From: Vincent JARDIN <vincent.jardin@6wind.com>
To: Thomas Graf <tgraf@redhat.com>
Cc: "dev@openvswitch.org" <dev@openvswitch.org>,
dev@dpdk.org, Gerald Rogers <gerald.rogers@intel.com>,
dpdk-ovs@ml01.01.org
Subject: Re: [dpdk-dev] [ovs-dev] [PATCH RFC] dpif-netdev: Add support Intel DPDK based ports.
Date: Wed, 29 Jan 2014 17:34:46 +0100 [thread overview]
Message-ID: <52E92DA6.9070704@6wind.com> (raw)
In-Reply-To: <52E8E2AB.1080600@redhat.com>
Thomas,
First and easy answer: it is open source, so anyone can recompile. So,
what's the issue?
> Without a concept of stable interfaces, it will be difficult to
> package and distribute RTE libraries, PMD, and DPDK applications. Right
> now, the obvious path would include packaging the PMD bits together
> with each DPDK application depending on the version of DPDK the binary
> was compiled against. This is clearly not ideal.
>
>> I agree that some areas could be improved since they are not into the
>> critical datapath of packets, but still other areas remain very CPU
>> constraints. For instance:
>> http://dpdk.org/browse/dpdk/commit/lib/librte_ether/rte_ethdev.h?id=c3d0564cf0f00c3c9a61cf72bd4bd1c441740637
>>
>> is bad:
>> struct eth_dev_ops
>> is churned, no comment, and a #ifdef that changes the structure
>> according to compilation!
>
> This is a very good example as it outlines the difference between
> control structures and the fast path. We have this same exact trade off
> in the kernel a lot where we have highly optimized internal APIs
> towards modules and drivers but want to provide binary compatibility to
> a certain extend.
As long as we agree on this limited scope, we'll think about it and
provide a proposal on dev@dpdk.org mailing list.
> As for the specific example you mention, it is relatively trivial to
> make eth_dev_ops backwards compatible by appending appropriate padding
> to the struct before a new major release and ensure that new members
> are added by replacing the padding accordingly. Obviously no ifdefs
> would be allowed anymore.
Of course, it is basic C!
>> Should an application use the librte libraries of the DPDK:
>> - you can use RTE_VERSION and RTE_VERSION_NUM :
>> http://dpdk.org/doc/api/rte__version_8h.html#a8775053b0f721b9fa0457494cfbb7ed9
>
> Right. This would be more or less identical to requiring a specific
> DPDK version in OVS_CHEC_DPDK. It's not ideal to require application to
> clutter their code with #ifdefs all over for every new minor release
> though.
>
>> - you can write your own wrapper (with CPU overhead) in order to have
>> a stable ABI, that wrapper should be tight to the versions of the librte
>> => the overhead is part of your application instead of the DPDK,
>> - *otherwise recompile your software, it is opensource, what's the
>> issue?*
>>
>> We are opened to any suggestion to have stable ABI, but it should never
>> remove the options to have fast/efficient/compilation/CPU execution
>> processing.
>
> Absolutely agreed. We also don't want to add tons of abstraction and
> overcomplicate everything. Still, I strongly believe that the definition
> of stable interfaces towards applications and especially PMD is
> essential.
>
> I'm not proposing to standardize all the APIs towards applications on
> the level of POSIX. DPDK is in early stages and disruptive changes will
> come along. What I would propose on an abstract level is:
>
> 1. Extend but not break API between minor releases. Postpone API
> breakages to the next major release. High cadence of major
> releases initially, lower cadence as DPDK matures.
>
> 2. Define ABI stability towards PMD for minor releases to allow
> isolated packaging of PMD by padding control structures and keeping
> functions ABI stable.
I get lost: do you mean ABI + API toward the PMDs or towards the
applications using the librte ?
Best regards,
Vincent
next prev parent reply other threads:[~2014-01-29 16:33 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-28 1:48 [dpdk-dev] " pshelar
[not found] ` <20140128044950.GA4545@nicira.com>
2014-01-28 5:28 ` [dpdk-dev] [ovs-dev] " Pravin Shelar
2014-01-28 14:47 ` [dpdk-dev] " Vincent JARDIN
2014-01-28 17:56 ` Pravin Shelar
2014-01-29 0:15 ` Vincent JARDIN
2014-01-29 19:32 ` Pravin Shelar
[not found] ` <52E7D2A8.400@redhat.com>
2014-01-28 18:20 ` [dpdk-dev] [ovs-dev] " Pravin Shelar
[not found] ` <52E7D13B.9020404@redhat.com>
2014-01-28 18:17 ` Pravin Shelar
2014-01-29 8:15 ` Thomas Graf
2014-01-29 10:26 ` Vincent JARDIN
2014-01-29 11:14 ` Thomas Graf
2014-01-29 16:34 ` Vincent JARDIN [this message]
2014-01-29 17:14 ` Thomas Graf
2014-01-29 18:42 ` Stephen Hemminger
2014-01-29 20:47 ` François-Frédéric Ozog
2014-01-29 23:15 ` Thomas Graf
2014-03-13 7:37 ` David Nyström
2014-01-29 8:56 ` [dpdk-dev] " Prashant Upadhyaya
2014-01-29 21:29 ` Pravin Shelar
2014-01-30 10:15 ` Prashant Upadhyaya
2014-01-30 16:27 ` Rogers, Gerald
2014-01-29 10:01 ` [dpdk-dev] [ovs-dev] " Thomas Graf
2014-01-29 21:49 ` Pravin Shelar
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=52E92DA6.9070704@6wind.com \
--to=vincent.jardin@6wind.com \
--cc=dev@dpdk.org \
--cc=dev@openvswitch.org \
--cc=dpdk-ovs@ml01.01.org \
--cc=gerald.rogers@intel.com \
--cc=tgraf@redhat.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).