mon Jan 30 23:20:49 CET 2012 > > Implement call_srcu() by using a state machine driven by > call_rcu_sched() and timer callbacks. > > The state machine is a direct derivation of the existing > synchronize_srcu() code and replaces synchronize_sched() calls with a > call_rcu_sched() callback and the schedule_timeout() calls with simple > timer callbacks. > > It then re-implements synchronize_srcu() using a completion where we > send the complete through call_srcu(). > > It completely wrecks synchronize_srcu_expedited() which is only used > by KVM. 3 of the 5
2 of the 5
> use cases look like they really want to use > call_srcu() instead, the remaining 2 I don't know but hope they can, > which would let us remove it.
They really need to return quickly to userspace, and they really need to perform some operation between rcu_assign_pointer() and returning, so no.
> > Compile tested only!! :-) >
How much did synchronize_srcu_expedited() regress? Presumably your compiler didn't tell you that.
Can we get it back to speed by scheduling a work function on all cpus? wouldn't that force a quiescent state and allow call_srcu() to fire?
In kvm's use case synchronize_srcu_expedited() is usually called when no thread is in a critical section, so we don't have to wait for anything except the srcu machinery.
-- error compiling committee.c: too many arguments to function
| |