[linux-lvm] Tracing IO requests?

[Bryn M. Reeves]

On 03/02/2011 08:09 PM, Bart Kus wrote:
> Hello,
> 
> I have the following setup:
> 
> md_RAID6(10x2TB) -> LVM2 -> cryptsetup -> XFS
> 
> When copying data onto the target XFS, I notice a large number of READs 
> occurring on the physical hard drives.  Is there any way of monitoring 
> what might be causing these read ops?

The blktrace command is extremely useful for this kind of I/O tracing. I've used
it numerous times to figure out where I/O is originating and also how it's
making its way through layers of stacked devices.

There's a conference talk overview here from a few years ago:

http://www.gelato.org/pdf/apr2006/gelato_ICE06apr_blktrace_brunelle_hp.pdf

And also a user's guide:

http://www.cse.unsw.edu.au/~aaronc/iosched/doc/blktrace.html
http://pdfedit.petricek.net/bt/file_download.php?file_id=17&type=bug

Regards,
Bryn.