diff options
author | Eric Dumazet <edumazet@google.com> | 2017-05-16 14:00:14 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-05-17 16:06:01 -0400 |
commit | 9a568de4818dea9a05af141046bd3e589245ab83 (patch) | |
tree | 6f1502edf55ecb7205660d62bd683ebcf912cfea /net/ipv4/tcp_timer.c | |
parent | ac9517fcf310327fa3e3b0d8366e4b11236b1b4b (diff) | |
download | op-kernel-dev-9a568de4818dea9a05af141046bd3e589245ab83.zip op-kernel-dev-9a568de4818dea9a05af141046bd3e589245ab83.tar.gz |
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>
Diffstat (limited to 'net/ipv4/tcp_timer.c')
-rw-r--r-- | net/ipv4/tcp_timer.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6629f47..27a667b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -153,8 +153,8 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int timeout, bool syn_set) { - unsigned int linear_backoff_thresh, start_ts; unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; + unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -172,7 +172,7 @@ static bool retransmits_timed_out(struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } - return (tcp_time_stamp - start_ts) >= timeout; + return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout); } /* A write timeout has occurred. Process the after effects. */ @@ -341,7 +341,7 @@ static void tcp_probe_timer(struct sock *sk) if (!start_ts) tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; @@ -561,7 +561,7 @@ void tcp_write_timer_handler(struct sock *sk) goto out; } - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { |