diff options
| author | David S. Miller <davem@davemloft.net> | 2015-05-09 16:42:32 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-05-09 16:42:32 -0400 |
| commit | 82ae9c6060c6dbaf103273a5c51b8f58b951d9a2 (patch) | |
| tree | 45729a77a2017ec24e8185e7279b97a2019f87fe /include | |
| parent | b063bc5ea77b1c1c0e7798f641f53504d0f64bf8 (diff) | |
| parent | e520af48c7e5acae5f17f82a79ba7ab7cf156f3b (diff) | |
Merge branch 'tcp-more-reliable-window-probes'
Eric Dumazet says:
====================
tcp: more reliable window probes
This series address a problem caused by small rto_min timers in DC,
leading to either timer storms or early flow terminations.
We also add two new SNMP counters for proper monitoring :
TCPWinProbe and TCPKeepAlive
v2: added TCPKeepAlive counter, as suggested by Yuchung & Neal
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
| -rw-r--r-- | include/net/tcp.h | 29 | ||||
| -rw-r--r-- | include/uapi/linux/snmp.h | 2 |
2 files changed, 25 insertions, 6 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d204f3f9df8..b8ea12880fd9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -527,7 +527,7 @@ int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); -int tcp_write_wakeup(struct sock *); +int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); @@ -1043,14 +1043,31 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } -static inline void tcp_check_probe_timer(struct sock *sk) +/* Something is really bad, we could not queue an additional packet, + * because qdisc is full or receiver sent a 0 window. + * We do not want to add fuel to the fire, or abort too early, + * so make sure the timer we arm now is at least 200ms in the future, + * regardless of current icsk_rto value (as it could be ~2ms) + */ +static inline unsigned long tcp_probe0_base(const struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); + return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); +} - if (!tp->packets_out && !icsk->icsk_pending) +/* Variant of inet_csk_rto_backoff() used for zero window probes */ +static inline unsigned long tcp_probe0_when(const struct sock *sk, + unsigned long max_when) +{ + u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff; + + return (unsigned long)min_t(u64, when, max_when); +} + +static inline void tcp_check_probe_timer(struct sock *sk) +{ + if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - icsk->icsk_rto, TCP_RTO_MAX); + tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 6a6fb747c78d..eee8968407f0 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -276,6 +276,8 @@ enum LINUX_MIB_TCPACKSKIPPEDFINWAIT2, /* TCPACKSkippedFinWait2 */ LINUX_MIB_TCPACKSKIPPEDTIMEWAIT, /* TCPACKSkippedTimeWait */ LINUX_MIB_TCPACKSKIPPEDCHALLENGE, /* TCPACKSkippedChallenge */ + LINUX_MIB_TCPWINPROBE, /* TCPWinProbe */ + LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */ __LINUX_MIB_MAX }; |