Re: sync: why disk cannot spin down

From: Andreas Bombe (
Date: Wed Aug 02 2000 - 11:35:05 EST

Disclaimer: The following statements are not hard facts but merely what
knowledge I have gathered from various sources. It may not be accurate.

On Tue, Aug 01, 2000 at 11:07:51AM +0200, Ookhoi wrote:
> I guess the heads (do they actually graze over the parking track, or
> do the arms lean on something when the disk is speeding up/slowing
> down?),

The heads touch down on the parking track when the disk spins down,
which is for this reason roughed up so that they don't stick to it when
the disk spins up again.

Some IBM (?) disks for mobile usage move their heads off the platters
onto holders whenever they don't read/write so that they are more shock
resistant when no accesses happen or the disk spins down. They have a
nice (tm) name for it, but I can't remember that right now.

> Sometimes a disk in a server runs for ages. If the disk is spun down, it
> sometimes never comes up again. What might be a technical reason for
> this? I've heard something about 'dust' which collects at the parking
> track, and in which the heads will kill themselves.

A touchdown on the parking tracks will blow the dust away, obviously.
If they don't touch down for years, too much may have accumulated so
that the heads stick when the disk spins up again. Nothing good will
come from that when they start moving around in that state.

> Ps, is the parking track equal to track 0, and is the parking track near
> the center or at the edge of a disk?

I don't think it's track 0 (the parking track can not be used for data,
after all) and I think it's usually in the middle.

When power suddenly goes away (e.g. computer switched off) the disks
have to use the rotation energy of the platters as power source to move
the heads to the parking track. That usually takes just the average
access time, so I don't think they run into power constraints here, but
I guess the disks move their heads to parking position when idle so a
position in the middle gives shorter average access times when an access

 Andreas E. Bombe <>    DSA key 0x04880A44

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to Please read the FAQ at

This archive was generated by hypermail 2b29 : Mon Aug 07 2000 - 21:00:08 EST