tcp: change txhash on SYN-data timeout
Subsystems (3)
PATCH 1/1 tcp: change txhash on SYN-data timeout
Previously upon SYN timeouts the sender recomputes the txhash to try a different path. However this does not apply on the initial timeout of SYN-data (active Fast Open). Therefore an active IPv6 Fast Open connection may incur one second RTO penalty to take on a new path after the second SYN retransmission uses a new flow label.
This patch removes this undesirable behavior so Fast Open changes the flow label just like the regular connections. This also helps avoid falsely disabling Fast Open on the sender which triggers after two consecutive SYN timeouts on Fast Open.
--- net/ipv4/tcp_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/tcp_timer.c +1 -1
@@ -226,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk)if ((1 << sk->sk_state) & (TCPF_SYN_SENT |TCPF_SYN_RECV )) {if (icsk->icsk_retransmits) {dst_negative_advice (sk); - }else if (!tp->syn_data && !tp->syn_fastopen) { + }else {sk_rethink_txhash (sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
Signature · 1 line
2.20.1.97.g81188d93c3-goog
David Miller
maintainerFrom: Yuchung Cheng <[email protected]>
Date: Tue, 8 Jan 2019 18:14:28 -0800
Quoted 6 lines
Previously upon SYN timeouts the sender recomputes the txhash to try a different path. However this does not apply on the initial timeout of SYN-data (active Fast Open). Therefore an active IPv6 Fast Open connection may incur one second RTO penalty to take on a new path after the second SYN retransmission uses a new flow label.
Quoted 7 lines
This patch removes this undesirable behavior so Fast Open changes the flow label just like the regular connections. This also helps avoid falsely disabling Fast Open on the sender which triggers after two consecutive SYN timeouts on Fast Open.
Signed-off-by Yuchung Cheng <[email protected]>Reviewed-by Neal Cardwell <[email protected]>
Applied and queued up for -stable, thanks!