Welcome to Experts Exchange

Add your voice to the tech community where 5M+ people, just like you, are talking about what matters.

  • Help others & share knowledge
  • Earn cash & points
  • Learn & ask questions
Solved

Performance issues

Posted on 2013-05-15
6
319 Views
Last Modified: 2013-05-31
Can some one share some experience on how to take a look at the performance issue on linux servers. normally people come to me and say i have performance issue in certain linux server, how do i start looking into the performance measure on linux servers

I am using redhat 5/6
0
Comment
Question by:ittechlab
  • 2
  • 2
  • 2
6 Comments
 
LVL 19

Expert Comment

by:jools
ID: 39167906
This is best measured over a period of time so that you have some sort of baseline to go on.

I use atop as it has good logging and playback facilities, you can use vmstat/iostat and sar for the overview performance type stuff but atop give a more granular view of the system.

If you already have it running you can check the logs and run thru the performance, on a busy server this will indicate some busy and quiet periods, there may be a way to produce some graphical views, if you have a large setup you can use nagios/zenoss to monitor system performance and produce pretty graphs for manager types :-)
0
 
LVL 8

Assisted Solution

by:Pepe2323
Pepe2323 earned 334 total points
ID: 39168015
well you can use top to check what is going on into the server.

Other option is use sar, sar has several option depends what you want to get.

sar -u --> is for cpu, to get a more accurate information i used to run like this sar -u 50 ( means i till take 50 samples of the cpu and then will show me the cpu status)
sar -r .. > is for memoery

sar also can be helpful if  the problem has passed but you want to check at what time did happen.

 sar -f /var/log/sysstat/sa04 -- using the log collected by the crontab

for more information how to enable sar to collect logs of the server performance check this link:

http://bencane.com/2012/07/sar-sysstat-linux-performance-statistics-with-ease/

finally you can list the top 10 process are using more resources.

ps -eo pcpu,pid,user,args | sort -k 1 -r | head -10 --> this top ten is based on cpu

for memory

ps -eo pid,ppid,rss,vsize,pcpu,pmem,cmd -ww --sort=pid

Regards.
0
 

Author Comment

by:ittechlab
ID: 39168085
I am not allowed to install atop in my environment.
0
Master Your Team's Linux and Cloud Stack!

The average business loses $13.5M per year to ineffective training (per 1,000 employees). Keep ahead of the competition and combine in-person quality with online cost and flexibility by training with Linux Academy.

 

Author Comment

by:ittechlab
ID: 39168101
sar -u 50
Linux 2.6.18-274.12.1.el5 (ulmdrpp1)    05/15/2013

09:39:54 AM       CPU     %user     %nice   %system   %iowait    %steal     %idle
09:40:44 AM       all      0.11      0.00      0.12      1.56      0.00     98.21
Average:          all      0.11      0.00      0.12      1.56      0.00     98.21

I ran sar -u 50, can you explain what is these numbers mean in details. Thanks
0
 
LVL 19

Assisted Solution

by:jools
jools earned 166 total points
ID: 39168272
is sar et al are your only options then use this as a reference (saves wasting time)

http://www.thegeekstuff.com/2011/03/sar-examples/


You need to collect the data still.
0
 
LVL 8

Accepted Solution

by:
Pepe2323 earned 334 total points
ID: 39168475
That means


%user

    Lists the percentage of time that the processor is in user mode
    ( Process started by a user like Database, appservers and more )

%nice:
Percentage of CPU utilization that occurred while executing at the user level with nice priority.

%system

    Lists the percentage of time that the processor is in system mode ( means running by kernel)

%iowait

    Lists the percentage of time that the processor is idle and waiting for I/O completion
   CPU spends waiting for I/O with no processes to run -- usually related with disk slowness

%steal
Percentage of time spent in involuntary wait by the virtual CPU or CPUs while the hypervisor was servicing another virtual processor.
(steal time is a metric that only has meaning in a virtualized computing environment. It represents the amount of CPU that is taken away from a virtual machine to serve other purposes.)

%idle

    Lists the percentage of time that the processor is idle and not waiting for I/O
    (Means you cpu is free)
0

Featured Post

Master Your Team's Linux and Cloud Stack

Come see why top tech companies like Mailchimp and Media Temple use Linux Academy to build their employee training programs.

Question has a verified solution.

If you are experiencing a similar issue, please ask a related question

Suggested Solutions

Title # Comments Views Activity
ftp to port 21 4 53
linux 13 75
What is the best way to transfer files from and to Linux VNC window? 9 49
WordPress: Debugging from my Windows 10 Desktop 6 26
Introduction We as admins face situation where we need to redirect websites to another. This may be required as a part of an upgrade keeping the old URL but website should be served from new URL. This document would brief you on different ways ca…
Setting up Secure Ubuntu server on VMware 1.      Insert the Ubuntu Server distribution CD or attach the ISO of the CD which is in the “Datastore”. Note that it is important to install the x64 edition on servers, not the X86 editions. 2.      Power on th…
Learn how to get help with Linux/Unix bash shell commands. Use help to read help documents for built in bash shell commands.: Use man to interface with the online reference manuals for shell commands.: Use man to search man pages for unknown command…
This demo shows you how to set up the containerized NetScaler CPX with NetScaler Management and Analytics System in a non-routable Mesos/Marathon environment for use with Micro-Services applications.

809 members asked questions and received personalized solutions in the past 7 days.

Join the community of 500,000 technology professionals and ask your questions.

Join & Ask a Question