mogadm check returns 0.0% for I/O

Mon Apr 21 15:57:31 UTC 2008

	Make sure you're running the latest official release of the
tools and server. I've noticed this behavior when running different
versions out of SVN on the client and server.

cheers,

- Jared

--
Jared Klett
Co-founder, blip.tv
office: 917.546.6989 x2002
mobile: 646.526.8948
aol im: JaredAtWrok
http://blog.blip.tv

________________________________

From: mogilefs-bounces at lists.danga.com
[mailto:mogilefs-bounces at lists.danga.com] On Behalf Of Clinton
Goudie-Nice
Sent: Thursday, April 17, 2008 1:26 PM
To: Artur Bergman
Cc: mogilefs
Subject: Re: mogadm check returns 0.0% for I/O

Here it is:

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           0.51    0.00    0.00    8.59    0.00   90.91

Device:         rrqm/s   wrqm/s   r/s   w/s    rkB/s    wkB/s avgrq-sz
avgqu-sz   await  svctm  %util
sda               0.00    14.14  0.00 10.10     0.00   101.01    20.00
0.23   22.50  12.30  12.42
sdb               0.00    14.14  0.00 10.10     0.00   101.01    20.00
0.26   25.50  14.10  14.24
md1               0.00     0.00  0.00 23.23     0.00    92.93     8.00
0.00    0.00   0.00   0.00
md0               0.00     0.00  0.00  0.00     0.00     0.00     0.00
0.00    0.00   0.00   0.00
dm-0              0.00     0.00  0.00  7.07     0.00    28.28     8.00
0.15   21.43   7.86   5.56
dm-1              0.00     0.00  0.00  0.00     0.00     0.00     0.00
0.00    0.00   0.00   0.00
dm-2              0.00     0.00  0.00  4.04     0.00    16.16     8.00
0.15   36.50  17.50   7.07
dm-3              0.00     0.00  0.00 12.12     0.00    48.48     8.00
0.29   23.75   9.25  11.21
dm-4              0.00     0.00  0.00  0.00     0.00     0.00     0.00
0.00    0.00   0.00   0.00
fd0               0.00     0.00  0.00  0.00     0.00     0.00     0.00
0.00    0.00   0.00   0.00

This iostat command comes from the sysstat-7.0.0-3.el5 rpm

Twelve Horses <http://web.twelvehorses.com/>  	Mobile
<http://web.twelvehorses.com/info_center/whitepaper/>  	Social
<http://web.twelvehorses.com/solutions/blogging_for_business/>
Web <http://web.twelvehorses.com/solutions/website_design/>  	Email
<http://web.twelvehorses.com/technology/>  	

Clinton Goudie-Nice
Architect / Senior Software Engineer
cgoudie at twelvehorses.com

Phone: 	+1.801.571.2665 ext 3264 	
Mobile: 	+1.801.915.0629 	
Fax: 	+1.801.571.2669 	
LinkedIn: 	http://www.linkedin.com/in/cgoudie 	

Twelve Horses
13961 Minuteman Drive
Suite 125
Draper, UT 84020
www.twelvehorses.com 	

On Thu, 2008-04-17 at 10:14 -0700, Artur Bergman wrote:

	I suspect your iostat gives a different output, can you paste a
line? 

	Artur 

	On Apr 17, 2008, at 9:57 AM, Clinton Goudie-Nice wrote: 

		Running iostat -x -k 1 shows that the storage nodes are
doing IO, and are in IOwait from time to time. While running that check,
I had mogadm looping, and it still showed 0.0% all the time. 

		Clint

				Twelve Horses
<http://web.twelvehorses.com/>  	Mobile
<http://web.twelvehorses.com/info_center/whitepaper/>  	Social
<http://web.twelvehorses.com/solutions/blogging_for_business/>
Web <http://web.twelvehorses.com/solutions/website_design/>  	Email
<http://web.twelvehorses.com/technology/>  	

		Clinton Goudie-Nice
		Architect / Senior Software Engineer
		cgoudie at twelvehorses.com

		Phone: 	+1.801.571.2665 ext 3264 	
		Mobile: 	+1.801.915.0629 	
		Fax: 	+1.801.571.2669 	
		LinkedIn: 	http://www.linkedin.com/in/cgoudie 	

		Twelve Horses
		13961 Minuteman Drive
		Suite 125
		Draper, UT 84020
		www.twelvehorses.com 	

		On Wed, 2008-04-16 at 16:54 -0700, Artur Bergman wrote: 

			Log in to the host and do iostat -x -k 1 and see
what it shows

			Artur

			On Apr 16, 2008, at 3:21 PM, Clinton Goudie-Nice
wrote:

			> Greetings all,
			>
			> I'm wondering if I have something configured
incorrectly, or  
			> something not installed.
			>
			> mogadm --tracker tracker02fs:6001 check
			>
			> Checking trackers...
			>   tracker02fs:6001 ... OK
			>
			> Checking hosts...
			>   [ 1] store01 ... OK
			>   [ 2] store02 ... OK
			>   [ 3] store03 ... OK
			>   [ 4] store04 ... OK
			>   [ 5] store05 ... OK
			>
			> Checking devices...
			>   host device         size(G)    used(G)
free(G)   use%   ob  
			> state   I/O%
			>   ---- ------------ ---------- ----------
---------- ------  
			> ---------- -----
			>   [ 1] dev1            10.504      1.693
8.811  16.12%   
			> writeable   0.0
			>   [ 2] dev2             8.567      0.906
7.661  10.57%   
			> writeable   0.0
			>   [ 3] dev3            53.549      3.104
50.445   5.80%   
			> writeable   0.0
			>   [ 4] dev4            52.157      2.789
49.368   5.35%   
			> writeable   0.0
			>   [ 5] dev5            14.409      1.940
12.469  13.47%   
			> writeable   0.0
			>   ---- ------------ ---------- ----------
---------- ------
			>              total:   139.185     10.432
128.753   7.49%
			>
			> This is on mostly garbage hardware, running
CentOS 5, and I'm  
			> pounding the storage nodes with puts and gets
while this is  
			> happening. I'd expect there to be something on
I/O
			>
			> My storage node conf files looks like:
			> httplisten=0.0.0.0:7500
			> mgmtlisten=0.0.0.0:7501
			> docroot=/var/mogdata
			>
			> Any thoughts?
			>
			> Tha