On Mon, Mar 10, 2014 at 11:52:48PM -0700, Andy Zhou wrote:
> Thanks for the reference. It provides the relevant background, especially
> on memory_order_consume.
>
> BTW, the example has an unfamiliar syntax, p -< next (Its usage looks
> like p -> next) Is this something new?
I think that's ju
Thanks for the reference. It provides the relevant background, especially
on memory_order_consume.
BTW, the example has an unfamiliar syntax, p -< next (Its usage looks
like p -> next) Is this something new?
Looking forward to the revision. Your implementation is much smaller than
the kernel R
On Wed, Mar 05, 2014 at 11:12:58PM -0800, Ben Pfaff wrote:
> RCU allows multiple threads to read objects in parallel without any
> performance penalty. The following commit will introduce the first use.
>
> Signed-off-by: Ben Pfaff
Hey, I just found out that memory_order_consume is designed spe
RCU allows multiple threads to read objects in parallel without any
performance penalty. The following commit will introduce the first use.
Signed-off-by: Ben Pfaff
---
lib/automake.mk | 2 +
lib/ovs-rcu.c | 293 ++
lib/ovs
