Hi,
I've setup a few zones on a T1000 and I'm finding that the response time is very poor. even though the load is very load and memory seems fine.
% time uptime
5:14pm up 2 day(s), 1:12, 5 users, load average: 0.28, 0.24, 0.27
uptime 0.00s user 2.83s system 130% cpu 2.161 total
% time ls -n
total 48
drwxr-x--- 2 60007 6005 241 Dec 15 10:32 hsperfdata_jboss
drwxr-xr-x 2 0 0 117 Dec 14 16:03 hsperfdata_root
drwxr-xr-x 2 60013 1 117 Dec 15 10:18 hsperfdata_XXX
ls -n 0.00s user 1.60s system 177% cpu 0.899 total
%
Response time in the global zone seem fine
# time ls -n
total 22592
-rw-r--r-- 1 0 3 53 Aug 12 06:54 csn.213
-rw-r--r-- 1 0 0 11534903 Nov 5 22:05 dot.lupi_zones.filelist.15007.15006
drwxr-xr-x 2 60002 60002 177 Aug 12 06:54 hsperfdata_noaccess
drwxr-xr-x 2 0 0 117 Aug 12 06:55 hsperfdata_root
ls -n 0.00s user 0.13s system 144% cpu 0.090 total
#
The only thing which I can seem which might be causing issues is that the zone is stored on an iscsi share off a netapp filer. However if I do something like an 'ls' in the same directory from the global zone, response time is fine.
All zones on this machine seem to have this problem. I have another t1000 box which doesn't have this problem.
Where should I be looking, what could be causing this?
running Solaris 10 11/06 s10s_u3wos_10 SPARC
Thanks