Hi all,

How to reduce the load average? I have two linux machines.. now my problem is that both the machines having same configuration and same processes are running in those two machines... But in one machine the load average is more than 3 and in other it is 0.5(when i am using top command).

For this load average one machine(where load average is more) is slow when i am running application on it..

Can anybody pls help me out..?

I want to know how to reduce it...


Thanks in advance

So what's different in these machines hardware and software-wise? What process are you talking about? Is the process being used similarly, like the same amount of clients, in both machines? Does load stay high from the start or does it gradually settle or does it only happen when used to its limits? If this application has configuration files, is there any difference between them on the two machines? Please try to be as verbose as possible with technical details.

In case of h/w and s/w both the machines are same.. no difference between them..

Same java processes are running in both the machine..

No difference between the configuration files...

I found the load avg of one is machine is gradually increase from 2.5 to 3.. and it stat with 2.4...

and another machine it is 0.4 to 0.6...

I am not understanding that if the configurations are same the why the diffrnc between the load avg and it leads to the slow performance of a machine

You mentioned that there are some Java processes running. What do they do? Have you run "top" on both systems to see what processes are using the most CPU time? Perhaps one system is being hit across the network and those Java processes are working a lot harder on the high load system.

Can you cut-n-paste the "top" output from both systems into a reply to this thread? It'll help if we can see what's going on.

--
Rick

after executing top command on two machines...

Machine which is faster than the other-
top - 20:18:22 up 3:05, 4 users, load average: 0.11, 0.21, 0.26
Tasks: 160 total, 3 running, 157 sleeping, 0 stopped, 0 zombie
Cpu(s): 45.4% us, 1.0% sy, 0.0% ni, 53.3% id, 0.0% wa, 0.3% hi, 0.0% si
Mem: 511944k total, 505896k used, 6048k free, 34868k buffers
Swap: 1024116k total, 305188k used, 718928k free, 45700k cached

Machine which is slow-

top - 20:10:08 up 1 day, 11:26, 4 users, load average: 2.37, 2.30, 2.33
Tasks: 187 total, 1 running, 186 sleeping, 0 stopped, 0 zombie
Cpu(s): 8.7% us, 1.0% sy, 0.0% ni, 73.6% id, 16.6% wa, 0.1% hi, 0.1% si
Mem: 511944k total, 506184k used, 5760k free, 34392k buffers
Swap: 1024116k total, 512056k used, 512060k free, 13936k cached

Actually, we need to see that and the top 5 or 10 processes running at that time, so we can see the load AND what's causing it.

There are few factors that determine the Load Average of the Server Load. If the server uses dual processors the acceptable server load average is 2.00. This load is considered optimal.

Give the command "top" and check which process is utilizing more resources.

Check for mainly these processes.

1)sendmail

2)mysql

3)java.

These applications running status depend upon the applications you install and use them.

Most of the times sendmail process will run multiple times. So once restart the sendmail process to make it normal.

/etc/init.d/sendmail restart


Thanks & Regards,
Gopal Varma

give top output from both the machines for better understanding of others

Guys, my last query/answer was 2 years ago; I'd let this one go.