#!/usr/bin/env bash
# Make validator VMIDs (1000-1004) writable by running e2fsck on their rootfs.
# Fixes "Read-only file system" / JNA UnsatisfiedLinkError when Besu tries to write temp files.
# SSHs to r630-01 (1000,1001,1002) and ml110 (1003,1004), stops each CT, e2fsck, starts.
#
# Usage: ./scripts/maintenance/make-validator-vmids-writable-via-ssh.sh [--dry-run]
# Run from project root. Requires SSH to r630-01 and ml110 (root, key-based).

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
[[ -f "${PROJECT_ROOT}/config/ip-addresses.conf" ]] && source "${PROJECT_ROOT}/config/ip-addresses.conf" 2>/dev/null || true

R630_01="${PROXMOX_HOST_R630_01:-192.168.11.11}"
ML110="${PROXMOX_ML110:-192.168.11.10}"
SSH_OPTS="-o ConnectTimeout=15 -o StrictHostKeyChecking=accept-new"

# Validators: 1000,1001,1002 on r630-01; 1003,1004 on ml110
VALIDATORS=(
  "1000:$R630_01"
  "1001:$R630_01"
  "1002:$R630_01"
  "1003:$ML110"
  "1004:$ML110"
)

DRY_RUN=false
[[ "${1:-}" == "--dry-run" ]] && DRY_RUN=true

log_info() { echo -e "\033[0;34m[INFO]\033[0m $1"; }
log_ok()   { echo -e "\033[0;32m[✓]\033[0m $1"; }
log_warn() { echo -e "\033[0;33m[⚠]\033[0m $1"; }

echo ""
echo "=== Make validator VMIDs writable (e2fsck) ==="
echo "  dry-run=$DRY_RUN"
echo ""

for entry in "${VALIDATORS[@]}"; do
  IFS=':' read -r vmid host <<< "$entry"
  if ! ssh $SSH_OPTS "root@$host" "echo OK" 2>/dev/null; then
    log_warn "Cannot SSH to $host; skip VMID $vmid"
    continue
  fi
  log_info "VMID $vmid @ $host: stop, e2fsck, start..."
  status=$(ssh $SSH_OPTS "root@$host" "pct status $vmid 2>/dev/null | awk '{print \$2}'" 2>/dev/null || echo "missing")
  if [[ "$status" == "missing" || -z "$status" ]]; then
    log_warn "  VMID $vmid not found; skip"
    continue
  fi
  if $DRY_RUN; then
    log_info "  [dry-run] would: pct stop $vmid; e2fsck -f -y /dev/pve/vm-${vmid}-disk-0; pct start $vmid"
    continue
  fi
  ssh $SSH_OPTS "root@$host" "pct stop $vmid 2>/dev/null || true"
  sleep 2
  out=$(ssh $SSH_OPTS "root@$host" "lvchange -ay /dev/pve/vm-${vmid}-disk-0 2>/dev/null; e2fsck -f -y /dev/pve/vm-${vmid}-disk-0 2>&1" || true)
  echo "$out" | tail -2
  if echo "$out" | grep -q "FILE SYSTEM WAS MODIFIED\|No errors detected\|e2fsck"; then
    log_ok "  e2fsck done for $vmid"
  else
    log_warn "  e2fsck may have failed for $vmid (LV name may differ)"
  fi
  ssh $SSH_OPTS "root@$host" "pct start $vmid 2>/dev/null" || log_warn "  pct start $vmid failed"
  sleep 2
  if ssh $SSH_OPTS "root@$host" "pct exec $vmid -- touch /tmp/.w 2>/dev/null && pct exec $vmid -- rm -f /tmp/.w 2>/dev/null"; then
    log_ok "  VMID $vmid writable"
  else
    log_warn "  VMID $vmid /tmp may still be read-only"
  fi
done

echo ""
log_ok "Done. Restart validators: bash scripts/fix-all-validators-and-txpool.sh"
log_info "Then: bash scripts/monitoring/monitor-blockchain-health.sh"
echo ""