libceph: tcp_nodelay support

TCP_NODELAY socket option set on connection sockets,
disables Nagle’s algorithm and improves latency characteristics.
tcp_nodelay(default)/notcp_nodelay option flags provided to
enable/disable setting the socket option.

Signed-off-by: Chaitanya Huilgol <chaitanya.huilgol@sandisk.com>
[idryomov@redhat.com: NO_TCP_NODELAY -> TCP_NODELAY, minor adjustments]
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>

include/linux/ceph/libceph.h

@@ -30,8 +30,9 @@
 #define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
 #define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
 #define CEPH_OPT_NOMSGAUTH	  (1<<4) /* not require cephx message signature */
+#define CEPH_OPT_TCP_NODELAY	  (1<<5) /* TCP_NODELAY on TCP sockets */
 
-#define CEPH_OPT_DEFAULT   (0)
+#define CEPH_OPT_DEFAULT   (CEPH_OPT_TCP_NODELAY)
 
 #define ceph_set_opt(client, opt) \
 	(client)->options->flags |= CEPH_OPT_##opt;

include/linux/ceph/messenger.h

@@ -57,6 +57,7 @@ struct ceph_messenger {
 
 	atomic_t stopping;
 	bool nocrc;
+	bool tcp_nodelay;
 
 	/*
 	 * the global_seq counts connections i (attempt to) initiate
@@ -264,7 +265,8 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr,
 			struct ceph_entity_addr *myaddr,
 			u64 supported_features,
 			u64 required_features,
-			bool nocrc);
+			bool nocrc,
+			bool tcp_nodelay);
 
 extern void ceph_con_init(struct ceph_connection *con, void *private,
 			const struct ceph_connection_operations *ops,

net/ceph/ceph_common.c

@@ -239,6 +239,8 @@ enum {
 	Opt_nocrc,
 	Opt_cephx_require_signatures,
 	Opt_nocephx_require_signatures,
+	Opt_tcp_nodelay,
+	Opt_notcp_nodelay,
 };
 
 static match_table_t opt_tokens = {
@@ -259,6 +261,8 @@ static match_table_t opt_tokens = {
 	{Opt_nocrc, "nocrc"},
 	{Opt_cephx_require_signatures, "cephx_require_signatures"},
 	{Opt_nocephx_require_signatures, "nocephx_require_signatures"},
+	{Opt_tcp_nodelay, "tcp_nodelay"},
+	{Opt_notcp_nodelay, "notcp_nodelay"},
 	{-1, NULL}
 };
 
@@ -457,6 +461,7 @@ ceph_parse_options(char *options, const char *dev_name,
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
+
 		case Opt_cephx_require_signatures:
 			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
 			break;
@@ -464,6 +469,13 @@ ceph_parse_options(char *options, const char *dev_name,
 			opt->flags |= CEPH_OPT_NOMSGAUTH;
 			break;
 
+		case Opt_tcp_nodelay:
+			opt->flags |= CEPH_OPT_TCP_NODELAY;
+			break;
+		case Opt_notcp_nodelay:
+			opt->flags &= ~CEPH_OPT_TCP_NODELAY;
+			break;
+
 		default:
 			BUG_ON(token);
 		}
@@ -518,10 +530,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
+
 	ceph_messenger_init(&client->msgr, myaddr,
 		client->supported_features,
 		client->required_features,
-		ceph_test_opt(client, NOCRC));
+		ceph_test_opt(client, NOCRC),
+		ceph_test_opt(client, TCP_NODELAY));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);

net/ceph/messenger.c

@@ -510,6 +510,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 
+	if (con->msgr->tcp_nodelay) {
+		int optval = 1;
+
+		ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+					(char *)&optval, sizeof(optval));
+		if (ret)
+			pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d",
+			       ret);
+	}
+
 	sk_set_memalloc(sock->sk);
 
 	con->sock = sock;
@@ -2922,7 +2932,8 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 			struct ceph_entity_addr *myaddr,
 			u64 supported_features,
 			u64 required_features,
-			bool nocrc)
+			bool nocrc,
+			bool tcp_nodelay)
 {
 	msgr->supported_features = supported_features;
 	msgr->required_features = required_features;
@@ -2937,6 +2948,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
 	encode_my_addr(msgr);
 	msgr->nocrc = nocrc;
+	msgr->tcp_nodelay = tcp_nodelay;
 
 	atomic_set(&msgr->stopping, 0);