Should You Use UMSDOS?

The UMSDOS filesystem allows you to install Linux in an MS-DOS directory on an existing DOS partition. The advantage of this is that you won’t need to reformat or repartition your existing system. There are two disadvantages to using this system, however.

First, the UMSDOS system is somewhat slower than a native Linux filesystem. This is especially true of machines with 8 megabytes of memory or less—UMSDOS is virtually unusable on a 4MB machine. The second disadvantage of UMSDOS has to do with a shortcoming of the MS-DOS FAT filesystem. MS-DOS allocates space for files in units called clusters. A cluster is usually 4K or 8K in size. This means that the smallest file that can be created on a UMSDOS filesystem takes up a full cluster (4096+ bytes), even if the file is much smaller. Linux contains many such small files, including symbolic links and device entries. As a result, installing with UMSDOS may require more drive space than installing with a native Linux filesystem.

Now that you’ve chosen your bootdisk and rootdisk images, it’s time to actually create the bootdisk and rootdisk.

Creating the Diskettes

For this step, you’ll need two high-density diskettes. It doesn’t matter what’s on the diskettes, but they must be formatted. Be warned that this process will completely wipe out anything currently stored on the diskettes. You might also wish to format a third high-density floppy disk at this time for the installation program to use later when it’s preparing your system bootdisk.

---

NOTE:  As you’ll recall from an earlier note, the images for the rootdisks do not need to be decompressed; the kernel will automatically decompress them as they are loaded into memory.

---

In these examples, we’ll be using the BARE.I and COLOR.GZ images. If you’re using a different set of images, just substitute those filenames instead.

---

NOTE:  The procedures in this section do not need to be done on the computer you’re planning to use as your Linux workstation. You can create the files on a different PC or even use a UNIX workstation to create the floppies. On a UNIX workstation the dd command is used to write an image to the floppy drive. When using dd on Suns, and possibly on some other UNIX workstations, you must provide an approximate block size. Here’s an example:

dd if=bare.i of=/dev/(rdfd0, rdf0c, fd0, or whatever) obs=18k

---

Now it’s time to make your bootdisk. First, move into the bootdisks.144 (or bootdisks.12 if you use a 1.2MB floppy drive) directory on your Slackware CD-ROM.

Assuming your CD-ROM drive has the drive letter E: assigned to it, you’d move into the directory like this:

     C:\> E:

          E:\> CD BOOTDSKS.144

     E:\BOOTDSKS.144>

Now you’ll actually create the bootdisk. Put the eventual bootdisk diskette in drive A: and type the following command:

     E:\> RAWRITE BARE.I A:

This will use the RAWRITE command (there’s a copy of this in each of the BOOTDSKS and ROOTDSKS directories) to copy the BARE.I disk image to the A: floppy drive. As it writes, RAWRITE will give you a status report. After it’s finished writing the bootdisk, remove the disk from the drive and put it aside.

Then insert another formatted high-density floppy and use the same procedure to write the rootdisk. In this case, you’ll need to move into the ROOTDSKS directory and write the COLOR.GZ image using RAWRITE:

     E:\BOOTDSKS.144> cd \ROOTDSKS

     E:\ROOTDSKS> RAWRITE COLOR.GZ A:

There’s really not a lot to the RAWRITE command; the only things that could trip you up would be if you’re not using a high-density diskette or if the diskette is flawed.