DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Joseph, Anoob" <Anoob.Joseph@caviumnetworks.com>
To: "Doherty, Declan" <declan.doherty@intel.com>,
	Pablo de Lara <pablo.de.lara.guarch@intel.com>
Cc: Akhil Goyal <akhil.goyal@nxp.com>,
	Ankur Dwivedi <ankur.dwivedi@caviumnetworks.com>,
	Jerin Jacob <jerin.jacob@caviumnetworks.com>,
	Narayana Prasad <narayanaprasad.athreya@caviumnetworks.com>,
	dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH 1/2] cryptodev: add min headroom and tailroom requirement
Date: Thu, 28 Jun 2018 08:26:13 +0530	[thread overview]
Message-ID: <d67077ce-f9fe-0090-9982-9f78c4f5bfef@caviumnetworks.com> (raw)
In-Reply-To: <cba4dbee-102e-d6af-284f-3d490123d5f0@intel.com>

Hi Declan,

Please see inline.

Thanks,

Anoob


On 26-06-2018 15:42, Doherty, Declan wrote:
> External Email
>
> On 19/06/2018 7:26 AM, Anoob Joseph wrote:
>> Enabling crypto devs to specify the minimum headroom and tailroom it
>> expects in the mbuf. For net PMDs, standard headroom has to be honoured
>> by applications, which is not strictly followed for crypto devs. This
>
> How is this done for NET PMDs, I don't see anything explicit in the
> ehtdev API for specification of headroom requirements.
In rte_mbuf.h, the minimum size required for packets involved in rx/tx 
is specified and that considers headroom also. Applications usually use 
these default macros while creating mbufs which are involved in rx/tx.
https://git.dpdk.org/dpdk/tree/lib/librte_mbuf/rte_mbuf.h#n411
>
>> prevents crypto devs from using free space in mbuf (available as
>> head/tailroom) for internal requirements in crypto operations. Addition
>> of head/tailroom requirement will help PMDs to communicate such
>> requirements to the application.
>>
>> The availability and use of head/tailroom is an optimization if the
>> hardware supports use of head/tailroom for crypto-op info. For devices
>> that do not support using the head/tailroom, they can continue to 
>> operate
>> without any performance-drop.
>>
> Is there any variations in requirements for terms headroom/tailroom on a
> per algorithmic basis or is it purely for the device?
It is purely per device basis. The device can specify upper bounds for 
the head/tailroom. A device that even specified the room, may not even 
use the entire room in all cases. So it doesn't have to be algo specific.
>
>> Signed-off-by: Anoob Joseph <anoob.joseph@caviumnetworks.com>
>> ---
>>   doc/guides/rel_notes/deprecation.rst | 4 ++++
>>   lib/librte_cryptodev/rte_cryptodev.h | 6 ++++++
>>   2 files changed, 10 insertions(+)
>>
>> diff --git a/doc/guides/rel_notes/deprecation.rst 
>> b/doc/guides/rel_notes/deprecation.rst
>> index 1ce692e..a547289 100644
>> --- a/doc/guides/rel_notes/deprecation.rst
>> +++ b/doc/guides/rel_notes/deprecation.rst
>> @@ -122,3 +122,7 @@ Deprecation Notices
>>     - Function ``rte_cryptodev_get_private_session_size()`` will be 
>> deprecated
>>       in 18.05, and it gets replaced with 
>> ``rte_cryptodev_sym_get_private_session_size()``.
>>       It will be removed in 18.08.
>> +  - New field, ``min_headroom_req``, added in ``rte_cryptodev_info`` 
>> structure. It will be
>> +    added in 18.11.
>> +  - New field, ``min_tailroom_req``, added in ``rte_cryptodev_info`` 
>> structure. It will be
>> +    added in 18.11.
>> diff --git a/lib/librte_cryptodev/rte_cryptodev.h 
>> b/lib/librte_cryptodev/rte_cryptodev.h
>> index 92ce6d4..fa944b8 100644
>> --- a/lib/librte_cryptodev/rte_cryptodev.h
>> +++ b/lib/librte_cryptodev/rte_cryptodev.h
>> @@ -382,6 +382,12 @@ struct rte_cryptodev_info {
>>       unsigned max_nb_queue_pairs;
>>       /**< Maximum number of queues pairs supported by device. */
>>
>> +     uint32_t min_headroom_req;
>> +     /**< Minimum mbuf headroom required by device */
>> +
>> +     uint32_t min_tailroom_req;
>> +     /**< Minimum mbuf tailroom required by device */
>> +
>>       struct {
>>               unsigned max_nb_sessions;
>>               /**< Maximum number of sessions supported by device. */
>>
>

  reply	other threads:[~2018-06-28  2:57 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-19  6:26 [dpdk-dev] [PATCH 0/2] add head/tailroom requirement for crypto PMDs Anoob Joseph
2018-06-19  6:26 ` [dpdk-dev] [PATCH 1/2] cryptodev: add min headroom and tailroom requirement Anoob Joseph
2018-06-21 14:24   ` Akhil Goyal
2018-06-22  6:52     ` Joseph, Anoob
2018-06-22 10:03       ` Akhil Goyal
2018-06-26 10:12   ` Doherty, Declan
2018-06-28  2:56     ` Joseph, Anoob [this message]
2018-06-28 11:41       ` De Lara Guarch, Pablo
2018-06-28 11:59         ` Joseph, Anoob
2018-06-19  6:26 ` [dpdk-dev] [PATCH 2/2] app/crypto-perf: honour cryptodev's min headroom/tailroom Anoob Joseph
2018-06-28 11:42   ` De Lara Guarch, Pablo
2018-07-04 13:55 ` [dpdk-dev] [PATCH v1 0/3] add head/tailroom requirement for crypto PMDs Anoob Joseph
2018-07-04 13:55   ` [dpdk-dev] [PATCH v1 1/3] cryptodev: add min headroom and tailroom requirement Anoob Joseph
2018-07-10 10:26     ` De Lara Guarch, Pablo
2018-07-10 10:50       ` Anoob Joseph
2018-07-04 13:55   ` [dpdk-dev] [PATCH v1 2/3] app/crypto-perf: honour cryptodev's min headroom/tailroom Anoob Joseph
2018-07-10 11:07     ` De Lara Guarch, Pablo
2018-07-10 11:16     ` De Lara Guarch, Pablo
2018-07-10 11:48     ` De Lara Guarch, Pablo
2018-07-10 12:23       ` Anoob Joseph
2018-07-10 13:27         ` De Lara Guarch, Pablo
2018-07-10 14:08           ` Anoob Joseph
2018-07-04 13:55   ` [dpdk-dev] [PATCH v1 3/3] test/crypto: skip validation of head/tailroom used by PMD Anoob Joseph
2018-07-10 14:42   ` [dpdk-dev] [PATCH v2 0/4] add head/tailroom requirement for crypto PMDs Anoob Joseph
2018-07-10 14:42     ` [dpdk-dev] [PATCH v2 1/4] cryptodev: add min headroom and tailroom requirement Anoob Joseph
2018-07-10 14:42     ` [dpdk-dev] [PATCH v2 2/4] app/crypto-perf: honour cryptodev's min headroom/tailroom Anoob Joseph
2018-07-10 14:42     ` [dpdk-dev] [PATCH v2 3/4] test/crypto: skip validation of head/tailroom used by PMD Anoob Joseph
2018-07-10 14:42     ` [dpdk-dev] [PATCH v2 4/4] crypto/scheduler: add minimum head/tailroom requirement Anoob Joseph
2018-07-10 17:20     ` [dpdk-dev] [PATCH v2 0/4] add head/tailroom requirement for crypto PMDs De Lara Guarch, Pablo
2018-07-10 17:29       ` De Lara Guarch, Pablo

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=d67077ce-f9fe-0090-9982-9f78c4f5bfef@caviumnetworks.com \
    --to=anoob.joseph@caviumnetworks.com \
    --cc=akhil.goyal@nxp.com \
    --cc=ankur.dwivedi@caviumnetworks.com \
    --cc=declan.doherty@intel.com \
    --cc=dev@dpdk.org \
    --cc=jerin.jacob@caviumnetworks.com \
    --cc=narayanaprasad.athreya@caviumnetworks.com \
    --cc=pablo.de.lara.guarch@intel.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).