Files
lab/migration/vyos-unifi-switch
Michal 7b5331ddcd fix(migration): the backup has no WAN by design; stop failing it for that
The cutover succeeded on vyos001 -- gateway live, bond0.53 holding
87.192.101.48 with the cloned MAC, kea serving, clients routing out through NAT.
vyos002 then ran the same script and was judged unhealthy, because the mandatory
checks are "default route exists / internet reachable / DNS resolves" and the
backup deliberately holds its WAN interfaces DOWN. Its config was correct; the
check did not apply to it. Confirmed by hand before the timer could revert a
good config.

This is the third instance of one mistake: asserting a condition that is not
true of the box being checked. First requiring every WAN when one suffices, now
requiring a WAN on the box that is configured not to have one.

A delta containing `interfaces ... disable` for the WAN now identifies the
backup, and the WAN-dependent checks are skipped with a note. kea and the DNS
forwarder remain mandatory on both -- those are what the backup must actually
be able to do.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DMVzWZgiKW2wquf5z8S1yH
2026-08-18 01:48:48 +01:00

305 lines
13 KiB
Bash
Executable File

#!/bin/bash
# Switch this VyOS box between passive (USG is the gateway) and active
# (VyOS is the gateway). Installed at /config/vyos-unifi-switch, which
# survives image upgrades, so it can be run from a local terminal or the
# JetKVM console with no workstation and no internet.
#
# vyos-unifi-switch report the current mode
# vyos-unifi-switch vyos take over: VIPs to .1, DHCP, DNS, PPPoE, NAT
# vyos-unifi-switch unifi revert; the USG can then be reconnected
#
# READ THIS BEFORE THE CUTOVER
#
# `unifi` is the escape hatch. It runs no health checks, asks no questions and
# has nothing that can refuse. If anything at all looks wrong, run it, then
# plug the USG back in.
#
# `vyos` commits with commit-confirm. If it is not confirmed -- because the
# health checks failed, or because you lost access, or because you walked away
# -- the box returns to the saved configuration on its own. That requires
# `system config-management commit-confirm action reload`; without it VyOS
# REBOOTS instead, which on a gateway is an outage rather than an undo. The
# script refuses to run if that setting is missing.
set -uo pipefail
MODES=/config/modes
UNIFI_BOOT="$MODES/unifi.boot"
DELTA="$MODES/to-vyos.commands"
SECRETS=/config/wan-secrets
MARKER="$MODES/current-mode"
CONFIRM_MINUTES="${CONFIRM_MINUTES:-10}"
OPRUN=/opt/vyatta/bin/vyatta-op-cmd-wrapper
say() { printf '[switch] %s\n' "$*"; }
warn() { printf '[switch] WARNING: %s\n' "$*" >&2; }
die() { printf '[switch] ERROR: %s\n' "$*" >&2; exit 1; }
# Run configuration commands in a real config session. Everything the caller
# feeds in runs between `configure` and `exit`.
run_cfg() {
local script rc
script="$(mktemp)"
{
echo 'source /opt/vyatta/etc/functions/script-template'
echo 'configure'
cat
echo 'exit'
} > "$script"
vbash "$script"; rc=$?
rm -f "$script"
return $rc
}
# Two traps live in this one function, both of which produced wrong answers
# rather than errors:
# 1. `show configuration commands` quotes values ("action 'reload'"), so the
# quotes have to go before matching or every value-bearing check fails.
# 2. `... | grep -q` under `set -o pipefail` reports FAILURE even on a match:
# grep exits at the first hit, the producer takes SIGPIPE, and pipefail
# surfaces that. Whether it triggers depends on output size, so it fails
# intermittently. Match against a captured string instead of a pipeline.
cfg_has() {
local out
out="$($OPRUN show configuration commands 2>/dev/null | tr -d "'")"
case "$out" in *"$1"*) return 0 ;; *) return 1 ;; esac
}
# ---------------------------------------------------------------- status ----
current_mode() {
# The marker records intent; the running config is the truth. Report the
# config, and complain if the two disagree.
local live="unknown"
if cfg_has "set service dhcp-server"; then live="vyos"; else live="unifi"; fi
echo "$live"
}
show_status() {
local live marked
live="$(current_mode)"
marked="$(cat "$MARKER" 2>/dev/null || echo "never set")"
echo "host: $(hostname)"
echo "mode: $live (marker: $marked)"
[ "$live" != "$marked" ] && [ "$marked" != "never set" ] && \
warn "marker disagrees with the running config -- trust the config"
echo "VRRP:"
$OPRUN show vrrp 2>/dev/null | sed -n '3,$p' | awk '{printf " %-9s %-12s %s\n", $1, $2, $4}'
echo "DHCP server: $(systemctl is-active isc-kea-dhcp4-server 2>/dev/null)"
echo "DNS forwarder: $(systemctl is-active pdns-recursor 2>/dev/null)"
echo "WAN (pppoe0): $(ip -4 -br addr show pppoe0 2>/dev/null | awk '{print $2, $3}' || echo 'not present')"
echo "default route: $(ip -4 route show default 2>/dev/null | head -1 || echo none)"
echo "unsaved changes: $(cfg_unsaved)"
}
cfg_unsaved() {
if /usr/bin/config-mgmt compare >/dev/null 2>&1; then echo "no"; else echo "possibly - check 'compare saved'"; fi
}
# ------------------------------------------------------------- preflight ----
require_files() {
[ -r "$UNIFI_BOOT" ] || die "missing $UNIFI_BOOT -- capture it while the USG is still the gateway"
[ -s "$UNIFI_BOOT" ] || die "$UNIFI_BOOT is empty"
}
require_reload_action() {
cfg_has "set system config-management commit-confirm action reload" && return 0
die "commit-confirm action is not 'reload'. Without it an unconfirmed switch
REBOOTS this box instead of reverting. Fix first:
configure
set system config-management commit-confirm action reload
commit; save"
}
# The single worst outcome available is two devices answering on the gateway
# address. It costs one ARP probe to make that impossible.
# Returns 0 (success) when something IS answering on a gateway address we are
# about to claim -- i.e. "yes, still alive, do not proceed".
usg_still_alive() {
local found=0 ip dev targets
targets="$(grep -oE "vrrp group [a-z0-9]+ address [0-9.]+" "$DELTA" 2>/dev/null | awk '{print $NF}')"
if [ -z "$targets" ]; then
# A delta with no VIPs cannot be probed, which means the single guard
# against two devices sharing a gateway address is inert. Refuse by
# default: an unprobeable delta on the real boxes is a broken delta, and
# "warn and continue" would let the one failure this script exists to
# prevent through unnoticed. The override is for the lab only.
if [ "${ALLOW_NO_VIP_DELTA:-0}" = "1" ]; then
warn "delta claims no VIPs; proceeding because ALLOW_NO_VIP_DELTA=1 (lab only)"
return 1
fi
die "this delta claims no VIPs, so the gateway-address guard cannot run.
On the real boxes that means a broken delta. If this really is a lab
run, re-invoke with ALLOW_NO_VIP_DELTA=1."
fi
for ip in $targets; do
dev="$(ip -4 route get "$ip" 2>/dev/null | sed -n 's/.* dev \([^ ]*\).*/\1/p' | head -1)"
if [ -n "$dev" ] && command -v arping >/dev/null 2>&1; then
# ARP is the right probe: it answers even when the host filters ICMP.
if arping -c 2 -w 3 -f -I "$dev" "$ip" >/dev/null 2>&1; then
warn "something already answers ARP on $ip (via $dev)"; found=1
fi
elif ping -c 2 -W 2 "$ip" >/dev/null 2>&1; then
warn "something already answers ICMP on $ip"; found=1
fi
done
[ "$found" -eq 1 ]
}
# ------------------------------------------------------------- to unifi -----
to_unifi() {
require_files
say "reverting to unifi mode (USG is the gateway)"
run_cfg <<EOF || die "load/commit failed -- the box is unchanged, use the console"
load $UNIFI_BOOT
commit
save
EOF
echo "unifi" > "$MARKER"
say "done. The USG can be reconnected."
say "If it was already connected during this, nothing was disturbed."
}
# -------------------------------------------------------------- to vyos -----
health_checks() {
local fails=0
_chk() { # name, command
if eval "$2" >/dev/null 2>&1; then say " ok $1"; else say " FAIL $1"; fails=$((fails+1)); fi
}
_chk "kea (DHCP) is running" "systemctl is-active --quiet isc-kea-dhcp4-server"
_chk "DNS forwarder is running" "systemctl is-active --quiet pdns-recursor"
# Only assert on the WAN if this delta actually brings one up. A delta with
# no PPPoE stanza is a lab/partial delta, and failing it on a missing
# pppoe0 would make the script untestable anywhere but the live cutover.
# Announced loudly, because a quietly skipped check is worse than no check.
# A box whose delta holds its WAN interfaces DOWN is the backup: it has no
# route out by design, and demanding one reverts a perfectly correct config.
# This tore down vyos002 on the first successful cutover -- vyos001 went live
# and its backup was judged unhealthy for lacking the WAN it is deliberately
# not carrying. Same mistake as requiring the failover line: checks that do
# not apply to the box being checked.
if grep -qE "^set interfaces (pppoe pppoe0|bonding bond0 vif 53) disable$" "$DELTA"; then
say " note this box holds its WAN down (backup); skipping WAN checks"
elif grep -qE "^set interfaces (pppoe|bonding bond0 vif 5)" "$DELTA"; then
# What matters is that SOME WAN works, not that every WAN works.
#
# This reverted a cutover that had genuinely succeeded. The 10 gig line came
# up on bond0.53 and the cloned MAC was handed the same public address the
# USG had (87.192.101.48); kea was serving real LAN clients at the same
# moment. The only failure was pppoe0 -- the Vodafone FAILOVER line -- and
# requiring it undid a working gateway.
#
# Written as [ -n "$(...)" ] rather than `... | grep -q` for the pipefail
# reason above: a pipeline ending in grep -q cannot be trusted here.
_chk "a default route exists" '[ -n "$(ip -4 route show default)" ]'
_chk "internet reachable" "ping -c2 -W3 8.8.8.8"
_chk "DNS resolves through us" "getent hosts vyos.net"
# Informational only: report each WAN, fail on neither. A failover line
# being down is worth seeing, not worth reverting for.
for _w in pppoe0 bond0.53; do
if [ -n "$(ip -4 -br addr show "$_w" 2>/dev/null | awk '{print $3}')" ]; then
say " ok WAN $_w has an address (informational)"
else
say " note WAN $_w has no address (informational, not fatal)"
fi
done
else
warn "this delta configures no WAN -- skipping all WAN health checks."
warn "That is expected in the lab and WRONG for the real cutover."
fi
return $fails
}
to_vyos() {
require_files
require_reload_action
[ -r "$DELTA" ] || die "missing $DELTA"
if usg_still_alive; then
die "refusing: something is still answering on a gateway address.
Disconnect the USG first. Two devices on the same gateway IP is the
one failure this script exists to prevent."
fi
local pw="" tmp
if [ -r "$SECRETS" ]; then
# shellcheck disable=SC1090
. "$SECRETS"; pw="${WAN_PASSWORD:-}"
fi
[ -n "$pw" ] || warn "no WAN_PASSWORD in $SECRETS -- PPPoE will not authenticate"
tmp="$(mktemp)"; chmod 600 "$tmp"
sed "s|@@WAN_PASSWORD@@|${pw}|g" "$DELTA" | grep -vE '^\s*(#|$)' > "$tmp"
say "switching to vyos mode (this box becomes the gateway)"
say "commit-confirm: ${CONFIRM_MINUTES} min to confirm, else it reverts itself"
# commit-confirm is TWO steps, and doing only the first commits nothing:
# `config-mgmt commit_confirm` arms the revert timer, then a normal `commit`
# applies the candidate config. The interactive prompt lives in the first
# step, which is why it is invoked directly with -y instead of via the
# `commit-confirm` alias. IN_COMMIT_CONFIRM is what the real CLI sets, and
# the commit hooks look at it.
if ! run_cfg < <(printf 'load %s\n' "$UNIFI_BOOT"; cat "$tmp";
printf 'sudo sg vyattacfg "/usr/bin/config-mgmt commit_confirm -y -t=%s"\n' "$CONFIRM_MINUTES";
printf 'export IN_COMMIT_CONFIRM=t\ncommit\nunset IN_COMMIT_CONFIRM\n'); then
rm -f "$tmp"
die "commit-confirm failed. Nothing was applied; the box is still in its
previous mode. Run '$0 unifi' if you are unsure."
fi
rm -f "$tmp"
# Poll, do not sample once.
#
# A cutover attempt failed here on a fixed 25s wait. That is far too short for
# a WAN: PPPoE is PADI/PADO/PADR/PADS then LCP, auth and IPCP, routinely 15-30s
# by itself, and both lines had just been released by the USG seconds earlier.
# ISPs commonly hold the previous session and MAC binding for minutes before
# leasing to the "same" CPE again -- which is precisely what a cloned MAC looks
# like to them. One sample at 25s reported a healthy setup as broken and
# reverted it.
#
# There is still a deadline, because commit-confirm is running: stop well
# before it so the decision is ours rather than the timer's.
local budget="${HEALTH_BUDGET:-180}" waited=0 step=15
say "committed. Polling health for up to ${budget}s (commit-confirm has ${CONFIRM_MINUTES} min)..."
while :; do
sleep "$step"; waited=$(( waited + step ))
if health_checks >/dev/null 2>&1; then
say "healthy after ${waited}s"
break
fi
if [ "$waited" -ge "$budget" ]; then
say "still unhealthy after ${waited}s -- final check:"
break
fi
say " not healthy yet at ${waited}s, still waiting..."
done
say "health checks:"
if health_checks; then
say "all checks passed -- confirming"
/usr/bin/config-mgmt confirm >/dev/null 2>&1 || die "confirm failed; it will revert on its own shortly"
run_cfg <<'EOF' || warn "save failed -- config is live but will not survive a reboot"
save
EOF
echo "vyos" > "$MARKER"
say "vyos mode is live and saved."
else
warn "health checks FAILED -- reverting now rather than waiting out the timer"
/usr/bin/config-mgmt revert_soft >/dev/null 2>&1 \
|| warn "revert_soft failed; the commit-confirm timer will still fire within ${CONFIRM_MINUTES} min"
echo "unifi" > "$MARKER"
die "reverted to the previous configuration. Reconnect the USG.
Check: ip addr show pppoe0; journalctl -u pppd; $0 status"
fi
}
# ----------------------------------------------------------------- main -----
case "${1:-status}" in
vyos) to_vyos ;;
unifi) to_unifi ;;
status) show_status ;;
*) echo "usage: $(basename "$0") [vyos|unifi|status]" >&2; exit 2 ;;
esac