| Previous | Table of Contents | Next |
by Jack Tackett
Various kinds of problems can result in loss of data: files get accidentally removed, hardware fails, important information stored in files is no longer available. Users should feel confident that, in such cases, they can access a timely backup of the “lost” files.
Your company’s future—and your future with your company—may depend on making those backup files available. At such times, you and others will be thankful that you’ve taken the time and effort to copy files to some sort of storage media according to a regular, rigorous, and well-documented schedule. Backing up files isn’t very glamorous, but no administrator can ignore the process.
The following are several issues to consider when backing up a system:
From an administrator’s point of view, the file system should be backed up according to some automated process with as little operator intervention as possible. It should also be done when the system is relatively quiet so that the backup is as complete as possible. This consideration must be balanced with convenience and costs. Should an operator or administrator have to stay until midnight on Friday to perform a full backup? Is it worth $2,000 for a DAT tape drive so that the entire system can be backed up automatically at 3 a.m. with no operator intervention?
Consider the alternatives, determine the true costs, and make a decision or recommend a course of action. It’s generally a lot cheaper and always easier to restore well-managed backup information than to re-create it or do without it.
The purpose of performing backups is being able to restore individual files or complete file systems as rapidly and easily as possible. Whatever you do about backups should be focused on that central purpose.
Set up a backup plan. Include the files to be backed up, how often they’ll be backed up, and how the files are to be restored. Let all users know the backup schedule and how they can request restoration of files. Be sure to stick with the plan.
Be sure to verify your backups. This could include reading a table of contents from the backup medium after it’s stored or restoring an arbitrarily chosen file from the medium. Remember that it’s possible for the backup medium—disk or tape—to have flaws.
Make backups so that files can be restored anywhere on the file system or on another computer system. Use backup or archive utilities that create archives that can be used on other Linux or UNIX computer systems.
Be sure to label all media—tapes, disks, whatever—used in a backup. If you have to use multiple tapes or disks, make sure that they’re numbered sequentially and dated. You must be able to find the file or files you need.
Plan for a disaster. Make copies of the files on your system so that the entire system can be restored in a reasonable amount of time. Store copies of backup tapes or disks off-site. The last sentence is very important! You should store at least one copy of your backup material off-site, away from your computers. If a disaster (such as a fire) wipes out your system, it will more than likely also destroy your nearby backups. Many businesses rent a safe deposit box to store their tapes and disks in. You should store a complete hardware list in the same off-site location so that you would be able to reorder identical parts should a disaster occur.
Plan to re-evaluate your backup procedures periodically to make sure that they’re meeting your needs.
Several tools are available that can help automate your backup procedure. Check out the Linux archives on sunsite.unc.edu for more information. Also, Linux supports the FTAPE extensions. FTAPE lets you perform backups to QIC-80 magnetic tape units that run off a floppy controller on your system. For detailed information, refer to the FTAPE HOWTO guide.
| Previous | Table of Contents | Next |