10-05-2013
OK, this clearly looks CPU-bound:
First, have a look at the "us", "sy", "id" and "wa" columns of the "cpu" part: these are percentages, denoting the time the processors spent (on average) in the "users", "system", "idle" and "wait" parts of processing: "user" is roughly your programs, "system" is kernel activity and other system services, "idle" is when no process is running and "wait" is like idle, but with I/O operations outstanding. If you would have high "wait" percentages it would hint to a I/O-bound system, but this isn't the case here. In fact your system is busy to saturation running your application, which is as it should be. If it is too slow the only thing that helps is more processing power.
Alas the system cannot get more processors right now. The last column, "ec" is the "entitled capacity" and it is at near 100(%) too. LPARs get some share of the systems processors per default, but can be entitled to some bigger amount should the necessity arise. These additional resources are dynamically added should the system get near saturation and are dynamically relinquished once the situation gets less demanding. This system already has already allocated as much as it will ever get and this still isn't enough.
Now, lets look at the top line of the output: you have 10 logical CPUs. What a "logical CPU" comprises (some fraction of a physical CPU) depends on the physical CPU backing it and ultimately on the hard you run: POWER5? POWER6? POWER7? It might be that 10 lCPUs are a poor layout for your underlying hardware and overtax the physical CPUs with too many context switches.
Anyway, you definitely have to add CPUs to this LPAR: at the HMC modify the LPAR profile to add more (physical) CPUs as "desired" and also increase the "maximum" processors to a new sensible value. To know what a "sensible value" for "maximum" is you probably will have to monitor the system for a while, so go with a good estimation and change that after a few days. After you changed the profile you will have to reboot (cold reboot/power cycle - simple "shutdown -r" won't help) to have the new profile used.
I hope this helps.
bakunin
These 2 Users Gave Thanks to bakunin For This Post:
9 More Discussions You Might Find Interesting
1. AIX
We are planning to move to AIX 5.3 and we would like to know if someone has had any 'bad' experiences with it.
We have a 32PE p690 Regatta and currently we are running the latest AIX 5.2 with the latest patches. Has anyone any interesting points to mention when transitioning to AXI 5.3?
Is... (1 Reply)
Discussion started by: miket
1 Replies
2. AIX
After install fix pack or APAR, if aix need reboot? if not, do we need stop database and all applications before we install fix pack or APAR? (3 Replies)
Discussion started by: rainbow_bean
3 Replies
3. AIX
Hi,
redbook documentation is telling that IY17981 fix is required for aix 4.3.3 to aix 5L migration. But there is no mention about that fix in any ML installation packages.
- My system is ML11 :
oslevel –r
4330-11
- But xlC.rte is on wrong version :
lslpp -L xlC.rte
xlC.rte ... (3 Replies)
Discussion started by: astjen
3 Replies
4. AIX
Hi,
I want to print from AIX 5.3/6.1 using 'pr' preprocessing filter and 'PCL' print file type.
Steps:
1. Smitty
2. Print Spooling
3. Create a print queue(remote->Generic)
4. change the attributes for that print queue.
5. Change print file type to PCL and... (1 Reply)
Discussion started by: meeraramanathan
1 Replies
5. AIX
Hi All,
I have this fix for AIX (5300-06-06-0811) and i need to install it.
How can i do this?
What are the prerequisites for this fix?
Thanks (1 Reply)
Discussion started by: lucaxvu
1 Replies
6. AIX
We have tried to install an APAR fix IZ20298 on a AIX test server. It is requiring a base level of bos.adt.prof of 5.3.0.0 I cannot find this file anywhere. I fould 5.3.0.1 and it still will not install without the base install. Any ideas where I can find bos.adt.prof 5.3.0.0? (1 Reply)
Discussion started by: daveisme
1 Replies
7. AIX
Hi
Could somebody explain me how AIX is using CPU??
For example when we have 2 processors system is giving all task to one of them till 100% is used ?? Or it's depend on configuration or anything else ??
Best regards
enda (3 Replies)
Discussion started by: enda
3 Replies
8. AIX
Hi All,
i'm try to update my aix 6100.06.05 to 6100.07.00.
i download the 4,5 GB of FixPack buy i don't have a required package (devices.chrp.pci.rte 6.1.7.0)
This package does not exist on the fix pack (i've check in the .toc file and in the .bff files)
On ibm website i see that this... (0 Replies)
Discussion started by: Zio Bill
0 Replies
9. AIX
Guys,
I have a question - when nmon reports a sizeable %CPU wait, does that mean -
1) IO operations are slowing CPU down, OR
2) paging slowing the CPU down, OR
3) one cant tell??
I thought the nmon documentation clearly suggested that CPU waits reported in nmon were from disk... (4 Replies)
Discussion started by: getback0
4 Replies
utild(1M) utild(1M)
NAME
utild - System-utilization collection daemon
SYNOPSIS
DESCRIPTION
is a lightweight daemon that records system-utilization data on a 5-minute interval. System-utilization data includes CPU, memory, disk,
and network data. is installed as part of the software, which also contains a WBEM provider that is the interface to the data collected by
stores up to 30 days worth of utilization data and consumes minimal system resources. The total disk space consumed by these data files
should not exceed 20 megabytes in the default installation. is respawned if it is killed, due to the following entry in /etc/inittab:
WARNINGS
Removing the removes any historical data that has been collected by as well as prevents and from functioning properly. To disable the
software can be removed with the following command (see swremove(1M)):
FILES
WBEM mof files documenting the class schema for retrieving utilization data
collected by
Data and configuration files. These files contain the definitions of
all workloads created on the system, and up to 30 days of collected utilization data. To ensure continuity of data
collection and prevent loss of workload definitions, HP recommends including this directory in daily backups.
AUTHORS
was developed by the Hewlett-Packard Company.
SEE ALSO
cimserver(1M)
utild(1M)