Best way to monitor a Grid of computers?

Posted by marc.riera on Server Fault See other posts from Server Fault or by marc.riera
Published on 2010-04-21T21:17:02Z Indexed on 2010/04/21 22:03 UTC
Read the original article Hit count: 461

Filed under:

gridengine

|

monitoring

|

performance-monitoring

I've installed Sun Grid Engine on 10 nodes, and one virtual master host.

Now I have to monitor all the resources prior to launching it into production, but I don't know which is the best way. I've tried using xml-qstat, but it seems unstable.

Any tips or suggestions?

Anyone got experience on this?

thanks.

© Server Fault or respective owner

Related posts about gridengine

Garbled UI with vnc, chicken-of-the-vnc, gridengine, qmon

as seen on Ask Ubuntu - Search for 'Ask Ubuntu'
Ubuntu 11.04 gridengine version 6.2u5-1ubuntu1 I start a desktop with the vncserver command. My ~/.vnc/xstartup ends with 'gnome-session'. I connect to it using chicken-of-the-VNC on my MacOSX Lion system. I run 'qmon'. Much of qmon works, but several critical tasks show hopelessly garbled grid… >>> More
Is there a way to tell SGE to run specific jobs as root on the execution node?

as seen on Server Fault - Search for 'Server Fault'
The title kinda says it all... We're using SGE/OGE to submit jobs to a set of worker nodes that then do things with specific pieces of equipment. The programs and scripts that have been created that manipulate this equipment rely on running as root. I'd like SGE to handle allocation of resources… >>> More
SGE: invoking qmake raises "critical error: can't resolve group"

as seen on Server Fault - Search for 'Server Fault'
I'm new to SGE an I'm trying to run qmake with the simple following Makefile with our very new cluster: merge.txt: job1.txt job2.txt job3.txt ... cat $^ > $@ job1.txt: sleep 1 echo "Hello From " $@ > $@ sleep 1 job2.txt: sleep 2 echo "Hello From " $@ > $@ sleep… >>> More
SGE - limit a user to a certain host, using resource quota configuration

as seen on Server Fault - Search for 'Server Fault'
Is it possible to limit a user to a particular host, using the Resource Quota Configuration option in qmon for Sun Grid Engine? I'm thinking of a line to the effect of: { ... limit users {john} to hostname=compute-1-1.local } The documentation mentions built in resource types: slots, arch, mem_total… >>> More
Parallel prologue and epilogue in Grid Engine

as seen on Server Fault - Search for 'Server Fault'
We have a cluster being used to run MPI jobs for a customer. Previously this cluster used Torque as the scheduler, but we are transitioning to Grid Engine 6.2u5 (for some other features). Unfortunately, we are having trouble duplicating some of our maintenance scripts in the Grid Engine environment… >>> More

Related posts about monitoring

Issues with signal handling [closed]

as seen on Programmers - Search for 'Programmers'
I am trying to actually study the signal handling behavior in multiprocess system. I have a system where there are three signal generating processes generating signals of type SIGUSR1 and SIGUSR1. I have two handler processes that handle a particular type of signal. I have another monitoring process… >>> More
JMX Based Monitoring - Part Two - JVM Monitoring

as seen on Oracle Blogs - Search for 'Oracle Blogs'
This the second article in the series focussing on the JMX based monitoring capabilities possible with the Oracle Utilities Application Framework. In all versions of the Oracle utilities Application Framework, it is possible to use the basic JMX based monitoring available with the Java Virtual Machine… >>> More
JMX Based Monitoring - Part Three - Web App Server Monitoring

as seen on Oracle Blogs - Search for 'Oracle Blogs'
In the last blog entry I showed a technique for integrating a JMX console with Oracle WebLogic which is a standard feature of Oracle WebLogic 11g. Customers on other Web Application servers and other versions of Oracle WebLogic can refer to the documentation provided with the server to do a similar… >>> More
JMX Based Monitoring - Part Four - Business App Server Monitoring

as seen on Oracle Blogs - Search for 'Oracle Blogs'
In the last blog entry I talked about the Oracle Utilities Application Framework V4 feature for monitoring and managing aspects of the Web Application Server using JMX. In this blog entry I am going to discuss a similar new feature that allows JMX to be used for management and monitoring the Oracle… >>> More
Keeping track of File System Utilization in Ops Center 12c

as seen on Oracle Blogs - Search for 'Oracle Blogs'
Enterprise Manager Ops Center 12c provides significant monitoring capabilities, combined with very flexible incident management. These capabilities even extend to monitoring the file systems associated with Solaris or Linux assets. Depending on your needs you can monitor and manage incidents, or you… >>> More