Welcome!

Java IoT Authors: Elizabeth White, Pat Romanski, William Schmarzo, XebiaLabs Blog, David Paquette

Related Topics: @BigDataExpo, Java IoT, IoT User Interface, @CloudExpo, Apache, SDN Journal

@BigDataExpo: Article

So What? – Monitoring Hadoop Beyond Ganglia

Don’t just run Hadoop jobs at scale, run them efficiently and at scale

Over the last couple of months I have been talking to more and more customers who are either bringing their Hadoop clusters into production or have already done so and are now getting serious about operations. This leads to some interesting discussions about how to monitor Hadoop properly and one thing pops up quite often: Do they need anything beyond Ganglia? If yes, what should they do beyond it?

The Basics
As in every other system, monitoring in a Hadoop environment starts with the basics: System Metrics - CPU, Disk, Memory you know the drill. Of special importance in a Hadoop system is a well-balanced cluster; you don't want to have some nodes being much more (or less) utilized then others. Besides CPU and memory utilization, Disk utilization and of course I/O throughput is of high importance. After all the most likely bottleneck in a Big Data system is I/O - either with ingress (network and disk), moving data around (e.g., MapReduce shuffle on the network) and straightforward read/write to disk.

The problem in a Hadoop system is of course its size. Nothing new for us, some of our customers monitor well beyond 1000+ JVMs with CompuwareAPM. The "advantage" in a Hadoop system is its relative conformity - every node looks pretty much like the other. This is what Ganglia leverages.

Cluster Monitoring with Ganglia
What Ganglia is very good at is providing an overview over how a cluster is utilized. The load chart is particularly interesting:

This chart shows the CPU load on a 1000 Server cluster that has roughly 15.000 CPUs

It tells us the number of available cores in the system and the number of running processes (in theory a core can never handle more than one process at a time) and the 1-min load average. If the system is getting fully utilized the 1-min load average would approach the total number of CPUs. Another view on this is the well-known CPU utilization chart:

CPU Utilization over the last day. While the utilization stays well below 10% we see a lot of I/O wait spikes.

While the load chart gives a good overall impression of usage, the utilization tells us the story of how the CPUs are used. While typical CPU charts show a single server, Ganglia specializes in showing whole clusters (the picture shows CPU usage of a 1000 machine cluster). In the case of the depicted chart we see that the CPUs are experiencing a lot of I/O wait spikes, which points toward heavy disk I/O. Basically it seems the disk I/O is the reason that we cannot utilize our CPU better at these times. But in general our cluster is well underutilized in terms of CPU.

Trends are also easy to understand, as can be seen in this memory chart over a year.

Memory capacity and usage over a year

All this looks pretty good, so what is missing? The "so what" and "why" is what is missing. If my memory demand is growing, I have no way of knowing why it is growing. If the CPU chart tells me that I spend a lot of time waiting, it does not tell what to do, or why that is so? These questions are beyond the scope of Ganglia.

What about Hadoop specifics?
Ganglia also has a Hadoop plugin, which basically gives you access to all the usual Hadoop metrics (unfortunately a comprehensive list of Hadoop metrics is really hard to find, appreciate if somebody commented the link). There is a good explanation on what is interesting on Edward Caproli's page: JoinTheGrid. Basically you can use those metrics to monitor the capacity and usage trends of HDFS and the NameNodes and also how many jobs, mappers and reducers are running.

Capacity of the DataNodes over time

Capacity of the Name Nodes over time

The DataNode Operations give me an impression of I/O pressure on the Hadoop cluster

All these charts can of course be easily built in any modern monitoring or APM solution like CompuwareAPM, but Ganglia gives you a simple starting point; and it's Free as in Beer.

What's missing again is the so what? If my jobs are running a lot longer than yesterday, what should I do? Why do they run longer? A Hadoop expert might dig into 10 different charts around I/O and Network, spilling, look at log files among other things and try an educated guess as to what might be the problem. But we aren't all experts, neither do we have the time to dig into all of these metrics and log files all the time.

This is the reason that we and our customers are moving beyond Ganglia - to solve the "Why" and "So What" within time constraints.

Beyond the Basics #1 - Understanding Cluster Utilization
A use case that we get from customers is that they want to know which users or which pools (in case of the fair scheduler) are responsible for how much of the cluster utilization. LinkedIn just released White Elephant, a tool that parses MapReduce logs and builds some nice dashboards and shows you which of your users occupy how much of your cluster. This is of course based on log file analysis and thus okay for analysis but not for monitoring. With proper tools in place we can do the same thing in near real time.

The CPU Usage in the Hadoop Cluster on per User basis

In this example I wanted to monitor which user consumed how much of my Amazon EMR cluster. If we see a user or pool that occupies a lot of the cluster we can course also see which jobs are running and how much of the cluster they occupy.

The CPU Usage in the Hadoop Cluster on per Job basis

And this will also tell us if that job has always been there, and just uses a lot more resources now. This would be our cue to start analyzing what has changed.

Beyond the Basics #2 - Understanding why my jobs are slow(er)
If we want to understand why a job is slow we need to look at a high-level break down first.

In which phase of the map reduce do we spend the most time, or did we spend more time than yesterday? Understanding these timings in context with the respective job counters, like Map Input or Spilled Records, helps us understand why the phase took longer.

Overview of the time spent in different phases and the respective input/output counters

At this point we will already have a pretty good idea as to what happened. We either simply have more data to crunch (more input data) or a portion of the MapReduce job consumes more CPU (code change?) or we spill more records to disk (code change or Hadoop config change?). We might also detect an unbalanced cluster in the performance breakdown.

This job is executing nearly exclusively on a single node instead of distributing

In this case we want to check whether all the involved nodes processed the same amount of data

Here we see that there is a wide range from minimum, average to maximum on mapped input and output records. The data is not balanced

or if the difference can again be found in the code (different kinds of computations). If we are running against HBase we might of course have an issue with HBase performance or distribution.

At the beginning of the job only a single HBase region Server consumes CPU while all others remain idle

On the other hand, if a lot of mapping time is spent in the garbage collector then you should maybe invest in larger JVMs.

The Performance Breakdown of this particular job shows considerable time in GC suspension

If spilling data to disk is where we spend our time, we should take a closer look at that phase. It might turn out that all of our time is spent on disk wait.

If the Disk were the bottleneck we would see it on disk I/O here

Now if disk write is our bottleneck, then really the only thing that we can do is reduce the map output records. Adding a combiner will not reduce the disk write (it will actually increase it, read here). In other words combining only optimizes the shuffle phase, thus the amount of data sent over the network, but not spill time!!

And at the very detailed level we can look at single task executions and understand in detail what is really going on.

The detailed data about each Map, Reduce Task Atttempt as well as the spills and shuffles

Conclusion
Ganglia is a great tool for high-level monitoring of your Hadoop cluster utilization, but it is not enough. The fact that everybody is working on additional means to understand the Hadoop cluster (Hortonworks with Ambari, Cloudera with their Manager, LinkedIn with White Elephant, the Star Fish project...) shows that there is a lot more needed beyond simple monitoring. Even those more advanced monitoring tools are not always answering the "why" though, which is what we really need to do. This is where the Performance Management discipline can add a lot of value and really help you get the best out of your Hadoop cluster. In other words don't just run Hadoop jobs at scale, run them efficiently and at scale!

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 (0)

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.


@ThingsExpo Stories
SYS-CON Events announced today that Pulzze Systems will exhibit at the 19th International Cloud Expo, which will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. Pulzze Systems, Inc. provides infrastructure products for the Internet of Things to enable any connected device and system to carry out matched operations without programming. For more information, visit http://www.pulzzesystems.com.
If you’re responsible for an application that depends on the data or functionality of various IoT endpoints – either sensors or devices – your brand reputation depends on the security, reliability, and compliance of its many integrated parts. If your application fails to deliver the expected business results, your customers and partners won't care if that failure stems from the code you developed or from a component that you integrated. What can you do to ensure that the endpoints work as expect...
Almost two-thirds of companies either have or soon will have IoT as the backbone of their business in 2016. However, IoT is far more complex than most firms expected. How can you not get trapped in the pitfalls? In his session at @ThingsExpo, Tony Shan, a renowned visionary and thought leader, will introduce a holistic method of IoTification, which is the process of IoTifying the existing technology and business models to adopt and leverage IoT. He will drill down to the components in this fra...
The Internet of Things can drive efficiency for airlines and airports. In their session at @ThingsExpo, Shyam Varan Nath, Principal Architect with GE, and Sudip Majumder, senior director of development at Oracle, will discuss the technical details of the connected airline baggage and related social media solutions. These IoT applications will enhance travelers' journey experience and drive efficiency for the airlines and the airports. The session will include a working demo and a technical d...
WebRTC adoption has generated a wave of creative uses of communications and collaboration through websites, sales apps, customer care and business applications. As WebRTC has become more mainstream it has evolved to use cases beyond the original peer-to-peer case, which has led to a repeating requirement for interoperability with existing infrastructures. In his session at @ThingsExpo, Graham Holt, Executive Vice President of Daitan Group, will cover implementation examples that have enabled ea...
SYS-CON Events announced today the Enterprise IoT Bootcamp, being held November 1-2, 2016, in conjunction with 19th Cloud Expo | @ThingsExpo at the Santa Clara Convention Center in Santa Clara, CA. Combined with real-world scenarios and use cases, the Enterprise IoT Bootcamp is not just based on presentations but with hands-on demos and detailed walkthroughs. We will introduce you to a variety of real world use cases prototyped using Arduino, Raspberry Pi, BeagleBone, Spark, and Intel Edison. Y...
Technology vendors and analysts are eager to paint a rosy picture of how wonderful IoT is and why your deployment will be great with the use of their products and services. While it is easy to showcase successful IoT solutions, identifying IoT systems that missed the mark or failed can often provide more in the way of key lessons learned. In his session at @ThingsExpo, Peter Vanderminden, Principal Industry Analyst for IoT & Digital Supply Chain to Flatiron Strategies, will focus on how IoT de...
Fact is, enterprises have significant legacy voice infrastructure that’s costly to replace with pure IP solutions. How can we bring this analog infrastructure into our shiny new cloud applications? There are proven methods to bind both legacy voice applications and traditional PSTN audio into cloud-based applications and services at a carrier scale. Some of the most successful implementations leverage WebRTC, WebSockets, SIP and other open source technologies. In his session at @ThingsExpo, Da...
SYS-CON Events announced today that China Unicom will exhibit at the 19th International Cloud Expo, which will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. China United Network Communications Group Co. Ltd ("China Unicom") was officially established in 2009 on the basis of the merger of former China Netcom and former China Unicom. China Unicom mainly operates a full range of telecommunications services including mobile broadband (GSM, WCDMA, LTE F...
SYS-CON Events announced today that Roundee / LinearHub will exhibit at the WebRTC Summit at @ThingsExpo, which will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. LinearHub provides Roundee Service, a smart platform for enterprise video conferencing with enhanced features such as automatic recording and transcription service. Slack users can integrate Roundee to their team via Slack’s App Directory, and '/roundee' command lets your video conference ...
DevOps at Cloud Expo, taking place Nov 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA, is co-located with 19th Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world. The widespread success of cloud computing is driving the DevOps revolution in enterprise IT. Now as never before, development teams must communicate and collaborate in a dynamic, 24/7/365 environment. There is no time to wait for long dev...
There is growing need for data-driven applications and the need for digital platforms to build these apps. In his session at 19th Cloud Expo, Muddu Sudhakar, VP and GM of Security & IoT at Splunk, will cover different PaaS solutions and Big Data platforms that are available to build applications. In addition, AI and machine learning are creating new requirements that developers need in the building of next-gen apps. The next-generation digital platforms have some of the past platform needs a...
I'm a lonely sensor. I spend all day telling the world how I'm feeling, but none of the other sensors seem to care. I want to be connected. I want to build relationships with other sensors to be more useful for my human. I want my human to understand that when my friends next door are too hot for a while, I'll soon be flaming. And when all my friends go outside without me, I may be left behind. Don't just log my data; use the relationship graph. In his session at @ThingsExpo, Ryan Boyd, Engi...
SYS-CON Events announced today that Numerex Corp, a leading provider of managed enterprise solutions enabling the Internet of Things (IoT), will exhibit at the 19th International Cloud Expo | @ThingsExpo, which will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. Numerex Corp. (NASDAQ:NMRX) is a leading provider of managed enterprise solutions enabling the Internet of Things (IoT). The Company's solutions produce new revenue streams or create operating...
Information technology is an industry that has always experienced change, and the dramatic change sweeping across the industry today could not be truthfully described as the first time we've seen such widespread change impacting customer investments. However, the rate of the change, and the potential outcomes from today's digital transformation has the distinct potential to separate the industry into two camps: Organizations that see the change coming, embrace it, and successful leverage it; and...
Data is an unusual currency; it is not restricted by the same transactional limitations as money or people. In fact, the more that you leverage your data across multiple business use cases, the more valuable it becomes to the organization. And the same can be said about the organization’s analytics. In his session at 19th Cloud Expo, Bill Schmarzo, CTO for the Big Data Practice at EMC, will introduce a methodology for capturing, enriching and sharing data (and analytics) across the organizati...
The vision of a connected smart home is becoming reality with the application of integrated wireless technologies in devices and appliances. The use of standardized and TCP/IP networked wireless technologies in line-powered and battery operated sensors and controls has led to the adoption of radios in the 2.4GHz band, including Wi-Fi, BT/BLE and 802.15.4 applied ZigBee and Thread. This is driving the need for robust wireless coexistence for multiple radios to ensure throughput performance and th...
Enterprise IT has been in the era of Hybrid Cloud for some time now. But it seems most conversations about Hybrid are focused on integrating AWS, Microsoft Azure, or Google ECM into existing on-premises systems. Where is all the Private Cloud? What do technology providers need to do to make their offerings more compelling? How should enterprise IT executives and buyers define their focus, needs, and roadmap, and communicate that clearly to the providers?
The Transparent Cloud-computing Consortium (abbreviation: T-Cloud Consortium) will conduct research activities into changes in the computing model as a result of collaboration between "device" and "cloud" and the creation of new value and markets through organic data processing High speed and high quality networks, and dramatic improvements in computer processing capabilities, have greatly changed the nature of applications and made the storing and processing of data on the network commonplace.
SYS-CON Events announced today that SoftLayer, an IBM Company, has been named “Gold Sponsor” of SYS-CON's 18th Cloud Expo, which will take place on June 7-9, 2016, at the Javits Center in New York, New York. SoftLayer, an IBM Company, provides cloud infrastructure as a service from a growing number of data centers and network points of presence around the world. SoftLayer’s customers range from Web startups to global enterprises.