failover: replace van-modem-usb-kick with van-modem-watch (detect-only, no recovery)
Hub power-cycle recovery was proven not to work — only a physical unplug/replug clears a cold-boot enumeration failure. Modem moved to the Pi's native USB port as the actual fix; this just pages via Pushover if it recurs instead of attempting a recovery that doesn't work. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Sonnet 5
parent
a1bad186b1
commit
3169297148
@@ -1,119 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""van-modem-usb-kick — recover the EC25 modem when it's missing after boot.
|
||||
|
||||
Seen on 2026-08-04, right after moving the modem onto the new powered UGreen
|
||||
hub: the 5GHz AP (rtw89, on the hub's outer USB chip) and the hub's built-in
|
||||
Ethernet (AX88179, on its inner cascaded USB2.1 hub chip) both enumerate
|
||||
cleanly at boot, but the EC25 modem — plugged into a port on that same inner
|
||||
hub chip — sometimes never does, even though it has power (LED on). dmesg
|
||||
shows no connect attempt at all for the modem's port during boot (contrast
|
||||
the Ethernet's clean enumeration, or the AP's one-shot retry after a
|
||||
descriptor-read error) — the port just never signalled a connect in time, and
|
||||
a hub only rescans a port on an actual connect/disconnect edge, so it stays
|
||||
invisible until something produces one. Physically unplugging/replugging
|
||||
either the whole hub or just the modem fixes it immediately, because both
|
||||
produce that edge. This script produces the same edge in software: unbind
|
||||
then rebind the inner hub chip's kernel driver, which forces it to redo
|
||||
enumeration of everything on it (the modem, and briefly the Starlink
|
||||
Ethernet — the AP is on the outer chip and is undisturbed).
|
||||
|
||||
The inner hub is found by walking up from STARLINK_IFACE's sysfs device (it's
|
||||
the Ethernet's parent hub) rather than hardcoding a bus/port path, since that
|
||||
identifies "the hub carrying the modem" without assuming a specific topology.
|
||||
|
||||
Bounded to a few minutes after boot, then exits — this is a boot-race
|
||||
backstop, not a permanent watcher (a modem physically removed later should
|
||||
just stay gone, not get fought).
|
||||
|
||||
Usage: van-modem-usb-kick [modem-usb-vendor] [starlink-iface]
|
||||
Defaults to 2c7c (Quectel) and enx6c1ff7d210a5 — see deploy.conf.
|
||||
"""
|
||||
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
MODEM_VENDOR = sys.argv[1] if len(sys.argv) > 1 else "2c7c"
|
||||
STARLINK_IFACE = sys.argv[2] if len(sys.argv) > 2 else "enx6c1ff7d210a5"
|
||||
INTERVAL = 20 # seconds between checks
|
||||
BUDGET_S = 6 * INTERVAL # ~2 minutes of retries after boot, then give up quietly
|
||||
USB_DEVICES = Path("/sys/bus/usb/devices")
|
||||
HUB_DRIVER = Path("/sys/bus/usb/drivers/hub")
|
||||
|
||||
|
||||
def log(msg, level="info"):
|
||||
# systemd journal severity prefixes (sd-daemon), same convention as van-ap-watchdog.
|
||||
pri = {"info": "<6>", "warn": "<4>", "crit": "<2>"}.get(level, "<6>")
|
||||
print(pri + msg, flush=True)
|
||||
|
||||
|
||||
def modem_present(vendor):
|
||||
for f in USB_DEVICES.glob("*/idVendor"):
|
||||
try:
|
||||
if f.read_text().strip() == vendor:
|
||||
return True
|
||||
except OSError:
|
||||
continue
|
||||
return False
|
||||
|
||||
|
||||
def inner_hub_name(starlink_iface):
|
||||
"""sysfs driver-name (e.g. '2-1.4') of the USB hub carrying starlink_iface —
|
||||
that's the same hub chip the modem's port is on. None if the Ethernet
|
||||
itself hasn't enumerated (nothing to walk up from)."""
|
||||
dev = Path(f"/sys/class/net/{starlink_iface}/device")
|
||||
if not dev.exists():
|
||||
return None
|
||||
# dev resolves to .../<hub>/<hub>.<port>/<hub>.<port>:<config>.<iface>
|
||||
# (e.g. .../2-1.4/2-1.4.2/2-1.4.2:2.0) — two levels up is the hub itself.
|
||||
hub = dev.resolve().parent.parent
|
||||
if not (hub / "bDeviceClass").exists():
|
||||
return None
|
||||
try:
|
||||
if hub.joinpath("bDeviceClass").read_text().strip() != "09": # 09 = hub
|
||||
return None
|
||||
except OSError:
|
||||
return None
|
||||
return hub.name
|
||||
|
||||
|
||||
def kick(hub_name):
|
||||
log(f"modem (vendor {MODEM_VENDOR}) absent — rebinding hub {hub_name} to force "
|
||||
f"re-enumeration (same effect as unplug/replug; briefly bounces {STARLINK_IFACE})",
|
||||
"warn")
|
||||
try:
|
||||
(HUB_DRIVER / "unbind").write_text(hub_name)
|
||||
time.sleep(2)
|
||||
(HUB_DRIVER / "bind").write_text(hub_name)
|
||||
except OSError as e:
|
||||
log(f"hub rebind failed: {e}", "warn")
|
||||
|
||||
|
||||
def main():
|
||||
log(f"van-modem-usb-kick up: watching for USB vendor {MODEM_VENDOR} for up to "
|
||||
f"{BUDGET_S}s after boot")
|
||||
elapsed = 0
|
||||
kicked = False
|
||||
while elapsed < BUDGET_S:
|
||||
if modem_present(MODEM_VENDOR):
|
||||
log("modem present — exiting" + (" (recovered)" if kicked else ""))
|
||||
return
|
||||
if not kicked:
|
||||
hub_name = inner_hub_name(STARLINK_IFACE)
|
||||
if hub_name:
|
||||
kick(hub_name)
|
||||
kicked = True
|
||||
# else: Ethernet itself isn't up yet — give the system more time
|
||||
# before assuming anything is wrong.
|
||||
time.sleep(INTERVAL)
|
||||
elapsed += INTERVAL
|
||||
if not modem_present(MODEM_VENDOR):
|
||||
log(f"modem still absent after {BUDGET_S}s — giving up "
|
||||
f"(leaving it for manual unplug/replug from here on)", "warn")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
main()
|
||||
except KeyboardInterrupt:
|
||||
sys.exit(0)
|
||||
@@ -1,11 +0,0 @@
|
||||
[Unit]
|
||||
Description=EC25 modem boot-recovery backstop (kicks its USB hub if the modem never enumerated)
|
||||
After=systemd-udev-settle.service
|
||||
Wants=systemd-udev-settle.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
ExecStart=/usr/local/sbin/van-modem-usb-kick @MODEM_USB_VENDOR@ @STARLINK_IFACE@
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
Reference in New Issue
Block a user