DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ori Kam <orika@nvidia.com>
To: Dmitry Kozlyuk <dkozlyuk@nvidia.com>,
	Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>,
	"dev@dpdk.org" <dev@dpdk.org>
Cc: David Marchand <david.marchand@redhat.com>
Subject: Re: [dpdk-dev] [PATCH 0/4] net/mlx5: keep indirect actions across port restart
Date: Wed, 28 Jul 2021 12:07:30 +0000	[thread overview]
Message-ID: <DM8PR12MB5400C92A258CBBE067D9BCD5D6EA9@DM8PR12MB5400.namprd12.prod.outlook.com> (raw)
In-Reply-To: <CH0PR12MB50916FCFFB6B38258491C8E1B9EA9@CH0PR12MB5091.namprd12.prod.outlook.com>

Hi Dmitry and Andrew,

> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Dmitry Kozlyuk
> Sent: Wednesday, July 28, 2021 2:19 PM
> 
> Hi Andrew,
> 
> > From: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> On 7/27/21
> > 10:31 AM, Dmitry Kozlyuk wrote:
> > > It was unspecified what happens to indirect actions when a port is
> > > stopped, possibly reconfigured, and started again. MLX5 PMD, the
> > > first one to use indirect actions, intended to keep them across such
> > > a sequence, but the implementation was buggy. Patches 1-3 fix the
> > > PMD behavior, patch 4 adds common specification with rationale.
> >
> > I'm sorry, but it looks very inconsistent. If flow rules are not
> > preserved across restart, indirect actions should not be preserved as
> > well. We need very strong reasons to introduce the inconsistency.
> 
> Indirect actions really don't need to behave like flow rules. They are just
> objects owned by the port and they can exist while it exists. Consider a
> counter: stopping and starting the port doesn't logically affect its state. MLX5
> PMD destroys flow rules on port stop for internal reasons and documents
> this behavior, but ethdev API doesn't require it either.
> 
> > If we finally accept it, I think it would be very useful to care about
> > PMDs which cannot preserve it in HW across restart from the very
> > beginning and save it in ethdev layer and restore on start
> > automatically (i.e. do not force all such PMDs to care about the restore
> internally and basically duplicate the code).
> 
> Or keeping indirect actions can be an advertised PMD capability.
> Given Ori's comments to patch 4, I think the common spec needs more work.
> For this patchset that fixes MLX5 we can have the behavior documented for
> PMD and not require it from all the drivers.

This also effects if flows can be stored or not, (there was other thread about it)
I think we should have device cap that says if flows are preserved,
if they can be created before start, the same goes to actions, but
what if some actions can be preserved and some not? For example RSS
can't in some HW (or due to configuration change) while other can? For example
counter?
I don't want to have cap for each action, I think this info is based explained in each
driver documentation.
Maybe we can have some general flag one for flows and one for actions, and each PMD will have
detail doc.


Best,
Ori


  reply	other threads:[~2021-07-28 12:07 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-27  7:31 Dmitry Kozlyuk
2021-07-27  7:31 ` [dpdk-dev] [PATCH 1/4] net/mlx5: discover max flow priority using DevX Dmitry Kozlyuk
2021-07-27  7:31 ` [dpdk-dev] [PATCH 2/4] net/mlx5: create drop queue " Dmitry Kozlyuk
2021-07-27  7:31 ` [dpdk-dev] [PATCH 3/4] net/mlx5: preserve indirect actions across port restart Dmitry Kozlyuk
2021-07-27  7:31 ` [dpdk-dev] [PATCH 4/4] ethdev: document indirect flow action life cycle Dmitry Kozlyuk
2021-07-28  9:50   ` Ori Kam
2021-07-28  8:05 ` [dpdk-dev] [PATCH 0/4] net/mlx5: keep indirect actions across port restart Andrew Rybchenko
2021-07-28 11:18   ` Dmitry Kozlyuk
2021-07-28 12:07     ` Ori Kam [this message]
2021-07-28 12:26     ` Andrew Rybchenko
2021-07-28 14:08       ` Dmitry Kozlyuk
2021-07-28 17:07         ` Ori Kam
2021-07-29 14:00 ` [dpdk-dev] [PATCH v2 " Dmitry Kozlyuk
2021-07-29 14:00   ` [dpdk-dev] [PATCH v2 1/3] net/mlx5: discover max flow priority using DevX Dmitry Kozlyuk
2021-07-29 14:00   ` [dpdk-dev] [PATCH v2 2/3] net/mlx5: create drop queue " Dmitry Kozlyuk
2021-07-29 14:00   ` [dpdk-dev] [PATCH v2 3/3] net/mlx5: preserve indirect actions across port restart Dmitry Kozlyuk

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=DM8PR12MB5400C92A258CBBE067D9BCD5D6EA9@DM8PR12MB5400.namprd12.prod.outlook.com \
    --to=orika@nvidia.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=dkozlyuk@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 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).