mirror of
https://github.com/Security-Onion-Solutions/securityonion.git
synced 2026-06-12 13:19:22 +02:00
Josh Patterson
e536ffa363
After the boot-time mine.update, have the manager actually render the node_data pillar and log whether it came back populated. node_data: False makes salt/top.sls apply the bootstrap recovery branch instead of the manager's real config, so surfacing this in the journal makes the condition visible before so-boot-highstate runs. Best-effort and non-blocking: always exits 0 so highstate proceeds regardless.
60 lines
2.6 KiB
Bash
Executable File
60 lines
2.6 KiB
Bash
Executable File
#!/bin/bash
|
|
#
|
|
# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
|
|
# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
|
|
# https://securityonion.net/license; you may not use this file except in compliance with the
|
|
# Elastic License 2.0.
|
|
|
|
# Runs once per boot on managers (via so-boot-mine-update.service), before
|
|
# so-boot-highstate.service. Waits for the responsive minion set to settle, then
|
|
# pushes mine.update to all minions so mine-backed pillars (node IPs, ES/Redis/
|
|
# Logstash discovery) are fresh before the boot highstate renders them.
|
|
|
|
MAX_WAIT=${MINE_UPDATE_MAX_WAIT:-180} # hard backstop only
|
|
INTERVAL=10
|
|
STABLE_CHECKS=3 # up-count must hold steady this many polls
|
|
elapsed=0
|
|
prev=-1
|
|
stable=0
|
|
up=0
|
|
|
|
# Wait for the *reachable* minion set to settle rather than for every accepted
|
|
# key to report up: an operator may accept a minion's key and then intentionally
|
|
# power off that host, so requiring up >= accepted would never be satisfied and
|
|
# we'd always burn the full MAX_WAIT. Once the responsive count stops growing we
|
|
# stop waiting and run mine.update against whoever is up.
|
|
while [ "$elapsed" -lt "$MAX_WAIT" ]; do
|
|
up=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null \
|
|
| python3 -c 'import sys,json; print(len(json.load(sys.stdin)))' 2>/dev/null)
|
|
up=${up:-0}
|
|
if [ "$up" -gt 0 ] && [ "$up" -eq "$prev" ]; then
|
|
stable=$((stable + 1))
|
|
[ "$stable" -ge "$STABLE_CHECKS" ] && break
|
|
else
|
|
stable=0
|
|
fi
|
|
prev=$up
|
|
sleep "$INTERVAL"
|
|
elapsed=$((elapsed + INTERVAL))
|
|
done
|
|
|
|
echo "so-boot-mine-update: ${up} minions up (settled after ${elapsed}s); running mine.update"
|
|
/usr/bin/salt '*' mine.update --out=txt
|
|
|
|
# Best-effort: confirm the manager can render node_data (non-False) now that the
|
|
# mine is updated. node_data: False makes salt/top.sls fall back to the bootstrap
|
|
# recovery branch instead of the manager's real config, so we surface that in the
|
|
# journal here. We never block highstate -- if still empty, the recovery branch
|
|
# and later highstates self-heal.
|
|
/usr/bin/salt-call saltutil.refresh_pillar >/dev/null 2>&1
|
|
sleep 2
|
|
status=$(/usr/bin/salt-call --out=json pillar.get node_data 2>/dev/null \
|
|
| python3 -c 'import sys,json; d=json.load(sys.stdin).get("local"); print("rendered" if d else "empty")' 2>/dev/null)
|
|
status=${status:-empty}
|
|
if [ "$status" = "rendered" ]; then
|
|
echo "so-boot-mine-update: node_data renders; highstate will apply manager config"
|
|
else
|
|
echo "so-boot-mine-update: WARNING node_data still empty after mine.update; highstate may hit the bootstrap recovery branch"
|
|
fi
|
|
exit 0
|