[TCP]: Keep copied_seq, rcv_wup and rcv_next together.

I noticed in oprofile study a cache miss in tcp_rcv_established() to read
copied_seq.

ffffffff80400a80 <tcp_rcv_established>: /* tcp_rcv_established total: 4034293  
2.0400 */

 55493  0.0281 :ffffffff80400bc9:   mov    0x4c8(%r12),%eax copied_seq
543103  0.2746 :ffffffff80400bd1:   cmp    0x3e0(%r12),%eax   rcv_nxt    

if (tp->copied_seq == tp->rcv_nxt &&
        len - tcp_header_len <= tp->ucopy.len) {

In this function, the cache line 0x4c0 -> 0x500 is used only for this
reading 'copied_seq' field.

rcv_wup and copied_seq should be next to rcv_nxt field, to lower number of
active cache lines in hot paths. (tcp_rcv_established(), tcp_poll(), ...)

As you suggested, I changed tcp_create_openreq_child() so that these fields
are changed together, to avoid adding a new store buffer stall.

Patch is 64bit friendly (no new hole because of alignment constraints)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet 2007-02-22 03:20:44 -08:00 committed by David S. Miller
parent cf4c6bf83d
commit 54287cc178
2 changed files with 4 additions and 6 deletions

View file

@ -242,6 +242,8 @@ struct tcp_sock {
* See RFC793 and RFC1122. The RFC writes these in capitals.
*/
u32 rcv_nxt; /* What we want to receive next */
u32 copied_seq; /* Head of yet unread data */
u32 rcv_wup; /* rcv_nxt on last window update sent */
u32 snd_nxt; /* Next sequence we send */
u32 snd_una; /* First byte we want an ack for */
@ -307,10 +309,8 @@ struct tcp_sock {
struct sk_buff_head out_of_order_queue; /* Out of order segments go here */
u32 rcv_wnd; /* Current receiver window */
u32 rcv_wup; /* rcv_nxt on last window update sent */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
u32 copied_seq; /* Head of yet unread data */
/* SACKs data */
struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */

View file

@ -387,8 +387,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
/* Now setup tcp_sock */
newtp = tcp_sk(newsk);
newtp->pred_flags = 0;
newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_nxt = newtp->snd_una = newtp->snd_sml = treq->snt_isn + 1;
newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
@ -422,10 +422,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
newtp->rcv_wup = treq->rcv_isn + 1;
newtp->write_seq = treq->snt_isn + 1;
newtp->pushed_seq = newtp->write_seq;
newtp->copied_seq = treq->rcv_isn + 1;
newtp->rx_opt.saw_tstamp = 0;