I'd vote against supporting variable block sizes, this way. Let's
keep it simpler until we have more use cases. fair enough.
we can go forward with the copy APIs. I appear to be out voted. ;-)
On Apr 26, 2006, at 10:33 AM, Doug Cutting wrote:
Eric Baldeschwieler wrote:
Instead, I think we need the following two functions:
tOffset getBlockSize(dfsFs fs);
char** geHosts(dfsFs fs, char* file, tOffset pos);
** Think your suggestion is good. An addition... I'd rather not
assume that block size is global. Why not require a file name in
the getBlockSize call? This may prove more future proof.
Good idea. To be fully future-proof, this could even become:
tOffset* getBlockStarts(dfsFs fs, char* file);
That would permit variable sized-blocks, which could happen, e.g.,
if we someday support appending to files. Is that overkill?
** Why not wait on the dfsCopy/Move type commands? These can be
implemented via a systems call to a commandline tool already, right?
Sure, but applications frequently call these too, so it's nice to
make them easily available to C applications. At some point
they'll get written in C: better to have them in one place than in
every application. But, you're right, they're not essential.
Doug
