[linux-lvm] Tracing IO requests?

[Wendy Cheng]

My guess is that these reads come from parity disk(s).... And the more
fragmented your blocks, the more read(s) you'll see.

-- Wendy

On Mon, Mar 7, 2011 at 8:02 AM, Frank Ch. Eigler <fche at redhat.com> wrote:
> Bart Kus <me at bartk.us> writes:
>
>>>>> issue is why all the reads?  It should be 99% writes.
>>> cp has to read something before it can write it elsewhere.
>> Ray, my bad, I should have specified, the cp reads from a different
>> volume/set of drives. [...]
>
> One way to try answering such "why" questions is to plop a systemtap
> probe at an event that should not be happening much, and print a
> backtrace.  In your case you could run this for a little while during
> the copy:
>
> # stap -c 'sleep 2' -e '
> probe ioblock.request {
>  if (devname == "sdg2")                # adjust to taste
>    if ((rw & 1) == 0)                  # ! REQ_WRITE
>      if (randint(100) < 2)             # 2% of occurrences, if you like
>         { println(devname, rw, size)
>           print_backtrace() }
> }
> '
>
>
> - FChE
>
> _______________________________________________
> linux-lvm mailing list
> linux-lvm at redhat.com
> https://www.redhat.com/mailman/listinfo/linux-lvm
> read the LVM HOW-TO at http://tldp.org/HOWTO/LVM-HOWTO/
>