On 12.09.2019 15:07, Eelco Chaudron wrote:
On 26 Aug 2019, at 16:54, Ilya Maximets wrote:
'tx_q' array is allocated for each DPDK netdev. 'struct dpdk_tx_queue'
is 8 bytes long, so 8 tx queues are sharing the same cache line in
case of 64B cacheline size. This causes 'false sharing' issue in
mutliqueue case because taking the spinlock implies write to memory
i.e. cache invalidation.
Signed-off-by: Ilya Maximets <i.maxim...@samsung.com>
---
I didn't really test the performance impact yet, so testing is very
welcome. Relevant test case could be PVP with 8 queues in HW NIC and
8 queues in vhost-user inerface and 8 PMD threads.
Did a quick test on my setup, but I do not have enough cores to do 8 PMD
threads and 8 VM cores. So I did a 4 core PMD/VM test running PV (not PVP as we
do not care about receiving traffic from the VHOST) using 64 bytes packets and
100 L3 flows.
Without the patch, I get 17,408,585 pps and with the patch 17,573,089 pps.
The patch looks good to me…
Acked-by: Eelco Chaudron <echau...@redhat.com>
Thanks! I'm expecting better results with more queues, but
it's a good improvement for 4 queues too.
Applied to master.
Best regards, Ilya Maximets.
_______________________________________________
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
