02-03-2004
I don't know where you got that .3 but it's way too low. You have double digit idle times on every cpu. You do have two processes that spend 98% of their time in the cpu. The kernel knows this and has given them a nasty priority. They only run when nothing else wants to. Since you have double digit idle times on each of your four cpu's, yes they run a lot.
HP has a product called glance or maybe it's glance-plus now. It looks like you can download a trial version
here. Try it. It will tell where your bottlenecks are.
10 More Discussions You Might Find Interesting
1. UNIX and Linux Applications
Ello group,
I have general question about how the performance of server/client should be?
My server is able to answer about 650times per second. Is it good performance?
the apache on the same machine makes 1600/sec BUT there is nine instances of httpd daemon what makes 180/ sec /instance.
of... (1 Reply)
Discussion started by: tomjan
1 Replies
2. UNIX for Dummies Questions & Answers
Hi,
I am supposed to run few jobs based on the usage of unix server. How to find out if the server is too busy. what are the commands we can use to find out that.
Thanks (1 Reply)
Discussion started by: dnat
1 Replies
3. Solaris
Hi,
i would like to ask if it is possible to get the server load on a solaris machine, but i don't want something like uptime (load average), iostat and vmstat. I would like to get something in percentage like CPU load in %, Disk usage in %, Ram usage in %.
I want to collect this data and to... (3 Replies)
Discussion started by: tafil
3 Replies
4. Solaris
Hi,
Please advice .. if server is slowness then what are the steps i have to follow...
Thanks,
Mani (5 Replies)
Discussion started by: Mani_apr08
5 Replies
5. Infrastructure Monitoring
There is a big problem with the server (VPS based on OpenVZ, CentOS 5, 3GB RAM). The problem is the following. The first 15-20 minutes after starting the server is operating normally, the load average is less than or about 1.0, but then begins to increase sharply% wa, then hovers around 95-99%.... (2 Replies)
Discussion started by: draiphod
2 Replies
6. Solaris
hi all,
My server box is slow running. I have provide some statistics below:
Where is the bottleneck on the server?
I guess the bottleneck is disk I/O?
bash-3.00# prstat -Z
PID USERNAME SIZE RSS STATE PRI NICE TIME CPU PROCESS/NLWP
29206 mobi1 334M 264M sleep ... (8 Replies)
Discussion started by: buyantugs
8 Replies
7. AIX
Hi,
I am new registered user here in this UNIX forums.
I am a new system administrator for AIX 6.1. One of our servers performs poorly every time our application (FINACLE) runs many processes/instances. (see below for topas snapshot)
I use NMON or Topas to monitor the server utilization. I... (9 Replies)
Discussion started by: guzzelle
9 Replies
8. UNIX for Advanced & Expert Users
Hi,
how can we define performance of a server (Windows or Unix or Linux) ?
If processes waiting for CPU (on queue) are usually more than 3 or 5 can we conclude that CPU is not enough for that usage ?
Thank you. (1 Reply)
Discussion started by: big123456
1 Replies
9. Red Hat
Hi Guys,
I am running Oracle database on RHEL 2.6.18-164.el5, now I want to check and make sure that my server is performing optimally.
I check top:
top - 09:45:03 up 2 days, 15:22, 3 users, load average: 2.57, 2.85, 2.77
Tasks: 433 total, 3 running, 430 sleeping, 0 stopped, 0... (1 Reply)
Discussion started by: Phuti
1 Replies
10. UNIX for Advanced & Expert Users
We are wondering if we are facing performance issue in our server when running Informatica jobs. Two things to suspect:
cache memory never comes down even when Top shows > 99% used.
There is some contention io or network related or Cache is clogged
top - 20:58:20 up 16 days, ... (3 Replies)
Discussion started by: smart_guy471
3 Replies
dappprof(1m) USER COMMANDS dappprof(1m)
NAME
dappprof - profile user and lib function usage. Uses DTrace.
SYNOPSIS
dappprof [-acehoTU] [-u lib] { -p PID | command }
DESCRIPTION
dappprof prints details on user and library call times for processes as a summary style aggragation. By default the user fuctions are
traced, options can be used to trace library activity. Output can include function counts, elapsed times and on cpu times.
The elapsed times are interesting, to help identify functions that take some time to complete (during which the process may have slept).
CPU time helps us identify syscalls that are consuming CPU cycles to run.
Since this uses DTrace, only users with root privileges can run this command.
OPTIONS
-a print all data
-c print function counts
-e print elapsed times, ns
-o print CPU times, ns
-T print totals
-p PID examine this PID
-u lib trace this library instead
-U trace all library and user functions
EXAMPLES
run and examine the "df -h" command,
# dappprof df -h
print elapsed times, on-cpu times and counts for "df -h",
# dappprof -ceo df -h
print elapsed times for PID 1871,
# dappprof -p 1871
print all data for PID 1871,
# dappprof -ap 1871
FIELDS
CALL Function call name
ELAPSED
Total elapsed time, nanoseconds
CPU Total on-cpu time, nanoseconds
COUNT Number of occurrences
DOCUMENTATION
See the DTraceToolkit for further documentation under the Docs directory. The DTraceToolkit docs may include full worked examples with ver-
bose descriptions explaining the output.
EXIT
dappprof will sample until Ctrl-C is hit.
AUTHOR
Brendan Gregg [Sydney, Australia]
SEE ALSO
dapptrace(1M), dtrace(1M), apptrace(1)
version 1.10 May 14, 2005 dappprof(1m)