[PATCH iproute2 1/3] Update inet_diag.h header to pick up INET_DIAG_MARK

[PATCH iproute2 1/3] Update inet_diag.h header to pick up INET_DIAG_MARK

[Neal Cardwell]

To ease the upcoming addition of BBR-related data to inet_diag.h, add
the declaration of INET_DIAG_MARK. That way the BBR-related paches
only contain BBR-related pieces.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
---
 include/linux/inet_diag.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 07e486c..5dac049 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -116,6 +116,7 @@ enum {
 	INET_DIAG_LOCALS,
 	INET_DIAG_PEERS,
 	INET_DIAG_PAD,
+	INET_DIAG_MARK,
 	__INET_DIAG_MAX,
 };
 
-- 
2.8.0.rc3.226.g39d4020

[PATCH iproute2 2/3] Update inet_diag.h to include INET_DIAG_BBRINFO and related structs

[Neal Cardwell]

Update to include the the inet_diag.h changes in:
  "tcp_bbr: add BBR congestion control"

Signed-off-by: Neal Cardwell <ncardwell@google.com>
---
 include/linux/inet_diag.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 5dac049..529a5a2 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -117,6 +117,7 @@ enum {
 	INET_DIAG_PEERS,
 	INET_DIAG_PAD,
 	INET_DIAG_MARK,
+	INET_DIAG_BBRINFO,
 	__INET_DIAG_MAX,
 };
 
@@ -150,8 +151,20 @@ struct tcp_dctcp_info {
 	__u32	dctcp_ab_tot;
 };
 
+/* INET_DIAG_BBRINFO */
+
+struct tcp_bbr_info {
+	/* u64 bw: max-filtered BW (app throughput) estimate in Byte per sec: */
+	__u32	bbr_bw_lo;		/* lower 32 bits of bw */
+	__u32	bbr_bw_hi;		/* upper 32 bits of bw */
+	__u32	bbr_min_rtt;		/* min-filtered RTT in uSec */
+	__u32	bbr_pacing_gain;	/* pacing gain shifted left 8 bits */
+	__u32	bbr_cwnd_gain;		/* cwnd gain shifted left 8 bits */
+};
+
 union tcp_cc_info {
 	struct tcpvegas_info	vegas;
 	struct tcp_dctcp_info	dctcp;
+	struct tcp_bbr_info	bbr;
 };
 #endif /* _INET_DIAG_H_ */
-- 
2.8.0.rc3.226.g39d4020

[PATCH iproute2 3/3] ss: output TCP BBR diag information

[Neal Cardwell]

Dump useful TCP BBR state information from a struct tcp_bbr_info that
was grabbed using the inet_diag API.

We tolerate info that is shorter or longer than expected, in case the
kernel is older or newer than the ss binary. We simply print the
minimum of what is expected from the kernel and what is provided from
the kernel. We use the same trick as that used for struct tcp_info:
when the info from the kernel is shorter than we hoped, we pad the end
with zeroes, and don't print fields if they are zero.

The BBR output looks like:
  bbr:(bw:1.2Mbps,mrtt:18.965,pacing_gain:2.88672,cwnd_gain:2.88672)

The motivation here is to be consistent with DCTCP, which looks like:
  dctcp(ce_state:23,alpha:23,ab_ecn:23,ab_tot:23)

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
---
 misc/ss.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/misc/ss.c b/misc/ss.c
index 9c456d4..14fff46 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -784,6 +784,7 @@ struct tcpstat {
 	bool		    has_fastopen_opt;
 	bool		    has_wscale_opt;
 	struct dctcpstat    *dctcp;
+	struct tcp_bbr_info *bbr_info;
 };
 
 static void sock_state_print(struct sockstat *s, const char *sock_name)
@@ -1727,6 +1728,25 @@ static void tcp_stats_print(struct tcpstat *s)
 		printf(" dctcp:fallback_mode");
 	}
 
+	if (s->bbr_info) {
+		__u64 bw;
+
+		bw = s->bbr_info->bbr_bw_hi;
+		bw <<= 32;
+		bw |= s->bbr_info->bbr_bw_lo;
+
+		printf(" bbr:(bw:%sbps,mrtt:%g",
+		       sprint_bw(b1, bw * 8.0),
+		       (double)s->bbr_info->bbr_min_rtt / 1000.0);
+		if (s->bbr_info->bbr_pacing_gain)
+			printf(",pacing_gain:%g",
+			       (double)s->bbr_info->bbr_pacing_gain / 256.0);
+		if (s->bbr_info->bbr_cwnd_gain)
+			printf(",cwnd_gain:%g",
+			       (double)s->bbr_info->bbr_cwnd_gain / 256.0);
+		printf(")");
+	}
+
 	if (s->send_bps)
 		printf(" send %sbps", sprint_bw(b1, s->send_bps));
 	if (s->lastsnd)
@@ -2005,6 +2025,16 @@ static void tcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
 			s.dctcp		= dctcp;
 		}
 
+		if (tb[INET_DIAG_BBRINFO]) {
+			const void *bbr_info = RTA_DATA(tb[INET_DIAG_BBRINFO]);
+			int len = min(RTA_PAYLOAD(tb[INET_DIAG_BBRINFO]),
+				      sizeof(*s.bbr_info));
+
+			s.bbr_info = calloc(1, sizeof(*s.bbr_info));
+			if (s.bbr_info && bbr_info)
+				memcpy(s.bbr_info, bbr_info, len);
+		}
+
 		if (rtt > 0 && info->tcpi_snd_mss && info->tcpi_snd_cwnd) {
 			s.send_bps = (double) info->tcpi_snd_cwnd *
 				(double)info->tcpi_snd_mss * 8000000. / rtt;
@@ -2027,6 +2057,7 @@ static void tcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
 			s.min_rtt = (double) info->tcpi_min_rtt / 1000;
 		tcp_stats_print(&s);
 		free(s.dctcp);
+		free(s.bbr_info);
 	}
 }
 
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH iproute2 3/3] ss: output TCP BBR diag information

[Stephen Hemminger]

On Tue, 20 Sep 2016 22:43:44 -0400
Neal Cardwell <ncardwell@google.com> wrote:

> Dump useful TCP BBR state information from a struct tcp_bbr_info that
> was grabbed using the inet_diag API.
> 
> We tolerate info that is shorter or longer than expected, in case the
> kernel is older or newer than the ss binary. We simply print the
> minimum of what is expected from the kernel and what is provided from
> the kernel. We use the same trick as that used for struct tcp_info:
> when the info from the kernel is shorter than we hoped, we pad the end
> with zeroes, and don't print fields if they are zero.
> 
> The BBR output looks like:
>   bbr:(bw:1.2Mbps,mrtt:18.965,pacing_gain:2.88672,cwnd_gain:2.88672)
> 
> The motivation here is to be consistent with DCTCP, which looks like:
>   dctcp(ce_state:23,alpha:23,ab_ecn:23,ab_tot:23)
> 
> Signed-off-by: Neal Cardwell <ncardwell@google.com>
> Signed-off-by: Yuchung Cheng <ycheng@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>

Applied, to net-next.
The first two patches were unnecessary. Already picked up current net-next headers.