From: jgg@ziepe.ca (Jason Gunthorpe)
Subject: [PATCH 2/2] nvme-rdma: Add remote_invalidation module parameter
Date: Sun, 29 Oct 2017 11:52:37 -0600 [thread overview]
Message-ID: <20171029175237.GD4488@ziepe.ca> (raw)
In-Reply-To: <1509295101-14081-3-git-send-email-idanb@mellanox.com>
On Sun, Oct 29, 2017@06:38:21PM +0200, idanb@mellanox.com wrote:
> +static bool remote_invalidation = true;
> +module_param(remote_invalidation, bool, 0444);
> +MODULE_PARM_DESC(remote_invalidation,
> + "request remote invalidation from subsystem (default: true)");
Please no module options.
If your device has a performance anomaly that makes
SEND_WITH_INVALIDATE slower than local invalidation, then we need to
talk about having a new verbs flag for this situation so all the ULPs
can avoid using SEND_WITH_INVALIDATE..
Sagi, is this really an apples to apples comparison?
When I was talking with Chuck on NFS there were some various issues on
that side that made the local invalidate run faster, but it wasn't
actually working properly.
Does nvme wait for the local invalidate to finish before moving on?
Jason
next prev parent reply other threads:[~2017-10-29 17:52 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-29 16:38 [PATCH 0/2] Performance Improvents for Secured Mode NVMe over Fabrics and other RDMA ULPs idanb
2017-10-29 16:38 ` [PATCH 1/2] IB/mlx5: posting klm/mtt list inline in the send queue for reg_wr idanb
2017-10-29 17:09 ` Sagi Grimberg
2018-04-19 21:11 ` roland
2018-04-20 2:04 ` Doug Ledford
2018-04-20 19:07 ` Max Gurtovoy
2017-10-29 16:38 ` [PATCH 2/2] nvme-rdma: Add remote_invalidation module parameter idanb
2017-10-29 17:52 ` Jason Gunthorpe [this message]
2017-10-30 8:14 ` Sagi Grimberg
2017-10-30 8:38 ` idanb
2017-10-30 9:44 ` Sagi Grimberg
2017-10-30 10:31 ` idanb
2017-10-30 10:33 ` Sagi Grimberg
2017-10-30 12:35 ` idanb
2017-10-29 18:24 ` Chuck Lever
2017-10-30 18:18 ` Chuck Lever
2017-10-30 8:11 ` Sagi Grimberg
2017-10-30 8:45 ` idanb
2017-10-29 16:59 ` [PATCH 0/2] Performance Improvents for Secured Mode NVMe over Fabrics and other RDMA ULPs Sagi Grimberg
2017-10-29 17:09 ` Max Gurtovoy
2017-10-29 17:43 ` Leon Romanovsky
[not found] ` <AM0PR0502MB38906F57CD68C3707F8FE765C5580@AM0PR0502MB3890.eurprd05.prod.outlook.com>
2017-10-30 5:21 ` Leon Romanovsky
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=20171029175237.GD4488@ziepe.ca \
--to=jgg@ziepe.ca \
/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).