On Fri, 5 Jan 2001, Robert Collins wrote:
> Sure I hate that too :]. What I meant was - the stats page doesn't
> call a storefsDirGetBlkSize() which then calls the code you've
> written if appropriate. The stats page calls it directly, so it
> _will_ require new fs drivers to be statsfs-able.
Sorry, I don't follow you.
storeDirStats() doesn't call storeDirGetBlkSize().
storeDirStats() prints the value of SD->fs.kperblk. This variable
is initialized to 1 (i.e. 1KB/block) by default, which is what the
old, hard-coded way assumed.
You could argue that storeDirStats should not print fs.kperblk
because some storage systems won't have a notion of block size.
new fs drivers don't have to be statfs-able. They can leave the
values at their defaults, which may or may not be meaningful. We
can always change this in the future if we need to.
Probably the right thing to do is make a FS method function
that returns the actual space used, including overheads.
I was too lazy to do it that way.
Received on Thu Jan 04 2001 - 19:09:30 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:09 MST