From 3b20fc389705a4c959adebc494578cb99bb8be9e Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Wed, 30 Sep 2015 16:54:07 -0400 Subject: [PATCH 1/3] RDS: Use a single TCP socket for both send and receive. Commit f711a6ae062c ("net/rds: RDS-TCP: Always create a new rds_sock for an incoming connection.") modified rds-tcp so that an incoming SYN would ignore an existing "client" TCP connection which had the local port set to the transient port. The motivation for ignoring the existing "client" connection in f711a6ae was to avoid race conditions and an endless duel of reconnect attempts triggered by a restart/abort of one of the nodes in the TCP connection. However, having separate sockets for active and passive sides is avoidable, and the simpler model of a single TCP socket for both send and receives of all RDS connections associated with that tcp socket makes for easier observability. We avoid the race conditions from f711a6ae by attempting reconnects in rds_conn_shutdown if, and only if, the (new) c_outgoing bit is set for RDS_TRANS_TCP. The c_outgoing bit is initialized in __rds_conn_create(). A side-effect of re-using the client rds_connection for an incoming SYN is the potential of encountering duelling SYNs, i.e., we have an outgoing RDS_CONN_CONNECTING socket when we get the incoming SYN. The logic to arbitrate this criss-crossing SYN exchange in rds_tcp_accept_one() has been modified to emulate the BGP state machine: the smaller IP address should back off from the connection attempt. Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- net/rds/connection.c | 22 ++++++---------------- net/rds/rds.h | 4 +++- net/rds/tcp_listen.c | 20 ++++++++------------ 3 files changed, 17 insertions(+), 29 deletions(-) diff --git a/net/rds/connection.c b/net/rds/connection.c index 49adeef8090c..d4564036a339 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -128,10 +128,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_transport *loop_trans; unsigned long flags; int ret; - struct rds_transport *otrans = trans; - if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) - goto new_conn; rcu_read_lock(); conn = rds_conn_lookup(net, head, laddr, faddr, trans); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && @@ -147,7 +144,6 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (conn) goto out; -new_conn: conn = kmem_cache_zalloc(rds_conn_slab, gfp); if (!conn) { conn = ERR_PTR(-ENOMEM); @@ -207,6 +203,7 @@ new_conn: atomic_set(&conn->c_state, RDS_CONN_DOWN); conn->c_send_gen = 0; + conn->c_outgoing = (is_outgoing ? 1 : 0); conn->c_reconnect_jiffies = 0; INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker); INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker); @@ -243,22 +240,13 @@ new_conn: /* Creating normal conn */ struct rds_connection *found; - if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) - found = NULL; - else - found = rds_conn_lookup(net, head, laddr, faddr, trans); + found = rds_conn_lookup(net, head, laddr, faddr, trans); if (found) { trans->conn_free(conn->c_transport_data); kmem_cache_free(rds_conn_slab, conn); conn = found; } else { - if ((is_outgoing && otrans->t_type == RDS_TRANS_TCP) || - (otrans->t_type != RDS_TRANS_TCP)) { - /* Only the active side should be added to - * reconnect list for TCP. - */ - hlist_add_head_rcu(&conn->c_hash_node, head); - } + hlist_add_head_rcu(&conn->c_hash_node, head); rds_cong_add_conn(conn); rds_conn_count++; } @@ -337,7 +325,9 @@ void rds_conn_shutdown(struct rds_connection *conn) rcu_read_lock(); if (!hlist_unhashed(&conn->c_hash_node)) { rcu_read_unlock(); - rds_queue_reconnect(conn); + if (conn->c_trans->t_type != RDS_TRANS_TCP || + conn->c_outgoing == 1) + rds_queue_reconnect(conn); } else { rcu_read_unlock(); } diff --git a/net/rds/rds.h b/net/rds/rds.h index afb4048d0cfd..b4c7ac021d5b 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -86,7 +86,9 @@ struct rds_connection { struct hlist_node c_hash_node; __be32 c_laddr; __be32 c_faddr; - unsigned int c_loopback:1; + unsigned int c_loopback:1, + c_outgoing:1, + c_pad_to_32:30; struct rds_connection *c_passive; struct rds_cong_map *c_lcong; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 444d78d0bd77..1d90240e5d82 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -110,28 +110,24 @@ int rds_tcp_accept_one(struct socket *sock) goto out; } /* An incoming SYN request came in, and TCP just accepted it. - * We always create a new conn for listen side of TCP, and do not - * add it to the c_hash_list. * * If the client reboots, this conn will need to be cleaned up. * rds_tcp_state_change() will do that cleanup */ rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data; - WARN_ON(!rs_tcp || rs_tcp->t_sock); + if (rs_tcp->t_sock && + ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) { + struct sock *nsk = new_sock->sk; - /* - * see the comment above rds_queue_delayed_reconnect() - */ - if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) { - if (rds_conn_state(conn) == RDS_CONN_UP) - rds_tcp_stats_inc(s_tcp_listen_closed_stale); - else - rds_tcp_stats_inc(s_tcp_connect_raced); - rds_conn_drop(conn); + nsk->sk_user_data = NULL; + nsk->sk_prot->disconnect(nsk, 0); + tcp_done(nsk); + new_sock = NULL; ret = 0; goto out; } + rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING); rds_tcp_set_callbacks(new_sock, conn); rds_connect_complete(conn); new_sock = NULL; From 1edd6a14d24f21b8b478970c63a243a08e2b55b0 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Wed, 30 Sep 2015 16:54:08 -0400 Subject: [PATCH 2/3] RDS-TCP: Do not bloat sndbuf/rcvbuf in rds_tcp_tune Using the value of RDS_TCP_DEFAULT_BUFSIZE (128K) clobbers efficient use of TSO because it inflates the size_goal that is computed in tcp_sendmsg/tcp_sendpage and skews packet latency, and the default values for these parameters actually results in significantly better performance. In request-response tests using rds-stress with a packet size of 100K with 16 threads (test parameters -q 100000 -a 256 -t16 -d16) between a single pair of IP addresses achieves a throughput of 6-8 Gbps. Without this patch, throughput maxes at 2-3 Gbps under equivalent conditions on these platforms. Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- net/rds/tcp.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index c42b60bf4c68..9d6ddbacd875 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -67,21 +67,13 @@ void rds_tcp_nonagle(struct socket *sock) set_fs(oldfs); } +/* All module specific customizations to the RDS-TCP socket should be done in + * rds_tcp_tune() and applied after socket creation. In general these + * customizations should be tunable via module_param() + */ void rds_tcp_tune(struct socket *sock) { - struct sock *sk = sock->sk; - rds_tcp_nonagle(sock); - - /* - * We're trying to saturate gigabit with the default, - * see svc_sock_setbufsize(). - */ - lock_sock(sk); - sk->sk_sndbuf = RDS_TCP_DEFAULT_BUFSIZE; - sk->sk_rcvbuf = RDS_TCP_DEFAULT_BUFSIZE; - sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK; - release_sock(sk); } u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc) From 76b29ef120f5b845f862de08b92c7d2317b50907 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Wed, 30 Sep 2015 16:54:09 -0400 Subject: [PATCH 3/3] RDS-TCP: Set up MSG_MORE and MSG_SENDPAGE_NOTLAST as appropriate in rds_tcp_xmit For the same reasons as commit 2f5338442425 ("tcp: allow splice() to build full TSO packets") and commit 35f9c09fe9c7 ("tcp: tcp_sendpages() should call tcp_push() once"), rds_tcp_xmit may have multiple pages to send, so use the MSG_MORE and MSG_SENDPAGE_NOTLAST as hints to tcp_sendpage() Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- net/rds/tcp_send.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 53b17ca0dff5..2894e6095e3b 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -83,6 +83,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, struct rds_tcp_connection *tc = conn->c_transport_data; int done = 0; int ret = 0; + int more; if (hdr_off == 0) { /* @@ -116,12 +117,15 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, goto out; } + more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0; while (sg < rm->data.op_nents) { + int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more; + ret = tc->t_sock->ops->sendpage(tc->t_sock, sg_page(&rm->data.op_sg[sg]), rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off, - MSG_DONTWAIT|MSG_NOSIGNAL); + flags); rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]), rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off, ret); @@ -134,6 +138,8 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, off = 0; sg++; } + if (sg == rm->data.op_nents - 1) + more = 0; } out: