DPDK patches and discussions
 help / color / mirror / Atom feed
From: David Marchand <david.marchand@redhat.com>
To: dev@dpdk.org
Cc: thomas@monjalon.net, stephen@networkplumber.org,
	luca.boccassi@gmail.com, stable@dpdk.org,
	Luca Boccassi <bluca@debian.org>,
	Chengwen Feng <fengchengwen@huawei.com>,
	Tyler Retzlaff <roretzla@linux.microsoft.com>
Subject: [PATCH v4] eal/unix: optimize thread creation
Date: Mon,  4 Nov 2024 09:57:08 +0100	[thread overview]
Message-ID: <20241104085708.3596816-1-david.marchand@redhat.com> (raw)
In-Reply-To: <20241102100839.2325651-1-david.marchand@redhat.com>

Setting the cpu affinity of the child thread from the parent thread is
racy when using pthread_setaffinity_np, as the child thread may start
running and initialize before affinity is set.

On the other hand, setting the cpu affinity from the child thread itself
may fail, so the parent thread waits for the child thread to report
whether this call succeeded.

This synchronisation point resulted in a significant slow down of
rte_thread_create() (as seen in the lcores_autotest unit tests, in OBS
for some ARM systems).

Another option for setting cpu affinity is to use the not portable
pthread_attr_setaffinity_np available in FreeBSD and glibc,
but not available in musl.

Fixes: b28c6196b132 ("eal/unix: fix thread creation")
Cc: stable@dpdk.org

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Luca Boccassi <bluca@debian.org>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Chengwen Feng <fengchengwen@huawei.com>
---
Changes since v3:
- since _np symbols are in (non standard header) pthread_np.h on FreeBSD,
  and since this header is unconditionnally included in rte_os.h,
  assumed availability of pthread_attr_setaffinity_np (added in 8.0),

Changes since v2:
- added pthread_attr_setaffinity_np() detection,

Changes since v1:
- fixed build with FreeBSD,

---
 lib/eal/unix/meson.build  |  5 +++++
 lib/eal/unix/rte_thread.c | 25 +++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/lib/eal/unix/meson.build b/lib/eal/unix/meson.build
index cc7d67dd32..f1eb82e16a 100644
--- a/lib/eal/unix/meson.build
+++ b/lib/eal/unix/meson.build
@@ -11,3 +11,8 @@ sources += files(
         'eal_unix_timer.c',
         'rte_thread.c',
 )
+
+if is_freebsd or cc.has_function('pthread_attr_setaffinity_np', args: '-D_GNU_SOURCE',
+                                 prefix : '#include <pthread.h>')
+    cflags += '-DRTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP'
+endif
diff --git a/lib/eal/unix/rte_thread.c b/lib/eal/unix/rte_thread.c
index 1b4c73f58e..ea629c2065 100644
--- a/lib/eal/unix/rte_thread.c
+++ b/lib/eal/unix/rte_thread.c
@@ -19,6 +19,7 @@ struct eal_tls_key {
 	pthread_key_t thread_index;
 };
 
+#ifndef RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP
 struct thread_start_context {
 	rte_thread_func thread_func;
 	void *thread_args;
@@ -28,6 +29,7 @@ struct thread_start_context {
 	int wrapper_ret;
 	bool wrapper_done;
 };
+#endif
 
 static int
 thread_map_priority_to_os_value(enum rte_thread_priority eal_pri, int *os_pri,
@@ -88,6 +90,7 @@ thread_map_os_priority_to_eal_priority(int policy, int os_pri,
 	return 0;
 }
 
+#ifndef RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP
 static void *
 thread_start_wrapper(void *arg)
 {
@@ -113,6 +116,7 @@ thread_start_wrapper(void *arg)
 
 	return (void *)(uintptr_t)thread_func(thread_args);
 }
+#endif
 
 int
 rte_thread_create(rte_thread_t *thread_id,
@@ -126,6 +130,7 @@ rte_thread_create(rte_thread_t *thread_id,
 		.sched_priority = 0,
 	};
 	int policy = SCHED_OTHER;
+#ifndef RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP
 	struct thread_start_context ctx = {
 		.thread_func = thread_func,
 		.thread_args = args,
@@ -134,6 +139,7 @@ rte_thread_create(rte_thread_t *thread_id,
 		.wrapper_mutex = PTHREAD_MUTEX_INITIALIZER,
 		.wrapper_cond = PTHREAD_COND_INITIALIZER,
 	};
+#endif
 
 	if (thread_attr != NULL) {
 		ret = pthread_attr_init(&attr);
@@ -144,6 +150,16 @@ rte_thread_create(rte_thread_t *thread_id,
 
 		attrp = &attr;
 
+#ifdef RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP
+		if (CPU_COUNT(&thread_attr->cpuset) > 0) {
+			ret = pthread_attr_setaffinity_np(attrp, sizeof(thread_attr->cpuset),
+				&thread_attr->cpuset);
+			if (ret != 0) {
+				EAL_LOG(DEBUG, "pthread_attr_setaffinity_np failed");
+				goto cleanup;
+			}
+		}
+#endif
 		/*
 		 * Set the inherit scheduler parameter to explicit,
 		 * otherwise the priority attribute is ignored.
@@ -178,6 +194,14 @@ rte_thread_create(rte_thread_t *thread_id,
 		}
 	}
 
+#ifdef RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP
+	ret = pthread_create((pthread_t *)&thread_id->opaque_id, attrp,
+		(void *)(void *)thread_func, args);
+	if (ret != 0) {
+		EAL_LOG(DEBUG, "pthread_create failed");
+		goto cleanup;
+	}
+#else /* !RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP */
 	ret = pthread_create((pthread_t *)&thread_id->opaque_id, attrp,
 		thread_start_wrapper, &ctx);
 	if (ret != 0) {
@@ -193,6 +217,7 @@ rte_thread_create(rte_thread_t *thread_id,
 
 	if (ret != 0)
 		rte_thread_join(*thread_id, NULL);
+#endif /* RTE_EAL_PTHREAD_ATTR_SETAFFINITY_NP */
 
 cleanup:
 	if (attrp != NULL)
-- 
2.46.2


  parent reply	other threads:[~2024-11-04  8:57 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-02 10:08 [PATCH] eal/unix: optimize thread creation with glibc David Marchand
2024-11-02 11:32 ` [PATCH v2] " David Marchand
2024-11-02 12:36   ` Luca Boccassi
2024-11-02 19:58 ` [PATCH] " Stephen Hemminger
2024-11-03 10:37   ` David Marchand
2024-11-03 11:25 ` [PATCH v3] " David Marchand
2024-11-03 16:10   ` Stephen Hemminger
2024-11-04  0:19   ` fengchengwen
2024-11-04  8:57 ` David Marchand [this message]
2024-11-04 17:12   ` [PATCH v4] eal/unix: optimize thread creation David Marchand

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=20241104085708.3596816-1-david.marchand@redhat.com \
    --to=david.marchand@redhat.com \
    --cc=bluca@debian.org \
    --cc=dev@dpdk.org \
    --cc=fengchengwen@huawei.com \
    --cc=luca.boccassi@gmail.com \
    --cc=roretzla@linux.microsoft.com \
    --cc=stable@dpdk.org \
    --cc=stephen@networkplumber.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).