linux tcp Nagle算法，TCP_NODELAY和TCP_CORK 转载

#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
case TCP_CORK:
/* When set indicates to always queue non-full frames.
* Later the user clears this option and we transmit
* any pending partial frames in the queue. This is
* meant to be used alongside sendfile() to get properly
* filled frames when the user (for example) must write
* out headers with a write() call first and then use
* sendfile to send out the data parts.
*
* TCP_CORK can be set together with TCP_NODELAY and it is
* stronger than TCP_NODELAY.
*/
if (val) {
tp->nonagle |= TCP_NAGLE_CORK;
} else {
tp->nonagle &= ~TCP_NAGLE_CORK;
if (tp->nonagle&TCP_NAGLE_OFF)
tp->nonagle |= TCP_NAGLE_PUSH;
tcp_push_pending_frames(sk);
}
break;
case TCP_NODELAY:
if (val) {
/* TCP_NODELAY is weaker than TCP_CORK, so that
* this option on corked socket is remembered, but
* it is not activated until cork is cleared.
*
* However, when TCP_NODELAY is set we make
* an explicit push, which overrides even TCP_CORK
* for currently queued segments.
*/
tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
tcp_push_pending_frames(sk);
} else {
tp->nonagle &= ~TCP_NAGLE_OFF;
}

int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
//size_goal表示GSO支持的大小，为mss_now的整数倍，不支持GSO时则相等
mss_now = tcp_send_mss(sk, &size_goal, flags);
// 把msg的用户态数据，按照GSO支持的最大大小，尽量copy到一个skb中
//skb_entail(sk,skb)到发送队列
//还有数据没copy，但是当前skb已经满了，可以发送了
if (forced_push(tp)) { //超过最大窗口的一半没有设置push了
tcp_mark_push(tp, skb); //设置push标记，更新pushed_seq
__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); //调用tcp_write_xmit马上发送
} else if (skb == tcp_send_head(sk)) //第一个包，直接发送
tcp_push_one(sk, mss_now);
else{
//说明发送队列前面还有skb等待发送，且距离之前push的包还不是非常久, 则只是继续放到队列中，继续开始创建下一个skb copy
continue
}
out:
//最后的包调用tcp_push发送
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
...
}
static void skb_entail(struct sock *sk, struct sk_buff *skb)
{
...
tcp_add_write_queue_tail(sk, skb); if (tp->nonagle & TCP_NAGLE_PUSH)
tp->nonagle &= ~TCP_NAGLE_PUSH; //创建新的skb放入发送队列，立刻清楚push选项
}

static void tcp_push(struct sock *sk, int flags, int mss_now,
int nonagle, int size_goal)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
if (!tcp_send_head(sk))
return;
skb = tcp_write_queue_tail(sk);
if (!(flags & MSG_MORE) || forced_push(tp))
tcp_mark_push(tp, skb);
tcp_mark_urg(tp, flags);
if (tcp_should_autocork(sk, skb, size_goal)) {
//利用tsq机制延后发送
/* avoid atomic op if TSQ_THROTTLED bit is already set */
if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
}
/* It is possible TX completion already happened
* before we set TSQ_THROTTLED.
*/
if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize)
return;
}
if (flags & MSG_MORE) //应用程序标记了很快有新的数据到来，则标记cork，不发送小包
nonagle = TCP_NAGLE_CORK;
__tcp_push_pending_frames(sk, mss_now, nonagle); //最终调用tcp_write_xmit
}

/* If a not yet filled skb is pushed, do not send it if
* we have data packets in Qdisc or NIC queues :
* Because TX completion will happen shortly, it gives a chance
* to coalesce future sendmsg() payload into this skb, without
* need for a timer, and with no latency trade off.
* As packets containing data payload have a bigger truesize
* than pure acks (dataless) packets, the last checks prevent
* autocorking if we only have an ACK in Qdisc/NIC queues,
* or if TX completion was delayed after we processed ACK packet.
*/
static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal && //不到最大GSO size
sysctl_tcp_autocorking && //默认开启
skb != tcp_write_queue_head(sk) && //发送队列前面还有其他skb
atomic_read(&sk->sk_wmem_alloc) > skb->truesize; //qdisc中有数据， 说明网卡发送后完成中断释放内存，会很快有新的数据到来
}

static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp)
{ max_segs = tcp_tso_segs(sk, mss_now); //当前tso支持的最大segs数量
while ((skb = tcp_send_head(sk))) { //遍历发送队列
tso_segs = tcp_init_tso_segs(skb, mss_now); //skb->len/mss，重新设置tcp_gso_segs，因为在tcp_sendmsg中被清零了
...
if (tso_segs == 1) {//tso_segs=1表示无需tso分段
/* 根据nagle算法，计算是否需要推迟发送数据 */
if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
(tcp_skb_is_last(sk, skb) ?
nonagle : TCP_NAGLE_PUSH)))) //last skb就直接发送
break; //推迟发送
} else { //tso分段
if (!push_one && //不只一个skb
tcp_tso_should_defer(sk, skb, &is_cwnd_limited, //如果发送窗口剩余不多，并且预计下一个ack将很快到来(意味着可用窗口会增加)，则推迟发送
max_segs))
break; //可以推迟
}
//不用推迟发送，马上发送
limit = mss_now;
...
if (tcp_small_queue_check(sk, skb, 0)) //tsq检查，qdisc是否达到限制
break;
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) //发送，如果包被qdisc丢了，则退出循环，不继续发送了
break;
tcp_event_new_data_sent(sk, skb);//更新sk_send_head和packets_out
/* 更新struct tcp_sock中的snd_sml字段。记录非全尺寸发送的最后一个字节序号，主要用来做nagle测试
*/
tcp_minshall_update(tp, mss_now, skb);
sent_pkts += tcp_skb_pcount(skb);
if (push_one) //只发一个skb的则退出循环
break;
}
...
//没有数据包inflight，并且有数据等待发送，则准备尝试0窗口探测
return !tp->packets_out && tcp_send_head(sk);
}

/* Return true if the Nagle test allows this packet to be
* sent now.
*/
static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb,
unsigned int cur_mss, int nonagle)
{
/* Nagle rule does not apply to frames, which sit in the middle of the
* write_queue (they have no chances to get new data).
*
* This is implemented in the callers, where they modify the 'nonagle'
* argument based upon the location of SKB in the send queue.
*/
if (nonagle & TCP_NAGLE_PUSH)
return true;
/* Don't use the nagle rule for urgent data (or for the final FIN). */
if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
return true;
if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle))
return true;
//skb->len < cur_mss且设置了TCP_NAGLE_CORK， 或者上一个发送的小包还未被确认， 则推迟发送
return false;
}
static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
int nonagle)
{
return partial && //skb->len < mss, 也就是说>=mss就直接发送
((nonagle & TCP_NAGLE_CORK) || //设置了cork则使用nagle
(!nonagle && tp->packets_out && tcp_minshall_check(tp))); //有inflight数据且上一个发送的小包还没被确认则进入nagle
}
/* Minshall's variant of the Nagle send check. */
static bool tcp_minshall_check(const struct tcp_sock *tp)
{
return after(tp->snd_sml, tp->snd_una) && //上一个发送的小包还没确认
!after(tp->snd_sml, tp->snd_nxt); //没有回绕
}
static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now,
const struct sk_buff *skb)
{
if (skb->len < tcp_skb_pcount(skb) * mss_now)
tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}

static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
bool *is_cwnd_limited, u32 max_segs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 age, send_win, cong_win, limit, in_flight;
struct tcp_sock *tp = tcp_sk(sk);
struct skb_mstamp now;
struct sk_buff *head;
int win_divisor;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto send_now;
if (icsk->icsk_ca_state >= TCP_CA_Recovery)
goto send_now;
/* Avoid bursty behavior by allowing defer
* only if the last write was recent.
*/
if ((s32)(tcp_time_stamp - tp->lsndtime) > 0)
goto send_now;
in_flight = tcp_packets_in_flight(tp);
BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight));
send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; //发送窗口
/* From in_flight test above, we know that cwnd > in_flight. */
cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache; //拥塞窗口
limit = min(send_win, cong_win); //最大发送窗口剩余
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= max_segs * tp->mss_cache) //支持最大尺寸的tso发送
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) //不是发送队列的最后一个，且满足发送窗口
goto send_now; //直接发送，不会有数据被添加到这个skb了
win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
if (win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
/* If at least some fraction of a window is available,
* just use it.
*/
chunk /= win_divisor;
if (limit >= chunk) //剩余的窗口大于总窗口的比例， 默认1/3
goto send_now;
} else {
/* Different approach, try not to defer past a single
* ACK. Receiver should ACK every other full sized
* frame, so if we have space for more than 3 frames
* then send now.
*/
if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache)
goto send_now;
}
head = tcp_write_queue_head(sk);
skb_mstamp_get(&now);
age = skb_mstamp_us_delta(&now, &head->skb_mstamp); //最早的未确认包的距离现在的时间
/* If next ACK is likely to come too late (half srtt), do not defer */
if (age < (tp->srtt_us >> 4)) // 也就是说下一个ack的到来很可能大于1/2的srtt，直接发送
goto send_now;
/* Ok, it looks like it is advisable to defer. */
//当前skb的收到cwnd限制
if (cong_win < send_win && cong_win <= skb->len)
*is_cwnd_limited = true;
//可以推迟发送了
return true;
send_now:
return false;
}