Just to expound on the advice other people gave, there are two limiting factors on an ext2 filesystem (which are the same as for most Unix filesystems).
First, there's the actual space available on the filesystem. Each file takes up pretty much exactly how much space it needs, and no more (actually, that's not true, as there is, on average, one half a block (where a block can be 1, 2, or 4kB) wasted per file, but that's not really all that significant). Also note that there is some overhead for the filesystem itself, and there is also some space, usually 5%, reserved for the superuser, to prevent the filesystem from becoming completely full. You might want to change that using tunefs if it's purely a data (and no logs) filesystem.
The other limiting factor is the number of inodes available. This is set at filesystem creation time and cannot be changed after the fact. Each distinct file requires one inode, and, if you run out, no more files can be created, no matter how much actual disk space you have left. By default, mke2fs creates one inode per 4kB. This means that as long as the average size of the files is 4kB or more, you'll be okay. If it's less, you'll run out of inodes before you run out of space. But having more inodes increases the filesystem overhead I mentioned above, so don't go overboard. You can see the number of inodes used and available with the ``df -i'' command.
_________________________
Bitt Faulk