adri wrote:
> Modified the store API so that STCHECKOBJ will return -1 if the FS
> is to be ignored, or a number between 0 and 1000 indicating the load.
> diskd returns a valid load figure. aufs, coss and ufs return constant
> load figures, which isn't very useful but its all I can think of at
> the moment. storeDirSelectSwapDir() has been rewritten again, and
> I'm sure its highly inefficient.
I'll add a load factor to aufs later. There is a queue length which
might be a good source for a load indicator, but I am not sure how it
should be scaled. Or maybe I'll add some service time measurements which
is a much better one (and can be done mostly for free).
/Henrik
Received on Sat Apr 29 2000 - 07:02:21 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:25 MST