bitmessage/docker/run.sh

#!/bin/sh

set -eu

export BITMESSAGE_API_USER="${BITMESSAGE_API_USER:-bitmessage_api_user}"
export BITMESSAGE_API_PASSWORD="${BITMESSAGE_API_PASSWORD:-bitmessage_api_password}"
export BITMESSAGE_SEED_ADDRESSES="${BITMESSAGE_SEED_ADDRESSES:-0}"
export BITMESSAGE_API_PORT="${BITMESSAGE_API_PORT:-8442}"
export BITMESSAGE_TTL="${BITMESSAGE_TTL:-172800}"
export BITMESSAGE_STOPRESENDINGAFTERXDAYS="${BITMESSAGE_STOPRESENDINGAFTERXDAYS:-30}"
export BITMESSAGE_APIVARIANT="${BITMESSAGE_APIVARIANT:-legacy}"
export BITMESSAGE_MAXTOTALCONNECTIONS="${BITMESSAGE_MAXTOTALCONNECTIONS:-200}"
export BITMESSAGE_TRUSTED_PEER="${BITMESSAGE_TRUSTED_PEER:-}"
export BITMESSAGE_SEND_OUTGOING="${BITMESSAGE_SEND_OUTGOING:-True}"
export BITMESSAGE_KNOWN_NODES="${BITMESSAGE_KNOWN_NODES:-}"
# The watchdog at the end of this file. A daemon that has lost every peer does
# not find its way back on its own, while one that has just started dials hard
# and does -- so a restart is the cure, and noticing is the whole difference.
# On by default; False leaves the supervisor holding the daemon and stops it
# acting. PERIOD is seconds between checks, AFTER how many peerless checks in a
# row it takes to act, COOLDOWN the floor between two restarts.
export BITMESSAGE_WATCHDOG="${BITMESSAGE_WATCHDOG:-True}"
export BITMESSAGE_WATCHDOG_PERIOD="${BITMESSAGE_WATCHDOG_PERIOD:-60}"
export BITMESSAGE_WATCHDOG_AFTER="${BITMESSAGE_WATCHDOG_AFTER:-5}"
export BITMESSAGE_WATCHDOG_COOLDOWN="${BITMESSAGE_WATCHDOG_COOLDOWN:-900}"

# Reject anything but a plain number: this value is written into keys.dat, and
# unlike the credentials below it has no business containing characters that
# esc() would have to neutralise. A typo here would otherwise land in the config
# as a key the daemon silently ignores.
case "$BITMESSAGE_MAXTOTALCONNECTIONS" in
	'' | *[!0-9]*)
		echo "BITMESSAGE_MAXTOTALCONNECTIONS must be a positive integer" >&2
		exit 1
		;;
esac

# sendoutgoingconnections is read with safeGetBoolean, which would take "yes" or
# "1" too; keys.dat is written by hand often enough that it is worth keeping one
# spelling in it. Anything else is a typo, and a typo here reads as False --
# a node that quietly never dials out.
case "$BITMESSAGE_SEND_OUTGOING" in
	[Tt]rue) BITMESSAGE_SEND_OUTGOING=True ;;
	[Ff]alse) BITMESSAGE_SEND_OUTGOING=False ;;
	*)
		echo "BITMESSAGE_SEND_OUTGOING must be True or False" >&2
		exit 1
		;;
esac

# The same two rules again, for the watchdog. Checked here rather than in the
# loop because a typo would otherwise surface hours later as a supervisor that
# spins, or one that never acts -- and both look like a working container.
case "$BITMESSAGE_WATCHDOG" in
	[Tt]rue) BITMESSAGE_WATCHDOG=True ;;
	[Ff]alse) BITMESSAGE_WATCHDOG=False ;;
	*)
		echo "BITMESSAGE_WATCHDOG must be True or False" >&2
		exit 1
		;;
esac

case "$BITMESSAGE_WATCHDOG_PERIOD" in
	'' | *[!0-9]* | 0)
		echo "BITMESSAGE_WATCHDOG_PERIOD must be a positive integer" >&2
		exit 1
		;;
esac

case "$BITMESSAGE_WATCHDOG_AFTER" in
	'' | *[!0-9]* | 0)
		echo "BITMESSAGE_WATCHDOG_AFTER must be a positive integer" >&2
		exit 1
		;;
esac

# Zero is allowed here and means "no floor": restart on every verdict.
case "$BITMESSAGE_WATCHDOG_COOLDOWN" in
	'' | *[!0-9]*)
		echo "BITMESSAGE_WATCHDOG_COOLDOWN must be a non-negative integer" >&2
		exit 1
		;;
esac

# host:port with a numeric port -- the form both consumers need. PyBitmessage
# does check trustedpeer itself, but by sys.exit() from a constructor deep in
# the network thread: the container dies with the reason buried in the daemon
# log. Fail here, where the message is the first thing in `docker logs`.
check_peer() {
	case "$1" in
		*:*) ;;
		*) return 1 ;;
	esac
	[ -n "${1%:*}" ] || return 1
	case "${1##*:}" in
		'' | *[!0-9]*) return 1 ;;
	esac
}

if [ -n "$BITMESSAGE_TRUSTED_PEER" ] && ! check_peer "$BITMESSAGE_TRUSTED_PEER"
then
	echo "BITMESSAGE_TRUSTED_PEER must be host:port" >&2
	exit 1
fi

if [ -z "${BITMESSAGE_SEED_PHRASE:-}" ]
then
  BITMESSAGE_SEED_PHRASE="$(cat /dev/random | tr -dc "a-z" | head -c32)"
  export BITMESSAGE_SEED_PHRASE
fi

# Escape a value for use on the right-hand side of the sed expressions below.
# There, a backslash starts an escape, "&" stands for the whole match, and "|"
# ends the replacement because it is the delimiter. Unescaped, a password
# containing "&" was silently rewritten into something else and one containing
# "|" made sed fail outright.
esc() {
	printf '%s' "$1" | sed -e 's/[\\&|]/\\&/g'
}

# maxtotalconnections is the only brake on a node whose P2P port (8444) is
# published: it caps inbound sockets at the total minus maxoutboundconnections.
# The substitution below is a no-op when the key is missing, which would ship a
# node that looks capped and is not -- and the PyBitmessage clone in the
# Dockerfile is unpinned, so the stock config is whatever upstream generates
# today. Add the key rather than trust the substitution alone; line 1 is the
# [bitmessagesettings] header the daemon reads it from.
if ! grep -q "^maxtotalconnections = " keys.dat
then
	sed -i "1a maxtotalconnections = $BITMESSAGE_MAXTOTALCONNECTIONS" keys.dat
fi

# trustedpeer is absent from the stock keys.dat entirely, so the substitution
# below is a no-op until the key exists -- same trap as maxtotalconnections.
# The key is added even when the value is empty, which is how it can be taken
# back off a node that was pinned before: safeGet returns "" and connectionpool
# falls back to chooseConnection. That empty case is also why the anchors here
# stop at "=" instead of "= ": with nothing to the right there is no trailing
# space to match, and the substitution would never fire again.
if ! grep -q "^trustedpeer =" keys.dat
then
	sed -i "1a trustedpeer = $(esc "$BITMESSAGE_TRUSTED_PEER")" keys.dat
fi

# Set config values. Every expression is anchored to the start of the line and
# names its key in the replacement, so no backreference is involved and nothing
# in another section can match. With set -e a failure here now stops the
# container instead of leaving the daemon on its previous settings unnoticed --
# including the case of a bind mount with no keys.dat at all.
sed -i \
	-e "s|^apiinterface = .*|apiinterface = 0.0.0.0|" \
	-e "s|^apivariant = .*|apivariant = $(esc "$BITMESSAGE_APIVARIANT")|" \
	-e "s|^apiusername = .*|apiusername = $(esc "$BITMESSAGE_API_USER")|" \
	-e "s|^apipassword = .*|apipassword = $(esc "$BITMESSAGE_API_PASSWORD")|" \
	-e "s|^apiport = .*|apiport = $(esc "$BITMESSAGE_API_PORT")|" \
	-e "s|^apienabled = .*|apienabled = True|" \
	-e "s|^ttl = .*|ttl = $(esc "$BITMESSAGE_TTL")|" \
	-e "s|^stopresendingafterxdays = .*|stopresendingafterxdays = $(esc "$BITMESSAGE_STOPRESENDINGAFTERXDAYS")|" \
	-e "s|^maxtotalconnections = .*|maxtotalconnections = $BITMESSAGE_MAXTOTALCONNECTIONS|" \
	-e "s|^trustedpeer =.*|trustedpeer = $(esc "$BITMESSAGE_TRUSTED_PEER")|" \
	-e "s|^sendoutgoingconnections = .*|sendoutgoingconnections = $BITMESSAGE_SEND_OUTGOING|" \
	-e "s|^udp = .*|udp = False|" keys.dat

# BITMESSAGE_KNOWN_NODES pins the peers the daemon starts from, and is rewritten
# on every start: in a private contour the seed *is* the topology, and a file
# left over from an earlier run names nodes that may no longer exist. Seeding it
# also switches off the DNS bootstrap -- json_deserialize_knownnodes raises
# knownNodesActual for any peer that is neither DEFAULT_NODES nor "self", and
# connectionpool calls startBootstrappers only while that flag is down, so the
# node never reaches bootstrap8080.bitmessage.org.
#
# Writing it "only when the file is missing" would have been a permanent no-op:
# the image ships a knownnodes.dat, produced by the `pybitmessage -t` run in the
# Dockerfile, and a named volume inherits it on first use.
if [ -n "$BITMESSAGE_KNOWN_NODES" ]
then
	now="$(date +%s)"
	nodes=""
	oldifs="$IFS"
	IFS=","
	for peer in $BITMESSAGE_KNOWN_NODES
	do
		IFS="$oldifs"
		if ! check_peer "$peer"
		then
			echo "BITMESSAGE_KNOWN_NODES entry '$peer' must be host:port" >&2
			exit 1
		fi
		[ -z "$nodes" ] || nodes="$nodes,"
		nodes="$nodes
    {\"stream\": 1, \"peer\": {\"host\": \"${peer%:*}\", \"port\": ${peer##*:}},
     \"info\": {\"lastseen\": $now, \"rating\": 0, \"self\": false}}"
		IFS=","
	done
	IFS="$oldifs"
	printf '[%s\n]\n' "$nodes" > knownnodes.dat
	chmod 600 knownnodes.dat
fi

# generate address from seed
if [ "$BITMESSAGE_SEED_ADDRESSES" -gt 0 ]
then
	# Four attempts, not a bash {1..4}: this runs under dash, where brace
	# expansion is literal and the loop would have run once. The call is
	# idempotent (createDeterministicAddresses returns nothing for an address
	# that already exists), so these are retries while the API comes up.
	for i in 1 2 3 4
	do
		sleep 15
		/usr/bin/python /usr/local/bin/seed_addr_gen.py
	done &
fi

# --- the daemon, and the supervisor that owns it --------------------------
#
# This file used to end at `exec pybitmessage -d`, which made the daemon PID 1,
# and it is a poor PID 1. daemonize() double-forks and parks the grandfather in
# `while True: time.sleep(1)`; the final child then SIGTERMs it to say "ready",
# and PID 1 drops that signal for want of a handler. Three
# things followed. The grandfather slept for ever. `docker stop` reached the
# real daemon only as the SIGKILL ten seconds later -- which is how a startup
# VACUUM gets cut in half and the node is then trapped retrying it. And a daemon
# that died on its own left the container Up around a corpse, because what PID 1
# was doing had nothing to do with whether the daemon was alive.
#
# Away from PID 1 that grandfather does die on the ready signal. Measured in
# this image: the call returns immediately with status 143 and leaves exactly
# one pybitmessage process behind. So starting the daemon is an ordinary
# blocking call, and everything below is ordinary shell.
#
# What the supervisor does NOT do is act on a daemon whose API is not answering
# at all. That is the trapped-VACUUM node, a restart does not cure it, and
# restarting anyway drops the next VACUUM half-done too. watchdog.py reports
# that case as its own exit code so this loop can leave it alone.

#: How long to wait for a daemon to go away before insisting, in seconds. Twice
#: this is the worst case for a stop, which is what `stop_grace_period` has to
#: cover -- see the note in the README: a clean PyBitmessage shutdown does not
#: fit in Docker's default ten seconds, so a compose file that does not raise
#: the grace period gets the SIGKILL this supervisor exists to avoid.
STOP_TIMEOUT=30

daemon_running() {
	pgrep -f pybitmessage >/dev/null 2>&1
}

start_daemon() {
	set +e
	pybitmessage -d
	rc=$?
	set -e
	# 143 is the ready signal reaching the grandfather, which is this call's
	# ordinary end. Anything but that or a plain 0 never daemonized.
	if [ "$rc" -ne 143 ] && [ "$rc" -ne 0 ]
	then
		echo "watchdog: the daemon did not start (status $rc)" >&2
		return 1
	fi
	echo "watchdog: daemon started"
}

stop_daemon() {
	daemon_running || return 0
	# Through the daemon's own API, which runs doCleanShutdown: the database is
	# closed instead of being cut off mid-write.
	python /usr/local/bin/watchdog.py shutdown || true
	waited=0
	while daemon_running && [ "$waited" -lt "$STOP_TIMEOUT" ]
	do
		sleep 1
		waited=$((waited + 1))
	done
	daemon_running || return 0
	# The API would not answer. TERM, and never KILL: the daemon installs a
	# handler for TERM (setSignalHandler) and shuts down properly on it.
	echo "watchdog: the API did not stop the daemon, sending TERM" >&2
	pkill -TERM -f pybitmessage || true
	waited=0
	while daemon_running && [ "$waited" -lt "$STOP_TIMEOUT" ]
	do
		sleep 1
		waited=$((waited + 1))
	done
}

on_signal() {
	echo "watchdog: stopping"
	stop_daemon
	exit 0
}

trap on_signal TERM INT

start_daemon || exit 1

streak=0
last_restart=0

while :
do
	sleep "$BITMESSAGE_WATCHDOG_PERIOD"

	if ! daemon_running
	then
		echo "watchdog: the daemon is gone, starting it again" >&2
		start_daemon || exit 1
		streak=0
		last_restart="$(date +%s)"
		continue
	fi

	[ "$BITMESSAGE_WATCHDOG" = True ] || continue

	set +e
	python /usr/local/bin/watchdog.py peers
	verdict=$?
	set -e

	# 1 is "answered, and has no peers" -- the only verdict worth acting on.
	# 2 is "did not answer", and the streak starts over rather than carrying an
	# interrupted observation forward.
	if [ "$verdict" -ne 1 ]
	then
		streak=0
		continue
	fi

	streak=$((streak + 1))
	[ "$streak" -ge "$BITMESSAGE_WATCHDOG_AFTER" ] || continue

	now="$(date +%s)"
	if [ "$((now - last_restart))" -lt "$BITMESSAGE_WATCHDOG_COOLDOWN" ]
	then
		continue
	fi

	echo "watchdog: no peers for $streak checks, restarting the daemon" >&2
	stop_daemon
	start_daemon || exit 1
	streak=0
	last_restart="$(date +%s)"
done