Click here to close now.

Welcome!

GovIT Authors: Liz McMillan, Esmeralda Swartz, Pat Romanski, Yeshim Deniz, Carmen Gonzalez

Related Topics: Java, Microservices Journal, Adobe Flex, AJAX & REA, Apache

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We recognize that the average no longer represents the bulk of the transactions but can be a lot higher than the median.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

Conclusion
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?

Thanks!

@ThingsExpo Stories
SYS-CON Media announced today that @ThingsExpo Blog launched with 7,788 original stories. @ThingsExpo Blog offers top articles, news stories, and blog posts from the world's well-known experts and guarantees better exposure for its authors than any other publication. @ThingsExpo Blog can be bookmarked. The Internet of Things (IoT) is the most profound change in personal and enterprise IT since the creation of the Worldwide Web more than 20 years ago.
The world's leading Cloud event, Cloud Expo has launched Microservices Journal on the SYS-CON.com portal, featuring over 19,000 original articles, news stories, features, and blog entries. DevOps Journal is focused on this critical enterprise IT topic in the world of cloud computing. Microservices Journal offers top articles, news stories, and blog posts from the world's well-known experts and guarantees better exposure for its authors than any other publication. Follow new article posts on Twitter at @MicroservicesE
SYS-CON Events announced today that robomq.io will exhibit at SYS-CON's @ThingsExpo, which will take place on June 9-11, 2015, at the Javits Center in New York City, NY. robomq.io is an interoperable and composable platform that connects any device to any application. It helps systems integrators and the solution providers build new and innovative products and service for industries requiring monitoring or intelligence from devices and sensors.
Wearable technology was dominant at this year’s International Consumer Electronics Show (CES) , and MWC was no exception to this trend. New versions of favorites, such as the Samsung Gear (three new products were released: the Gear 2, the Gear 2 Neo and the Gear Fit), shared the limelight with new wearables like Pebble Time Steel (the new premium version of the company’s previously released smartwatch) and the LG Watch Urbane. The most dramatic difference at MWC was an emphasis on presenting wearables as fashion accessories and moving away from the original clunky technology associated with t...
SYS-CON Events announced today that Litmus Automation will exhibit at SYS-CON's 16th International Cloud Expo®, which will take place on June 9-11, 2015, at the Javits Center in New York City, NY. Litmus Automation’s vision is to provide a solution for companies that are in a rush to embrace the disruptive Internet of Things technology and leverage it for real business challenges. Litmus Automation simplifies the complexity of connected devices applications with Loop, a secure and scalable cloud platform.
In 2015, 4.9 billion connected "things" will be in use. By 2020, Gartner forecasts this amount to be 25 billion, a 410 percent increase in just five years. How will businesses handle this rapid growth of data? Hadoop will continue to improve its technology to meet business demands, by enabling businesses to access/analyze data in real time, when and where they need it. Cloudera's Chief Technologist, Eli Collins, will discuss how Big Data is keeping up with today's data demands and how in the future, data and analytics will be pervasive, embedded into every workflow, application and infra...
As Marc Andreessen says software is eating the world. Everything is rapidly moving toward being software-defined – from our phones and cars through our washing machines to the datacenter. However, there are larger challenges when implementing software defined on a larger scale - when building software defined infrastructure. In his session at 16th Cloud Expo, Boyan Ivanov, CEO of StorPool, will provide some practical insights on what, how and why when implementing "software-defined" in the datacenter.
So I guess we’ve officially entered a new era of lean and mean. I say this with the announcement of Ubuntu Snappy Core, “designed for lightweight cloud container hosts running Docker and for smart devices,” according to Canonical. “Snappy Ubuntu Core is the smallest Ubuntu available, designed for security and efficiency in devices or on the cloud.” This first version of Snappy Ubuntu Core features secure app containment and Docker 1.6 (1.5 in main release), is available on public clouds, and for ARM and x86 devices on several IoT boards. It’s a Trend! This announcement comes just as...
SYS-CON Events announced today that Vicom Computer Services, Inc., a provider of technology and service solutions, will exhibit at SYS-CON's 16th International Cloud Expo®, which will take place on June 9-11, 2015, at the Javits Center in New York City, NY. They are located at booth #427. Vicom Computer Services, Inc. is a progressive leader in the technology industry for over 30 years. Headquartered in the NY Metropolitan area. Vicom provides products and services based on today’s requirements around Unified Networks, Cloud Computing strategies, Virtualization around Software defined Data Ce...
Containers and microservices have become topics of intense interest throughout the cloud developer and enterprise IT communities. Accordingly, attendees at the upcoming 16th Cloud Expo at the Javits Center in New York June 9-11 will find fresh new content in a new track called PaaS | Containers & Microservices Containers are not being considered for the first time by the cloud community, but a current era of re-consideration has pushed them to the top of the cloud agenda. With the launch of Docker's initial release in March of 2013, interest was revved up several notches. Then late last...
The only place to be June 9-11 is Cloud Expo & @ThingsExpo 2015 East at the Javits Center in New York City. Join us there as delegates from all over the world come to listen to and engage with speakers & sponsors from the leading Cloud Computing, IoT & Big Data companies. Cloud Expo & @ThingsExpo are the leading events covering the booming market of Cloud Computing, IoT & Big Data for the enterprise. Speakers from all over the world will be hand-picked for their ability to explore the economic strategies that utility/cloud computing provides. Whether public, private, or in a hybrid form, clo...
Internet of Things (IoT) will be a hybrid ecosystem of diverse devices and sensors collaborating with operational and enterprise systems to create the next big application. In their session at @ThingsExpo, Bramh Gupta, founder and CEO of robomq.io, and Fred Yatzeck, principal architect leading product development at robomq.io, will discuss how choosing the right middleware and integration strategy from the get-go will enable IoT solution developers to adapt and grow with the industry, while at the same time reduce Time to Market (TTM) by using plug and play capabilities offered by a robust I...
IoT is still a vague buzzword for many people. In his session at @ThingsExpo, Mike Kavis, Vice President & Principal Cloud Architect at Cloud Technology Partners, discussed the business value of IoT that goes far beyond the general public's perception that IoT is all about wearables and home consumer services. He also discussed how IoT is perceived by investors and how venture capitalist access this space. Other topics discussed were barriers to success, what is new, what is old, and what the future may hold. Mike Kavis is Vice President & Principal Cloud Architect at Cloud Technology Pa...
From telemedicine to smart cars, digital homes and industrial monitoring, the explosive growth of IoT has created exciting new business opportunities for real time calls and messaging. In his session at @ThingsExpo, Ivelin Ivanov, CEO and Co-Founder of Telestax, shared some of the new revenue sources that IoT created for Restcomm – the open source telephony platform from Telestax. Ivelin Ivanov is a technology entrepreneur who founded Mobicents, an Open Source VoIP Platform, to help create, deploy, and manage applications integrating voice, video and data. He is the co-founder of TeleStax, a...
@ThingsExpo has been named the Top 5 Most Influential Internet of Things Brand by Onalytica in the ‘The Internet of Things Landscape 2015: Top 100 Individuals and Brands.' Onalytica analyzed Twitter conversations around the #IoT debate to uncover the most influential brands and individuals driving the conversation. Onalytica captured data from 56,224 users. The PageRank based methodology they use to extract influencers on a particular topic (tweets mentioning #InternetofThings or #IoT in this case) takes into account the number and quality of contextual references that a user receives.
Buzzword alert: Microservices and IoT at a DevOps conference? What could possibly go wrong? Join this panel of experts as they peel away the buzz and discuss the important architectural principles behind implementing IoT solutions for the enterprise. As remote IoT devices and sensors become increasingly intelligent, they become part of our distributed cloud environment, and we must architect and code accordingly. At the very least, you’ll have no problem filling in your buzzword bingo cards.
SYS-CON Events announced today that AIC, a leading provider of OEM/ODM server and storage solutions, will exhibit at SYS-CON's 16th International Cloud Expo®, which will take place on June 9-11, 2015, at the Javits Center in New York City, NY. AIC is a leading provider of both standard OTS, off-the-shelf, and OEM/ODM server and storage solutions. With expert in-house design capabilities, validation, manufacturing and production, AIC's broad selection of products are highly flexible and are configurable to any form factor or custom configuration. AIC leads the industry with nearly 20 years of ...
How is unified communications transforming the way businesses operate? In his session at WebRTC Summit, Arvind Rangarajan, Director of Product Marketing at BroadSoft, will discuss how to extend unified communications experience outside the enterprise through WebRTC. He will also review use cases across different industry verticals. Arvind Rangarajan is Director, Product Marketing at BroadSoft. He has over 19 years of experience in the telecommunications industry in various roles such as Software Development, Product Management and Product Marketing, applied across Wireless, Unified Communic...
SYS-CON Events announced today the IoT Bootcamp – Jumpstart Your IoT Strategy, being held June 9–10, 2015, in conjunction with 16th Cloud Expo and Internet of @ThingsExpo at the Javits Center in New York City. This is your chance to jumpstart your IoT strategy. Combined with real-world scenarios and use cases, the IoT Bootcamp is not just based on presentations but includes hands-on demos and walkthroughs. We will introduce you to a variety of Do-It-Yourself IoT platforms including Arduino, Raspberry Pi, BeagleBone, Spark and Intel Edison. You will also get an overview of cloud technologies s...
SOA Software has changed its name to Akana. With roots in Web Services and SOA Governance, Akana has established itself as a leader in API Management and is expanding into cloud integration as an alternative to the traditional heavyweight enterprise service bus (ESB). The company recently announced that it achieved more than 90% year-over-year growth. As Akana, the company now addresses the evolution and diversification of SOA, unifying security, management, and DevOps across SOA, APIs, microservices, and more.