From: yanjun.zhu@linux.dev
To: "Parav Pandit" <parav@nvidia.com>,
dust.li@linux.alibaba.com, "Zhu Yanjun" <yanjun.zhu@intel.com>,
jgg@ziepe.ca, leon@kernel.org, linux-rdma@vger.kernel.org
Subject: Re: [PATCH 0/3] RDMA net namespace
Date: Thu, 27 Oct 2022 03:39:07 +0000 [thread overview]
Message-ID: <6d841d006c9a79d9ecb1b1bae8d10a28@linux.dev> (raw)
In-Reply-To: <PH0PR12MB54819EFE62D489FD489A307DDC339@PH0PR12MB5481.namprd12.prod.outlook.com>
October 27, 2022 11:21 AM, "Parav Pandit" <parav@nvidia.com> wrote:
>> From: yanjun.zhu@linux.dev <yanjun.zhu@linux.dev>
>> Sent: Wednesday, October 26, 2022 11:17 PM
>>
>> October 27, 2022 11:10 AM, "Parav Pandit" <parav@nvidia.com> wrote:
>>
>> From: yanjun.zhu@linux.dev <yanjun.zhu@linux.dev>
>> Sent: Wednesday, October 26, 2022 11:08 PM
>>
>> October 27, 2022 11:01 AM, "Parav Pandit" <parav@nvidia.com> wrote:
>>
>> From: Dust Li <dust.li@linux.alibaba.com>
>> Sent: Wednesday, October 26, 2022 10:31 PM
>>
>> 2. else we are in
>> exclusive mode. When the corresponding netdevice of the RoCE or iWarp
>> device is moved from one net namespace to another, we move the RDMA
>> device into that net namespace
>>
>> What do you think ?
>>
>> No. one device is not supposed to move other devices.
>> Every device is independent that should be moved by explicit command.
>>
>> Can you show us where we can find this rule "Every device is
>> independent that should be moved by explicit command."?
>>
>> Also changes like above breaks the existing orchestration, it no-go.
>>
>> In a RoCE device, ib device is related with the net device. When a
>> net device is moved to a new net namespace, if the ib device is not
>> in the same net device, how to make ib device work?
>>
>> RDMA device should also be moved to the same net namespace as that of
>> netdev.
>>
>> sure. I know the following commands.
>>
>> In my commits, the process of moving IB devices to the same net namespace
>> with net devices is automatically finished.
>>
>> Is it OK?
>
> No.
> Change like this breaks the user space who expect to move the rdma device to the net namespace
> explicitly.
Which specification makes this kind of rule? Where can we find it?
> It wont find the device which got moved as part of some other device movement.
> Currently define scheme covers at least 3 different types of RDMA devices.
> 1. IB and IPoIB
> 2. RoCE
> 3. iWarp
>
> Each has somewhat different relation to their net device.
IPoIB, RoCE and iWarp are somewhat different relation to their net device.
To RoCE and iWarp devices, ib devices should be the same net namespace with the related net devices.
Or else we can not make ib devices work. This is why I send out these commits.
Zhu Yanjun
next prev parent reply other threads:[~2022-10-27 3:39 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-23 22:04 [PATCH 0/3] RDMA net namespace Zhu Yanjun
2022-10-23 13:04 ` Leon Romanovsky
2022-10-23 13:42 ` Yanjun Zhu
2022-10-23 16:45 ` Leon Romanovsky
2022-10-24 7:20 ` yanjun.zhu
2022-10-23 22:04 ` [PATCH 1/3] RDMA/core: Move ib device to the same net namespace with net device Zhu Yanjun
2022-10-23 22:04 ` [PATCH 2/3] RDMA/core: The legacy IB devices still work with shared/exclusive mode Zhu Yanjun
2022-10-23 22:04 ` [PATCH 3/3] RDMA/core: Get all the ib devices from net devices Zhu Yanjun
2022-10-24 1:10 ` [PATCH 0/3] RDMA net namespace Dust Li
2022-10-24 6:15 ` yanjun.zhu
2022-10-24 11:52 ` Dust Li
2022-10-24 13:12 ` Yanjun Zhu
2022-10-24 14:35 ` Dust Li
2022-10-24 16:41 ` Jason Gunthorpe
2022-10-25 2:51 ` Yanjun Zhu
2022-10-26 4:08 ` Dust Li
2022-10-26 15:01 ` Dust Li
2022-10-27 2:30 ` Dust Li
2022-10-27 2:54 ` yanjun.zhu
2022-10-27 3:01 ` Parav Pandit
2022-10-27 3:07 ` yanjun.zhu
2022-10-27 3:10 ` Parav Pandit
2022-10-27 3:17 ` yanjun.zhu
2022-10-27 3:21 ` Parav Pandit
2022-10-27 3:39 ` yanjun.zhu [this message]
2022-10-27 3:48 ` Parav Pandit
2022-10-27 6:01 ` yanjun.zhu
2022-10-27 14:06 ` Parav Pandit
2022-10-28 3:21 ` Yanjun Zhu
2022-10-28 3:31 ` Parav Pandit
2022-10-28 3:49 ` Yanjun Zhu
2022-10-28 3:58 ` Parav Pandit
2022-11-11 2:38 ` Yanjun Zhu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6d841d006c9a79d9ecb1b1bae8d10a28@linux.dev \
--to=yanjun.zhu@linux.dev \
--cc=dust.li@linux.alibaba.com \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=parav@nvidia.com \
--cc=yanjun.zhu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox