Microsoft Cloud Authors: Pat Romanski, Jnan Dash, Andreas Grabner, Lori MacVittie, Jim Kaskade

Related Topics: Java IoT, Microservices Expo, Adobe Flex, Machine Learning , Apache

Java IoT: Article

Why Averages Are Inadequate, and Percentiles Are Great

Averages are ineffective because they are too simplistic and one-dimensional

Anyone who ever monitored or analyzed an application uses or has used averages. They are simple to understand and calculate. We tend to ignore just how wrong the picture is that averages paint of the world. To emphasis the point let me give you a real-world example outside of the performance space that I read recently in a newspaper.

The article was explaining that the average salary in a certain region in Europe was 1900 Euro's (to be clear this would be quite good in that region!). However when looking closer they found out that the majority, namely 9 out of 10 people, only earned around 1000 Euros and one would earn 10.000 (I over simplified this of course, but you get the idea). If you do the math you will see that the average of this is indeed 1900, but we can all agree that this does not represent the "average" salary as we would use the word in day to day live. So now let's apply this thinking to application performance.

The Average Response Time
The average response time is by far the most commonly used metric in application performance management. We assume that this represents a "normal" transaction, however this would only be true if the response time is always the same (all transaction run at equal speed) or the response time distribution is roughly bell curved.

A Bell curve represents the "normal" distribution of response times in which the average and the median are the same. It rarely ever occurs in real applications

In a Bell Curve the average (mean) and median are the same. In other words observed performance would represent the majority (half or more than half) of the transactions.

In reality most applications have few very heavy outliers; a statistician would say that the curve has a long tail. A long tail does not imply many slow transactions, but few that are magnitudes slower than the norm.

This is a typical Response Time Distribution with few but heavy outliers - it has a long tail. The average here is dragged to the right by the long tail.

We recognize that the average no longer represents the bulk of the transactions but can be a lot higher than the median.

You can now argue that this is not a problem as long as the average doesn't look better than the median. I would disagree, but let's look at another real-world scenario experienced by many of our customers:

This is another typical Response Time Distribution. Here we have quite a few very fast transactions that drag the average to the left of the actual median

In this case a considerable percentage of transactions are very, very fast (10-20 percent), while the bulk of transactions are several times slower. The median would still tell us the true story, but the average all of a sudden looks a lot faster than most of our transactions actually are. This is very typical in search engines or when caches are involved - some transactions are very fast, but the bulk are normal. Another reason for this scenario are failed transactions, more specifically transactions that failed fast. Many real-world applications have a failure rate of 1-10 percent (due to user errors or validation errors). These failed transactions are often magnitudes faster than the real ones and consequently distorted an average.

Of course performance analysts are not stupid and regularly try to compensate with higher frequency charts (compensating by looking at smaller aggregates visually) and by taking in minimum and maximum observed response times. However we can often only do this if we know the application very well, those unfamiliar with the application might easily misinterpret the charts. Because of the depth and type of knowledge required for this, it's difficult to communicate your analysis to other people - think how many arguments between IT teams have been caused by this. And that's before we even begin to think about communicating with business stakeholders!

A better metric by far are percentiles, because they allow us to understand the distribution. But before we look at percentiles, let's take a look a key feature in every production monitoring solution: Automatic Baselining and Alerting.

Automatic Baselining and Alerting
In real-world environments, performance gets attention when it is poor and has a negative impact on the business and users. But how can we identify performance issues quickly to prevent negative effects? We cannot alert on every slow transaction, since there are always some. In addition, most operations teams have to maintain a large number of applications and are not familiar with all of them, so manually setting thresholds can be inaccurate, quite painful and time-consuming.

The industry has come up with a solution called Automatic Baselining. Baselining calculates out the "normal" performance and only alerts us when an application slows down or produces more errors than usual. Most approaches rely on averages and standard deviations.

Without going into statistical details, this approach again assumes that the response times are distributed over a bell curve:

The Standard Deviation represents 33% of all transactions with the mean as the middle. 2xStandard Deviation represents 66% and thus the majority, everything outside could be considered an outlier. However most real world scenarios are not bell curved...

Typically, transactions that are outside two times standard deviation are treated as slow and captured for analysis. An alert is raised if the average moves significantly. In a bell curve this would account for the slowest 16.5 percent (and you can of course adjust that); however; if the response time distribution does not represent a bell curve, it becomes inaccurate. We either end up with a lot of false positives (transactions that are a lot slower than the average but when looking at the curve lie within the norm) or we miss a lot of problems (false negatives). In addition if the curve is not a bell curve, then the average can differ a lot from the median; applying a standard deviation to such an average can lead to quite a different result than you would expect. To work around this problem these algorithms have many tunable variables and a lot of "hacks" for specific use cases.

Why I Love Percentiles
A percentile tells me which part of the curve I am looking at and how many transactions are represented by that metric. To visualize this look at the following chart:

This chart shows the 50th and 90th percentile along with the average of the same transaction. It shows that the average is influenced far mor heavily by the 90th, thus by outliers and not by the bulk of the transactions

The green line represents the average. As you can see it is very volatile. The other two lines represent the 50th and 90th percentile. As we can see the 50th percentile (or median) is rather stable but has a couple of jumps. These jumps represent real performance degradation for the majority (50%) of the transactions. The 90th percentile (this is the start of the "tail") is a lot more volatile, which means that the outliers slowness depends on data or user behavior. What's important here is that the average is heavily influenced (dragged) by the 90th percentile, the tail, rather than the bulk of the transactions.

If the 50th percentile (median) of a response time is 500ms that means that 50% of my transactions are either as fast or faster than 500ms. If the 90th percentile of the same transaction is at 1000ms it means that 90% are as fast or faster and only 10% are slower. The average in this case could either be lower than 500ms (on a heavy front curve), a lot higher (long tail) or somewhere in between. A percentile gives me a much better sense of my real world performance, because it shows me a slice of my response time curve.

For exactly that reason percentiles are perfect for automatic baselining. If the 50th percentile moves from 500ms to 600ms I know that 50% of my transactions suffered a 20% performance degradation. You need to react to that.

In many cases we see that the 75th or 90th percentile does not change at all in such a scenario. This means the slow transactions didn't get any slower, only the normal ones did. Depending on how long your tail is the average might not have moved at all in such a scenario.!

In other cases we see the 98th percentile degrading from 1s to 1.5 seconds while the 95th is stable at 900ms. This means that your application as a whole is stable, but a few outliers got worse, nothing to worry about immediately. Percentile-based alerts do not suffer from false positives, are a lot less volatile and don't miss any important performance degradations! Consequently a baselining approach that uses percentiles does not require a lot of tuning variables to work effectively.

The screenshot below shows the Median (50th Percentile) for a particular transaction jumping from about 50ms to about 500ms and triggering an alert as it is significantly above the calculated baseline (green line). The chart labeled "Slow Response Time" on the other hand shows the 90th percentile for the same transaction. These "outliers" also show an increase in response time but not significant enough to trigger an alert.

Here we see an automatic baselining dashboard with a violation at the 50th percentile. The violation is quite clear, at the same time the 90th percentile (right upper chart) does not violate. Because the outliers are so much slower than the bulk of the transaction an average would have been influenced by them and would not have have reacted quite as dramatically as the 50th percentile. We might have missed this clear violation!

How Can We Use Percentiles for Tuning?
Percentiles are also great for tuning, and giving your optimizations a particular goal. Let's say that something within my application is too slow in general and I need to make it faster. In this case I want to focus on bringing down the 90th percentile. This would ensure sure that the overall response time of the application goes down. In other cases I have unacceptably long outliers I want to focus on bringing down response time for transactions beyond the 98th or 99th percentile (only outliers). We see a lot of applications that have perfectly acceptable performance for the 90th percentile, with the 98th percentile being magnitudes worse.

In throughput oriented applications on the other hand I would want to make the majority of my transactions very fast, while accepting that an optimization makes a few outliers slower. I might therefore make sure that the 75th percentile goes down while trying to keep the 90th percentile stable or not getting a lot worse.

I could not make the same kind of observations with averages, minimum and maximum, but with percentiles they are very easy indeed.

Averages are ineffective because they are too simplistic and one-dimensional. Percentiles are a really great and easy way of understanding the real performance characteristics of your application. They also provide a great basis for automatic baselining, behavioral learning and optimizing your application with a proper focus. In short, percentiles are great!

More Stories By Michael Kopp

Michael Kopp has over 12 years of experience as an architect and developer in the Enterprise Java space. Before coming to CompuwareAPM dynaTrace he was the Chief Architect at GoldenSource, a major player in the EDM space. In 2009 he joined dynaTrace as a technology strategist in the center of excellence. He specializes application performance management in large scale production environments with special focus on virtualized and cloud environments. His current focus is how to effectively leverage BigData Solutions and how these technologies impact and change the application landscape.

Comments (1) View Comments

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.

Most Recent Comments
rtalexander 11/21/12 12:58:00 AM EST

Hey, could you post a reference or two that covers the theory and/or practicalities of the approach you describe?


@ThingsExpo Stories
IoT is at the core or many Digital Transformation initiatives with the goal of re-inventing a company's business model. We all agree that collecting relevant IoT data will result in massive amounts of data needing to be stored. However, with the rapid development of IoT devices and ongoing business model transformation, we are not able to predict the volume and growth of IoT data. And with the lack of IoT history, traditional methods of IT and infrastructure planning based on the past do not app...
"LinearHub provides smart video conferencing, which is the Roundee service, and we archive all the video conferences and we also provide the transcript," stated Sunghyuk Kim, CEO of LinearHub, in this SYS-CON.tv interview at @ThingsExpo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
With major technology companies and startups seriously embracing IoT strategies, now is the perfect time to attend @ThingsExpo 2016 in New York. Learn what is going on, contribute to the discussions, and ensure that your enterprise is as "IoT-Ready" as it can be! Internet of @ThingsExpo, taking place June 6-8, 2017, at the Javits Center in New York City, New York, is co-located with 20th Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry p...
"There's a growing demand from users for things to be faster. When you think about all the transactions or interactions users will have with your product and everything that is between those transactions and interactions - what drives us at Catchpoint Systems is the idea to measure that and to analyze it," explained Leo Vasiliou, Director of Web Performance Engineering at Catchpoint Systems, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York Ci...
The 20th International Cloud Expo has announced that its Call for Papers is open. Cloud Expo, to be held June 6-8, 2017, at the Javits Center in New York City, brings together Cloud Computing, Big Data, Internet of Things, DevOps, Containers, Microservices and WebRTC to one location. With cloud computing driving a higher percentage of enterprise IT budgets every year, it becomes increasingly important to plant your flag in this fast-expanding business opportunity. Submit your speaking proposal ...
Discover top technologies and tools all under one roof at April 24–28, 2017, at the Westin San Diego in San Diego, CA. Explore the Mobile Dev + Test and IoT Dev + Test Expo and enjoy all of these unique opportunities: The latest solutions, technologies, and tools in mobile or IoT software development and testing. Meet one-on-one with representatives from some of today's most innovative organizations
20th Cloud Expo, taking place June 6-8, 2017, at the Javits Center in New York City, NY, will feature technical sessions from a rock star conference faculty and the leading industry players in the world. Cloud computing is now being embraced by a majority of enterprises of all sizes. Yesterday's debate about public vs. private has transformed into the reality of hybrid cloud: a recent survey shows that 74% of enterprises have a hybrid cloud strategy.
SYS-CON Events announced today that Super Micro Computer, Inc., a global leader in Embedded and IoT solutions, will exhibit at SYS-CON's 20th International Cloud Expo®, which will take place on June 7-9, 2017, at the Javits Center in New York City, NY. Supermicro (NASDAQ: SMCI), the leading innovator in high-performance, high-efficiency server technology, is a premier provider of advanced server Building Block Solutions® for Data Center, Cloud Computing, Enterprise IT, Hadoop/Big Data, HPC and E...
SYS-CON Events announced today that Linux Academy, the foremost online Linux and cloud training platform and community, will exhibit at SYS-CON's 20th International Cloud Expo®, which will take place on June 6-8, 2017, at the Javits Center in New York City, NY. Linux Academy was founded on the belief that providing high-quality, in-depth training should be available at an affordable price. Industry leaders in quality training, provided services, and student certification passes, its goal is to c...
WebRTC is the future of browser-to-browser communications, and continues to make inroads into the traditional, difficult, plug-in web communications world. The 6th WebRTC Summit continues our tradition of delivering the latest and greatest presentations within the world of WebRTC. Topics include voice calling, video chat, P2P file sharing, and use cases that have already leveraged the power and convenience of WebRTC.
"A lot of times people will come to us and have a very diverse set of requirements or very customized need and we'll help them to implement it in a fashion that you can't just buy off of the shelf," explained Nick Rose, CTO of Enzu, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York City, NY.
WebRTC sits at the intersection between VoIP and the Web. As such, it poses some interesting challenges for those developing services on top of it, but also for those who need to test and monitor these services. In his session at WebRTC Summit, Tsahi Levent-Levi, co-founder of testRTC, reviewed the various challenges posed by WebRTC when it comes to testing and monitoring and on ways to overcome them.
Every successful software product evolves from an idea to an enterprise system. Notably, the same way is passed by the product owner's company. In his session at 20th Cloud Expo, Oleg Lola, CEO of MobiDev, will provide a generalized overview of the evolution of a software product, the product owner, the needs that arise at various stages of this process, and the value brought by a software development partner to the product owner as a response to these needs.
WebRTC services have already permeated corporate communications in the form of videoconferencing solutions. However, WebRTC has the potential of going beyond and catalyzing a new class of services providing more than calls with capabilities such as mass-scale real-time media broadcasting, enriched and augmented video, person-to-machine and machine-to-machine communications. In his session at @ThingsExpo, Luis Lopez, CEO of Kurento, introduced the technologies required for implementing these idea...
The WebRTC Summit New York, to be held June 6-8, 2017, at the Javits Center in New York City, NY, announces that its Call for Papers is now open. Topics include all aspects of improving IT delivery by eliminating waste through automated business models leveraging cloud technologies. WebRTC Summit is co-located with 20th International Cloud Expo and @ThingsExpo. WebRTC is the future of browser-to-browser communications, and continues to make inroads into the traditional, difficult, plug-in web co...
The Internet of Things will challenge the status quo of how IT and development organizations operate. Or will it? Certainly the fog layer of IoT requires special insights about data ontology, security and transactional integrity. But the developmental challenges are the same: People, Process and Platform. In his session at @ThingsExpo, Craig Sproule, CEO of Metavine, demonstrated how to move beyond today's coding paradigm and shared the must-have mindsets for removing complexity from the develop...
While not quite mainstream yet, WebRTC is starting to gain ground with Carriers, Enterprises and Independent Software Vendors (ISV’s) alike. WebRTC makes it easy for developers to add audio and video communications into their applications by using Web browsers as their platform. But like any market, every customer engagement has unique requirements, as well as constraints. And of course, one size does not fit all. In her session at WebRTC Summit, Dr. Natasha Tamaskar, Vice President, Head of C...
Who are you? How do you introduce yourself? Do you use a name, or do you greet a friend by the last four digits of his social security number? Assuming you don’t, why are we content to associate our identity with 10 random digits assigned by our phone company? Identity is an issue that affects everyone, but as individuals we don’t spend a lot of time thinking about it. In his session at @ThingsExpo, Ben Klang, Founder & President of Mojo Lingo, discussed the impact of technology on identity. Sho...
DevOps is being widely accepted (if not fully adopted) as essential in enterprise IT. But as Enterprise DevOps gains maturity, expands scope, and increases velocity, the need for data-driven decisions across teams becomes more acute. DevOps teams in any modern business must wrangle the ‘digital exhaust’ from the delivery toolchain, "pervasive" and "cognitive" computing, APIs and services, mobile devices and applications, the Internet of Things, and now even blockchain. In this power panel at @...
With all the incredible momentum behind the Internet of Things (IoT) industry, it is easy to forget that not a single CEO wakes up and wonders if “my IoT is broken.” What they wonder is if they are making the right decisions to do all they can to increase revenue, decrease costs, and improve customer experience – effectively the same challenges they have always had in growing their business. The exciting thing about the IoT industry is now these decisions can be better, faster, and smarter. Now ...