Mission Critical Computing Blog
Your source for the latest insights on HP Integrity, mission critical computing, and other relevant server and technology topics from the BCS team.

NonStop Real-Time Process Monitor (RPM) for ultra-fast process monitoring

In the well known comic strip Wallace & Gromit, the term RPM was used by Wallace to describe “rabbits per minute”. For mechanical-oriented folks and those working on hard disk technology, RPM stands for “revolutions per minute”. And for those that work on Linux, RPM also stands for Red Hat Package Manager.

 

For those of us that are knowledgeable in NonStop, RPM is the name of a low-cost, highly-efficient, real-time monitoring product that continuously provides CPU and process resource consumption data. It can discover and display the busiest CPUs and processes across Expand-connected NonStop systems, and it does that ultra-fast in real-time.

 

If you are not already using RPM in your NonStop environment, here are the top reasons I think you can really benefit from using it.

 

It’s incredibly scalable

We have designed RPM from the ground-up to be highly scalable. Thus, it can concurrently monitor 4000+ CPUs and millions of processes across an Expand network. As a matter of fact, because of its unique architecture, RPM can support an unlimited number of NonStop systems in linearly expandable fashion.

 

It is easy to setup and use

I really like RPM because it is very easy to setup and really simple to use. The RPM installation wizard conducts an English language style question and answer interview. Regardless of whether RPM is being installed on just 1 system or 100 systems, the installation and setup are simple and easy. Once installed, RPM can be run directly from a TACL prompt.

 

You can view its output on many display devices

RPM supports almost all device types to display its data – whether it is TTY, VT100, ANSI or a T6530 terminal. Support of VT100 allows the data to be displayed in a Windows Telnet session without any need for a terminal emulator. RPM supports super-sized devices, including support for 300 X 300 ANSI/VT100, 80 X 25 T6530, and 132 X 254 T6530 displays. You can also stream the tabular output from RPM to a disk or a process.

 

It provides a configurable sampling interval

RPM provides configurability for the end-user so that you can configure how often to collect statistic sampling - all the way down to 1 second. RPM continuously updates the display based on your configured sampling interval.

 

It has customizable color-coded displays

You can define your own critical, warning and info thresholds, which results in color-coding of the offending busy process displays. For example, you can display processes >50% busy in red (critical), those >10% busy in yellow (warning), and those >1% busy in cyan (info).

 

It can filter and sort in a multitude of ways

There are many different filtering and sorting options to display the data in the way you prefer. For example, you can display the busiest processes in a particular CPU, a particular NonStop system,  selected NonStop systems, or in the whole Expand network. In addition, you can sort processes in the order of those consuming the most CPU cycles, those receiving most input messages, those sending most output messages, those sending and receiving the most messages, those consuming the most memory, those consuming the most Process File Segments (PFS), those building the longest receive queue, those with the most page faults, and so forth.. You can also view both short-term and long-term CPU and process usage statistics simultaneously!

 

It supports both OSS and Guardian

RPM monitors, analyzes and displays both OSS and Guardian process paths and filenames.

 

You don’t need Measure or Super group access

RPM, unlike most other performance monitoring applications on NonStop, does not require Measure – which means it is low-cost and has extremely low resource overhead. Also, RPM does not require Super group access.

 

It complements other NonStop performance monitoring applications

RPM does not replace extensive in-depth NonStop performance monitoring applications such as ASAP, but it certainly does complement them. For example, I often see RPM used as a solution for developers in development and test environments to see how an application is performing before deploying it in the production environment. 

 

If you are not yet using RPM, talk to your account team and see how it might be useful in  your environment.

Leave a Comment

We encourage you to share your comments on this post. Comments are moderated and will be reviewed
and posted as promptly as possible during regular business hours

To ensure your comment is published, be sure to follow the community guidelines.

Be sure to enter a unique name. You can't reuse a name that's already in use.
Be sure to enter a unique email address. You can't reuse an email address that's already in use.
Type the characters you see in the picture above.Type the words you hear.
Search
Showing results for 
Search instead for 
Do you mean 
About the Author
Vinay Gupta is an HP Distinguished Technologist and the NonStop Manageability Architect. He joined Tandem in 1994 after graduating from Indi...
Featured


Follow Us
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation.