#!/bin/bash
# {{ ansible_managed }}
# Power truenas.localdomain back on after an outage, but only when it is
# genuinely safe to do so. Called by upssched once mains has been stable,
# and once at boot by ups-restore.service (deep-drain recovery).
#
# Deliberately stateless: we ask the iDRAC whether the chassis is off
# rather than tracking whether we were the ones who shut it down. A NAS
# powered off by hand while on mains is safe, because no ONLINE event
# fires in that case and the boot path checks UPS status first.
#
# NOTE: as of now this is a best-effort secondary path. The R415 has no
# iDRAC6 Enterprise card ("iDRAC6 Ent Pres ... Absent"), so its shared-LOM
# BMC has no standby power and goes unreachable whenever the chassis is
# off - exactly when we would want it. An unreachable iDRAC is therefore
# the EXPECTED case here, and we exit quietly rather than alarming.
#
# The primary restore path needs no IPMI: the R415 power restore policy is
# set to always-on, so when the UPS cuts and then restores its output the
# server powers itself back up. Fit an iDRAC6 Enterprise card and switch it
# to dedicated mode and this script starts working with no changes.
set -uo pipefail

TAG=ups-restore
UPS={{ ups_name }}@localhost

log() { logger -t "$TAG" -- "$*"; echo "$TAG: $*"; }

# At boot, upsd may not be serving yet. Wait a bounded amount of time.
for _ in $(seq 1 30); do
    if upsc "$UPS" ups.status >/dev/null 2>&1; then
        break
    fi
    sleep 2
done

status=$(upsc "$UPS" ups.status 2>/dev/null || echo UNKNOWN)
if [[ "$status" != *OL* ]]; then
    log "UPS status is '$status', not on line - refusing to power TrueNAS on"
    exit 0
fi

power=$(/usr/local/bin/truenas-power.sh status 2>&1 || true)
case "$power" in
    *"is off"*)
        log "mains stable and chassis off - powering TrueNAS on"
        if /usr/local/bin/truenas-power.sh on; then
            log "power-on command accepted"
        else
            log "power-on command FAILED - check iDRAC at {{ idrac_host }}"
            exit 1
        fi
        ;;
    *"is on"*)
        log "TrueNAS already on, nothing to do"
        ;;
    *)
        # Expected while the box has no iDRAC6 Enterprise card: the BMC is
        # simply not on the network with the chassis powered down.
        log "iDRAC at {{ idrac_host }} unreachable - relying on the" \
            "always-on power restore policy instead ($power)"
        ;;
esac