Ladies and Gents, of those of you who run AIX I have a question:
What would cause the wait of the CPU to constantly be this high? (or
what are some of the things) My Disk is barely busy, the NIC which is
etherchanneled in failover mode, doesn't appear peaked out, so I'm
looking for some ideas. Below is a snapshot of the topas screen:
Topas Monitor for host: tultsm01 EVENTS/QUEUES
FILE/TTY
Thu Nov 20 09:18:00 2008 Interval: 2 Cswitch 1275 Readch
14.0M
Syscall 1211 Writech
14.3M
Kernel 2.0 |# | Reads 187 Rawin
0
User 2.8 |# | Writes 61 Ttyout
135
Wait 83.0 |######################## | Forks 0 Igets
0
Idle 12.2 |#### | Execs 0 Namei
0
Runqueue 0.0 Dirblk
0
Network KBPS I-Pack O-Pack KB-In KB-Out Waitqueue 0.0
en3 201.2 123.5 93.0 137.7 63.5
lo0 0.0 0.0 0.0 0.0 0.0 PAGING MEMORY
Faults 0 Real,MB
10240
Disk Busy% KBPS TPS KB-Read KB-Writ Steals 0 % Comp
13.3
hdisk2 0.0 14.1K 90.5 14.0K 128.0 PgspIn 0 %
Noncomp 2.2
hdisk1 0.0 0.0 0.0 0.0 0.0 PgspOut 0 %
Client 2.2
hdisk0 0.0 0.0 0.0 0.0 0.0 PageIn 0
cd0 0.0 0.0 0.0 0.0 0.0 PageOut 0 PAGING
SPACE
Sios 0 Size,MB
512
Name PID CPU% PgSp Owner % Used
0.0
dsmserv 413784 3.1 127.7 root NFS (calls/sec) % Free
100.0
topas 266266 0.2 1.6 root ServerV2 0
gil 49176 0.0 0.1 root ClientV2 0
Press:
sshd 360670 0.0 0.9 root ServerV3 0 "h"
for help
xntpd 323600 0.0 0.4 root ClientV3 0 "q"
to quit
Box is an older rs/6000 7026, with 10 GB RAM, 2 procs, and a single LUN
that is 380 GB (someone just assigned me the whole thing that way).
Oh, running AIX 5.3 ML6, TSM 5.5.1
See Ya'
Howard Coles Jr.
Sr. Systems Engineer
Ardent Health Services
615-296-3416
John 3:16!
|