Tzahi
Thx - Fair enough - I can look in archives.

I may be mistaken, but afaik, there is no /proc/sys/vm/block_dump on Red Hat EL3 - I couldn't find any /proc counters that were per process and all the counters I can see
are system-wide.

Looking for a real solution today; I started poking around io-accounting and taskstats - lot of interesting stuff in the 2.6.19 kernel, but I have a production system and I dont have the luxury of doing kernel updates and patching stuff. Gotta go with what I have.

Still looking.

Danny

Tzahi Fadida wrote:
Check out the archives.
We discussed this in the past.
IIRC, you can use echo "1" > /proc/sys/vm/block_dump (it might also involve /proc/sys/vm/laptop_mode but i can't remember why).
and then tail /proc/kmsg to see the dump of the processes i/o requests.

On Wednesday 20 December 2006 12:32, Danny Lieberman wrote:
guys

How do I get the real IO (block reads/writes per second, not cached) of
each process on a running Linux system?
vmstat and iostat dont provide process level detail

I'm looking at a system right now which is CPU idle but very IO busy and
I cant figure out who's moving the disks around.


I thought this would be the most trivial question....maybe it is....

10x


--
Danny Lieberman


Call us today!
--------------------------------------------------------------------------------------------
www.software.co.il - Deliver secure software to your customers
www.opensolutions.co.il - Reduce operational risk of information security
www.extrusiondetection.net - Stop data theft
www.software.co.il/pta     - Download a free copy of the PTA-Practical threat 
analysis tool
--------------------------------------------------------------------------------------------
Tel Aviv   + 972  3 610-9750
Bethesda   + 1-301-841-7122
Cell       + 972 54 447-1114


=================================================================
To unsubscribe, send mail to [EMAIL PROTECTED] with
the word "unsubscribe" in the message body, e.g., run the command
echo unsubscribe | mail [EMAIL PROTECTED]

Reply via email to