[Gllug] dd and iotop weirdness

[John Edwards]

On Mon, Nov 29, 2010 at 07:05:52PM +0000, general_email at technicalbloke.com wrote:
<snip> 
> What on earth is going on?

Iotop calculating I/O speed based on bad information?

Communication with drive sdb hung?

> Why should the write speeds be so far apart?

I don't believe any SATA drive is capable of 500MB/s, so sdb is likely
to be the problem.

> Where is iotop getting it's numbers from?

/proc/<proc-id>/io

> Why should starting ddrescue bump off a disk that isn't even referenced 
> in its invocation?

Maybe communication problems with sdb caused a SATA bus reset?

> What log should I check to see what happed to it?

You should look at where the kernel messages go:

/var/log/syslog (Debian-like)
/var/log/messages (RedHat-like)
dmesg (for no syslog)

> Also, my caddy/mobo isn't hot swappable AFAIK but given it has 
> disappeared from fdisk (and so presumably the kernel) is it safe to yank 
> the dead drive out so I can put it in another machine and scan it for 
> errors?

Probably not. It is likely to cause another bus reset. Just because
the kernel doesn't display it doesn't mean that the hardware is not
in use.

I would power off the machine, then only plug and wipe one of the
drives at each time.

Also if you want to securely wipe a drive then the 'wipe' program
is better than writing zeroes.


-- 
#---------------------------------------------------------#
|    John Edwards   Email: john at cornerstonelinux.co.uk    |
#---------------------------------------------------------#
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 204 bytes
Desc: Digital signature
URL: <http://mailman.lug.org.uk/pipermail/gllug/attachments/20101129/d61c7a92/attachment.pgp>
-------------- next part --------------
-- 
Gllug mailing list  -  Gllug at gllug.org.uk
http://lists.gllug.org.uk/mailman/listinfo/gllug