universe/scripts/validators.sh

#!/usr/bin/env bash
# The five validators of Lux mainnet, where they actually run, and the one way
# to move them to a new luxd.
#
# They are NOT in a Kubernetes cluster. deploy/lux-mainnet/luxd.yaml describes a
# StatefulSet against luxd-headless.lux-mainnet.svc.cluster.local:9630, and no
# such Service exists on the k3s cluster this estate has: the DOKS cluster that
# file was written for is gone. The validators are five docker containers on the
# LAN host `evo`, started by hand, with no compose file, no unit and no script —
# which is why finding them took an afternoon. This file is that missing script.
#
# Ports are positional: node i answers HTTP on 9730+10i and stakes on 9731+10i,
# with its ledger at /var/lib/luxd/mainnet/data-i. Every node bootstraps off the
# staking ports of the other four. Consensus is sample 5 / quorum 4, so four
# must be up to decide anything: roll ONE at a time, and only when the one
# before it is back, bootstrapped and connected to the other four.
#
#   scripts/validators.sh list
#   scripts/validators.sh roll 1.37.1
set -euo pipefail

host=${LUXD_HOST:-evo}
root=/var/lib/luxd/mainnet
repo=ghcr.io/luxfi/node
chain=0x17871   # 96369, Lux mainnet C-Chain

# index:name — the name is the node's identity, the index is its port and ledger.
# Three of the five answered to hanzo-*/zoo-* names for a while; they are five
# validators of one network (all mount the same genesis) and are named for it.
nodes=(0:lux-mainnet-0 1:lux-mainnet-1 2:lux-mainnet-2 3:lux-mainnet-3 4:lux-mainnet-4)

http() { echo $((9730 + 10 * $1)); }
stake() { echo $((9731 + 10 * $1)); }

# beacons are the staking ports of every node except this one.
beacons() {
	local self=$1 i out=
	for i in 0 1 2 3 4; do
		[ "$i" = "$self" ] && continue
		out="${out:+$out,}127.0.0.1:$(stake "$i")"
	done
	echo "$out"
}

# run recreates node $1 on image $2, keeping its ledger. Every flag the running
# fleet carries is here; nothing is defaulted silently.
run() {
	local i=$1 name=$2 image=$3
	ssh "$host" docker rm -f "$name" 2>/dev/null || true
	ssh "$host" docker run -d --name "$name" --network host --restart unless-stopped \
		-v "$root/genesis.json:/genesis/genesis.json:ro" \
		-v "$root/chainconf:/chainconf:ro" \
		-v "$root/data-$i:/data" \
		"$image" /bin/sh -c "'
      mkdir -p /data/plugins
      cp /luxd/build/plugins/* /data/plugins/ 2>/dev/null || true
      exec /luxd/build/luxd --network-id=1 --genesis-file=/genesis/genesis.json \
        --chain-config-dir=/chainconf --data-dir=/data --db-type=zapdb --plugin-dir=/data/plugins \
        --staking-tls-cert-file=/data/staking/staker.crt \
        --staking-tls-key-file=/data/staking/staker.key \
        --staking-signer-key-file=/data/staking/signer.key \
        --http-host=0.0.0.0 --http-port=$(http "$i") --http-allowed-hosts=\"*\" --staking-port=$(stake "$i") \
        --sybil-protection-enabled=true \
        --consensus-sample-size=5 --consensus-quorum-size=4 \
        --consensus-preference-quorum-size=4 --consensus-confidence-quorum-size=4 \
        --consensus-commit-threshold=2 \
        --network-require-validator-to-connect=true --network-allow-private-ips=true \
        --bootstrap-nodes=\"$(beacons "$i")\" --skip-bootstrap=false --track-all-chains=true \
        --public-ip=127.0.0.1 --api-admin-enabled=true --index-enabled=true --log-level=info
    '" >/dev/null
}

# ask prints "version peers head bootstrapped prefix" for the node on port $1.
#
# It reads both generations because a roll leaves the fleet mixed. Up to
# luxfi/constants v1.6.3 a chain hung off /v1/bc and info was JSON-RPC at
# /v1/info; from v1.6.4 the segment is /v1/chain and info is typed operations
# under /v1/info/ops. The prefix a node answers on is the fact this rolls for,
# so it is reported, not assumed.
ask() {
	local p=$1 v peers head boot prefix
	v=$(ssh "$host" "curl -s -m 6 http://127.0.0.1:$p/v1/info/ops/node/version" 2>/dev/null |
		sed -n 's/.*"version":"\([^"]*\)".*/\1/p')
	if [ -n "$v" ]; then
		prefix=chain
		peers=$(ssh "$host" "curl -s -m 6 http://127.0.0.1:$p/v1/info/ops/peers" 2>/dev/null |
			sed -n 's/.*"numPeers":"\([0-9]*\)".*/\1/p')
		boot=$(ssh "$host" "curl -s -m 6 'http://127.0.0.1:$p/v1/info/ops/chain/bootstrapped?chain=C'" 2>/dev/null |
			sed -n 's/.*"isBootstrapped":\([a-z]*\).*/\1/p')
	else
		prefix=bc
		v=$(ssh "$host" "curl -s -m 6 -X POST -H 'content-type: application/json' --data '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"info.getNodeVersion\",\"params\":[]}' http://127.0.0.1:$p/v1/info" 2>/dev/null |
			sed -n 's/.*"version":"\([^"]*\)".*/\1/p')
		peers=$(ssh "$host" "curl -s -m 6 -X POST -H 'content-type: application/json' --data '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"info.peers\",\"params\":[]}' http://127.0.0.1:$p/v1/info" 2>/dev/null |
			sed -n 's/.*"numPeers":"\([0-9]*\)".*/\1/p')
		boot=$(ssh "$host" "curl -s -m 6 -X POST -H 'content-type: application/json' --data '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"info.isBootstrapped\",\"params\":{\"chain\":\"C\"}}' http://127.0.0.1:$p/v1/info" 2>/dev/null |
			sed -n 's/.*"isBootstrapped":\([a-z]*\).*/\1/p')
	fi
	head=$(ssh "$host" "curl -s -m 6 -X POST -H 'content-type: application/json' --data '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"eth_blockNumber\",\"params\":[]}' http://127.0.0.1:$p/v1/$prefix/C/rpc" 2>/dev/null |
		sed -n 's/.*"result":"\([^"]*\)".*/\1/p')
	echo "${v:-down} ${peers:-0} ${head:--} ${boot:-false} ${prefix}"
}

list() {
	printf '%-16s %-6s %-18s %-6s %-10s %-6s %s\n' NODE PORT VERSION PEERS HEAD BOOT PREFIX
	local e i name
	for e in "${nodes[@]}"; do
		i=${e%%:*}; name=${e##*:}
		# shellcheck disable=SC2046
		printf '%-16s %-6s %-18s %-6s %-10s %-6s %s\n' "$name" "$(http "$i")" $(ask "$(http "$i")")
	done
}

# roll moves every node to $1, one at a time. A node that does not come back on
# the new prefix with four peers stops the roll where it stands: four of five is
# quorum exactly, so a second unhealthy node is the network.
roll() {
	local want=${1#v} image e i name p line v peers prefix waited
	image="$repo:v$want"
	ssh "$host" docker pull -q "$image" >/dev/null
	for e in "${nodes[@]}"; do
		i=${e%%:*}; name=${e##*:}; p=$(http "$i")
		echo "== $name ($p) before: $(ask "$p")"
		run "$i" "$name" "$image"
		waited=0
		while [ "$waited" -lt 300 ]; do
			line=$(ask "$p"); v=${line%% *}
			case "$v" in luxd/"$want") break ;; esac
			sleep 10; waited=$((waited + 10))
		done
		line=$(ask "$p")
		set -- $line; v=$1; peers=$2; prefix=$5
		echo "== $name  after: $line"
		if [ "$v" != "luxd/$want" ] || [ "$prefix" != chain ] || [ "${peers:-0}" -lt 4 ]; then
			echo "STOP: $name did not come back as luxd/$want on /v1/chain with four peers" >&2
			exit 1
		fi
		ssh "$host" "curl -s -m 6 -X POST -H 'content-type: application/json' --data '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"eth_chainId\",\"params\":[]}' http://127.0.0.1:$p/v1/chain/C/rpc" |
			grep -q "$chain" || { echo "STOP: $name does not answer $chain on /v1/chain/C/rpc" >&2; exit 1; }
	done
	list
}

case "${1:-list}" in
	list) list ;;
	roll) roll "${2:?usage: validators.sh roll X.Y.Z}" ;;
	*) echo "usage: validators.sh [list | roll X.Y.Z]" >&2; exit 2 ;;
esac