#!/bin/bash
# ansipa_pve — CheckMK local check for a Proxmox VE hypervisor node.
#
# Install: copy to /usr/lib/check_mk_agent/local/ansipa_pve and chmod 755
# (ansipa-infra-checkmk-install.sh does this for you, along with installing
# the CheckMK agent itself and registering the host).
#
# Requires only `pvesh` (ships with pve-manager on every PVE node) — no jq
# or python3 dependency. JSON is requested as "json-pretty" (one key per
# line) and scraped with a small grep/awk parser so the script works on a
# bare PVE install. Any command that fails or returns nothing degrades that
# one service to CheckMK state 3 (UNKNOWN) rather than aborting the others.
#
# Emits (CheckMK local-check format: "<state> <service> <perfdata> <text>"):
#   Ansipa_PVE_Cluster   quorum / standalone status
#   Ansipa_PVE_Storage   worst storage utilisation on this node
#   Ansipa_PVE_Guests    VM/CT counts (running vs stopped)
#   Ansipa_PVE_Backup    freshness + outcome of the last vzdump job
#
# CPU/RAM/disk-root are already covered by CheckMK's stock Linux checks —
# not duplicated here.

command -v pvesh >/dev/null 2>&1 \
    || { echo "3 Ansipa_PVE - pvesh not found (not a Proxmox VE host?)"; exit 0; }

NODE=$(hostname -s 2>/dev/null || echo "")

# Extract every value of a JSON key from json-pretty text (one "key": value per line).
_jp() { grep -oP "^\s*\"$1\"\s*:\s*\"?\K[^\",]+" || true; }

# ── Cluster / quorum ────────────────────────────────────────────────────────
CSTAT=$(pvesh get /cluster/status --output-format json-pretty 2>/dev/null || true)
if [[ -z "$CSTAT" ]]; then
    echo "3 Ansipa_PVE_Cluster - could not query /cluster/status"
else
    mapfile -t CTYPES < <(_jp type <<< "$CSTAT")
    QUORATE=$(_jp quorate <<< "$CSTAT" | head -1)
    _clustered=false
    for t in "${CTYPES[@]}"; do [[ "$t" == "cluster" ]] && _clustered=true && break; done
    if [[ "$_clustered" == false ]]; then
        echo "0 Ansipa_PVE_Cluster - standalone node (no cluster configured)"
    elif [[ "$QUORATE" == "1" ]]; then
        echo "0 Ansipa_PVE_Cluster - cluster quorate"
    else
        echo "2 Ansipa_PVE_Cluster - cluster NOT quorate"
    fi
fi

# ── Storage usage (worst-case % across all storages on this node) ────────────
SSTAT=""
[[ -n "$NODE" ]] && SSTAT=$(pvesh get "/nodes/${NODE}/storage" --output-format json-pretty 2>/dev/null || true)
if [[ -z "$SSTAT" ]]; then
    echo "3 Ansipa_PVE_Storage - could not query node storage"
else
    mapfile -t SNAMES < <(_jp storage <<< "$SSTAT")
    mapfile -t STOTAL < <(_jp total   <<< "$SSTAT")
    mapfile -t SUSED  < <(_jp used    <<< "$SSTAT")
    WORST=0; WORST_NAME=""; PERF=""
    for i in "${!SNAMES[@]}"; do
        t="${STOTAL[$i]:-0}"; u="${SUSED[$i]:-0}"
        [[ "$t" =~ ^[0-9]+$ && "$u" =~ ^[0-9]+$ && "$t" -gt 0 ]] || continue
        pct=$(( u * 100 / t ))
        PERF+=" ${SNAMES[$i]}_pct=${pct}%;80;90"
        (( pct > WORST )) && { WORST=$pct; WORST_NAME="${SNAMES[$i]}"; }
    done
    if [[ -z "$WORST_NAME" ]]; then
        echo "3 Ansipa_PVE_Storage - no usable storage entries found"
    elif (( WORST >= 90 )); then
        echo "2 Ansipa_PVE_Storage${PERF} CRIT — ${WORST_NAME} at ${WORST}%"
    elif (( WORST >= 80 )); then
        echo "1 Ansipa_PVE_Storage${PERF} WARN — ${WORST_NAME} at ${WORST}%"
    else
        echo "0 Ansipa_PVE_Storage${PERF} worst: ${WORST_NAME} at ${WORST}%"
    fi
fi

# ── Guests (VMs + containers) ─────────────────────────────────────────────────
RSTAT=$(pvesh get /cluster/resources --output-format json-pretty 2>/dev/null || true)
if [[ -z "$RSTAT" ]]; then
    echo "3 Ansipa_PVE_Guests - could not query /cluster/resources"
else
    mapfile -t RTYPES  < <(_jp type   <<< "$RSTAT")
    mapfile -t RSTATUS < <(_jp status <<< "$RSTAT")
    VMS=0; CTS=0; RUNNING=0; STOPPED=0
    for i in "${!RTYPES[@]}"; do
        case "${RTYPES[$i]}" in
            qm)  VMS=$((VMS+1)) ;;
            lxc) CTS=$((CTS+1)) ;;
            *) continue ;;
        esac
        if [[ "${RSTATUS[$i]:-}" == "running" ]]; then RUNNING=$((RUNNING+1)); else STOPPED=$((STOPPED+1)); fi
    done
    TOTAL=$((VMS + CTS))
    PERF="vms=${VMS};; cts=${CTS};; running=${RUNNING};; stopped=${STOPPED};;"
    echo "0 Ansipa_PVE_Guests ${PERF} ${TOTAL} guest(s): ${RUNNING} running, ${STOPPED} stopped"
fi

# ── Most recent vzdump backup job (from cluster task history) ───────────────
TSTAT=$(pvesh get /cluster/tasks --output-format json-pretty 2>/dev/null || true)
if [[ -z "$TSTAT" ]]; then
    echo "3 Ansipa_PVE_Backup - could not query /cluster/tasks"
else
    mapfile -t TTYPE   < <(_jp type      <<< "$TSTAT")
    mapfile -t TSTATUS < <(_jp status    <<< "$TSTAT")
    mapfile -t TSTART  < <(_jp starttime <<< "$TSTAT")
    LAST_TS=0; LAST_STATUS=""
    for i in "${!TTYPE[@]}"; do
        [[ "${TTYPE[$i]}" == "vzdump" ]] || continue
        st="${TSTART[$i]:-0}"
        [[ "$st" =~ ^[0-9]+$ ]] || continue
        if (( st > LAST_TS )); then LAST_TS=$st; LAST_STATUS="${TSTATUS[$i]:-}"; fi
    done
    if [[ "$LAST_TS" -eq 0 ]]; then
        echo "1 Ansipa_PVE_Backup - no vzdump backup job found in recent task history"
    else
        AGE_H=$(( ( $(date +%s) - LAST_TS ) / 3600 ))
        PERF="last_backup_hours=${AGE_H}"
        if [[ "$LAST_STATUS" != "OK" ]]; then
            echo "2 Ansipa_PVE_Backup ${PERF} Last vzdump job FAILED (${AGE_H}h ago): ${LAST_STATUS}"
        elif (( AGE_H >= 48 )); then
            echo "1 Ansipa_PVE_Backup ${PERF} Last successful backup ${AGE_H}h ago (stale)"
        else
            echo "0 Ansipa_PVE_Backup ${PERF} Last backup OK, ${AGE_H}h ago"
        fi
    fi
fi