netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: KY Srinivasan <kys@microsoft.com>
To: David Miller <davem@davemloft.net>
Cc: "eric.dumazet@gmail.com" <eric.dumazet@gmail.com>,
	Haiyang Zhang <haiyangz@microsoft.com>,
	"edumazet@google.com" <edumazet@google.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Subject: RE: [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled
Date: Tue, 3 Nov 2015 18:09:52 +0000	[thread overview]
Message-ID: <BY2PR0301MB16545CDB0F10CC8DB3058D8EA02B0@BY2PR0301MB1654.namprd03.prod.outlook.com> (raw)
In-Reply-To: <20151103.103319.1465681990237533576.davem@davemloft.net>



> -----Original Message-----
> From: David Miller [mailto:davem@davemloft.net]
> Sent: Tuesday, November 3, 2015 7:33 AM
> To: KY Srinivasan <kys@microsoft.com>
> Cc: eric.dumazet@gmail.com; Haiyang Zhang <haiyangz@microsoft.com>;
> edumazet@google.com; netdev@vger.kernel.org
> Subject: Re: [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET
> is enabled
> 
> From: KY Srinivasan <kys@microsoft.com>
> Date: Tue, 3 Nov 2015 07:59:36 +0000
> 
> > I have implemented the scheme we had discussed a few weeks ago. In
> > this new implementation our driver is NOT requesting addition
> > headroom - rndis header and the per packet state is being maintained
> > outside of the skb. What I am seeing is that when I have
> > LL_MAX_HEADER set to 220 bytes, even though our driver is not using
> > the additional head room, I see about a 10% boost in the peak
> > performance (about 34 Gbps on a 40Gbps interface). However, when I
> > set the LL_MAX_HEADER value to the current default, the peak
> > performance drops back to what we currently have (around 31
> > Gbps). In both these cases, there is no reallocation of skb since no
> > additional headroom is being requested and yet there is a
> > significant difference in performance.  I trying to figure out why
> > this is the case, your insights will be greatly appreciated.
> 
> It probably has something to do with cache line or data alignment.

Thanks David. I too am leaning towards the same conclusion. Since I am
not using any part of skb, it looks like the alignment issue is solved by
having a larger LL_MAX_HEADER (220 bytes to be specific). I will do some
bare metal testing on the setup we have and report back.

Regards,

K. Y 

  parent reply	other threads:[~2015-11-03 18:09 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-10-29 21:49 [patch] tcp: attach SYNACK messages to request sockets instead of listener Haiyang Zhang
2015-10-29 22:58 ` Eric Dumazet
2015-10-30 19:38   ` Haiyang Zhang
2015-10-30 20:02     ` Eric Dumazet
2015-10-30 20:18       ` Eric Dumazet
2015-10-30 21:42         ` Haiyang Zhang
2015-10-30 23:52           ` Eric Dumazet
2015-11-01 17:20             ` [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled Eric Dumazet
2015-11-01 20:58               ` David Miller
2015-11-01 22:36                 ` Eric Dumazet
2015-11-01 22:58                   ` [PATCH net-next] net: make skb_set_owner_w() more robust Eric Dumazet
2015-11-01 23:18                     ` kbuild test robot
2015-11-01 23:27                       ` Eric Dumazet
2015-11-01 23:36                     ` [PATCH v2 " Eric Dumazet
2015-11-02 20:05                       ` Haiyang Zhang
2015-11-02 20:09                         ` Eric Dumazet
2015-11-02 20:26                           ` David Miller
2015-11-02 21:29                       ` David Miller
2015-11-03  7:59                 ` [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled KY Srinivasan
2015-11-03 15:33                   ` David Miller
2015-11-03 16:37                     ` Eric Dumazet
2015-11-03 17:34                       ` Haiyang Zhang
2015-11-03 18:20                         ` David Miller
2015-11-03 18:49                           ` Haiyang Zhang
2015-11-03 19:50                             ` David Miller
2015-11-03 21:00                               ` Haiyang Zhang
2015-11-03 18:09                     ` KY Srinivasan [this message]
2015-10-30 20:28       ` [patch] tcp: attach SYNACK messages to request sockets instead of listener KY Srinivasan

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=BY2PR0301MB16545CDB0F10CC8DB3058D8EA02B0@BY2PR0301MB1654.namprd03.prod.outlook.com \
    --to=kys@microsoft.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=eric.dumazet@gmail.com \
    --cc=haiyangz@microsoft.com \
    --cc=netdev@vger.kernel.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).