[PATCH net] tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate

[PATCH net] tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate

[Ryan Sharpelletti]

From: Ryan Sharpelletti <sharpelletti@google.com>

During loss recovery, retransmitted packets are forced to use TCP
timestamps to calculate the RTT samples, which have a millisecond
granularity. BBR is designed using a microsecond granularity. As a
result, multiple RTT samples could be truncated to the same RTT value
during loss recovery. This is problematic, as BBR will not enter
PROBE_RTT if the RTT sample is <= the current min_rtt sample, meaning
that if there are persistent losses, PROBE_RTT will constantly be
pushed off and potentially never re-entered. This patch makes sure
that BBR enters PROBE_RTT by checking if RTT sample is < the current
min_rtt sample, rather than <=.

The Netflix transport/TCP team discovered this bug in the Linux TCP
BBR code during lab tests.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Ryan Sharpelletti <sharpelletti@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
 net/ipv4/tcp_bbr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6c4d79baff26..6ea3dc2e4219 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 	filter_expired = after(tcp_jiffies32,
 			       bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
 	if (rs->rtt_us >= 0 &&
-	    (rs->rtt_us <= bbr->min_rtt_us ||
+	    (rs->rtt_us < bbr->min_rtt_us ||
 	     (filter_expired && !rs->is_ack_delayed))) {
 		bbr->min_rtt_us = rs->rtt_us;
 		bbr->min_rtt_stamp = tcp_jiffies32;
-- 
2.29.2.299.gdc1121823c-goog

Re: [PATCH net] tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate

[Soheil Hassas Yeganeh]

LGTM. Thanks!

On Mon, Nov 16, 2020 at 12:44 PM Ryan Sharpelletti
<sharpelletti.kdev@gmail.com> wrote:
>
> From: Ryan Sharpelletti <sharpelletti@google.com>
>
> During loss recovery, retransmitted packets are forced to use TCP
> timestamps to calculate the RTT samples, which have a millisecond
> granularity. BBR is designed using a microsecond granularity. As a
> result, multiple RTT samples could be truncated to the same RTT value
> during loss recovery. This is problematic, as BBR will not enter
> PROBE_RTT if the RTT sample is <= the current min_rtt sample, meaning
> that if there are persistent losses, PROBE_RTT will constantly be
> pushed off and potentially never re-entered. This patch makes sure
> that BBR enters PROBE_RTT by checking if RTT sample is < the current
> min_rtt sample, rather than <=.
>
> The Netflix transport/TCP team discovered this bug in the Linux TCP
> BBR code during lab tests.
>
> Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
> Signed-off-by: Ryan Sharpelletti <sharpelletti@google.com>
> Signed-off-by: Neal Cardwell <ncardwell@google.com>
> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
> Signed-off-by: Yuchung Cheng <ycheng@google.com>
> ---
>  net/ipv4/tcp_bbr.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
> index 6c4d79baff26..6ea3dc2e4219 100644
> --- a/net/ipv4/tcp_bbr.c
> +++ b/net/ipv4/tcp_bbr.c
> @@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
>         filter_expired = after(tcp_jiffies32,
>                                bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
>         if (rs->rtt_us >= 0 &&
> -           (rs->rtt_us <= bbr->min_rtt_us ||
> +           (rs->rtt_us < bbr->min_rtt_us ||
>              (filter_expired && !rs->is_ack_delayed))) {
>                 bbr->min_rtt_us = rs->rtt_us;
>                 bbr->min_rtt_stamp = tcp_jiffies32;
> --
> 2.29.2.299.gdc1121823c-goog
>

Re: [PATCH net] tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to netdev/net.git (refs/heads/master):

On Mon, 16 Nov 2020 17:44:13 +0000 you wrote:
> From: Ryan Sharpelletti <sharpelletti@google.com>
> 
> During loss recovery, retransmitted packets are forced to use TCP
> timestamps to calculate the RTT samples, which have a millisecond
> granularity. BBR is designed using a microsecond granularity. As a
> result, multiple RTT samples could be truncated to the same RTT value
> during loss recovery. This is problematic, as BBR will not enter
> PROBE_RTT if the RTT sample is <= the current min_rtt sample, meaning
> that if there are persistent losses, PROBE_RTT will constantly be
> pushed off and potentially never re-entered. This patch makes sure
> that BBR enters PROBE_RTT by checking if RTT sample is < the current
> min_rtt sample, rather than <=.
> 
> [...]

Here is the summary with links:
  - [net] tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate
    https://git.kernel.org/netdev/net/c/1b9e2a8c99a5

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html