All of lore.kernel.org
 help / color / mirror / Atom feed
From: hch@lst.de (Christoph Hellwig)
Subject: [PATCH 2/3] nvme: introduce max_segments controller attribute
Date: Tue, 22 Aug 2017 08:32:15 +0200	[thread overview]
Message-ID: <20170822063215.GA6627@lst.de> (raw)
In-Reply-To: <39824829-4a0c-6418-2de7-719461fb3662@grimberg.me>

On Sun, Aug 20, 2017@09:35:25AM +0300, Sagi Grimberg wrote:
>> But the controller needs to support it, and NVMe controllers are
>> only required to support a 4k page size, the rest is optional.
>
> How exacly is the controller required to support the pag_size for
> fabrics?

It doesn't matter at all, except as the scaling factor for a few
reported values.

>> For PCIe (before fabrics existed) we used to do that, but we changed
>> it for ppc64 in this commit:
>>
>> c5c9f25b98 ("NVMe: default to 4k device page size")
>
> Yea... I'm wandering if this is specific to NVMe or it can trigger
> in RDMA as well.

As far as I can tell we could hit it with RDMA under the same
circumstances (weird iommu with a smaller page size than the system
page size), but for RDMA the nvme controller page size isn't the
one that matter, but rather the MR page size.

So for now to be safe it might be a good idea to always use a 4k
MR page size..

  reply	other threads:[~2017-08-22  6:32 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-16 10:20 [PATCH 1/3] nvme: add virt boundary per ctrl Max Gurtovoy
2017-08-16 10:20 ` [PATCH 2/3] nvme: introduce max_segments controller attribute Max Gurtovoy
2017-08-16 13:29   ` Sagi Grimberg
2017-08-16 14:35     ` Max Gurtovoy
2017-08-16 19:04       ` Sagi Grimberg
2017-08-17  7:40         ` Christoph Hellwig
2017-08-20  6:35           ` Sagi Grimberg
2017-08-22  6:32             ` Christoph Hellwig [this message]
2017-08-22  9:36               ` Max Gurtovoy
2017-08-22  9:40                 ` Christoph Hellwig
2017-08-16 10:21 ` [PATCH 3/3] nvme-rdma: fix virtual boundary calculation Max Gurtovoy
2017-08-21 22:45 ` [PATCH 1/3] nvme: add virt boundary per ctrl James Smart

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=20170822063215.GA6627@lst.de \
    --to=hch@lst.de \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.