Commit 1402d366 authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller

tcp: introduce tcp_try_coalesce

commit c8628155 (tcp: reduce out_of_order memory use) took care of
coalescing tcp segments provided by legacy devices (linear skbs)

We extend this idea to fragged skbs, as their truesize can be heavy.

ixgbe for example uses 256+1024+PAGE_SIZE/2 = 3328 bytes per segment.

Use this coalescing strategy for receive queue too.

This contributes to reduce number of tcp collapses, at minimal cost, and
reduces memory overhead and packets drops.
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent e29ecd51
...@@ -4449,6 +4449,58 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) ...@@ -4449,6 +4449,58 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
return 0; return 0;
} }
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
* @to: prior buffer
* @from: buffer to add in queue
*
* Before queueing skb @from after @to, try to merge them
* to reduce overall memory use and queue lengths, if cost is small.
* Packets in ofo or receive queues can stay a long time.
* Better try to coalesce them right now to avoid future collapses.
* Returns > 0 value if caller should free @from instead of queueing it
*/
static int tcp_try_coalesce(struct sock *sk,
struct sk_buff *to,
struct sk_buff *from)
{
int len = from->len;
if (tcp_hdr(from)->fin)
return 0;
if (len <= skb_tailroom(to)) {
BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
merge:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOALESCE);
TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
return 1;
}
if (skb_headlen(from) == 0 &&
!skb_has_frag_list(to) &&
!skb_has_frag_list(from) &&
(skb_shinfo(to)->nr_frags +
skb_shinfo(from)->nr_frags <= MAX_SKB_FRAGS)) {
int delta = from->truesize - ksize(from->head) -
SKB_DATA_ALIGN(sizeof(struct sk_buff));
WARN_ON_ONCE(delta < len);
memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
skb_shinfo(from)->frags,
skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
skb_shinfo(from)->nr_frags = 0;
to->truesize += delta;
atomic_add(delta, &sk->sk_rmem_alloc);
sk_mem_charge(sk, delta);
to->len += len;
to->data_len += len;
goto merge;
}
return 0;
}
static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{ {
struct tcp_sock *tp = tcp_sk(sk); struct tcp_sock *tp = tcp_sk(sk);
...@@ -4487,23 +4539,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) ...@@ -4487,23 +4539,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
end_seq = TCP_SKB_CB(skb)->end_seq; end_seq = TCP_SKB_CB(skb)->end_seq;
if (seq == TCP_SKB_CB(skb1)->end_seq) { if (seq == TCP_SKB_CB(skb1)->end_seq) {
/* Packets in ofo can stay in queue a long time. if (tcp_try_coalesce(sk, skb1, skb) <= 0) {
* Better try to coalesce them right now __skb_queue_after(&tp->out_of_order_queue, skb1, skb);
* to avoid future tcp_collapse_ofo_queue(), } else {
* probably the most expensive function in tcp stack.
*/
if (skb->len <= skb_tailroom(skb1) && !tcp_hdr(skb)->fin) {
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPRCVCOALESCE);
BUG_ON(skb_copy_bits(skb, 0,
skb_put(skb1, skb->len),
skb->len));
TCP_SKB_CB(skb1)->end_seq = end_seq;
TCP_SKB_CB(skb1)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
__kfree_skb(skb); __kfree_skb(skb);
skb = NULL; skb = NULL;
} else {
__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
} }
if (!tp->rx_opt.num_sacks || if (!tp->rx_opt.num_sacks ||
...@@ -4624,14 +4664,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) ...@@ -4624,14 +4664,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
} }
if (eaten <= 0) { if (eaten <= 0) {
struct sk_buff *tail;
queue_and_out: queue_and_out:
if (eaten < 0 && if (eaten < 0 &&
tcp_try_rmem_schedule(sk, skb->truesize)) tcp_try_rmem_schedule(sk, skb->truesize))
goto drop; goto drop;
tail = skb_peek_tail(&sk->sk_receive_queue);
eaten = tail ? tcp_try_coalesce(sk, tail, skb) : -1;
if (eaten <= 0) {
skb_set_owner_r(skb, sk); skb_set_owner_r(skb, sk);
__skb_queue_tail(&sk->sk_receive_queue, skb); __skb_queue_tail(&sk->sk_receive_queue, skb);
} }
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (skb->len) if (skb->len)
tcp_event_data_recv(sk, skb); tcp_event_data_recv(sk, skb);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment