What is a good approach for a performance testing tool suite for web applications? I am specifically interested in tools that execute a certain set of tasks well as opposed to tuning high traffic sites. In other words, a profiler would be a good idea to have, although I understand these tools are specific to a language. A profiler will help me understand where most time is spent in executing a particular part of the code, but does not provide me with a start-to-end view of where performance could be improved. Is there a tool that provides profiling data on where in the chain browser, web server, application server, database server most time is spent?
Hi,
We have HP OpenView tool to extract utilization report and extract them in csv. Every month I pull 30 days CPU and Memory utilization, every 5 minutes via GUI and export it in csv (excel) format. It is always a time consuming process to run it on a set of servers and then pick next set because... (0 Replies)
Dear experts ,
Pls advice for any good Tool to monitor the CPU and performance of AIX the system ..
to keep monitoring to show me the utilization of that system .. (12 Replies)
Hello friends,
I'm working on a Thesis and right now I'm in a phase of comparing a Linux vs Windows performance in similar situations on the same machine.
I'm asking here because I would like help on this, since I've always worked in Linux as an Administrator and a user, never as a... (6 Replies)
I'm doing performance testing for one application which works on AIX.
But I don't know which performance parameters of memory need to be collected. Now, I just know very few:
1. page in
2. page out
3. fre
They are all collected by "vmstat" command.
I want to know, except for above... (2 Replies)
So, I've been told and heard a million times that malloc and free are expensive calls to be avoided. So many times I avoid malloc by reusing already allocated memory blocks. Store them on free lists somewhere myself and don't call free when I know malloc will be called very shortly thereafter.
... (6 Replies)
Could someone point me in the correct direction or web link containing instructions for installing the System Performance Tool (aka STP) software on an IBM-AIX version 4.? machine. My client has the software (that came from their original server) on a 3" floppy. Thanks! (1 Reply)
CHUDREMOTECTRL(1) General Commands Manual CHUDREMOTECTRL(1)NAME
chudRemoteCtrl - start or stop the collection of performance monitor data in a performance monitor remote server application.
SYNOPSIS
chudRemoteCtrl [ -m ] [ executable [args... ] ]
chudRemoteCtrl -s label
chudRemoteCtrl -e
chudRemoteCtrl -k PID
DESCRIPTION
chudRemoteCtrl is a command line tool that allows for the collection of performance data by any active performance monitor remote server
application. There are currently two CHUD Tools that can be put in remote performance monitor server mode: MONster, and Shark (as well as
their command line counterparts). Typically, chudRemoteCtrl is invoked on the command line or in a shell script, followed by the path to an
executable to be measured and its arguments. chudRemoteCtrl issues a chudStartRemotePerfMonitor message immediately after launching the
specified target program. When the launched program terminates, chudRemoteCtrl issues a chudStopRemotePerfMonitor message, and then exits.
When the '-s', '-e' or '-k PID' options are used, no program is launched.
OPTIONS -r seconds: If the 'chudStartRemotePerfMonitor' message fails to either acquire or start the remote monitoring service, then keep try-
ing to start again, until the specified number of seconds has elapsed. The same thing is true of the '-e' option. If there is a '-r
<seconds>' argument on the command line, and a failure occurs trying to stop the remote profiling program, the stop message will be
sent again until the retry time limit is reached.
-s label: Issue a chudStartRemotePerfMonitor message with the specified label and exit. A 'label' is a string of up to 32 characters.
-e Issue a chudStopRemotePerfMonitor message and exit.
-q silence some of the non-essential warning and error output.
-kPID Send a UNIX signal (SIGUSR1 to start profiling, SIGUSR2 to stop profiling) to the specified process-id. For example, if a command-
line profiling tool, is running as PID 4267, using '-k 4267' along with a '-s' will send a SIGUSR1 to the command-line profiling
tool and it will start sampling, while '-k 4267' along with a '-e' will send a SIGUSR2 to the command-line profiling tool and it
will stop sampling. A 'start' example: % chudRemoteCtrl -s session_42 -k 4267. And a 'stop' example: % chudRemoteCtrl -e -k 4267.
The command-line CHUD tool 'shark' responds to UNIX signals and toggles performance profiling. You can repeatedly send '-s <label>
-k <PID#>' to shark and it will toggle profiling start or stop. Sending '-e -k <PID#>' to shark will stop sampling (if it's run-
ning) and cause shark to EXIT.
-m Set the performance monitor mark bit in the main thread of the launched child process.
DIAGNOSTICS
chudRemoteCtrl returns a zero (0) upon success and a non-zero value on failure.
BUGS
Please send your comments, suggestions and bug reports to: perftools-feedback@group.apple.com
SEE ALSO monster(1), shark(1)CHUD 6 October 2003 CHUDREMOTECTRL(1)