ghe-storage-verify-mysql-migration.sh

#!/bin/bash
#/ Usage: ghe-storage-verify-mysql-migration <backup-path> <destination-path>
#/ Verifies that two MySQL datadir trees are identical by comparing md5sums
#/ of every file beneath each path.
#/
#/ Example (after ghe-storage-migrate-mysql):
#/   ghe-storage-verify-mysql-migration /data/user/mysql-backup/github_enterprise /data/multi-disk/db/mysql/github_enterprise

set -e

if [ "$1" = "--help" ] || [ "$1" = "-h" ]; then
  grep '^#/' <"$0" | cut -c4-
  exit 2
fi

if [ "$#" -ne 2 ]; then
  grep '^#/' <"$0" | cut -c4- >&2
  exit 1
fi

BACKUP_PATH="$1"
DEST_PATH="$2"

[ "$(whoami)" = "root" ] || {
  exec sudo -u root "$0" "$@"
}

if [ ! -d "$BACKUP_PATH" ]; then
  echo "Error: backup path not found: $BACKUP_PATH" >&2
  exit 1
fi

if [ ! -d "$DEST_PATH" ]; then
  echo "Error: destination path not found: $DEST_PATH" >&2
  exit 1
fi

checksum_tree() {
  local root=$1
  # Produce "<md5>  <relative-path>" lines, sorted, for deterministic diff.
  ( cd "$root" && find . -type f -print0 \
      | sort -z \
      | xargs -0 md5sum )
}

TMPDIR=$(mktemp -d)
trap 'rm -rf "$TMPDIR"' EXIT

BACKUP_SUMS="$TMPDIR/backup.md5"
DEST_SUMS="$TMPDIR/dest.md5"

echo "Computing md5sums under $BACKUP_PATH..."
checksum_tree "$BACKUP_PATH" > "$BACKUP_SUMS"

echo "Computing md5sums under $DEST_PATH..."
checksum_tree "$DEST_PATH" > "$DEST_SUMS"

echo "Comparing..."
if diff -u "$BACKUP_SUMS" "$DEST_SUMS"; then
  echo "OK: $BACKUP_PATH and $DEST_PATH are identical ($(wc -l < "$BACKUP_SUMS") files)."
  exit 0
else
  echo "MISMATCH: differences found between $BACKUP_PATH and $DEST_PATH." >&2
  exit 1
fi