A 24h7d up server I look after was reinstalled after a disk crash. Alas,
it is told to now have Ultra-<some salespeople blabla>-DMA IDE disks and
they are said to be fast. Well, I normally use SCSI whereever I can and
don't have ANY IDE experience, but currently these IDE-disks are dead
slow. You even notice it when doing file accesses and compiles from a
shell in the idle system.
Now, it appears the bootup scripts did not attempt any hdparm setups and
the disks are running in the slowest possible default mode (hdparm tells
that). I don't know the capabilities of the disks exactly (only they told
me they are really good) and do not really trust what I was told about
them, but I fear just running a 'hdparm -c' now is too dangerous. After
some downtime the server was just reinstalled, and I don't want to reboot
it (rather keep it slow) or risk a crash (esp. when it might corrupt the
disk once again).
So: 1) Can/should 'hdparm -c' be run while there is disk activity?
2) How good are the guesses of 'hdparm -c'? Or, how likely is it
to misdetect some feature which is then enabled and crashes the
machine.
Thanks,
Michael.
--Michael Weller: eowmob@exp-math.uni-essen.de, eowmob@ms.exp-math.uni-essen.de, or even mat42b@spi.power.uni-essen.de. If you encounter an eowmob account on any machine in the net, it's very likely it's me.
- 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/