From: Ilya Maximets <i.maximets@samsung.com>
To: dev@dpdk.org, Huawei Xie <huawei.xie@intel.com>,
Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Dyasly Sergey <s.dyasly@samsung.com>,
Ilya Maximets <i.maximets@samsung.com>
Subject: [dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst().
Date: Wed, 24 Feb 2016 14:47:15 +0300 [thread overview]
Message-ID: <1456314438-4021-1-git-send-email-i.maximets@samsung.com> (raw)
Implementation of rte_vhost_enqueue_burst() based on lockless ring-buffer
algorithm and contains almost all to be thread-safe, but it's not.
This set adds required changes.
First patch in set is a standalone patch that fixes many times discussed
issue with barriers on different architectures.
Second and third adds fixes to make rte_vhost_enqueue_burst thread safe.
version 3:
* Rebased on top of current master.
version 2:
* Documentation patch dropped. Other patches of series still
may be merged to fix existing issues and keep code in
consistent state for the future.
* buf_vec field of struct vhost_virtqueue marked as deprecated.
Ilya Maximets (3):
vhost: use SMP barriers instead of compiler ones.
vhost: make buf vector for scatter RX local.
vhost: avoid reordering of used->idx and last_used_idx updating.
doc/guides/rel_notes/deprecation.rst | 1 +
lib/librte_vhost/rte_virtio_net.h | 2 +-
lib/librte_vhost/vhost_rxtx.c | 71 ++++++++++++++++++++----------------
3 files changed, 42 insertions(+), 32 deletions(-)
--
2.5.0
next reply other threads:[~2016-02-24 11:47 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-24 11:47 Ilya Maximets [this message]
2016-02-24 11:47 ` [dpdk-dev] [PATCH RFC v3 1/3] vhost: use SMP barriers instead of compiler ones Ilya Maximets
2016-03-18 10:08 ` Xie, Huawei
2016-03-18 10:23 ` Ilya Maximets
2016-03-18 10:27 ` Xie, Huawei
2016-03-18 10:39 ` Ilya Maximets
2016-03-18 10:47 ` Xie, Huawei
2016-03-18 11:00 ` Ilya Maximets
[not found] ` <C37D651A908B024F974696C65296B57B4C67825C@SHSMSX101.ccr.corp.intel.com>
[not found] ` <56EBE9AE.9070400@samsung.com>
[not found] ` <56EBF256.8040409@samsung.com>
2016-03-18 12:28 ` Ilya Maximets
2016-03-18 12:23 ` [dpdk-dev] [PATCH v4] " Ilya Maximets
2016-03-18 12:41 ` Yuanhan Liu
2016-03-21 4:49 ` Ilya Maximets
2016-03-21 14:07 ` Ananyev, Konstantin
2016-03-21 17:25 ` Xie, Huawei
2016-03-21 17:36 ` Ananyev, Konstantin
2016-03-23 14:07 ` Xie, Huawei
2016-03-31 13:46 ` Thomas Monjalon
2016-02-24 11:47 ` [dpdk-dev] [PATCH RFC v3 2/3] vhost: make buf vector for scatter RX local Ilya Maximets
2016-02-24 11:47 ` [dpdk-dev] [PATCH RFC v3 3/3] vhost: avoid reordering of used->idx and last_used_idx updating Ilya Maximets
2016-03-17 15:29 ` [dpdk-dev] [PATCH RFC v3 0/3] Thread safe rte_vhost_enqueue_burst() Thomas Monjalon
2016-03-18 8:00 ` Yuanhan Liu
2016-03-18 8:09 ` Thomas Monjalon
2016-03-18 9:16 ` Yuanhan Liu
2016-03-18 9:34 ` Thomas Monjalon
2016-03-18 9:46 ` Yuanhan Liu
2016-03-18 9:55 ` Ilya Maximets
2016-03-18 10:10 ` Xie, Huawei
2016-03-18 10:24 ` 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=1456314438-4021-1-git-send-email-i.maximets@samsung.com \
--to=i.maximets@samsung.com \
--cc=dev@dpdk.org \
--cc=huawei.xie@intel.com \
--cc=s.dyasly@samsung.com \
--cc=yuanhan.liu@linux.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).