Login or Register to Ask a Question and Join Our Community


UNIX for Advanced & Expert Users

CPU utlization

Login to Discuss or Reply to this Discussion in Our Community

 
Thread Tools Search this Thread
Top Forums UNIX for Advanced & Expert Users CPU utlization
# 15  
Old 03-31-2010
What do you mean by "load avg"? And when you quote specific numbers (somehow related to the number of CPU's in your server) what do you mean?

Are you expecting that your program (however number of processes it may spawn) will get distributed to different CPU's for processing without having to make specific compiler modifications to do so? If so, you are mistaken my friend.....
Last edited by druidmatrix; 03-31-2010 at 07:36 AM..
# 16  
Old 03-31-2010
Quote:
Originally Posted by druidmatrix
That is not the definition of "load" at all. Here are my load balances:
Code:
bash-3.00# w
  2:46am  up 2 day(s), 10:33,  1 user,  load average: 0.00, 0.00, 0.00

So am I to understand nothing is running at all? Here are my running processes:
Code:
bash-3.00# prstat
   PID USERNAME  SIZE   RSS STATE  PRI NICE      TIME  CPU PROCESS/NLWP
  1163 root     3624K 3152K cpu0    49    0   0:00:00 0.2% prstat/1
   288 root     3120K 2624K sleep   49    0   0:00:00 0.0% bash/1
   192 root     2520K 1640K sleep  100    -   0:00:24 0.0% xntpd/1
   610 root       10M 5960K sleep   59    0   0:00:17 0.0% httpd/1
   233 daemon   7016K 6424K sleep   59    0   0:00:12 0.0% nfsmapid/4
   476 root     8160K 2784K sleep   59    0   0:00:09 0.0% sendmail/1
   128 root     7640K 4104K sleep   59    0   0:00:15 0.0% nscd/30
   236 root     2360K 1816K sleep   59    0   0:00:00 0.0% rpc.bootparamd/1
   229 daemon   2760K 2112K sleep   59    0   0:00:00 0.0% rpcbind/1
   253 root     2456K 1912K sleep   59    0   0:00:00 0.0% ttymon/1
   201 root     2864K 1664K sleep   59    0   0:00:00 0.0% cron/1
   109 root     3096K 2224K sleep   59    0   0:00:00 0.0% picld/4
   234 daemon   2768K 2320K sleep   59    0   0:00:00 0.0% statd/1
   122 daemon   4568K 2696K sleep   59    0   0:00:00 0.0% kcfd/3
     9 root       10M 9432K sleep   59    0   0:00:33 0.0% svc.configd/17
Total: 44 processes, 166 lwps, load averages: 0.00, 0.00, 0.00

Please note it is a 1 core machine.
No, not nothing at all. Just not very much. By my definition, and please supply a better one if you have it, the base load is 0. Only running or runnable processes add to that, but not processes that are sleeping, eg because they're waiting for a timer to run out, or for user input.

Now, in your example you're showing a pretty idle machine (httpd with a total of 17 CPU seconds, while the machine is up for more than 2 days), with most processes waiting for some kind of external input or waking up occasionally (eg cron). That means the load counter isn't getting increased very much at each data point. And if the load is then averaged, the average seems to fall below 0.005 (because at that point it'd be rounded up to 0.01).
# 17  
Old 03-31-2010
I am not that expert.

Let me put it very simple.

I have 96 smilar processes to finish and i want them very fast.

which is the best way, by all that compiler parameters as default,

starting all 96 at a time or in batches of 48 or batchs of 24 ?

The time taken to process all 96 should be less.

Please explain me on this case


Regards
Kumaran
# 18  
Old 03-31-2010
True. To tell you the truth, I have not been able to make any sense of Sun's definition for either pre or post Solaris 10's load averages. In general, from experience, I have found that machines that get slow once the load averages start approaching digits (even 3-4 for me has shown noticeably slow performance) - now I have never had the experience of a 48 core machine, but have plenty of experience with Netra series quad core servers.
# 19  
Old 03-31-2010
Thanks Mr.druidmatrix

Do you think any one can help on this.
# 20  
Old 03-31-2010
I am not sure what you are asking me. But here are some pointers:
All your data is stored in the memory bank of the CPU that is running your program. Your program and all its spawned processes will be executed on a single CPU unless you compile it very specifically for multi-processor CPU's.

Generally the memory allocated for each CPU is by banks on the Sun boxes, and a particular CPU has a specific set of DIMM's dedicated to it. As long as your data structures (combined total) is not greater than the size of your memory bank (not counting the overhead space) you dont need to worry about it. In fact, when this space is exceeded, it will swap - so to the user this should be transparent. So you could potentially spwawn a thread for every single process you have.
# 21  
Old 03-31-2010
Quote:
Originally Posted by druidmatrix
That is not the definition of "load" at all.
The load average counts running processes, not idle ones.
Login or Register to Ask a Question

Previous Thread | Next Thread

10 More Discussions You Might Find Interesting

1. UNIX for Beginners Questions & Answers

Why Entitlement CPU can't be set to same as Virtual CPU?

I read that Entitlement CPU should be set to max 75% compare to Virtual CPU. May I know the reason. I have set the Entitlement CPU = Virtual CPU on AIX . It works fine . Can you help to understand. (1 Reply)
Discussion started by: gabhanes
1 Replies

2. AIX

Entitled CPU lesser Than Used CPU !!

Hi All, It may be a n00b question, but i really want to know , How Entitled Capacity is less and Used CPU is more when there is no Free CPU is available in the managed system. I have 5LPARs in a MS with Dual VIO. Managed System CPU details Available: 0.20 Assigned to partitions: 15.80... (11 Replies)
Discussion started by: Thala
11 Replies

3. UNIX for Dummies Questions & Answers

Is it possible to combine multiple CPU to act as a single CPU on the same server?

We have a single threaded application which is restricted by CPU usage even though there are multiple CPUs on the server, hence leading to significant performance issues. Is it possible to merge / combine multiple CPUs at OS level so it appear as a single CPU for the application? (6 Replies)
Discussion started by: Dissa
6 Replies

4. Solaris

Find why CPU utlization WAS high yesterday

I want to investigate why CPU utilization was high yesterday on my solaris 10 machine. I have been reported this problem but how can I investigate why CPU utilization went high at that time? :confused: (4 Replies)
Discussion started by: kashif_islam
4 Replies

5. Solaris

Difference between CPU CHIP and CPU ID

Hi All, What is the difference between CPU CHIP and CUP ID on SUN/ Oracle M5000 servers.. Thanks in advance (3 Replies)
Discussion started by: kumarmani
3 Replies

6. Solaris

CPU and CPU-Utilization

Hi, I am a weblogic Admin I our env there are 5 servers running in one Solaris 10 Sparc machine. But when i tried for process status using <top> command I got the following output load averages: 1.75, 2.18, 2.12; up 134+08:28:49 22:24:21 79 processes: 77 sleeping, 1 running,... (1 Reply)
Discussion started by: Joseph Antoine
1 Replies

7. Solaris

cpu-shares vs cpu-cap in solaris

Can anyone tell me difference between cpu-shares vs cpu-cap in solaris & how FSS will work with cpu-caps ? (9 Replies)
Discussion started by: fugitive
9 Replies

8. Solaris

Multi CPU Solaris system shows 100% CPU usage.

Hello Friends, On one of my Solaris 10 box, CPU usage shows 100% using "sar", "vmstat". However, it has 4 CPUs and prstat and glance are not showing enough processes to justify high CPU utilization. ========================================================================= $ prstat -a ... (4 Replies)
Discussion started by: mahive
4 Replies

9. UNIX for Dummies Questions & Answers

how to get persistant cpu utilization values per process per cpu in linux (! top,ps)

hi, i want to know cpu utilizatiion per process per cpu..for single processor also if multicore in linux ..to use these values in shell script to kill processes exceeding cpu utilization.ps (pcpu) command does not give exact values..top does not give persistant values..psstat,vmstat..does njot... (3 Replies)
Discussion started by: pankajd
3 Replies

10. Solaris

How to down a particular CPU in a server, witch is having 16 CPU's

Hi.., my dout is a solaris server is having 16 cpu's. in tht one cpu running some error process, accupaying more space. I wanna down tht particular CPU only with out interrupting the other 15 CPU's. how can i do this. is there any command for this ?? (5 Replies)
Discussion started by: b.janardhanguru
5 Replies
Login or Register to Ask a Question