Performance


 
Thread Tools Search this Thread
Top Forums UNIX for Advanced & Expert Users Performance
# 1  
Old 03-01-2002
Data Performance

Hello,

i have changed a slow server with Solaris 7 to a bigger one with
Solaris 8 (Sun Ultra 2). Now i have a real bad performance
problem (only CPU).

Solaris 7 ran with standard FTP and Samba 2.0.7.
The new machine is running ProFTP and Samba 2.0.9.
There are a lot of NFS Shares and about 70 Samba
connections at the same moment.

Does anybody know problems with any of these software
components?

Thanks,
Oli
# 2  
Old 03-01-2002
The machine has 2 GB RAM and 2 x 168 Mhz CPU.
The one before was smaller and worked better.

Top shows 99% Kernel CPU state. Average 24h is about 80%!
# 3  
Old 03-01-2002
Suggestion ...

You might want to get some stats on what is happening on your system.
I don't know if Solaris has these utilities, but you could run a number of cpusar, cpusar -P 1, cpusar -P 2, mpsar -b, mpsar -d.

The cpusar will provide stats averaging both cpu's.
The cpusar -P ? will provide stats on separate cpu's.
I've noticed on a report that I created recently that our CPU #2 was hardly being utilised !!

Might be the same case for youself? Always worth a look.

Hope that helps.
# 4  
Old 03-04-2002
Thanks for answering!

The problem is, that no tool shows the real CPU
Usage. Top shows the top 20 processes. But together
they cost about 5 % CPU Usage. If I sum all
processes, I get about 10%. Who uses the
rest?

prstat and other tools show the same.
# 5  
Old 03-05-2002
You might try increasing ncsize in /etc/system try 5000 as well as doubling that for ufs_ninode (10000).

It sounds like you have a larger problem though. Solaris out of the box is tuned for workstation use, and it sounds like you have a server here. I'd look at increasing maxpgio and slowscan. Your hardware is definitly capable of handling the loads youre subjecting it to....what you have is a kernel tuning problem.
# 6  
Old 03-06-2002
Quote:
Originally posted by olso
Thanks for answering!

The problem is, that no tool shows the real CPU
Usage. Top shows the top 20 processes. But together
they cost about 5 % CPU Usage. If I sum all
processes, I get about 10%. Who uses the
rest?

prstat and other tools show the same.
Have you checked the process table? Perhaps you have many small processes caused by an endless loop like:

A user has /bin/sh as a login shell and wants start another after login and writes in his .profile the following line which can cause such as situation:
/bin/zsh --login

Check for similar things and small problems on your systemSmilie
Login or Register to Ask a Question

Previous Thread | Next Thread

7 More Discussions You Might Find Interesting

1. UNIX for Dummies Questions & Answers

Performance issue

hi I am having a performance issue with the following requirement i have to create a permutation and combination on a set of three files such that each record in each file is picked and the output is redirected in a specific format but it is taking around 70 odd hours to prepare a combination... (7 Replies)
Discussion started by: mad_man12
7 Replies

2. Solaris

best way and best performance

Hi all, I have two storadge 3510 Fc .. with 12 disks 146Gb ..total 1752Gb each storadge. I need to use about 1.4 Tb of it. and want RAID1 .. I need 13 mount points .. So question: for best performance and redundjancy how I must do it. create 13 logical drives on each stordge with same size... (1 Reply)
Discussion started by: samar
1 Replies

3. News, Links, Events and Announcements

Announcing collectl - new performance linux performance monitor

About 4 years ago I wrote this tool inspired by Rob Urban's collect tool for DEC's Tru64 Unix. What makes this tool as different as collect was in its day is its ability to run at a low overhead and collect tons of stuff. I've expanded the general concept and even include data not available in... (0 Replies)
Discussion started by: MarkSeger
0 Replies

4. UNIX for Advanced & Expert Users

performance issue

Hi, on a linux server I have the following : vmstat 2 10 procs memory swap io system cpu r b w swpd free buff cache si so bi bo in cs us sy id 0 4 0 675236 39836 206060 1617660 3 3 3 6 8 7 1 1 ... (1 Reply)
Discussion started by: big123456
1 Replies

5. UNIX for Advanced & Expert Users

I/O performance

i want to determine I/O performance of an executable, but iostat dont give correct results because the disk that i am writing to and reading from, are not physical disk of the host machine, instead of these local disks we are using a network storage. is there any standard way in unix to get... (2 Replies)
Discussion started by: gfhgfnhhn
2 Replies

6. UNIX for Advanced & Expert Users

performance

Hi, I have this on a AIX UNIX machine : ps aux| head -20 USER PID %CPU %MEM SZ RSS TTY STAT STIME TIME COMMAND root 516 23.7 0.0 12 15808 - A 19:38:15 903:13 wait root 774 23.7 0.0 12 15808 - A 19:38:15 902:13 wait root 1290 23.6 0.0 ... (2 Replies)
Discussion started by: big123456
2 Replies

7. UNIX for Advanced & Expert Users

performance

Hi, 1-in vmstat commande line, in reply, which column is the more important to look and verify if server is very slow ? 2-how can I see how many sessions are opened with the same login ? Many thanks before. (2 Replies)
Discussion started by: big123456
2 Replies
Login or Register to Ask a Question