[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4a721959-c3c3-4377-d1e3-7fa7d6c3e814@grimberg.me>
Date: Wed, 26 Oct 2022 14:02:34 +0300
From: Sagi Grimberg <sagi@...mberg.me>
To: Christoph Hellwig <hch@....de>, Aurelien Aptel <aaptel@...dia.com>
Cc: netdev@...r.kernel.org, davem@...emloft.net, kuba@...nel.org,
edumazet@...gle.com, pabeni@...hat.com, saeedm@...dia.com,
tariqt@...dia.com, leon@...nel.org, linux-nvme@...ts.infradead.org,
kbusch@...nel.org, axboe@...com, chaitanyak@...dia.com,
smalin@...dia.com, ogerlitz@...dia.com, yorayz@...dia.com,
borisp@...dia.com, aurelien.aptel@...il.com, malin1024@...il.com
Subject: Re: [PATCH v7 04/23] Revert "nvme-tcp: remove the unused queue_size
member in nvme_tcp_queue"
>> This reverts commit fb8745d040ef5b9080003325e56b91fefe1022bb.
>>
>> The newly added NVMeTCP offload requires the field
>> nvme_tcp_queue->queue_size in the patch
>> "nvme-tcp: Add DDP offload control path" in nvme_tcp_offload_socket().
>> The queue size is part of struct ulp_ddp_config
>> parameters.
>
> Please never do reverts if you just bring something back for an entirely
> differenet reason.
Agreed.
> And I think we need a really good justification of
> why you have a code path that can get the queue struct and not the
> controller, which really should not happen.
What is wrong with just using either ctrl->sqsize/NVME_AQ_DEPTH based
on the qid?
Powered by blists - more mailing lists