DPDK patches and discussions
 help / color / mirror / Atom feed
From: Joyce Kong <joyce.kong@arm.com>
To: dev@dpdk.org
Cc: nd@arm.com, jerinj@marvell.com, konstantin.ananyev@intel.com,
	chaozhu@linux.vnet.ibm.com, bruce.richardson@intel.com,
	thomas@monjalon.net, hemant.agrawal@nxp.com,
	honnappa.nagarahalli@arm.com, gavin.hu@arm.com, stable@dpdk.org
Subject: [dpdk-dev] [PATCH v4 2/3] test/rwlock: add perf test case on all available cores
Date: Wed, 20 Mar 2019 14:25:08 +0800	[thread overview]
Message-ID: <1553063109-57574-3-git-send-email-joyce.kong@arm.com> (raw)
Message-ID: <20190320062508.heEeGxpXmUr8Gw65ZryxeFoiLxYfs79-R2IW60HWBrQ@z> (raw)
In-Reply-To: <1553063109-57574-1-git-send-email-joyce.kong@arm.com>
In-Reply-To: <1544672265-219262-2-git-send-email-joyce.kong@arm.com>

Add performance test on all available cores to benchmark
the scaling up performance of rwlock.

Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org

Suggested-by: Gavin Hu <gavin.hu@arm.com>
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
---
 app/test/test_rwlock.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/app/test/test_rwlock.c b/app/test/test_rwlock.c
index 224f0de..f1c5f40 100644
--- a/app/test/test_rwlock.c
+++ b/app/test/test_rwlock.c
@@ -36,6 +36,7 @@
 
 static rte_rwlock_t sl;
 static rte_rwlock_t sl_tab[RTE_MAX_LCORE];
+static rte_atomic32_t synchro;
 
 enum {
 	LC_TYPE_RDLOCK,
@@ -83,6 +84,77 @@ test_rwlock_per_core(__attribute__((unused)) void *arg)
 	return 0;
 }
 
+static rte_rwlock_t lk = RTE_RWLOCK_INITIALIZER;
+static volatile uint64_t rwlock_data;
+static uint64_t lock_count[RTE_MAX_LCORE] = {0};
+
+#define TIME_MS 100
+#define TEST_RWLOCK_DEBUG 0
+
+static int
+load_loop_fn(__attribute__((unused)) void *arg)
+{
+	uint64_t time_diff = 0, begin;
+	uint64_t hz = rte_get_timer_hz();
+	uint64_t lcount = 0;
+	const unsigned int lcore = rte_lcore_id();
+
+	/* wait synchro for slaves */
+	if (lcore != rte_get_master_lcore())
+		while (rte_atomic32_read(&synchro) == 0)
+			;
+
+	begin = rte_rdtsc_precise();
+	while (time_diff < hz * TIME_MS / 1000) {
+		rte_rwlock_write_lock(&lk);
+		++rwlock_data;
+		rte_rwlock_write_unlock(&lk);
+
+		rte_rwlock_read_lock(&lk);
+		if (TEST_RWLOCK_DEBUG & !(lcount % 100))
+			printf("Core [%u] rwlock_data = %"PRIu64"\n",
+					lcore, rwlock_data);
+		rte_rwlock_read_unlock(&lk);
+
+		lcount++;
+		/* delay to make lock duty cycle slightly realistic */
+		rte_pause();
+		time_diff = rte_rdtsc_precise() - begin;
+	}
+
+	lock_count[lcore] = lcount;
+	return 0;
+}
+
+static int
+test_rwlock_perf(void)
+{
+	unsigned int i;
+	uint64_t total = 0;
+
+	printf("\nRwlock Perf Test on %u cores...\n", rte_lcore_count());
+
+	/* clear synchro and start slaves */
+	rte_atomic32_set(&synchro, 0);
+	if (rte_eal_mp_remote_launch(load_loop_fn, NULL, SKIP_MASTER) < 0)
+		return -1;
+
+	/* start synchro and launch test on master */
+	rte_atomic32_set(&synchro, 1);
+	load_loop_fn(NULL);
+
+	rte_eal_mp_wait_lcore();
+
+	RTE_LCORE_FOREACH(i) {
+		printf("Core [%u] count = %"PRIu64"\n", i, lock_count[i]);
+		total += lock_count[i];
+	}
+
+	printf("Total count = %"PRIu64"\n", total);
+
+	return 0;
+}
+
 /*
  * - There is a global rwlock and a table of rwlocks (one per lcore).
  *
@@ -132,6 +204,9 @@ rwlock_test1(void)
 
 	rte_eal_mp_wait_lcore();
 
+	if (test_rwlock_perf() < 0)
+		return -1;
+
 	return 0;
 }
 
-- 
2.7.4


  parent reply	other threads:[~2019-03-20  6:25 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-13  3:37 [dpdk-dev] [PATCH v1 0/2] reimplement rwlock and add relevant perf test case Joyce Kong
2018-12-13  3:37 ` [dpdk-dev] [PATCH v1 1/2] test/rwlock: add " Joyce Kong
2018-12-19 23:34   ` Ananyev, Konstantin
2018-12-20  1:01     ` Gavin Hu (Arm Technology China)
2018-12-20  1:45       ` Honnappa Nagarahalli
2019-03-14 13:15   ` [dpdk-dev] [PATCH v3 0/3] rwlock: reimplement rwlock with atomic and add relevant " Joyce Kong
2019-03-14 13:15     ` Joyce Kong
2019-03-14 13:15   ` [dpdk-dev] [PATCH v3 1/3] rwlock: reimplement with atomic builtins Joyce Kong
2019-03-14 13:15     ` Joyce Kong
2019-03-14 15:54     ` Stephen Hemminger
2019-03-14 15:54       ` Stephen Hemminger
2019-03-15  3:04       ` Gavin Hu (Arm Technology China)
2019-03-15  3:04         ` Gavin Hu (Arm Technology China)
2019-03-15 11:41     ` Ananyev, Konstantin
2019-03-15 11:41       ` Ananyev, Konstantin
2019-03-19  8:31       ` Gavin Hu (Arm Technology China)
2019-03-19  8:31         ` Gavin Hu (Arm Technology China)
2019-03-14 13:15   ` [dpdk-dev] [PATCH v3 2/3] test/rwlock: add perf test case on all available cores Joyce Kong
2019-03-14 13:15     ` Joyce Kong
2019-03-14 13:15   ` [dpdk-dev] [PATCH v3 3/3] test/rwlock: amortize the cost of getting time Joyce Kong
2019-03-14 13:15     ` Joyce Kong
2019-03-14 15:02     ` Honnappa Nagarahalli
2019-03-14 15:02       ` Honnappa Nagarahalli
2019-03-20  6:25   ` [dpdk-dev] [PATCH v4 0/3] rwlock: reimplement rwlock with atomic and add relevant perf test case Joyce Kong
2019-03-20  6:25     ` Joyce Kong
2019-03-20  6:25   ` [dpdk-dev] [PATCH v4 1/3] rwlock: reimplement with atomic builtins Joyce Kong
2019-03-20  6:25     ` Joyce Kong
2019-03-21 18:43     ` Ananyev, Konstantin
2019-03-21 18:43       ` Ananyev, Konstantin
2019-03-25  9:18       ` Joyce Kong (Arm Technology China)
2019-03-25  9:18         ` Joyce Kong (Arm Technology China)
2019-03-20  6:25   ` Joyce Kong [this message]
2019-03-20  6:25     ` [dpdk-dev] [PATCH v4 2/3] test/rwlock: add perf test case on all available cores Joyce Kong
2019-03-21 18:44     ` Ananyev, Konstantin
2019-03-21 18:44       ` Ananyev, Konstantin
2019-03-20  6:25   ` [dpdk-dev] [PATCH v4 3/3] test/rwlock: amortize the cost of getting time Joyce Kong
2019-03-20  6:25     ` Joyce Kong
2019-03-21 18:44     ` Ananyev, Konstantin
2019-03-21 18:44       ` Ananyev, Konstantin
2019-03-25  9:14   ` [dpdk-dev] [PATCH v5 0/3] rwlock: reimplement rwlock with atomic and add relevant perf test case Joyce Kong
2019-03-25  9:14     ` Joyce Kong
2019-03-28 10:50     ` Thomas Monjalon
2019-03-28 10:50       ` Thomas Monjalon
2019-04-16 14:57     ` Kevin Traynor
2019-04-16 14:57       ` Kevin Traynor
2019-03-25  9:14   ` [dpdk-dev] [PATCH v5 1/3] rwlock: reimplement with atomic builtins Joyce Kong
2019-03-25  9:14     ` Joyce Kong
2019-03-25  9:14   ` [dpdk-dev] [PATCH v5 2/3] test/rwlock: add perf test case on all available cores Joyce Kong
2019-03-25  9:14     ` Joyce Kong
2019-03-25  9:14   ` [dpdk-dev] [PATCH v5 3/3] test/rwlock: amortize the cost of getting time Joyce Kong
2019-03-25  9:14     ` Joyce Kong
2018-12-13  3:37 ` [dpdk-dev] [PATCH v1 2/2] rwlock: reimplement with __atomic builtins Joyce Kong
2018-12-19 23:50   ` Ananyev, Konstantin
2018-12-13  5:27 ` [dpdk-dev] [PATCH v1 0/2] reimplement rwlock and add relevant perf test case Stephen Hemminger
2018-12-14  1:30   ` Gavin Hu (Arm Technology China)
2018-12-17  5:16     ` Honnappa Nagarahalli
2018-12-19 20:37       ` 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=1553063109-57574-3-git-send-email-joyce.kong@arm.com \
    --to=joyce.kong@arm.com \
    --cc=bruce.richardson@intel.com \
    --cc=chaozhu@linux.vnet.ibm.com \
    --cc=dev@dpdk.org \
    --cc=gavin.hu@arm.com \
    --cc=hemant.agrawal@nxp.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=jerinj@marvell.com \
    --cc=konstantin.ananyev@intel.com \
    --cc=nd@arm.com \
    --cc=stable@dpdk.org \
    --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).