feat: TCP connect fallback for ping, flag high latency vs. ping

- If a peer filters ICMP, measure the TCP connect time to its peer port instead; such values are marked with a trailing "t" - Show ⚡ between Latency and Ping when stellar-core's latency exceeds the ping/TCP RTT by more than LATENCY_PING_RATIO (3), hinting at a VPN exit / relay in front of the actual node - Legend below the peer table, only for markers actually shown Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 08:40:31 +00:00
parent 602592e304
commit 20740b3704
2 changed files with 68 additions and 16 deletions
@@ -49,7 +49,7 @@ Single self-contained script (`pi-stat`). Logic is split into helper functions a
 - **PostgreSQL** — `psql` inside the container; used for peer DB counts and pubkey→IP mapping
 - **ZFS CLI** — `zpool`/`zfs` commands on the host for disk health (`z01pool`); if `zpool` is not found (`HAS_ZFS = False`), falls back to `shutil.disk_usage()` — works on Linux without ZFS, WSL2, and Windows
 - **ip-api.com** — batch geolocation (Country, City), cached in `_geo_cache`; only fetched with `-g`
- **System `ping`** — one ICMP ping per peer IP from the host (`ping_batch()`, parallel, 1 s timeout, private IPs skipped); shown as `Ping` next to stellar-core's `Latency` in the `-p`/`-g` table, `—` if the peer filters ICMP
+- **System `ping` / TCP connect** — per peer from the host (`ping_batch()`, parallel, private IPs skipped): one ICMP ping (1 s timeout); if the peer filters ICMP, falls back to a TCP connect on the peer port from its address (1 s timeout). Shown as `Ping` next to stellar-core's `Latency` in the `-p`/`-g` table; TCP values are marked with a trailing `t` (legend printed below the table), `—` if neither answers

 ### Output sections (in order)

@@ -76,7 +76,7 @@ The refresh deadline is anchored to the start of the cycle (`cycle_start`), not
 - **Dynamic column widths** — all table columns sized at runtime from actual data length
 - **NAT detection** — inbound peers with private IPs are replaced with their DB-stored public IP (`db_peer_addr` from PostgreSQL)
 - **Validator matching** — `load_validators()` parses `stellar-core.cfg` and indexes by IP, name, and public key; matched peers show a truncated key + `(Vn)` label
- **Ping vs. Latency** — `Latency` is stellar-core's round trip to the peer *process*, `Ping` is ICMP to the peer's IP; a low ping with high latency hints at a VPN exit / relay in front of the actual node
+- **Ping vs. Latency** — `Latency` is stellar-core's round trip to the peer *process*, `Ping` is ICMP to the peer's IP; a low ping with high latency hints at a VPN exit / relay in front of the actual node. Peers with `Latency > LATENCY_PING_RATIO (3) × Ping` get a `⚡` between the two columns (2-column cell, since `⚡` is double-width in terminals); a legend line is printed below the table only when a `⚡` or `t` marker is present
 - **Geo caching** — `_geo_cache` is a module-level dict; `geo_batch()` only fetches IPs not already cached
 - **Flag parsing** — manual `sys.argv` parsing; `-g` implies `-p`; `-i` accepts an optional next argument as the refresh interval
 - **Config precedence** — `config_refresh()` reads the config value; an explicit `-i SEC` argument overrides it
@@ -43,6 +43,7 @@ HORIZON_URL          = "http://127.0.0.1:8000"  # queried from inside the contai
 CFG_PATH             = os.path.join(os.path.dirname(os.path.realpath(__file__)), "stellar-core.cfg")
 DEFAULT_REFRESH      = 5
 REFRESH_WARN_RATIO   = 0.8  # warn if a cycle takes >= 80% of the refresh interval
+LATENCY_PING_RATIO   = 3    # mark peers with ⚡ when core latency > 3× ping/TCP RTT
 CONFIG_PATHS         = [
    os.environ.get("PI_STAT_CONFIG"),
    os.path.join(os.path.expanduser("~"), ".config", "pi-stat", "config.json"),
@@ -179,19 +180,44 @@ def ping_rtt(ip, timeout_s=1):
                    pass
    return None

-def ping_batch(ips):
-    """Ping all public IPs in parallel. Returns {ip: rtt_ms or None}; private/invalid IPs are skipped."""
-    targets = []
-    for ip in set(ips):
+def tcp_rtt(ip, port, timeout_s=1):
+    """TCP connect time to ip:port in ms (≈ 1 RTT: SYN → SYN/ACK), or None if not connectable."""
+    t = time.perf_counter()
    try:
-            if not ipaddress.ip_address(ip).is_private:
-                targets.append(ip)
+        with socket.create_connection((ip, port), timeout=timeout_s):
+            return (time.perf_counter() - t) * 1000
+    except OSError:
+        return None
+
+def probe_rtt(ip, port):
+    """ICMP ping first; if the peer filters ICMP, fall back to a TCP connect on its peer port.
+    Returns (rtt_ms, "icmp" | "tcp") or (None, None)."""
+    if HAS_PING:
+        v = ping_rtt(ip)
+        if v is not None:
+            return v, "icmp"
+    if port:
+        v = tcp_rtt(ip, port)
+        if v is not None:
+            return v, "tcp"
+    return None, None
+
+def ping_batch(addrs):
+    """Probe all public peer addresses ("ip:port") in parallel.
+    Returns {ip: (rtt_ms, kind)}; private/invalid IPs are skipped."""
+    targets = {}
+    for addr in addrs:
+        ip, _, port = addr.rpartition(":")
+        try:
+            if ipaddress.ip_address(ip).is_private:
+                continue
        except ValueError:
-            pass
-    if not HAS_PING or not targets:
+            continue
+        targets[ip] = int(port) if port.isdigit() else None
+    if not targets:
        return {}
    with ThreadPoolExecutor(max_workers=min(32, len(targets))) as ex:
-        return dict(zip(targets, ex.map(ping_rtt, targets)))
+        return dict(zip(targets, ex.map(lambda t: probe_rtt(*t), targets.items())))

 def fmt_ms(v):
    """Format a millisecond value: one decimal below 10 ms, integer above."""
@@ -199,6 +225,11 @@ def fmt_ms(v):
        return "—"
    return f"{v:.1f}ms" if v < 10 else f"{v:.0f}ms"

+def fmt_ping(res):
+    """Ping cell: ICMP value plain, TCP-connect value marked with a trailing 't'."""
+    v, kind = res if res else (None, None)
+    return f"{fmt_ms(v)} {'t' if kind == 'tcp' else ' '}"
+
 def load_config():
    """Read the first existing config file (JSON object). Returns {} if none is usable."""
    for path in CONFIG_PATHS:
@@ -600,7 +631,8 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
            # --- Ping from this host to each peer's known IP ---
            # Compared with stellar-core's "Latency", a low ping but high
            # latency hints at a VPN exit / relay in front of the actual node.
-            ping_ms = ping_batch([p.get("address", "").rsplit(":", 1)[0] for p in inbound + outbound])
+            # ICMP first, TCP connect to the peer port as fallback (marked 't').
+            ping_ms = ping_batch([p.get("address", "") for p in inbound + outbound])

            def _is_private(ip):
                try:
@@ -696,10 +728,12 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
                ratio_total = max(ratio_total, len("RX/TX"))
                _traffic_hdr  = f"  {'RX/TX':>{ratio_total}}"
                _traffic_node = f"  {fmt_ratio_cell(None, ratio_l_w, ratio_r_w):>{ratio_total}}"
-            HDR      = f"  {hdr_num_prefix}{'NodeID':<{col_w}}  {'Version':<{ver_w}}{_ip_hdr_part}{_geo_hdr_part}  {'Latency':>8}  {'Ping':>7}  {'Uptime':<8}{_traffic_hdr}  Flow"
-            NODE_ROW = f"  {node_row_prefix}{node_id_str:<{col_w}}  {node_ver_str:<{ver_w}}{_ip_node_part}{_geo_node_part}  {'—':>8}  {'—':>7}  {node_up_str:<8}{_traffic_node}  {node_flow_str}"
+            HDR      = f"  {hdr_num_prefix}{'NodeID':<{col_w}}  {'Version':<{ver_w}}{_ip_hdr_part}{_geo_hdr_part}  {'Latency':>8} {'':2} {'Ping':>9}  {'Uptime':<8}{_traffic_hdr}  Flow"
+            NODE_ROW = f"  {node_row_prefix}{node_id_str:<{col_w}}  {node_ver_str:<{ver_w}}{_ip_node_part}{_geo_node_part}  {'—':>8} {'':2} {fmt_ping(None):>9}  {node_up_str:<8}{_traffic_node}  {node_flow_str}"
            SEP      = "  " + "─" * (len(HDR) - 2)

+            lat_flagged = []  # peers marked ⚡ (for the legend)
+
            def show(peers, is_out):
                for p in sorted(peers, key=lambda p: p.get("elapsed", 0), reverse=True):
                    raw_addr = p.get("address", "?").rsplit(":", 1)[0]
@@ -715,7 +749,16 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
                    ver   = fmt_version(p.get("ver", ""))
                    lat   = p.get("latency", "?")
                    lat_s = "n/a" if lat == 86400000 else f"{lat}ms"
-                    ping_s = fmt_ms(ping_ms.get(raw_addr))
+                    ping_res = ping_ms.get(raw_addr)
+                    ping_s = fmt_ping(ping_res)
+                    # ⚡ when stellar-core's latency exceeds the network RTT by more than
+                    # LATENCY_PING_RATIO (possible VPN exit / relay in front of the node).
+                    # "⚡" is 2 columns wide in the terminal, so the blank is 2 spaces.
+                    rtt = ping_res[0] if ping_res else None
+                    lat_flag = ("⚡" if isinstance(lat, (int, float)) and lat != 86400000
+                                and rtt and lat > LATENCY_PING_RATIO * rtt else "  ")
+                    if lat_flag == "⚡":
+                        lat_flagged.append(pid)
                    up    = fmt_up(p.get("elapsed", 0))
                    rx      = p.get("byte_read",  0) or 0
                    tx      = p.get("byte_write", 0) or 0
@@ -744,7 +787,7 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
                    else:
                        _parts = fmt_ratio_parts(rx, tx)
                        _traffic_row = f"  {fmt_ratio_cell(_parts, ratio_l_w, ratio_r_w):>{ratio_total}}"
-                    print(f"  {row_prefix}{node_col:<{col_w}}  {ver:<{ver_w}}{_ip_row_part}{_geo_row_part}  {lat_s:>8}  {ping_s:>7}  {up:<8}{_traffic_row}  {flow}")
+                    print(f"  {row_prefix}{node_col:<{col_w}}  {ver:<{ver_w}}{_ip_row_part}{_geo_row_part}  {lat_s:>8} {lat_flag} {ping_s:>9}  {up:<8}{_traffic_row}  {flow}")

            print()
            print(HDR)
@@ -758,6 +801,15 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
                    print()
                print("  Outbound")
                show(outbound, True)
+            legend = []
+            if lat_flagged:
+                legend.append(f"⚡ = Latency > {LATENCY_PING_RATIO}× Ping (possible VPN exit / relay)")
+            if any(kind == "tcp" for _, kind in ping_ms.values()):
+                legend.append("Ping: t = TCP connect to peer port (ICMP filtered)")
+            if legend:
+                print()
+                for line in legend:
+                    print(f"  {line}")

    print()
    return outbound_numbered, container