DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Richardson, Bruce" <bruce.richardson@intel.com>
To: "De Lara Guarch, Pablo" <pablo.de.lara.guarch@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v2 6/6] mbuf: flatten struct vlan_macip into mbuf	struct
Date: Sun, 7 Sep 2014 19:40:01 +0000	[thread overview]
Message-ID: <59AF69C657FD0841A61C55336867B5B0343EF578@IRSMSX103.ger.corp.intel.com> (raw)
In-Reply-To: <E115CCD9D858EF4F90C690B0DCB4D89722614382@IRSMSX108.ger.corp.intel.com>

> -----Original Message-----
> From: De Lara Guarch, Pablo
> Sent: Friday, September 05, 2014 5:21 PM
> To: Richardson, Bruce; dev@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v2 6/6] mbuf: flatten struct vlan_macip into
> mbuf struct
> 
> 
> 
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Bruce Richardson
> > Sent: Thursday, August 28, 2014 4:43 PM
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [PATCH v2 6/6] mbuf: flatten struct vlan_macip into
> > mbuf struct
> >
> > The vlan_macip structure combined a vlan tag id with l2 and l3 headers
> > lengths for tracking offloads. However, this structure was only used as
> > a unit by the e1000 and ixgbe drivers, not generally.
> >
> > This patch removes the structure from the mbuf header and places the
> > fields into the mbuf structure directly at the required point, without
> > any net effect on the structure layout. This allows us to treat the vlan
> > tags and header length fields as separate for future mbuf changes. The
> > drivers which were written to use the combined structure still do so,
> > using a driver-local definition of it.
> >
> > Changes in V2:
> > * None
> >
> > Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
> 
> After applying this patch, I see a performance degradation (around 5%) using
> testpmd with the default RX path, so this may require a v3 patch.
> 
> Thanks,
> Pablo

Thanks for Pablo for flagging this. Since no fields are moved in the structure, merely flattened, I suspect any degradation must come from having the l2_len and l3_len bit fields split out. I'll do up a v3 with a union to allow them to be assigned simultaneously and see if it helps things. Fast-path is unaffected in my tests.

/Bruce

  reply	other threads:[~2014-09-07 19:35 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-08-27 15:50 [dpdk-dev] [PATCH 0/6] Mbuf structure Rework, part 1 Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 1/6] ixgbe: put only non-zero initializer in definition Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 2/6] mbuf: rename RTE_MBUF_SCATTER_GATHER into RTE_MBUF_REFCNT Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 3/6] mbuf: remove rte_ctrlmbuf Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 4/6] mbuf: remove the rte_pktmbuf structure Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 5/6] mbuf: rename in_port to just port Bruce Richardson
2014-08-27 15:50 ` [dpdk-dev] [PATCH 6/6] mbuf: flatten struct vlan_macip into mbuf struct Bruce Richardson
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 0/6] Mbuf structure Rework, part 1 Bruce Richardson
2014-09-17  9:30   ` Thomas Monjalon
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 1/6] ixgbe: put only non-zero initializer in definition Bruce Richardson
2014-09-05 16:14   ` De Lara Guarch, Pablo
2014-09-08  7:55   ` Olivier MATZ
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 2/6] mbuf: rename RTE_MBUF_SCATTER_GATHER into RTE_MBUF_REFCNT Bruce Richardson
2014-09-05 16:14   ` De Lara Guarch, Pablo
2014-09-08  8:01   ` Olivier MATZ
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 3/6] mbuf: remove rte_ctrlmbuf Bruce Richardson
2014-09-05 16:15   ` De Lara Guarch, Pablo
2014-09-08  8:21   ` Olivier MATZ
2014-09-09  8:48     ` Richardson, Bruce
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 4/6] mbuf: remove the rte_pktmbuf structure Bruce Richardson
2014-09-04 13:25   ` [dpdk-dev] [PATCH v3 " Bruce Richardson
2014-09-05 16:17     ` De Lara Guarch, Pablo
2014-09-08  8:29     ` Olivier MATZ
2014-09-05 16:15   ` [dpdk-dev] [PATCH v2 " De Lara Guarch, Pablo
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 5/6] mbuf: rename in_port to just port Bruce Richardson
2014-09-05 16:16   ` De Lara Guarch, Pablo
2014-09-08  8:45   ` Olivier MATZ
2014-08-28 15:42 ` [dpdk-dev] [PATCH v2 6/6] mbuf: flatten struct vlan_macip into mbuf struct Bruce Richardson
2014-09-05 16:21   ` De Lara Guarch, Pablo
2014-09-07 19:40     ` Richardson, Bruce [this message]
2014-09-08  9:07   ` Olivier MATZ
2014-09-09 14:40     ` [dpdk-dev] [PATCH v3 " Bruce Richardson
2014-09-09 15:20       ` De Lara Guarch, Pablo
2014-09-08 12:32 ` [dpdk-dev] [PATCH 0/6] Mbuf structure Rework, part 1 Olivier MATZ
2014-09-09  9:03   ` Richardson, Bruce

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=59AF69C657FD0841A61C55336867B5B0343EF578@IRSMSX103.ger.corp.intel.com \
    --to=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --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).