Commit f9af2dbb authored by Thomas Higdon's avatar Thomas Higdon Committed by David S. Miller

tcp: Add TCP_INFO counter for packets received out-of-order

For receive-heavy cases on the server-side, we want to track the
connection quality for individual client IPs. This counter, similar to
the existing system-wide TCPOFOQueue counter in /proc/net/netstat,
tracks out-of-order packet reception. By providing this counter in
TCP_INFO, it will allow understanding to what degree receive-heavy
sockets are experiencing out-of-order delivery and packet drops
indicating congestion.

Please note that this is similar to the counter in NetBSD TCP_INFO, and
has the same name.

Also note that we avoid increasing the size of the tcp_sock struct by
taking advantage of a hole.
Signed-off-by: default avatarThomas Higdon <tph@fb.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 40ba6a12
...@@ -354,6 +354,8 @@ struct tcp_sock { ...@@ -354,6 +354,8 @@ struct tcp_sock {
#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
#endif #endif
u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
/* Receiver side RTT estimation */ /* Receiver side RTT estimation */
u32 rcv_rtt_last_tsecr; u32 rcv_rtt_last_tsecr;
struct { struct {
......
...@@ -270,6 +270,8 @@ struct tcp_info { ...@@ -270,6 +270,8 @@ struct tcp_info {
__u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */
__u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */
__u32 tcpi_reord_seen; /* reordering events seen */ __u32 tcpi_reord_seen; /* reordering events seen */
__u32 tcpi_rcv_ooopack; /* Out-of-order packets received */
}; };
/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
......
...@@ -2653,6 +2653,7 @@ int tcp_disconnect(struct sock *sk, int flags) ...@@ -2653,6 +2653,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->rx_opt.saw_tstamp = 0; tp->rx_opt.saw_tstamp = 0;
tp->rx_opt.dsack = 0; tp->rx_opt.dsack = 0;
tp->rx_opt.num_sacks = 0; tp->rx_opt.num_sacks = 0;
tp->rcv_ooopack = 0;
/* Clean up fastopen related fields */ /* Clean up fastopen related fields */
...@@ -3295,6 +3296,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) ...@@ -3295,6 +3296,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_bytes_retrans = tp->bytes_retrans;
info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_dsack_dups = tp->dsack_dups;
info->tcpi_reord_seen = tp->reord_seen; info->tcpi_reord_seen = tp->reord_seen;
info->tcpi_rcv_ooopack = tp->rcv_ooopack;
unlock_sock_fast(sk, slow); unlock_sock_fast(sk, slow);
} }
EXPORT_SYMBOL_GPL(tcp_get_info); EXPORT_SYMBOL_GPL(tcp_get_info);
......
...@@ -4555,6 +4555,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) ...@@ -4555,6 +4555,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
tp->pred_flags = 0; tp->pred_flags = 0;
inet_csk_schedule_ack(sk); inet_csk_schedule_ack(sk);
tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
seq = TCP_SKB_CB(skb)->seq; seq = TCP_SKB_CB(skb)->seq;
end_seq = TCP_SKB_CB(skb)->end_seq; end_seq = TCP_SKB_CB(skb)->end_seq;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment