Re: [PATCH 0/2] nvmet: support polling task for RDMA and TCP

[Hannes Reinecke <hare@suse.de>]

On 7/4/24 10:10, Ping Gan wrote:
>> On 02/07/2024 13:02, Ping Gan wrote:
[ .. ]
>>> And the bandwidth of a node is only 3100MB. While we used the patch
>>> and enable 6 polling task, the bandwidth can be 4000MB. It's a good
>>> improvement.
>>
>> I think you will see similar performance with unbound workqueue and
>> rps.
> 
> Yes, I remodified the nvmet-tcp/nvmet-rdma code for supporting unbound
> workqueue, and in same prerequisites of above to run test, and compared
> the result of unbound workqueue and polling mode task. And I got a good
> performance for unbound workqueue. For unbound workqueue TCP we got
> 3850M/node, it's almost equal to polling task. And also tested
> nvmet-rdma we get 5100M/node for unbound workqueue RDMA versus 5600M for
> polling task, seems the diff is very small. Anyway, your advice is good.
> Do you think we should submit the unbound workqueue patches for nvmet-tcp
> and nvmet-rdma to upstream nvmet?

Please do. I have been using pretty much the same patch during
development of my nvme-tcp scalability patchset, and using WQ_UNBOUND
definitely improves the situation here.

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare@suse.de                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich