Mailing List
Home
Forum Home
Linux - General Red Hat Linux discussion list
Installation - Getting started with Red Hat Linux
Enterprise Linux 3 - Discussion of Red Hat Enterprise Linux 3 (Taroon)
Red Hat Linux 9 - Discussion of Red Hat Linux 9 (Shrike)
Red Hat Linux 7.3 - Discussion of Red Hat Linux 7.3 (Valhalla)
Red Hat Linux 7.2 - Discussion of Red Hat Linux 7.2 (Enigma)
Apache Web Server
Oracle database, Microsoft SQL server ...
Subjects
application/x mplayer2 plugin
RPM error: db4 error(16) from dbenv >remove: Device or resource
   busy
Command stream end of file while reading
X Windows problem (xauth)
Upgrading openoffice 1 1 rpm
FTP: connection refused
FTP: connection refused
mount: /dev/cdrom: is not a valid block device
Dell Precision 650, RedHat 9, no sound
how to trace the cause resulting in the crash of bind server
Virus on the list
UNINSTALL RPM MYSQL
usb pen drives: mounting as a user
broadcom network interface
make mrproper
sendmail configuration on redhat
Couldn 't open PID file /var/run/named/named pid Permission denied
Promise 378 controller
kernel 2 6 and /dev/sound/mixer not found
Problem using up2date
mrtg step by step howto/configuration for a newbie?
Compiling and Installing Kernel 2 6
Can 't locate module ppp0, can 't locate module ppp compress 21
HOW I CAN MAKE BOOTABLE FLOPPY DISKET
Lotus Notes under Wine
/etc/security/limits conf question
Intel E/1000 driver
Command stream end of file while reading
rpm database corrupt
qla2300 modules
 
Search:  
Power your search with and, or, +, -, or "some phrase" operators.
I/O Utilization Statistic Strangeness in U5

I/O Utilization Statistic Strangeness in U5

2005-06-13       - By Ed Greshko

 Back
Reply:     1     2     3     4     5     6  



Tom Sightler wrote:
> Over the weekend we upgraded several of our RHEL3 systems to U5 and
> since then we have noticed that our network monitoring started alerting
> us to high IO utilization values on multiple servers.  Upon looking into
> this problem we've found that running 'iostat -x 1' does show 100%
> utilization even though nothing is really going on on the disk.  It
> would appear that this might be a bug in iostat, or that something
> changes in /proc/partitions that iostat was using because older versions
> of iostat report even stranger numbers.
>
> Also, if we reboot a system it initially reports normal, but continues
> to grow as IO occurs.  This would imply that iostat might be reading the
> wrong information from /proc/partitions.
>
> Anyone else seeing this or is it some uniqueness on our systems?
>
> Running a quick 'iostat -x 1' and see if any of your drives show 100%
> utilization would be an easy way to show it.

Seeing the same thing.  It should be noted however that only the drive
itself shows 100%.  e.g. /dev/hdc  Individual partitions seem to
reporting just fine.  In reading the man page for iostat I see:

      Because of what seems to be a Linux kernel bug, iostat -x  may
display huge  I/O response times (svctm) and a bandwidth utilization
(%util) of 100% for some devices. Indeed these devices have a value for
the  field #9  in  /proc/{partitions,diskstats}  which is always
different from 0, and even negative sometimes. Yet this field should go
to zero, since it gives  the  number  of I/Os currently in progress (it
is incremented as requests are submitted, and decremented as they finish).

So, it appears you have stumbled upon a known issue?


--
What if everything is an illusion and nothing exists?  In that case, I
definitely overpaid for my carpet.
    -- Woody Allen, "Without Feathers"

--
Taroon-list mailing list
Taroon-list@(protected)
http://www.redhat.com/mailman/listinfo/taroon-list

Earn $52 per hosting referral at Lunarpages.