Sponsored Content
Special Forums UNIX and Linux Applications Infrastructure Monitoring Multiple Processors and Load Average Post 302842311 by Smiling Dragon on Thursday 8th of August 2013 10:29:59 PM
Old 08-08-2013
"Load average" in top is actually the run queue average length.
Over 1 means on average things are waiting on the cpu, below 1 means on average no-one has to wait. Don't confuse this with %cpu - it's not like that.

The bold summary line show percentages should always be across all the cores, but can get confused if you have the wrong version of top, so always add them up to check you get 100 the first time you use top on a new machine to check this.

As for process %cpu, that depends on your version of top - if it's compiled for your arcihtecture properly, it understands and the % is how much of one CPU is beign used (so more than 100% would require multithreading across multiple cores).

To complicate matters further, a system running at 100% cpu might not be terrible if your shceduler is beign smart - it could well be that you've got a bunch of low priority things in the background that get a bunch of work done while the system is idel, then throtle back when you need it - ie sitting at 100% you might still find that your CPU hungry command you want to run goes just fine and the cpu load happily stays at 100% during and after. It's often a waste of time to monitor CPU percentages overall.
Better is to look at:
* overall wait % ("wa") - you don't want that to get very high or it indicates something is thrashing in swap or disk.
* run queue length

In your java example:
Code:
PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
25437 root      23   0 22.7g  22g 9272 S 142.9 70.6  42140:15 java

Its saying that you have a Priority 23 task, (lower numbers get priority on CPU time) using 70.6% of your free memory and 142.9% of one CPU (ie it's multithreaded and is using about 1.5 Cores).

Last edited by Smiling Dragon; 08-08-2013 at 11:34 PM.. Reason: added the java example breakdown.
This User Gave Thanks to Smiling Dragon For This Post:
 

10 More Discussions You Might Find Interesting

1. UNIX for Advanced & Expert Users

load average

we have an unix system which has load average normally about 20. but while i am running a particular unix batch which performs heavy operations on filesystem and database average load reduces to 15. how can we explain this situation? while running that batch idle cpu time is about %60-65... (0 Replies)
Discussion started by: gfhgfnhhn
0 Replies

2. UNIX for Dummies Questions & Answers

Load Average

Hello all, I have a question about load averages. I've read the man pages for the uptime and w command for two or three different flavors of Unix (Red Hat, Tru64, Solaris). All of them agree that in the output of the 2 aforementioned commands, you are given the load average for the box, but... (3 Replies)
Discussion started by: Heathe_Kyle
3 Replies

3. Shell Programming and Scripting

Determening load average.

Hi, I'm new to shell scripting. I need to make a script to add on to my cronjobs. The script must get the value of load average from my server and if its greater than 10 it should stop my apache service. I cant find a way to get the value of load average in integer type to do the check. Any... (4 Replies)
Discussion started by: jibsonline
4 Replies

4. Solaris

load average query.

Hi, i have installed solaris 10 on t-5120 sparc enterprise. I am little surprised to see load average of 2 or around on this OS. when checked with ps command following process is using highest CPU. looks like it is running for long time and does not want to stop, but I do not know... (5 Replies)
Discussion started by: upengan78
5 Replies

5. UNIX for Advanced & Expert Users

Replicate CPU load to other processors in server

Hi Folks, We have 6 processors in our sun server. I do see that CPU usage by one of the processor is always more than 70-80% and for remaining 5 processors, its only 20%. Is there a way to delegate the excess CPU load on one of the processors in server to other processors in same server? Is... (3 Replies)
Discussion started by: vaibhav.kanchan
3 Replies

6. UNIX for Dummies Questions & Answers

Please Help me in my load average

Hello AlL,.. I want from experts to help me as my load average is increased and i dont know where is the problem !! this is my top result : root@a4s # top top - 11:30:38 up 40 min, 1 user, load average: 3.06, 2.49, 4.66 Mem: 8168788k total, 2889596k used, 5279192k free, 47792k... (3 Replies)
Discussion started by: black-code
3 Replies

7. UNIX for Dummies Questions & Answers

Load Average threshold

What should be the threshold for load average of a quad core processor? What constitutes "good" and "bad" load average values? (2 Replies)
Discussion started by: proactiveaditya
2 Replies

8. UNIX for Advanced & Expert Users

Load average in UNIX

Hi , I am using 48 CPU sunOS server at my work. The application has facility to check the current load average before starting a new process to control the load. Right now it is configured as 48. So it does mean that each CPU can take maximum one proces and no processe is waiting. ... (2 Replies)
Discussion started by: kumaran_5555
2 Replies

9. Solaris

Load Average and Lwps

NPROC USERNAME SWAP RSS MEMORY TIME CPU 320 oracle 23G 22G 69% 582:55:11 85% 47 root 148M 101M 0.3% 99:29:40 0.3% 53 rafmsdb 38M 60M 0.2% 0:46:17 0.1% 1 smmsp 1296K 5440K 0.0% 0:00:08 0.0% 7 daemon ... (2 Replies)
Discussion started by: snjksh
2 Replies

10. UNIX for Dummies Questions & Answers

Help with load average?

how load average is calculated and what exactly is it difference between cpu% and load average (9 Replies)
Discussion started by: robo
9 Replies
psradm(1M)                                                System Administration Commands                                                psradm(1M)

NAME
psradm - change processor operational status SYNOPSIS
psradm -f | -i | -n | -s [-v] [-F] processor_id psradm -a -f | -i | -n | -s [-v] [-F] DESCRIPTION
The psradm utility changes the operational status of processors. The legal states for the processor are on-line, off-line, spare, faulted, and no-intr. An on-line processor processes LWPs (lightweight processes) and can be interrupted by I/O devices in the system. An off-line processor does not process any LWPs. Usually, an off-line processor is not interruptible by I/O devices in the system. On some processors or under certain conditions, it might not be possible to disable interrupts for an off-line processor. Thus, the actual effect of being off-line might vary from machine to machine. A spare processor does not process any LWPs. A spare processor can be brought on-line, off-line or to no-intr by a privileged user of the system or by the kernel in response to changes in the system state. A faulted processor is identified by the kernel, which monitors the behavior of processors over time. A privileged user can set the state of a faulted processor to be on-line, off-line, spare or no-intr, but must use the force option to do so. A no-intr processor processes LWPs but is not interruptible by I/O devices. A processor can not be taken off-line or made spare if there are LWPs that are bound to the processor unless the additional -F option is used. The -F option removes processor bindings of such LWPs before changing the processor's operational status. On some architectures, it might not be possible to take certain processors off-line or spare if, for example, the system depends on some resource provided by the processor. At least one processor in the system must be able to process LWPs. At least one processor must also be able to be interrupted. Since an off-line or spare processor can be interruptible, it is possible to have an operational system with one processor no-intr and all other processors off-line or spare but with one or more accepting interrupts. If any of the specified processors are powered off, psradm might power on one or more processors. Only superusers can use the psradm utility. OPTIONS
The following options are supported: -a Perform the action on all processors, or as many as possible. -f Take the specified processors off-line. -F Force the transition to the additional specified state. Required if one or more of the specified processors was in the faulted state. Set the specified processors to faulted, if no other transition option was specified. Forced transitions can only be made to faulted, spare, or off-line states. Administrators are encouraged to use the -Q option for pbind(1M) to find out which threads will be affected by forced a processor state transition. -i Set the specified processors no-intr. -n Bring the specified processors on-line. -s Make the specified processors spare. -v Output a message giving the results of each attempted operation. OPERANDS
The following operands are supported: processor_id The processor ID of the processor to be set on-line or off-line, spare, or no-intr. Specify processor_id as an individual processor number (for example, 3), multiple processor numbers separated by spaces (for example, 1 2 3), or a range of processor numbers (for example, 1-4). It is also possible to combine ranges and (indi- vidual or multiple) processor_ids (for example, 1-3 5 7-8 9). EXAMPLES
Example 1: Setting Processors to off-line The following example sets processors 2 and 3 off-line: % psradm -f 2 3 Example 2: Setting Processors to no-intr The following example sets processors 1 and 2 no-intr: % psradm -i 1 2 Example 3: Setting Processors to spare The following example sets processors 1 and 2 spare, even if either of the processors was in the faulted state: % psradm -F -s 1 2 Example 4: Setting All Processors on-line % psradm -a -n Example 5: Forcing Processors to off-line The following example sets processors 1 and 2 offline, and revokes the processor bindings from the processes bound to them: % psradm -F -f 1 2 EXIT STATUS
The following exit values are returned: 0 Successful completion. >0 An error occurred. FILES
/etc/wtmpx Records logging processor status changes ATTRIBUTES
See attributes(5) for descriptions of the following attributes: +-----------------------------+-----------------------------+ | ATTRIBUTE TYPE | ATTRIBUTE VALUE | +-----------------------------+-----------------------------+ |Availability |SUNWcsu | +-----------------------------+-----------------------------+ SEE ALSO
pbind(1M), psrinfo(1M), psrset(1M), p_online(2), processor_bind(2), attributes(5) DIAGNOSTICS
psradm: processor 4: Invalid argument The specified processor does not exist in the configuration. psradm: processor 3: Device busy The specified processor could not be taken off-line because it either has LWPs bound to it, is the last on-line processor in the sys- tem, or is needed by the system because it provides some essential service. psradm: processor 3: Device busy The specified processor could not be set no-intr because it is the last interruptible processor in the system, or or it is the only processor in the system that can service interrupts needed by the system. psradm: processor 3: Device busy The specified processor is powered off, and it cannot be powered on because some platform-specific resource is unavailable. psradm: processor 0: Not owner The user does not have permission to change processor status. psradm: processor 2: Operation not supported The specified processor is powered off, and the platform does not support power on of individual processors. SunOS 5.10 17 Aug 2004 psradm(1M)
All times are GMT -4. The time now is 10:38 PM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy