> Another patch:
>
> COSS would very much benefit from a 32bit swap_filn space.
> Henrik patched things a while back to move it to a 25 bit number
> in the StoreEntry, which is a little limiting (and confusing
> when debugging COSS!)
>
> I'd like to propose that we move swap_filn back to a 32bit int,
> and we move swap_dirn to a signed char (rather than an int).
>
> Trying to tweak the StoreEntry size for optimal storage is a nice
> idea, but its rather malloc/platform dependant.
>
> I personally think that the real solution would be to implement
> a block allocator like andre's.
>
> What do people think? It'll allow me to actually complete COSS. :-)
I'd like to have COSS. I also second your idea to try and maintain the
byte boundary for data structures, but since I'm not touching them,
I'm in the hands of those who do.
If possible, I'd move all of my storage to it, esp. if it was available in
async/diskd flavours.
-- /kinkieReceived on Fri Aug 10 2001 - 01:32:44 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:10 MST