Re: Journaling pointless with today's hard disks?

Steve Underwood (steveu@coppice.org)
Tue, 27 Nov 2001 09:57:00 +0800


Jonathan Lundell wrote:

> At 12:49 AM +0100 11/27/01, Martin Eriksson wrote:
>
>> I sure think the drives could afford the teeny-weeny cost of a power
>> failure
>> detection unit, that when a power loss/sway is detected, halts all
>> operations to the platters except for the writing of the current sector.
>
>
> That's hard to do. You really need to do the power-fail detection on the
> AC line, or have some sort of energy storage and a dc-dc converter,
> which is expensive. If you simply detect a drop in dc power, there
> simply isn't enough margin to reliably write a block.
>
> Years (many years) back, Diablo had a short-lived model (400, IIRC) that
> had an interesting twist on this. On a power failure, the spinning disk
> (this was in the days of 14" platters, so plenty of energy) drove the
> spindle motor as a generator, providing power to the drive electronics
> for several seconds before it spun down to below operating speed.
>
> Of course, that was in the days of thousands of dollars for maybe 20MB
> of storage....

Quite true. The drives really need to get an "oh heck, the power's about
to die. Quick, tidy up" signal from the outside world (like down the
ribbon). Cheap, at the limit, PSUs probably couldn't give enough notice
to be very helpful. Server grade ones should - they can usually ride
over brief hiccups in the power, so they should be able to give a few
10s of ms notice before the regulated power lines start to droop.
Perhaps the ATA command set should include such a feature, so the OS
could take instruction from the hardware on the power situation, and
tell the drives what to do.

Regards,
Steve

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