DPDK patches and discussions
 help / color / mirror / Atom feed
From: Phil Yang <phil.yang@arm.com>
To: dev@dpdk.org, thomas@monjalon.net
Cc: david.hunt@intel.com, reshma.pattan@intel.com, gavin.hu@arm.com,
	honnappa.nagarahalli@arm.com, phil.yang@arm.com, nd@arm.com
Subject: [dpdk-dev] [PATCH v4 2/3] test/distributor: replace sync builtins with atomic builtins
Date: Mon,  8 Apr 2019 11:02:30 +0800	[thread overview]
Message-ID: <1554692551-28275-3-git-send-email-phil.yang@arm.com> (raw)
Message-ID: <20190408030230.oJ6s15FIT1Sek_HyjoHxIiCJgtnw7Qi64UXN6nYD4GA@z> (raw)
In-Reply-To: <1554692551-28275-1-git-send-email-phil.yang@arm.com>
In-Reply-To: <1546508946-12552-1-git-send-email-phil.yang@arm.com>

'__sync' built-in functions are deprecated, should use the '__atomic'
built-in instead. the sync built-in functions are full barriers, while
atomic built-in functions offer less restrictive one-way barriers,
which help performance.

Here is the example test result on TX2:
sudo ./arm64-armv8a-linuxapp-gcc/app/test -l 112-139 \
-n 4 --socket-mem=1024,1024 -- -i
RTE>>distributor_perf_autotest

*** distributor_perf_autotest without this patch ***
==== Cache line switch test ===
Time for 33554432 iterations = 1519202730 ticks
Ticks per iteration = 45

*** distributor_perf_autotest with this patch ***
==== Cache line switch test ===
Time for 33554432 iterations = 1251715496 ticks
Ticks per iteration = 37

Less ticks needed for the cache line switch test. It got 17% of
performance improvement.

Signed-off-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 app/test/test_distributor.c      | 7 ++++---
 app/test/test_distributor_perf.c | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/app/test/test_distributor.c b/app/test/test_distributor.c
index 98919ec..0364637 100644
--- a/app/test/test_distributor.c
+++ b/app/test/test_distributor.c
@@ -62,7 +62,7 @@ handle_work(void *arg)
 	struct worker_params *wp = arg;
 	struct rte_distributor *db = wp->dist;
 	unsigned int count = 0, num = 0;
-	unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+	unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
 	int i;
 
 	for (i = 0; i < 8; i++)
@@ -270,7 +270,7 @@ handle_work_with_free_mbufs(void *arg)
 	unsigned int count = 0;
 	unsigned int i;
 	unsigned int num = 0;
-	unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+	unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
 
 	for (i = 0; i < 8; i++)
 		buf[i] = NULL;
@@ -343,7 +343,8 @@ handle_work_for_shutdown_test(void *arg)
 	unsigned int total = 0;
 	unsigned int i;
 	unsigned int returned = 0;
-	const unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+	const unsigned int id = __atomic_fetch_add(&worker_idx, 1,
+			__ATOMIC_RELAXED);
 
 	num = rte_distributor_get_pkt(d, id, buf, buf, num);
 
diff --git a/app/test/test_distributor_perf.c b/app/test/test_distributor_perf.c
index edf1998..89b28f0 100644
--- a/app/test/test_distributor_perf.c
+++ b/app/test/test_distributor_perf.c
@@ -111,7 +111,7 @@ handle_work(void *arg)
 	unsigned int count = 0;
 	unsigned int num = 0;
 	int i;
-	unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+	unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
 	struct rte_mbuf *buf[8] __rte_cache_aligned;
 
 	for (i = 0; i < 8; i++)
-- 
2.7.4


  parent reply	other threads:[~2019-04-08  3:01 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-03  9:49 [dpdk-dev] [PATCH] packet_ordering: " Phil Yang
2019-03-28 18:42 ` Thomas Monjalon
2019-03-28 18:42   ` Thomas Monjalon
2019-03-29  1:34   ` Phil Yang (Arm Technology China)
2019-03-29  1:34     ` Phil Yang (Arm Technology China)
2019-03-29 10:56 ` [dpdk-dev] [PATCH v2 0/3] example and test cases optimizations Phil Yang
2019-03-29 10:56   ` Phil Yang
2019-03-29 10:56 ` [dpdk-dev] [PATCH v2 1/3] packet_ordering: add statistics for each worker thread Phil Yang
2019-03-29 10:56   ` Phil Yang
2019-03-29 16:39   ` Pattan, Reshma
2019-03-29 16:39     ` Pattan, Reshma
2019-03-30 16:55     ` Phil Yang (Arm Technology China)
2019-03-30 16:55       ` Phil Yang (Arm Technology China)
2019-04-01 12:58       ` Pattan, Reshma
2019-04-01 12:58         ` Pattan, Reshma
2019-04-02  3:33         ` Phil Yang (Arm Technology China)
2019-04-02  3:33           ` Phil Yang (Arm Technology China)
2019-03-29 10:56 ` [dpdk-dev] [PATCH v2 2/3] test/distributor: replace sync builtins with atomic builtins Phil Yang
2019-03-29 10:56   ` Phil Yang
2019-04-01 16:24   ` Honnappa Nagarahalli
2019-04-01 16:24     ` Honnappa Nagarahalli
2019-04-02  3:43     ` Phil Yang (Arm Technology China)
2019-04-02  3:43       ` Phil Yang (Arm Technology China)
2019-03-29 10:56 ` [dpdk-dev] [PATCH v2 3/3] test/ring_perf: " Phil Yang
2019-03-29 10:56   ` Phil Yang
2019-04-01 16:24   ` Honnappa Nagarahalli
2019-04-01 16:24     ` Honnappa Nagarahalli
2019-04-03  6:59 ` [dpdk-dev] [PATCH v3 0/3] example and test cases optimizations Phil Yang
2019-04-03  6:59   ` Phil Yang
2019-04-03  6:59   ` [dpdk-dev] [PATCH v3 1/3] packet_ordering: add statistics for each worker thread Phil Yang
2019-04-03  6:59     ` Phil Yang
2019-04-04 23:24     ` Thomas Monjalon
2019-04-04 23:24       ` Thomas Monjalon
2019-04-08  4:04       ` Phil Yang (Arm Technology China)
2019-04-08  4:04         ` Phil Yang (Arm Technology China)
2019-04-03  6:59   ` [dpdk-dev] [PATCH v3 2/3] test/distributor: replace sync builtins with atomic builtins Phil Yang
2019-04-03  6:59     ` Phil Yang
2019-04-04 15:30     ` Honnappa Nagarahalli
2019-04-04 15:30       ` Honnappa Nagarahalli
2019-04-03  6:59   ` [dpdk-dev] [PATCH v3 3/3] test/ring_perf: " Phil Yang
2019-04-03  6:59     ` Phil Yang
2019-04-08  3:02 ` [dpdk-dev] [PATCH v4 0/3] example and test cases optimizations Phil Yang
2019-04-08  3:02   ` Phil Yang
2019-07-04 20:15   ` Thomas Monjalon
2019-07-05  3:19     ` Phil Yang (Arm Technology China)
2019-07-08 14:38   ` Thomas Monjalon
2019-04-08  3:02 ` [dpdk-dev] [PATCH v4 1/3] packet_ordering: add statistics for each worker thread Phil Yang
2019-04-08  3:02   ` Phil Yang
2019-04-08  3:02 ` Phil Yang [this message]
2019-04-08  3:02   ` [dpdk-dev] [PATCH v4 2/3] test/distributor: replace sync builtins with atomic builtins Phil Yang
2019-04-10 14:05   ` Hunt, David
2019-04-10 14:05     ` Hunt, David
2019-04-11 11:31     ` Phil Yang (Arm Technology China)
2019-04-11 11:31       ` Phil Yang (Arm Technology China)
2019-04-08  3:02 ` [dpdk-dev] [PATCH v4 3/3] test/ring_perf: " Phil Yang
2019-04-08  3:02   ` Phil Yang

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=1554692551-28275-3-git-send-email-phil.yang@arm.com \
    --to=phil.yang@arm.com \
    --cc=david.hunt@intel.com \
    --cc=dev@dpdk.org \
    --cc=gavin.hu@arm.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=nd@arm.com \
    --cc=reshma.pattan@intel.com \
    --cc=thomas@monjalon.net \
    /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).