[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <fe4292e1-c3fa-b3e6-4beb-b2d48bbcff9d@fb.com>
Date: Thu, 9 Nov 2017 13:12:57 -0700
From: Jens Axboe <axboe@...com>
To: Thomas Gleixner <tglx@...utronix.de>
CC: Sagi Grimberg <sagi@...mberg.me>, Jes Sorensen <jsorensen@...com>,
Tariq Toukan <tariqt@...lanox.com>,
Saeed Mahameed <saeedm@....mellanox.co.il>,
Networking <netdev@...r.kernel.org>,
Leon Romanovsky <leonro@...lanox.com>,
Saeed Mahameed <saeedm@...lanox.com>,
Kernel Team <kernel-team@...com>,
Christoph Hellwig <hch@....de>
Subject: Re: mlx5 broken affinity
On 11/09/2017 10:07 AM, Thomas Gleixner wrote:
> On Thu, 9 Nov 2017, Jens Axboe wrote:
>
>> On 11/09/2017 09:01 AM, Sagi Grimberg wrote:
>>>> Now you try to blame the people who implemented the managed affinity stuff
>>>> for the wreckage, which was created by people who changed drivers to use
>>>> it. Nice try.
>>>
>>> I'm not trying to blame anyone, really. I was just trying to understand
>>> how to move forward with making users happy and still enjoy subsystem
>>> services instead of doing lots of similar things inside mlx5 driver.
>>
>> Exactly. The key here is how we make it work for both cases. But there
>> has to be a willingness to make the infrastructure work for that.
>
> I say it one last time: It can be done and I'm willing to help.
It didn't sound like it earlier, but that's good news.
> Please tell me what exactly you expect and I can have a look what needs to
> be done w/o creating an utter mess.
See the previous email, should have all the details.
--
Jens Axboe
Powered by blists - more mailing lists