On 7/21/2020 5:38 PM, Matan Azrad wrote:
> The commit below changed the readiness condition of vhost device to fix
> multi-queues issues showed with QEMU versions.
>
> Now, the vhost device is ready when the first queue-pair is ready.
> When more queues are being ready, the queue state callback will be
> triggered to notify the vhost manager.
>
> In case of Rx interrupt configuration, the vhost driver set the
> kickfd queue file descriptor in order to be notified on Rx traffic.
>
> So, when queue becomes ready, the kickfd may be changed and should be
> updated in the Rx interrupt structure.
>
> Update kickfd when the queue state callback is invoked.
> Also update event notification when it is enabled by the user.
>
> Fixes: d0fcc38f5fa4 ("vhost: improve device readiness notifications")
>
> Signed-off-by: Matan Azrad <ma...@mellanox.com>
Suggested-by: Marvin Liu <yong....@intel.com>
This patch addresses a ~%20 performance drop in vhost reported with -rc1.
Although it is missing component maintainers ack, I will merge it relying on
offline discussion Maxime, Matan, Marvin & Chenbo involved, to address the
performance issue observed in -rc2.
Hopefully won't but if we observe issues with this patch, there will be time to
address it before -rc3, I believe it is safer/better to merge it for -rc2 than
holding this fix till -rc3, at least it can be verified this way as part of
-rc2.
Applied to dpdk-next-net/master, thanks.
