details: http://hg.nginx.org/nginx/rev/4f6efabcb09b
branches:
changeset: 6153:4f6efabcb09b
user: Maxim Dounin <mdounin@mdounin.ru>
date: Wed May 20 15:51:56 2015 +0300
description:
The "reuseport" option of the "listen" directive.

When configured, an individual listen socket on a given address is
created for each worker process. This allows to reduce in-kernel lock
contention on configurations with high accept rates, resulting in better
performance. As of now it works on Linux and DragonFly BSD.

Note that on Linux incoming connection requests are currently tied up
to a specific listen socket, and if some sockets are closed, connection
requests will be reset, see https://lwn.net/Articles/542629/. With
nginx, this may happen if the number of worker processes is reduced.
There is no such problem on DragonFly BSD.

Based on previous work by Sepherosa Ziehau and Yingqi Lu.

diffstat:

auto/unix | 10 +++
src/core/ngx_connection.c | 110 ++++++++++++++++++++++++++++++++++++
src/core/ngx_connection.h | 7 ++
src/core/ngx_cycle.c | 11 +++
src/event/ngx_event.c | 6 +
src/event/ngx_event_accept.c | 25 ++++++-
src/http/ngx_http.c | 8 ++
src/http/ngx_http_core_module.c | 13 ++++
src/http/ngx_http_core_module.h | 3 +
src/stream/ngx_stream.c | 4 +
src/stream/ngx_stream.h | 3 +
src/stream/ngx_stream_core_module.c | 12 +++
12 files changed, 206 insertions(+), 6 deletions(-)

diffs (truncated from 426 to 300 lines):

diff --git a/auto/unix b/auto/unix
--- a/auto/unix
+++ b/auto/unix
@@ -308,6 +308,16 @@ ngx_feature_test="setsockopt(0, SOL_SOCK
. auto/feature


+ngx_feature="SO_REUSEPORT"
+ngx_feature_name="NGX_HAVE_REUSEPORT"
+ngx_feature_run=no
+ngx_feature_incs="#include <sys/socket.h>"
+ngx_feature_path=
+ngx_feature_libs=
+ngx_feature_test="setsockopt(0, SOL_SOCKET, SO_REUSEPORT, NULL, 0)"
+. auto/feature
+
+
ngx_feature="SO_ACCEPTFILTER"
ngx_feature_name="NGX_HAVE_DEFERRED_ACCEPT"
ngx_feature_run=no
diff --git a/src/core/ngx_connection.c b/src/core/ngx_connection.c
--- a/src/core/ngx_connection.c
+++ b/src/core/ngx_connection.c
@@ -91,6 +91,43 @@ ngx_create_listening(ngx_conf_t *cf, voi


ngx_int_t
+ngx_clone_listening(ngx_conf_t *cf, ngx_listening_t *ls)
+{
+#if (NGX_HAVE_REUSEPORT)
+
+ ngx_int_t n;
+ ngx_core_conf_t *ccf;
+ ngx_listening_t ols;
+
+ if (!ls->reuseport) {
+ return NGX_OK;
+ }
+
+ ols = *ls;
+
+ ccf = (ngx_core_conf_t *) ngx_get_conf(cf->cycle->conf_ctx,
+ ngx_core_module);
+
+ for (n = 1; n < ccf->worker_processes; n++) {
+
+ /* create a socket for each worker process */
+
+ ls = ngx_array_push(&cf->cycle->listening);
+ if (ls == NULL) {
+ return NGX_ERROR;
+ }
+
+ *ls = ols;
+ ls->worker = n;
+ }
+
+#endif
+
+ return NGX_OK;
+}
+
+
+ngx_int_t
ngx_set_inherited_sockets(ngx_cycle_t *cycle)
{
size_t len;
@@ -106,6 +143,9 @@ ngx_set_inherited_sockets(ngx_cycle_t *c
#if (NGX_HAVE_DEFERRED_ACCEPT && defined TCP_DEFER_ACCEPT)
int timeout;
#endif
+#if (NGX_HAVE_REUSEPORT)
+ int reuseport;
+#endif

ls = cycle->listening.elts;
for (i = 0; i < cycle->listening.nelts; i++) {
@@ -215,6 +255,25 @@ ngx_set_inherited_sockets(ngx_cycle_t *c
#endif
#endif

+#if (NGX_HAVE_REUSEPORT)
+
+ reuseport = 0;
+ olen = sizeof(int);
+
+ if (getsockopt(ls[i].fd, SOL_SOCKET, SO_REUSEPORT,
+ (void *) &reuseport, &olen)
+ == -1)
+ {
+ ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_socket_errno,
+ "getsockopt(SO_REUSEPORT) %V failed, ignored",
+ &ls[i].addr_text);
+
+ } else {
+ ls[i].reuseport = reuseport ? 1 : 0;
+ }
+
+#endif
+
#if (NGX_HAVE_TCP_FASTOPEN)

olen = sizeof(int);
@@ -332,6 +391,31 @@ ngx_open_listening_sockets(ngx_cycle_t *
continue;
}

+#if (NGX_HAVE_REUSEPORT)
+
+ if (ls[i].add_reuseport) {
+
+ /*
+ * to allow transition from a socket without SO_REUSEPORT
+ * to multiple sockets with SO_REUSEPORT, we have to set
+ * SO_REUSEPORT on the old socket before opening new ones
+ */
+
+ int reuseport = 1;
+
+ if (setsockopt(ls[i].fd, SOL_SOCKET, SO_REUSEPORT,
+ (const void *) &reuseport, sizeof(int))
+ == -1)
+ {
+ ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_socket_errno,
+ "setsockopt(SO_REUSEPORT) %V failed, ignored",
+ &ls[i].addr_text);
+ }
+
+ ls[i].add_reuseport = 0;
+ }
+#endif
+
if (ls[i].fd != (ngx_socket_t) -1) {
continue;
}
@@ -370,6 +454,32 @@ ngx_open_listening_sockets(ngx_cycle_t *
return NGX_ERROR;
}

+#if (NGX_HAVE_REUSEPORT)
+
+ if (ls[i].reuseport) {
+ int reuseport;
+
+ reuseport = 1;
+
+ if (setsockopt(s, SOL_SOCKET, SO_REUSEPORT,
+ (const void *) &reuseport, sizeof(int))
+ == -1)
+ {
+ ngx_log_error(NGX_LOG_EMERG, log, ngx_socket_errno,
+ "setsockopt(SO_REUSEPORT) %V failed, ignored",
+ &ls[i].addr_text);
+
+ if (ngx_close_socket(s) == -1) {
+ ngx_log_error(NGX_LOG_EMERG, log, ngx_socket_errno,
+ ngx_close_socket_n " %V failed",
+ &ls[i].addr_text);
+ }
+
+ return NGX_ERROR;
+ }
+ }
+#endif
+
#if (NGX_HAVE_INET6 && defined IPV6_V6ONLY)

if (ls[i].sockaddr->sa_family == AF_INET6) {
diff --git a/src/core/ngx_connection.h b/src/core/ngx_connection.h
--- a/src/core/ngx_connection.h
+++ b/src/core/ngx_connection.h
@@ -51,6 +51,8 @@ struct ngx_listening_s {
ngx_listening_t *previous;
ngx_connection_t *connection;

+ ngx_uint_t worker;
+
unsigned open:1;
unsigned remain:1;
unsigned ignore:1;
@@ -66,6 +68,10 @@ struct ngx_listening_s {
#if (NGX_HAVE_INET6 && defined IPV6_V6ONLY)
unsigned ipv6only:1;
#endif
+#if (NGX_HAVE_REUSEPORT)
+ unsigned reuseport:1;
+ unsigned add_reuseport:1;
+#endif
unsigned keepalive:2;

#if (NGX_HAVE_DEFERRED_ACCEPT)
@@ -203,6 +209,7 @@ struct ngx_connection_s {

ngx_listening_t *ngx_create_listening(ngx_conf_t *cf, void *sockaddr,
socklen_t socklen);
+ngx_int_t ngx_clone_listening(ngx_conf_t *cf, ngx_listening_t *ls);
ngx_int_t ngx_set_inherited_sockets(ngx_cycle_t *cycle);
ngx_int_t ngx_open_listening_sockets(ngx_cycle_t *cycle);
void ngx_configure_listening_sockets(ngx_cycle_t *cycle);
diff --git a/src/core/ngx_cycle.c b/src/core/ngx_cycle.c
--- a/src/core/ngx_cycle.c
+++ b/src/core/ngx_cycle.c
@@ -493,6 +493,10 @@ ngx_init_cycle(ngx_cycle_t *old_cycle)
continue;
}

+ if (ls[i].remain) {
+ continue;
+ }
+
if (ngx_cmp_sockaddr(nls[n].sockaddr, nls[n].socklen,
ls[i].sockaddr, ls[i].socklen, 1)
== NGX_OK)
@@ -540,6 +544,13 @@ ngx_init_cycle(ngx_cycle_t *old_cycle)
nls[n].add_deferred = 1;
}
#endif
+
+#if (NGX_HAVE_REUSEPORT)
+ if (nls[n].reuseport && !ls[i].reuseport) {
+ nls[n].add_reuseport = 1;
+ }
+#endif
+
break;
}
}
diff --git a/src/event/ngx_event.c b/src/event/ngx_event.c
--- a/src/event/ngx_event.c
+++ b/src/event/ngx_event.c
@@ -725,6 +725,12 @@ ngx_event_process_init(ngx_cycle_t *cycl
ls = cycle->listening.elts;
for (i = 0; i < cycle->listening.nelts; i++) {

+#if (NGX_HAVE_REUSEPORT)
+ if (ls[i].reuseport && ls[i].worker != ngx_worker) {
+ continue;
+ }
+#endif
+
c = ngx_get_connection(ls[i].fd, cycle->log);

if (c == NULL) {
diff --git a/src/event/ngx_event_accept.c b/src/event/ngx_event_accept.c
--- a/src/event/ngx_event_accept.c
+++ b/src/event/ngx_event_accept.c
@@ -11,7 +11,7 @@


static ngx_int_t ngx_enable_accept_events(ngx_cycle_t *cycle);
-static ngx_int_t ngx_disable_accept_events(ngx_cycle_t *cycle);
+static ngx_int_t ngx_disable_accept_events(ngx_cycle_t *cycle, ngx_uint_t all);
static void ngx_close_accepted_connection(ngx_connection_t *c);


@@ -109,7 +109,7 @@ ngx_event_accept(ngx_event_t *ev)
}

if (err == NGX_EMFILE || err == NGX_ENFILE) {
- if (ngx_disable_accept_events((ngx_cycle_t *) ngx_cycle)
+ if (ngx_disable_accept_events((ngx_cycle_t *) ngx_cycle, 1)
!= NGX_OK)
{
return;
@@ -390,7 +390,7 @@ ngx_trylock_accept_mutex(ngx_cycle_t *cy
"accept mutex lock failed: %ui", ngx_accept_mutex_held);

if (ngx_accept_mutex_held) {
- if (ngx_disable_accept_events(cycle) == NGX_ERROR) {
+ if (ngx_disable_accept_events(cycle, 0) == NGX_ERROR) {
return NGX_ERROR;
}

@@ -413,7 +413,7 @@ ngx_enable_accept_events(ngx_cycle_t *cy

c = ls[i].connection;

- if (c->read->active) {
+ if (c == NULL || c->read->active) {
continue;
}

@@ -427,7 +427,7 @@ ngx_enable_accept_events(ngx_cycle_t *cy


static ngx_int_t
-ngx_disable_accept_events(ngx_cycle_t *cycle)
+ngx_disable_accept_events(ngx_cycle_t *cycle, ngx_uint_t all)
{
ngx_uint_t i;
ngx_listening_t *ls;
@@ -438,10 +438,23 @@ ngx_disable_accept_events(ngx_cycle_t *c

c = ls[i].connection;

- if (!c->read->active) {
+ if (c == NULL || !c->read->active) {
continue;
}


_______________________________________________
nginx-devel mailing list
nginx-devel@nginx.org
http://mailman.nginx.org/mailman/listinfo/nginx-devel