tcp: switch TCP TS option (RFC 7323) to 1ms clock
TCP Timestamps option is defined in RFC 7323
Traditionally on linux, it has been tied to the internal
'jiffies' variable, because it had been a cheap and good enough
generator.
For TCP flows on the Internet, 1 ms resolution would be much better
than 4ms or 10ms (HZ=250 or HZ=100 respectively)
For TCP flows in the DC, Google has used usec resolution for more
than two years with great success [1]
Receive size autotuning (DRS) is indeed more precise and converges
faster to optimal window size.
This patch converts tp->tcp_mstamp to a plain u64 value storing
a 1 usec TCP clock.
This choice will allow us to upstream the 1 usec TS option as
discussed in IETF 97.
[1] https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 22854f0..542ca1a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -123,7 +123,7 @@ struct tcp_request_sock_ops;
struct tcp_request_sock {
struct inet_request_sock req;
const struct tcp_request_sock_ops *af_specific;
- struct skb_mstamp snt_synack; /* first SYNACK sent time */
+ u64 snt_synack; /* first SYNACK sent time */
bool tfo_listener;
u32 txhash;
u32 rcv_isn;
@@ -211,7 +211,7 @@ struct tcp_sock {
/* Information of the most recently (s)acked skb */
struct tcp_rack {
- struct skb_mstamp mstamp; /* (Re)sent time of the skb */
+ u64 mstamp; /* (Re)sent time of the skb */
u32 rtt_us; /* Associated RTT */
u32 end_seq; /* Ending TCP sequence of the skb */
u8 advanced; /* mstamp advanced since last lost marking */
@@ -240,7 +240,7 @@ struct tcp_sock {
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
/* RTT measurement */
- struct skb_mstamp tcp_mstamp; /* most recent packet received/sent */
+ u64 tcp_mstamp; /* most recent packet received/sent */
u32 srtt_us; /* smoothed round trip time << 3 in usecs */
u32 mdev_us; /* medium deviation */
u32 mdev_max_us; /* maximal mdev for the last rtt period */
@@ -280,8 +280,8 @@ struct tcp_sock {
u32 delivered; /* Total data packets delivered incl. rexmits */
u32 lost; /* Total data packets lost incl. rexmits */
u32 app_limited; /* limited until "delivered" reaches this val */
- struct skb_mstamp first_tx_mstamp; /* start of window send phase */
- struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */
+ u64 first_tx_mstamp; /* start of window send phase */
+ u64 delivered_mstamp; /* time we reached "delivered" */
u32 rate_delivered; /* saved rate sample: packets delivered */
u32 rate_interval_us; /* saved rate sample: time elapsed */
@@ -335,16 +335,16 @@ struct tcp_sock {
/* Receiver side RTT estimation */
struct {
- u32 rtt_us;
- u32 seq;
- struct skb_mstamp time;
+ u32 rtt_us;
+ u32 seq;
+ u64 time;
} rcv_rtt_est;
/* Receiver queue space */
struct {
- int space;
- u32 seq;
- struct skb_mstamp time;
+ int space;
+ u32 seq;
+ u64 time;
} rcvq_space;
/* TCP-specific MTU probe information. */