diff options
| -rw-r--r-- | tcp.c | 31 | ||||
| -rw-r--r-- | tcp_conn.h | 9 | ||||
| -rw-r--r-- | util.c | 14 | ||||
| -rw-r--r-- | util.h | 1 |
4 files changed, 48 insertions, 7 deletions
@@ -202,9 +202,13 @@ * - ACT_TIMEOUT, in the presence of any event: if no activity is detected on * either side, the connection is reset * - * - ACK_INTERVAL elapsed after data segment received from tap without having + * - RTT / 2 elapsed after data segment received from tap without having * sent an ACK segment, or zero-sized window advertised to tap/guest (flag - * ACK_TO_TAP_DUE): forcibly check if an ACK segment can be sent + * ACK_TO_TAP_DUE): forcibly check if an ACK segment can be sent. + * + * RTT, here, is an approximation of the RTT value reported by the kernel via + * TCP_INFO, with a representable range from RTT_STORE_MIN (100 us) to + * RTT_STORE_MAX (3276.8 ms). The timeout value is clamped accordingly. * * * Summary of data flows (with ESTABLISHED event) @@ -341,7 +345,6 @@ enum { #define MSS_DEFAULT 536 #define WINDOW_DEFAULT 14600 /* RFC 6928 */ -#define ACK_INTERVAL 10 /* ms */ #define RTO_INIT 1 /* s, RFC 6298 */ #define RTO_INIT_AFTER_SYN_RETRIES 3 /* s, RFC 6298 */ #define FIN_TIMEOUT 60 @@ -593,7 +596,9 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn) } if (conn->flags & ACK_TO_TAP_DUE) { - it.it_value.tv_nsec = (long)ACK_INTERVAL * 1000 * 1000; + it.it_value.tv_sec = RTT_GET(conn) / 2 / ((long)1000 * 1000); + it.it_value.tv_nsec = RTT_GET(conn) / 2 % ((long)1000 * 1000) * + 1000; } else if (conn->flags & ACK_FROM_TAP_DUE) { int exp = conn->retries, timeout = RTO_INIT; if (!(conn->events & ESTABLISHED)) @@ -608,9 +613,17 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn) it.it_value.tv_sec = ACT_TIMEOUT; } - flow_dbg(conn, "timer expires in %llu.%03llus", - (unsigned long long)it.it_value.tv_sec, - (unsigned long long)it.it_value.tv_nsec / 1000 / 1000); + if (conn->flags & ACK_TO_TAP_DUE) { + flow_trace(conn, "timer expires in %llu.%03llums", + (unsigned long)it.it_value.tv_sec * 1000 + + (unsigned long long)it.it_value.tv_nsec % + ((long)1000 * 1000), + (unsigned long long)it.it_value.tv_nsec / 1000); + } else { + flow_dbg(conn, "timer expires in %llu.%03llus", + (unsigned long long)it.it_value.tv_sec, + (unsigned long long)it.it_value.tv_nsec / 1000 / 1000); + } if (timerfd_settime(conn->timer, 0, &it, NULL)) flow_perror(conn, "failed to set timer"); @@ -1144,6 +1157,10 @@ int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn, conn_flag(c, conn, ACK_TO_TAP_DUE); out: + /* Opportunistically store RTT approximation on valid TCP_INFO data */ + if (tinfo) + RTT_SET(conn, tinfo->tcpi_rtt); + return new_wnd_to_tap != prev_wnd_to_tap || conn->seq_ack_to_tap != prev_ack_to_tap; } @@ -49,6 +49,15 @@ struct tcp_tap_conn { #define MSS_SET(conn, mss) (conn->tap_mss = (mss >> (16 - TCP_MSS_BITS))) #define MSS_GET(conn) (conn->tap_mss << (16 - TCP_MSS_BITS)) +#define RTT_EXP_BITS 4 + unsigned int rtt_exp :RTT_EXP_BITS; +#define RTT_EXP_MAX MAX_FROM_BITS(RTT_EXP_BITS) +#define RTT_STORE_MIN 100 /* us, minimum representable */ +#define RTT_STORE_MAX ((long)(RTT_STORE_MIN << RTT_EXP_MAX)) +#define RTT_SET(conn, rtt) \ + (conn->rtt_exp = MIN(RTT_EXP_MAX, ilog2(MAX(1, rtt / RTT_STORE_MIN)))) +#define RTT_GET(conn) (RTT_STORE_MIN << conn->rtt_exp) + int sock :FD_REF_BITS; uint8_t events; @@ -614,6 +614,9 @@ int __daemon(int pidfile_fd, int devnull_fd) * fls() - Find last (most significant) bit set in word * @x: Word * + * Note: unlike ffs() and other implementations of fls(), notably the one from + * the Linux kernel, the starting position is 0 and not 1, that is, fls(1) = 0. + * * Return: position of most significant bit set, starting from 0, -1 if none */ int fls(unsigned long x) @@ -630,6 +633,17 @@ int fls(unsigned long x) } /** + * ilog2() - Integral part (floor) of binary logarithm (logarithm to the base 2) + * @x: Argument + * + * Return: integral part of binary logarithm of @x, -1 if undefined (if @x is 0) + */ +int ilog2(unsigned long x) +{ + return fls(x); +} + +/** * write_file() - Replace contents of file with a string * @path: File to write * @buf: String to write @@ -233,6 +233,7 @@ int output_file_open(const char *path, int flags); void pidfile_write(int fd, pid_t pid); int __daemon(int pidfile_fd, int devnull_fd); int fls(unsigned long x); +int ilog2(unsigned long x); int write_file(const char *path, const char *buf); intmax_t read_file_integer(const char *path, intmax_t fallback); int write_all_buf(int fd, const void *buf, size_t len); |