From: Gage Eads <gage.eads@intel.com>
To: dev@dpdk.org
Cc: jerin.jacob@caviumnetworks.com, harry.van.haaren@intel.com,
bruce.richardson@intel.com, hemant.agrawal@nxp.com,
nipun.gupta@nxp.com, santosh.shukla@caviumnetworks.com
Subject: [dpdk-dev] [PATCH 0/2] add implicit release disable capability
Date: Wed, 29 Nov 2017 22:20:34 -0600 [thread overview]
Message-ID: <1512015636-31878-1-git-send-email-gage.eads@intel.com> (raw)
This patch set introduces an event device capability for disabling implicit
release -- in which rte_event_dequeue_burst() releases any unreleased,
previously dequeued events -- on a per-port basis. The port configuration
struct is likewise extended with a disable_implicit_release option, for PMDs
that support the capability. If the option is set for a port, the application
is responsible for releasing the port's dequeued events (either with
RTE_EVENT_OP_RELEASE or RTE_EVENT_OP_FORWARD).
This behavior was previously discussed
(http://dpdk.org/ml/archives/dev/2017-November/081037.html) as a way to avoid
flow migration problems when using eventdev with look-aside hardware (such as
cryptodev). For instance, if each worker puts dequeued events in a per-worker
crypto request queue and periodically polls the response queue to forward the
packets, it shouldn't release the events until the crypto operation completes.
By disabling the implicit release, it can dequeue further events and process
them while the crypto operation(s) execute in parallel.
The only PMD that supports this capability is the sw PMD. For all PMDs, the
default port configuration is implicit releases enabled.
The second patch in the series isn't directly related to implicit release,
but the code changes depend on the first patch.
Gage Eads (2):
eventdev: add implicit release disable capability
event/sw: simplify credit scheme
drivers/event/dpaa2/dpaa2_eventdev.c | 2 ++
drivers/event/octeontx/ssovf_evdev.c | 1 +
drivers/event/skeleton/skeleton_eventdev.c | 1 +
drivers/event/sw/sw_evdev.c | 10 +++++---
drivers/event/sw/sw_evdev.h | 1 +
drivers/event/sw/sw_evdev_worker.c | 38 +++++++++++++++---------------
examples/eventdev_pipeline_sw_pmd/main.c | 24 ++++++++++++++++++-
lib/librte_eventdev/rte_eventdev.c | 9 +++++++
lib/librte_eventdev/rte_eventdev.h | 23 +++++++++++++++---
test/test/test_eventdev.c | 9 +++++++
test/test/test_eventdev_sw.c | 20 ++++++++++++++--
11 files changed, 110 insertions(+), 28 deletions(-)
--
2.7.4
next reply other threads:[~2017-11-30 4:20 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-30 4:20 Gage Eads [this message]
2017-11-30 4:20 ` [dpdk-dev] [PATCH 1/2] eventdev: " Gage Eads
2017-12-11 12:36 ` Van Haaren, Harry
2017-12-11 17:39 ` Eads, Gage
2017-12-11 17:56 ` [dpdk-dev] [PATCH v2 " Gage Eads
2017-12-11 17:56 ` [dpdk-dev] [PATCH v2 2/2] event/sw: simplify credit scheme Gage Eads
2017-12-16 8:50 ` [dpdk-dev] [PATCH v2 1/2] eventdev: add implicit release disable capability Jerin Jacob
2017-11-30 4:20 ` [dpdk-dev] [PATCH 2/2] event/sw: simplify credit scheme Gage Eads
2017-12-11 13:42 ` Van Haaren, Harry
2017-12-16 8:54 ` Jerin Jacob
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=1512015636-31878-1-git-send-email-gage.eads@intel.com \
--to=gage.eads@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=harry.van.haaren@intel.com \
--cc=hemant.agrawal@nxp.com \
--cc=jerin.jacob@caviumnetworks.com \
--cc=nipun.gupta@nxp.com \
--cc=santosh.shukla@caviumnetworks.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).