05-13-2013
I do not think this is going to give you a statistic you really want, but I may be mistaken - as it all depends on what you are trying to "relate" to/with each other.
The physc ($PC) value is already "relative" in the sense that you are computing it (I think) because it is an expression of the processing milliseconds used for the time period (9.1 means 91 msec per 10 msec - which is the PHYP real-time scheduling window - entitlement is guaranteed processing - if requested -, in real terms: (EC * 10) msec per 10 msec.
So if I use 91 msec - that might be 10 processors (9 running non-stop for 10msec, and one (the tenth) running only 1msec, or it could be 91 processors all running only 1 msec.
Looking at user/sys time and comparing them to physc could make sense on Power6 and earlier - where one thread running user+sys = 100 could equal physc = 1.0, but on POWER7 a single thread is considered to only be 0.66 of 1.0 while the other three threads (logical cpu 1,2,3 = even though idle is 100% are considered to be "using" .11 physc each - because there are additional processing components on a Power7 that, by definition, are not being used. In other words, it is impossible for a single thread to fully utilize a POWER7 processor potential.
In short, I think the statistic to use is just physc. You could perhaps give it a weight by multiplying it by lbusy% - but this depends on what you are trying to make "standardized".
Hope this helps (i.e. is understandable)!
Michael
7 More Discussions You Might Find Interesting
1. Solaris
Dear All,
We are going for Disaster Recovery project, the vendor asked for more details about how much is the daily data changes only. using sar / iostat can any one help me to collect this ?!
Note: only I need the changed data size not the daily increasing data. this is to know how much... (1 Reply)
Discussion started by: adel8483
1 Replies
2. What is on Your Mind?
Hi,
I got 2 courses Intermediate and advanced Solaris 10 Administration before 1 month.
I was studying the material of the 1st course I will finish it soon. I want to get the Exam. What is your advice?
Which is the best Exam Quastion ( Testking or ,,,,,,,, Etc) ....
Regards (1 Reply)
Discussion started by: adel8483
1 Replies
3. AIX
Hi All,
What do you usually use for capacity planning on AIX?
Any idea will do?
Thanks in advance,
itik (1 Reply)
Discussion started by: itik
1 Replies
4. Solaris
Hi All,
What do you usually use for capacity planning tool on solaris 8 or later?
Thanks in advance. (2 Replies)
Discussion started by: itik
2 Replies
5. AIX
Hi all,
I have the following configuration
2 ds3524 storage disk systems located over 2 locations
2 P720 server located over 2 locations
DS3524 are connected to san switch.
Each vio server has 1 fc adapter attached to a san switch.
per p720 server 2 virtual io servers. Vio 1 has 1 lun... (2 Replies)
Discussion started by: markiemark
2 Replies
6. AIX
There can be configurations in IBM Server wherein a
standalone partition is created on some supported IBM Server
Or
A VIOS - VIOC LPARs created.
Now in both cases they are lpars. But if I want to differentiate b/w a standalone LPAR vs an VIOC LPAR how can I do..?
On a... (2 Replies)
Discussion started by: Manish00712
2 Replies
7. AIX
can anyone tell me how to reduce Fs capacity by using echo zero. (3 Replies)
Discussion started by: nkchand
3 Replies
CHCPU(8) System Administration CHCPU(8)
NAME
chcpu - configure CPUs
SYNOPSIS
chcpu -c|-d|-e|-g cpu-list
chcpu -p mode
chcpu -r|-h|-V
DESCRIPTION
chcpu can modify the state of CPUs. It can enable or disable CPUs, scan for new CPUs, change the CPU dispatching mode of the underlying
hypervisor, and request CPUs from the hypervisor (configure) or return CPUs to the hypervisor (deconfigure).
Some options have a cpu-list argument. Use this argument to specify a comma-separated list of CPUs. The list can contain individual CPU
addresses or ranges of addresses. For example, 0,5,7,9-11 makes the command applicable to the CPUs with the addresses 0, 5, 7, 9, 10, and
11.
OPTIONS
-c, --configure cpu-list
Configure the specified CPUs. Configuring a CPU means that the hypervisor takes a CPU from the CPU pool and assigns it to the vir-
tual hardware on which your kernel runs.
-d, --disable cpu-list
Disable the specified CPUs. Disabling a CPU means that the kernel sets it offline.
-e, --enable cpu-list
Enable the specified CPUs. Enabling a CPU means that the kernel sets it online. A CPU must be configured, see -c, before it can be
enabled.
-g, --deconfigure cpu-list
Deconfigure the specified CPUs. Deconfiguring a CPU means that the hypervisor removes the CPU from the virtual hardware on which
the Linux instance runs and returns it to the CPU pool. A CPU must be offline, see -d, before it can be deconfigured.
-p, --dispatch mode
Set the CPU dispatching mode (polarization). This option has an effect only if your hardware architecture and hypervisor support
CPU polarization. Available modes are:
horizontal The workload is spread across all available CPUs.
vertical The workload is concentrated on few CPUs.
-r, --rescan
Trigger a rescan of CPUs. After a rescan, the Linux kernel recognizes the new CPUs. Use this option on systems that do not auto-
matically detect newly attached CPUs.
-V, --version
Display version information and exit.
-h, --help
Display help text and exit.
RETURN CODES
chcpu has the following return codes:
0 success
1 failure
64 partial success
AUTHOR
Heiko Carstens <heiko.carstens@de.ibm.com>
COPYRIGHT
Copyright IBM Corp. 2011
SEE ALSO
lscpu(1)
AVAILABILITY
The chcpu command is part of the util-linux package and is available from Linux Kernel Archive <https://www.kernel.org/pub/linux/utils
/util-linux/>.
util-linux July 2014 CHCPU(8)