From: Mesut Ali Ergin <mesut.a.ergin@intel.com>
To: beilei.xing@intel.com, qi.z.zhang@intel.com
Cc: dev@dpdk.org, Mesut Ali Ergin <mesut.a.ergin@intel.com>
Subject: [dpdk-dev] [PATCH 0/3] net/i40e: improve rte_flow offload with MARK + RSS
Date: Wed, 15 May 2019 21:28:02 -0700 [thread overview]
Message-ID: <1557980885-183777-1-git-send-email-mesut.a.ergin@intel.com> (raw)
Message-ID: <20190516042802.EDktLM_DX8BiO9R10thBEoGtl0G804eeDvSDF5d4w9o@z> (raw)
Applications using DPDK, including but not limited to OVS DPDK,
utilize rte_flow to benefit from hardware flow offloads. Three
patches in this set improves i40e offload capabilities by
(*) Enhancing Flow Director to support MARK + RSS action combination
(*) Giving applications ability to disable vector RX at runtime, since
Flow Director is not currently supported using the vector RX path
For example, with this patchset, OVS DPDK's existing hw-offload feature
becomes functional using i40e, improving phy-to-phy switching
performance more than 200% for a use case with 1,000,000 UDP flows
switched by 1,000 rules in Open Flow tables.
Mesut Ali Ergin (3):
net/i40e: add support for MARK + RSS action in rte_flow
net/i40e: add runtime option to disable vector rx
net/i40e: fix inadvertent override of vector RX allowance
doc/guides/nics/i40e.rst | 14 +++++++
drivers/net/i40e/i40e_ethdev.c | 70 ++++++++++++++++++++++++++++++++-
drivers/net/i40e/i40e_ethdev.h | 1 +
drivers/net/i40e/i40e_flow.c | 29 ++++++++++++++
drivers/net/i40e/i40e_rxtx.c | 4 ++
drivers/net/i40e/i40e_rxtx_vec_common.h | 4 ++
6 files changed, 121 insertions(+), 1 deletion(-)
--
2.7.4
next reply other threads:[~2019-05-16 4:28 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-16 4:28 Mesut Ali Ergin [this message]
2019-05-16 4:28 ` Mesut Ali Ergin
2019-05-16 4:28 ` [dpdk-dev] [PATCH 1/3] net/i40e: add support for MARK + RSS action in rte_flow Mesut Ali Ergin
2019-05-16 4:28 ` Mesut Ali Ergin
2019-05-22 12:30 ` Zhang, Qi Z
2019-05-16 4:28 ` [dpdk-dev] [PATCH 2/3] net/i40e: add runtime option to disable vector rx Mesut Ali Ergin
2019-05-16 4:28 ` Mesut Ali Ergin
2019-05-16 8:17 ` Maxime Coquelin
2019-05-16 8:17 ` Maxime Coquelin
2019-05-16 21:26 ` Ergin, Mesut A
2019-05-20 8:29 ` Ananyev, Konstantin
2019-05-20 17:53 ` Ergin, Mesut A
2019-05-20 23:11 ` Ananyev, Konstantin
2019-05-21 16:33 ` Ergin, Mesut A
2019-05-21 17:20 ` Ananyev, Konstantin
2019-05-21 20:55 ` Ergin, Mesut A
2019-05-22 11:01 ` Ananyev, Konstantin
2019-05-22 14:05 ` Thomas Monjalon
2019-05-22 14:32 ` Zhang, Qi Z
2019-05-23 13:10 ` Jerin Jacob Kollanukkaran
2019-05-23 17:54 ` Ergin, Mesut A
2019-05-16 4:28 ` [dpdk-dev] [PATCH 3/3] net/i40e: fix inadvertent override of vector RX allowance Mesut Ali Ergin
2019-05-16 4:28 ` Mesut Ali Ergin
2019-05-16 8:17 ` Maxime Coquelin
2019-05-16 8:17 ` Maxime Coquelin
2019-05-16 20:57 ` Ergin, Mesut A
2019-05-22 12:42 ` Zhang, Qi Z
2019-05-23 18:25 ` Ergin, Mesut A
2019-05-24 2:39 ` Zhang, Qi Z
2019-05-24 18:08 ` Ergin, Mesut A
2019-05-25 11:29 ` Zhang, Qi Z
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=1557980885-183777-1-git-send-email-mesut.a.ergin@intel.com \
--to=mesut.a.ergin@intel.com \
--cc=beilei.xing@intel.com \
--cc=dev@dpdk.org \
--cc=qi.z.zhang@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).