Performance monitoring is about understanding what's happening right now. It usually includes dealing with immediate performance problems or collecting data that will be used by the other performance tools (such as capacity planning) to plan for future peak loads.
In performance monitoring you need to know three things:
- The incoming workload
- The resulting resource consumption
- What is normal under this load
Without these three things you can only solve the most obvious performance problems and have to rely on tools outside the scientific realm (such as a Ouija Board, or a Magic 8 Ball) to predict the future.
You need to know the incoming workload (what the users are asking your system to do) because all computers run just fine under no load. Performance problems crop up as the load goes up. These performance problems come in two basic flavors: Expected and Unexpected.
Expected problems are when the users are simply asking the application for more things per second than it can do. You see this during an expected peak in demand like the biggest shopping day of the year. Expected problems are no fun, but they can be foreseen and, depending on the situation, your response might be to endure them, because money is tight or because the fix might introduce too much risk.
Unexpected problems are when the incoming workload should be well within the capabilities of the application, but something is wrong and either the end-user performance is bad or some performance meter makes no sense. Unexpected problems cause much unpleasantness and demand rapid diagnosis and repair.
Know What is Normal
The key to all performance work is to know what is normal. Let me illustrate that with a trip to the grocery store.
One day I was buying three potatoes and an onion for a soup I was making. The new kid behind the cash register looked at me and said: “That will be $22.50.” What surprised me was the total lack of internal error checking at this outrageous price (in 2012) for three potatoes and an onion. This could be a simple case of them not caring about doing a good job, but my more charitable assessment is that he had no idea what “normal” was, so everything the register told him had to be taken at face value. Don't be like that kid.
On any given day you, as the performance person, should be able to have a fairly good idea of how much work the users are asking the system to do and what the major performance meters are showing. If you have a good sense of what is normal for your situation, then any abnormality will jump right out at you in the same way you notice subtle changes in a loved one that a stranger would miss. This can save your bacon because if you spot the unexpected utilization before the peak occurs, then you have time to find and fix the problem before the system comes under a peak load.
There are some challenges in getting this data. For example:
- There is no workload data.
- The only workload data available (ex: per day transaction volume) is at too low a resolution to be any good for rapid performance changes.
- The workload is made of many different transaction types (buy, sell, etc.) It's not clear what to meter.
With rare exception I've found the lack of easily available workload information to be the single best predictor of how bad the overall situation is performance wise. Over the years as I visited company after company this led me to develop Bob's First Rule of Performance Work: “The less a company knows about the work their system did in the last five minutes, the more deeply screwed up they are.”
What meters should you collect? Meters fall into big categories. There are utilization meters that tell you how busy a resource is, there are count meters that count interesting events (some good, some bad), and there are duration meters that tell you how long something took. As the commemorative plate infomercial says: “Collect them all!” Please don't wait for perfection. Start somewhere, collect something and, as you explore and discover, add newly discovered meters to your collection.
When should you run the meters? Your meters should be running all the time (like bank security cameras) so that when weird things happen you have a multitude of clues to look at. You will want to search this data by time (What happened at 10:30?), so be sure to include timestamps.
The data you collect can also be used to predict the future with tools like: Capacity Planning, Load Testing, and Modeling.
ABOUT Bob Wescott
Bob Wescott is the author of The Every Computer Performance Book. Since 1987, Wescott has worked in the field of computer performance, doing professional services work and teaching how to do capacity planning, load testing, simulation modeling and web performance for Gomez/Compuware, HyPerformix/CA and Stratus Computer/Technologies. Now, Wescott is mostly retired, and his job is to give back what he has been given. His latest project is The Every Computer Performance Blog based on the book.
This time last year, we predicted that IT managers were going to move away from the "hybrid data center" and finally realize the reality of the "hybrid application" – and this year, we saw that prediction of an increased focus on applications come to pass, as organizations increasingly made buying and deployment decisions based on the needs of their applications ...
Not surprisingly, organizations will expand the use of cloud services in 2019 for both existing and new applications, further accelerating the migration of workloads from the datacenter to the cloud. With IT staff now becoming more comfortable in the cloud, their concerns about HA and DR will also begin to ease ...
APMdigest invited industry experts to predict how Cloud will evolve and impact application performance and business in 2019. Part 3, the final installment, covers monitoring and managing application performance in the Cloud ...
APMdigest invited industry experts to predict how Cloud will evolve and impact application performance and business in 2019. Part 2 covers multi-cloud, hybrid cloud, serverless and more ...
As a continuation of the list of 2019 predictions, APMdigest invited industry experts to predict how Cloud will evolve and impact application performance and business in 2019 ...
APMdigest invited industry experts to predict how Network Performance Management (NPM) and related technologies will evolve and impact business in 2019 ...
I would like to highlight some of the predictions made at the start of 2018, and how those have panned out, or not actually occurred. I will review some of the predictions and trends from APMdigest's 2018 APM Predictions. Here is Part 2 ...
I would like to highlight some of the predictions made at the start of 2018, and how those have panned out, or not actually occurred. I will review some of the predictions and trends from APMdigest's 2018 APM Predictions ...
I sat down with Stephen Elliot, VP of Management Software and DevOps at IDC, to discuss where the market is headed, how legacy vendors will need to adapt, and how customers can get ahead of these trends to gain a competitive advantage. Part 2 of the interview ...
Monitoring and observability requirements are continuing to adapt to the rapid advances in public cloud, containers, serverless, microservices, and DevOps and CI/CD practices. As new technology and development processes become mainstream, enterprise adoption begins to increase, bringing its own set of security, scalability, and manageability needs. I sat down with Stephen Elliot, VP of Management Software and DevOps at IDC, to discuss where the market is headed, how legacy vendors will need to adapt, and how customers can get ahead of these trends to gain a competitive advantage ...