From 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Jul 2012 05:50:31 +0000 Subject: tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet Cc: Dave Taht Cc: Tom Herbert Cc: Matt Mathis Cc: Yuchung Cheng Cc: Nandita Dukkipati Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 154 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 153 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c465d3e51e28..03854abfd9d8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -50,6 +50,9 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1; */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; +/* Default TSQ limit of two TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 131072; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -65,6 +68,8 @@ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) @@ -783,6 +788,140 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb return size; } + +/* TCP SMALL QUEUES (TSQ) + * + * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) + * to reduce RTT and bufferbloat. + * We do this using a special skb destructor (tcp_wfree). + * + * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb + * needs to be reallocated in a driver. + * The invariant being skb->truesize substracted from sk->sk_wmem_alloc + * + * Since transmit from skb destructor is forbidden, we use a tasklet + * to process all sockets that eventually need to send more skbs. + * We use one tasklet per cpu, with its own queue of sockets. + */ +struct tsq_tasklet { + struct tasklet_struct tasklet; + struct list_head head; /* queue of tcp sockets */ +}; +static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); + +/* + * One tasklest per cpu tries to send more skbs. + * We run in tasklet context but need to disable irqs when + * transfering tsq->head because tcp_wfree() might + * interrupt us (non NAPI drivers) + */ +static void tcp_tasklet_func(unsigned long data) +{ + struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; + LIST_HEAD(list); + unsigned long flags; + struct list_head *q, *n; + struct tcp_sock *tp; + struct sock *sk; + + local_irq_save(flags); + list_splice_init(&tsq->head, &list); + local_irq_restore(flags); + + list_for_each_safe(q, n, &list) { + tp = list_entry(q, struct tcp_sock, tsq_node); + list_del(&tp->tsq_node); + + sk = (struct sock *)tp; + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } else { + /* defer the work to tcp_release_cb() */ + set_bit(TSQ_OWNED, &tp->tsq_flags); + } + bh_unlock_sock(sk); + + clear_bit(TSQ_QUEUED, &tp->tsq_flags); + sk_free(sk); + } +} + +/** + * tcp_release_cb - tcp release_sock() callback + * @sk: socket + * + * called from release_sock() to perform protocol dependent + * actions before socket release. + */ +void tcp_release_cb(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } +} +EXPORT_SYMBOL(tcp_release_cb); + +void __init tcp_tasklet_init(void) +{ + int i; + + for_each_possible_cpu(i) { + struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + + INIT_LIST_HEAD(&tsq->head); + tasklet_init(&tsq->tasklet, + tcp_tasklet_func, + (unsigned long)tsq); + } +} + +/* + * Write buffer destructor automatically called from kfree_skb. + * We cant xmit new skbs from this context, as we might already + * hold qdisc lock. + */ +void tcp_wfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) && + !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) { + unsigned long flags; + struct tsq_tasklet *tsq; + + /* Keep a ref on socket. + * This last ref will be released in tcp_tasklet_func() + */ + atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc); + + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = &__get_cpu_var(tsq_tasklet); + list_add(&tp->tsq_node, &tsq->head); + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + } else { + sock_wfree(skb); + } +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -844,7 +983,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); - skb_set_owner_w(skb, sk); + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? + tcp_wfree : sock_wfree; + atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); @@ -1780,6 +1924,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1800,6 +1945,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } + /* TSQ : sk_wmem_alloc accounts skb truesize, + * including skb overhead. But thats OK. + */ + if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + break; + } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, -- cgit v1.2.3-55-g7522