[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

[Linux-cluster] System load at 1.00 for gfs2?



Running a gfs2 filesystem on RHEL 5.3 PPC (kernel 2.6.18-128.1.10.el5)
backed by clvm (two nodes).

# gfs2_tool list
253:4 domus:homedir1

# gfs2_tool getargs /domus1
data 2
suiddir 0
quota 0
posix_acl 0
num_glockd 1
upgrade 0
debug 0
localflocks 0
localcaching 0
ignore_local_fs 0
spectator 0
hostdata jid=1:id=196610:first=0
locktable 
lockproto 

As soon as I mount the gfs2 filesystem on either node, that node's
system load average goes to 1.00 and stays there until the filesystem
is unmounted.

top, sar and iostat all show the system as being completely idle, and
no iowait going on:

Linux 2.6.18-128.1.10.el5 (domusA.esri.com)   05/13/2009

12:00:01 AM   runq-sz  plist-sz   ldavg-1   ldavg-5  ldavg-15
12:10:01 AM         0       145      1.00      1.00      1.00
12:20:01 AM         0       145      1.00      1.00      1.00
12:30:01 AM         0       145      1.00      1.01      1.00
12:40:01 AM         0       145      1.00      1.00      1.00
12:50:01 AM         0       145      1.01      1.01      1.00
01:00:01 AM         0       145      1.00      1.00      1.00
01:10:01 AM         0       145      1.00      1.00      1.00

12:00:01 AM       CPU     %user     %nice   %system   %iowait    %steal     %idle
12:10:01 AM       all      0.09      0.00      0.46      0.02      0.00     99.43
12:20:01 AM       all      0.09      0.00      0.45      0.02      0.00     99.44
12:30:01 AM       all      0.09      0.52      0.48      0.02      0.00     98.88
12:40:01 AM       all      0.10      0.00      0.45      0.02      0.00     99.43
12:50:01 AM       all      0.09      0.00      0.45      0.02      0.00     99.44
01:00:01 AM       all      0.09      0.00      0.45      0.02      0.00     99.44
01:10:01 AM       all      0.09      0.00      0.45      0.02      0.00     99.43

Can anyone speculate on what might be causing this?  I found one other
post on the subject[1], but there were no replies.  Would any other
information be helpful?

Ray

[1]: http://www.redhat.com/archives/linux-cluster/2009-March/msg00166.html


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]