Re: IDE drives and unmaskirq

From: Martijn van Oosterhout (kleptog@cupid.suninternet.com)
Date: Fri Apr 21 2000 - 09:20:32 EST


Mark Hahn wrote:
>
> > which always defaults to zero. But on all the machines I can
> > get my hands on I set it to one because it makes the system
> > smoother under high disk load.
>
> this is a sign that your systems are either misconfigured or old,
> since that setting is only relevant to PIO modes. seriously,
> unless you have >4 year old hardware, you owe it to yourself to
> get it into a non-crippled (DMA/UDMA) mode, rather than sugar-coating
> the horrible, archaic, PIO mode...

???

Odd, both my hard disks are UDMA. You're saying unmaskirq has
no effect on UDMA systems?

What about CDROMs? My guess is that they still use PIO and
thus unmaskirq will help there (your HDD can receive
interrupts while your CDROM is seeking).

> > off? What system s actually have a problem with this?
>
> legend has it that some very old systems can't deal with
> interrupts during a rep insw/outsw. since the setting is
> irrelevant for any modern system, defaulting to safe is correct.

Well, from the source code it seems the unmaskirq is always used
except you're saying that with modern systems the period that
interrupts are disabled is so short to not matter?

-- 
Martijn van Oosterhout <kleptog@cupid.suninternet.com>
http://cupid.suninternet.com/~kleptog/

- 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/



This archive was generated by hypermail 2b29 : Sun Apr 23 2000 - 21:00:19 EST