DPDK website maintenance
 help / color / mirror / Atom feed
From: "Mcnamara, John" <john.mcnamara@intel.com>
To: Thomas Monjalon <thomas.monjalon@6wind.com>,
	"Poole, James G" <james.g.poole@intel.com>
Cc: "web@dpdk.org" <web@dpdk.org>,
	"O'Driscoll, Tim" <tim.odriscoll@intel.com>
Subject: Re: [dpdk-web] [PATCH] roadmap: update to 16.11 roadmap items
Date: Wed, 13 Jul 2016 11:03:57 +0000	[thread overview]
Message-ID: <B27915DBBA3421428155699D51E4CFE2025906EE@IRSMSX103.ger.corp.intel.com> (raw)
In-Reply-To: <1605364.DcJpcoMCeS@xps13>

Hi Thomas,

Comments below.

> -----Original Message-----
> From: web [mailto:web-bounces@dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Monday, July 11, 2016 9:49 PM
> To: Poole, James G <james.g.poole@intel.com>
> Cc: web@dpdk.org
> Subject: Re: [dpdk-web] [PATCH] roadmap: update to 16.11 roadmap items
> 
> Hi,
> 
> Thanks for helping to update the website.
> Below are some comments:
> 
> 2016-07-08 08:27, James Poole:
> > -		<li>Rx Filtering Rework
> > -		<li>QEMU Vhost backend Reconnect
> 
> Yes it is in 16.07 already.

Yes. So it is okay to take it off the older roadmap. Right?


> 
> > -		<li>Delay Packet Copy in Vhost-user
> > -		<li>Fix library and symbol Namespace
> > +		<li>Cryptodev Support for Hardware Acceleration (via Intel(r)
> QuickAssist Technology) for Additional Algorithms
> > +		<li>Cryptodev Support for Software Acceleration for Additional
> > +Algorithms
> 
> It's a bit too long.
> Why not just "More Crypto Algorithms" instead of the above 2 lines?

Ok. Having them as two item is probably a result of us thinking about them separately. We will update to one item with:

"Additional Hardware and Software Crypto Algorithms"



> 
> > +		<li>Cryptodev Performance Optimisation
> > +		<li>IPsec Sample App Enhancements
> 
> Which IPsec enhancements?

The details are on Tim's longer announcement to the list: 
"Add support for AES-GCM, AES-CTR, config file support to remove hard-coding of SAs/SPs etc., use forward cipher function to generate IV on CBC mode.""

I don't think it helps to get into that level of detail here.

> 
> > +		<li>Generic Flow Director/Filtering/Classification API
> 
> The old API was already meant to be generic :) I think the "Rx Filtering"
> wording is a simpler name than "Flow Director/Filtering/Classification".

The name actually came from Adrien's RFC. :-) No problem changing it. "Rx Filtering API" seems fine to me.


> 
> > +		<li>Cuckoo Hash Enhancements
> 
> Which enhancements?

Optimize the Cuckoo Hash lookup stages by using intelligent prefetching for keys and using IA AVX instructions for vector processing of keys. The details are on the longer list.


> 
> > +		<li>Add vHost PMD xStats
> 
> The previous lines had no verb "Add".
> 
> > +		<li>Delay Packet Copy in vHost-User Dequeue
> 

No problem. We can just call it " vHost PMD xStats"


James will make the changes and submit a v2. If you have any other concerns you can just make the changes during merge.

John

  reply	other threads:[~2016-07-13 11:04 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-08  7:27 James Poole
2016-07-11 20:49 ` Thomas Monjalon
2016-07-13 11:03   ` Mcnamara, John [this message]
2016-07-13 11:55     ` Thomas Monjalon

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=B27915DBBA3421428155699D51E4CFE2025906EE@IRSMSX103.ger.corp.intel.com \
    --to=john.mcnamara@intel.com \
    --cc=james.g.poole@intel.com \
    --cc=thomas.monjalon@6wind.com \
    --cc=tim.odriscoll@intel.com \
    --cc=web@dpdk.org \
    /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).