From 1ae2c7d44e7e9a9f16bd629eecf9017cfdac5eed Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 15 Oct 2023 13:47:00 -0400 Subject: [PATCH] tcp: fix excessive TLP and RACK timeouts from HZ rounding commit 1c2709cfff1dedbb9591e989e2f001484208d914 upstream. We discovered from packet traces of slow loss recovery on kernels with the default HZ=250 setting (and min_rtt < 1ms) that after reordering, when receiving a SACKed sequence range, the RACK reordering timer was firing after about 16ms rather than the desired value of roughly min_rtt/4 + 2ms. The problem is largely due to the RACK reorder timer calculation adding in TCP_TIMEOUT_MIN, which is 2 jiffies. On kernels with HZ=250, this is 2*4ms = 8ms. The TLP timer calculation has the exact same issue. This commit fixes the TLP transmit timer and RACK reordering timer floor calculation to more closely match the intended 2ms floor even on kernels with HZ=250. It does this by adding in a new TCP_TIMEOUT_MIN_US floor of 2000 us and then converting to jiffies, instead of the current approach of converting to jiffies and then adding th TCP_TIMEOUT_MIN value of 2 jiffies. Our testing has verified that on kernels with HZ=1000, as expected, this does not produce significant changes in behavior, but on kernels with the default HZ=250 the latency improvement can be large. For example, our tests show that for HZ=250 kernels at low RTTs this fix roughly halves the latency for the RACK reorder timer: instead of mostly firing at 16ms it mostly fires at 8ms. Suggested-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Fixes: bb4d991a28cc ("tcp: adjust tail loss probe timeout") Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20231015174700.2206872-1-ncardwell.sw@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/tcp.h | 3 +++ net/ipv4/tcp_output.c | 9 +++++---- net/ipv4/tcp_recovery.c | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 2a17c0b42394..4fcae463ba19 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -138,6 +138,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ + +#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ + #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4c90a61148da..ba2d64c26bbf 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2504,7 +2504,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2528,11 +2528,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 22ec8dcc1428..db3469c95c49 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -123,7 +123,7 @@ bool tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); }