IO To IDE Blocking In 5.1

[Mark Kirkwood]

Poor form to anwser my own question but ....

I removed and inspected the IDE cables... found one with some damage - I 
suspect this is the
cause.

Happend to get a Promise TX2000 raid card yesterday , so I reinstalled 
(+ new cables).
Retesting the scenario finds that iostat is not blocked.

regards

Mark

P.s : Still seeing loss of 2 processor scaling where *any* io is 
involved, but I will study this some more and post to smp if cant 
understand it (I wonder if its something to do with running 2 copies of 
the *same* binary).


Mark Kirkwood wrote:

> .....
> iostat blocks until the process is completed. If I start iostat 
> *first*, then it does not block, and
> I can see the io activity generated by the process when it starts.
>
> I am running the SMP kernel, but can reproduce this using GENERIC.
>
> Any ideas ?