>
> I applied this to master with the below incremental.
>
> We _usually_ use positive error numbers in int return value.
>
> I think there was an extra COVERAGE_INC(seq_change)
>
> Thanks for the patch!
Hi,
Could this be backported to the 2.5 branch?
Thanks,
Ciara
>
> diff --git a/lib/ovs
On Fri, Jul 08, 2016 at 04:19:14PM -0700, Daniele Di Proietto wrote:
> I applied this to master with the below incremental.
>
> We _usually_ use positive error numbers in int return value.
>
> I think there was an extra COVERAGE_INC(seq_change)
>
> Thanks for the patch!
Your Changes are good, t
I applied this to master with the below incremental.
We _usually_ use positive error numbers in int return value.
I think there was an extra COVERAGE_INC(seq_change)
Thanks for the patch!
diff --git a/lib/ovs-rcu.c b/lib/ovs-rcu.c
index 7462579..8aef1f1 100644
--- a/lib/ovs-rcu.c
+++ b/lib/ovs-
The PMD thread needs to keep processing RX queues in order
to achieve maximum throughput. It also needs to sweep emc
cache and quiesce which use seq_mutex. That mutex can
eventually block the PMD thread causing latency spikes and
affecting the throughput.
Since there is no requirement for running