From: James Smart <jsmart2021@gmail.com>
To: Max Gurtovoy <maxg@mellanox.com>, Christoph Hellwig <hch@lst.de>
Cc: axboe@kernel.dk, sagi@grimberg.me, martin.petersen@oracle.com,
shlomin@mellanox.com, linux-rdma@vger.kernel.org,
israelr@mellanox.com, vladimirk@mellanox.com,
linux-nvme@lists.infradead.org, idanb@mellanox.com,
jgg@mellanox.com, oren@mellanox.com, kbusch@kernel.org
Subject: Re: [PATCH 05/17] nvme-fabrics: Allow user enabling metadata/T10-PI support
Date: Wed, 22 Apr 2020 15:24:25 -0700 [thread overview]
Message-ID: <70f40e49-d9d7-68fe-6a63-a73fabcd146d@gmail.com> (raw)
In-Reply-To: <54c05d2d-2ea5-bf58-455f-91efa085aa9b@mellanox.com>
On 4/22/2020 3:07 PM, Max Gurtovoy wrote:
>
> On 4/21/2020 6:17 PM, Christoph Hellwig wrote:
>> On Fri, Mar 27, 2020 at 08:15:33PM +0300, Max Gurtovoy wrote:
>>> From: Israel Rukshin <israelr@mellanox.com>
>>>
>>> Preparation for adding metadata (T10-PI) over fabric support. This will
>>> allow end-to-end protection information passthrough and validation for
>>> NVMe over Fabric.
>> So actually - for PCIe we enable PI by default. Not sure why RDMA would
>> be any different? If we have a switch to turn it off we probably want
>> it work similar (can't be the same due to the lack of connect) for PCIe
>> as well.
>
> For PCI we use a format command to configure metadata. In fabrics we can
> choose doing it in the connect command and we can also choose to have
> "protected" controllers and "non-protected" controllers.
>
> I don't think it's all or nothing case, and configuration using nvme-cli
> (or other tool) seems reasonable and flexible.
I think you need to change this to "some fabrics".
With FC, we don't do anything in connect. The transport passes
attributes on what it can do for PI support, including: passing through
metadata (no checks); checking of metadata (normal); generation/strip of
metadata on the wire (meaning OS does not have to have a metadata
buffer), and so on. Enablement is just like pci - format the ns, then
match up the attribute with the behavior. There is no such thing as
protected and non-protected controllers. There's either a ns that has
metadata or not. If metadata and the attributes of the transport can't
support it, the ns is inaccessible.
I understand why you are describing it as you are, but I'm a bit
concerned about the creation of things that aren't comprehended in the
standards at all right now (protected vs non-protected controllers).
This affects how multipath configures as well.
-- james
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2020-04-22 22:24 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-27 17:15 [PATCH 00/17 V5] nvme-rdma/nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-03-27 17:15 ` [PATCH 1/1] nvme-cli/fabrics: Add pi_enable param to connect cmd Max Gurtovoy
2020-03-27 17:15 ` [PATCH 01/17] nvme: introduce namespace features flag Max Gurtovoy
2020-04-21 11:59 ` Christoph Hellwig
2020-04-21 15:53 ` James Smart
2020-04-21 18:11 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 02/17] nvme: Add has_md field to the nvme_req structure Max Gurtovoy
2020-04-21 11:59 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 03/17] nvme: Enforce extended LBA format for fabrics metadata Max Gurtovoy
2020-04-21 12:08 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 04/17] nvme: introduce max_integrity_segments ctrl attribute Max Gurtovoy
2020-04-21 12:09 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 05/17] nvme-fabrics: Allow user enabling metadata/T10-PI support Max Gurtovoy
2020-04-21 12:12 ` Christoph Hellwig
2020-04-21 15:17 ` Christoph Hellwig
2020-04-22 22:07 ` Max Gurtovoy
2020-04-22 22:24 ` James Smart [this message]
2020-04-22 22:39 ` Max Gurtovoy
2020-04-23 5:54 ` Christoph Hellwig
2020-04-23 7:30 ` Max Gurtovoy
2020-04-24 7:06 ` Christoph Hellwig
2020-04-26 9:48 ` Max Gurtovoy
2020-04-27 6:04 ` Christoph Hellwig
2020-04-27 13:52 ` Max Gurtovoy
2020-04-27 13:54 ` Christoph Hellwig
2020-04-28 9:18 ` Max Gurtovoy
2020-04-23 5:53 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 06/17] nvme: introduce NVME_INLINE_MD_SG_CNT Max Gurtovoy
2020-04-21 12:12 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 07/17] nvme-rdma: Introduce nvme_rdma_sgl structure Max Gurtovoy
2020-04-21 12:13 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 08/17] nvme-rdma: add metadata/T10-PI support Max Gurtovoy
2020-04-21 12:20 ` Christoph Hellwig
2020-04-23 9:22 ` Max Gurtovoy
2020-04-24 7:09 ` Christoph Hellwig
2020-04-26 10:04 ` Max Gurtovoy
2020-03-27 17:15 ` [PATCH 09/17] nvmet: prepare metadata request Max Gurtovoy
2020-04-21 15:21 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 10/17] nvmet: add metadata characteristics for a namespace Max Gurtovoy
2020-04-21 15:23 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 11/17] nvmet: Rename nvmet_rw_len to nvmet_rw_data_len Max Gurtovoy
2020-03-27 17:15 ` [PATCH 12/17] nvmet: Rename nvmet_check_data_len to nvmet_check_transfer_len Max Gurtovoy
2020-03-27 17:15 ` [PATCH 13/17] nvme: Add Metadata Capabilities enumerations Max Gurtovoy
2020-04-21 15:24 ` Christoph Hellwig
2020-04-23 12:09 ` Max Gurtovoy
2020-04-24 7:12 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 14/17] nvmet: Add metadata/T10-PI support Max Gurtovoy
2020-04-21 15:30 ` Christoph Hellwig
2020-04-23 12:39 ` Max Gurtovoy
2020-04-24 7:14 ` Christoph Hellwig
2020-04-26 10:50 ` Max Gurtovoy
2020-04-27 6:06 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 15/17] nvmet: Add metadata support for block devices Max Gurtovoy
2020-04-21 15:33 ` Christoph Hellwig
2020-04-23 17:25 ` Max Gurtovoy
2020-04-24 7:54 ` Christoph Hellwig
2020-03-27 17:15 ` [PATCH 16/17] RDMA/rw: Expose maximal page list for a device per 1 MR Max Gurtovoy
2020-03-27 17:15 ` [PATCH 17/17] nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-04-21 15:37 ` Christoph Hellwig
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=70f40e49-d9d7-68fe-6a63-a73fabcd146d@gmail.com \
--to=jsmart2021@gmail.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=idanb@mellanox.com \
--cc=israelr@mellanox.com \
--cc=jgg@mellanox.com \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-rdma@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=maxg@mellanox.com \
--cc=oren@mellanox.com \
--cc=sagi@grimberg.me \
--cc=shlomin@mellanox.com \
--cc=vladimirk@mellanox.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;
as well as URLs for NNTP newsgroup(s).