From: Jason Gunthorpe <jgg@nvidia.com>
To: Michael Guralnik <michaelgur@nvidia.com>
Cc: leonro@nvidia.com, linux-rdma@vger.kernel.org, maorg@nvidia.com,
Aharon Landau <aharonl@nvidia.com>
Subject: Re: [PATCH v2 rdma-next 2/6] RDMA/mlx5: Remove explicit ODP cache entry
Date: Wed, 7 Dec 2022 20:02:27 -0400 [thread overview]
Message-ID: <Y5Epk+nLntyjxmOr@nvidia.com> (raw)
In-Reply-To: <20221207085752.82458-3-michaelgur@nvidia.com>
On Wed, Dec 07, 2022 at 10:57:48AM +0200, Michael Guralnik wrote:
> From: Aharon Landau <aharonl@nvidia.com>
>
> Explicit ODP mkey doesn't have unique properties. There is no need to
> devote to it a special entry. Removing it.
This isn't quite true, the purpose of this entry to is to create a
cache block of order 30, which is higher than the usual max of 22
Though, I'm not really sure we should even be caching such huge MRs, I
can understand why ODP would want this cache, at least for fairly
short term.
At the end of this do we still have caching for order 30 MRs?
Also, is the MTT vs KSM access_mode UMRable?
Jason
next prev parent reply other threads:[~2022-12-08 0:02 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-07 8:57 [PATCH v2 rdma-next 0/6] RDMA/mlx5: Switch MR cache to use RB-tree Michael Guralnik
2022-12-07 8:57 ` [PATCH v2 rdma-next 1/6] RDMA/mlx5: Don't keep umrable 'page_shift' in cache entries Michael Guralnik
2022-12-07 8:57 ` [PATCH v2 rdma-next 2/6] RDMA/mlx5: Remove explicit ODP cache entry Michael Guralnik
2022-12-08 0:02 ` Jason Gunthorpe [this message]
2022-12-08 0:22 ` Jason Gunthorpe
2022-12-07 8:57 ` [PATCH v2 rdma-next 3/6] RDMA/mlx5: Change the cache structure to RB-tree Michael Guralnik
2022-12-08 0:17 ` Jason Gunthorpe
2022-12-07 8:57 ` [PATCH v2 rdma-next 4/6] RDMA/mlx5: Introduce mlx5r_cache_rb_key Michael Guralnik
2022-12-08 0:39 ` Jason Gunthorpe
2022-12-13 12:12 ` Michael Guralnik
2022-12-07 8:57 ` [PATCH v2 rdma-next 5/6] RDMA/mlx5: Cache all user cacheable mkeys on dereg MR flow Michael Guralnik
2022-12-08 0:44 ` Jason Gunthorpe
2022-12-07 8:57 ` [PATCH v2 rdma-next 6/6] RDMA/mlx5: Add work to remove temporary entries from the cache Michael Guralnik
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=Y5Epk+nLntyjxmOr@nvidia.com \
--to=jgg@nvidia.com \
--cc=aharonl@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=maorg@nvidia.com \
--cc=michaelgur@nvidia.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 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.