feat: add ICMP ping column to peer table

- ping_batch() pings each peer's public IP in parallel from the host (system ping, 1 packet, 1 s timeout, private IPs skipped) - New "Ping" column next to stellar-core's "Latency" in the -p/-g table; "—" when the peer filters ICMP - Low ping with high latency hints at a VPN exit / relay in front of the actual node Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-23 08:21:36 +00:00
parent 6bca2c62e6
commit 602592e304
2 changed files with 59 additions and 3 deletions
@@ -49,6 +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

 ### Output sections (in order)

@@ -75,6 +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
 - **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
@@ -18,6 +18,7 @@ import socket
 import subprocess
 import sys
 import time
+from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime, timezone
 from urllib.request import urlopen, Request
 from urllib.error import URLError
@@ -151,6 +152,53 @@ def geo_str(ip):
        return ", ".join(p for p in geo if p)
    return ""

+HAS_PING = shutil.which("ping") is not None
+_PING_RE = re.compile(r"[=<]\s*([\d.,]+)\s*ms", re.IGNORECASE)
+
+def ping_rtt(ip, timeout_s=1):
+    """Single ICMP ping via the system 'ping'. Returns RTT in ms, or None (no reply / filtered)."""
+    if os.name == "nt":
+        cmd = ["ping", "-n", "1", "-w", str(timeout_s * 1000), ip]
+    else:
+        cmd = ["ping", "-c", "1", "-W", str(timeout_s), "-n", ip]
+    try:
+        r = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout_s + 2,
+                           env={**os.environ, "LC_ALL": "C"})
+    except Exception:
+        return None
+    if r.returncode != 0:
+        return None
+    # Linux: "time=37.5 ms", Windows: "time=37ms" / "Zeit<1ms"
+    for line in r.stdout.splitlines():
+        if "ttl" in line.lower():
+            mt = _PING_RE.search(line)
+            if mt:
+                try:
+                    return float(mt.group(1).replace(",", "."))
+                except ValueError:
+                    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):
+        try:
+            if not ipaddress.ip_address(ip).is_private:
+                targets.append(ip)
+        except ValueError:
+            pass
+    if not HAS_PING or not targets:
+        return {}
+    with ThreadPoolExecutor(max_workers=min(32, len(targets))) as ex:
+        return dict(zip(targets, ex.map(ping_rtt, targets)))
+
+def fmt_ms(v):
+    """Format a millisecond value: one decimal below 10 ms, integer above."""
+    if v is None:
+        return "—"
+    return f"{v:.1f}ms" if v < 10 else f"{v:.0f}ms"
+
 def load_config():
    """Read the first existing config file (JSON object). Returns {} if none is usable."""
    for path in CONFIG_PATHS:
@@ -549,6 +597,11 @@ def run_cycle(client, peers_extended, geo_enabled, show_ip, interactive=False, e
                    _all_ips.append(node_ip_str)
                geo_batch([ip for ip in _all_ips if ip])

+            # --- 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])
+
            def _is_private(ip):
                try:
                    return ipaddress.ip_address(ip).is_private
@@ -643,8 +696,8 @@ 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}  {'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}  {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}  {'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}"
            SEP      = "  " + "─" * (len(HDR) - 2)

            def show(peers, is_out):
@@ -662,6 +715,7 @@ 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))
                    up    = fmt_up(p.get("elapsed", 0))
                    rx      = p.get("byte_read",  0) or 0
                    tx      = p.get("byte_write", 0) or 0
@@ -690,7 +744,7 @@ 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}  {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}  {ping_s:>7}  {up:<8}{_traffic_row}  {flow}")

            print()
            print(HDR)