Re: elevator algorithm bug in ll_rw_blk.c

Simon Kenyon (simon@koala.ie)
Mon, 16 Nov 1998 16:24:27 -0000 (GMT)


On 16-Nov-98 Helge Hafting wrote:
> You would need to do timing tests on every physical cylinder (not
> knowing where they start in the first place) and build a big table.
> Not something we want during bootup. And timing could go wrong
> if anything else happen with the machine in the meantime.

yes, but doing this when mkfs runs might be feasable
or perhaps why not tackle a subset of the problem and just optimise swap partitions

not knowing for sure, but are writes stored per disk or per partition and could
the ordering of reads/writes be done differenly for say the swap partition as
opposed to say an ordinary file system?
putting the swap in the middle of the disk might be an option

--
simon

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/