poor fdc(4) performance

Peter Jeremy PeterJeremy at optushome.com.au
Sat Nov 12 07:37:15 GMT 2005


On Sat, 2005-Nov-12 16:18:15 +0900, Pyun YongHyeon wrote:
>I encountered a P3 SMP system that shows poor fdc(4) performance.
>But when I use larger block size, say 36b, it seems it works
>as expected.

36b is one track.  My suspicion is that the system isn't fast enough
to read sequential blocks, one at a time, so you're forced to wait
a complete revolution (plus a bit) for each block you read.

-- 
Peter Jeremy


More information about the freebsd-hackers mailing list