Welcome!

Java IoT Authors: Yeshim Deniz, Elizabeth White, Pat Romanski, Carmen Gonzalez, Liz McMillan

Related Topics: @BigDataExpo, Java IoT, Machine Learning , @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 Tappest will exhibit MooseFS 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. MooseFS is a breakthrough concept in the storage industry. It allows you to secure stored data with either duplication or erasure coding using any server. The newest – 4.0 version of the software enables users to maintain the redundancy level with even 50% less hard drive space required. The software func...
Most technology leaders, contemporary and from the hardware era, are reshaping their businesses to do software in the hope of capturing value in IoT. Although IoT is relatively new in the market, it has already gone through many promotional terms such as IoE, IoX, SDX, Edge/Fog, Mist Compute, etc. Ultimately, irrespective of the name, it is about deriving value from independent software assets participating in an ecosystem as one comprehensive solution.
SYS-CON Events announced today that EARP 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. "We are a software house, so we perfectly understand challenges that other software houses face in their projects. We can augment a team, that will work with the same standards and processes as our partners' internal teams. Our teams will deliver the same quality within the required time and budget just as our partn...
SYS-CON Events announced today that delaPlex will exhibit at SYS-CON's @ThingsExpo, which will take place on June 6-8, 2017, at the Javits Center in New York City, NY. delaPlex pioneered Software Development as a Service (SDaaS), which provides scalable resources to build, test, and deploy software. It’s a fast and more reliable way to develop a new product or expand your in-house team.
In his keynote at @ThingsExpo, Chris Matthieu, Director of IoT Engineering at Citrix and co-founder and CTO of Octoblu, focused on building an IoT platform and company. He provided a behind-the-scenes look at Octoblu’s platform, business, and pivots along the way (including the Citrix acquisition of Octoblu).
SYS-CON Events announced today that Outscale, a global pure play Infrastructure as a Service provider and strategic partner of Dassault Systèmes, 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. Founded in 2010, Outscale simplifies infrastructure complexities and boosts the business agility of its customers. Outscale delivers a secure, reliable and industrial strength solution for its customers, which in...
SYS-CON Events announced today that Outscale 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. Outscale's technology makes an automated and adaptable Cloud available to businesses, supporting them in the most complex IT projects while controlling their operational aspects. You boost your IT infrastructure's reactivity, with request responses that only take a few seconds.
SYS-CON Events announced today that Systena America 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. Systena Group has been in business for various software development and verification in Japan, US, ASEAN, and China by utilizing the knowledge we gained from all types of device development for various industries including smartphones (Android/iOS), wireless communication, security technology and IoT serv...
DevOps at Cloud Expo – being held October 31 - November 2, 2017, at the Santa Clara Convention Center in Santa Clara, CA – announces that its Call for Papers is open. Born out of proven success in agile development, cloud computing, and process automation, DevOps is a macro trend you cannot afford to miss. From showcase success stories from early adopters and web-scale businesses, DevOps is expanding to organizations of all sizes, including the world's largest enterprises – and delivering real r...
Five years ago development was seen as a dead-end career, now it’s anything but – with an explosion in mobile and IoT initiatives increasing the demand for skilled engineers. But apart from having a ready supply of great coders, what constitutes true ‘DevOps Royalty’? It’ll be the ability to craft resilient architectures, supportability, security everywhere across the software lifecycle. In his keynote at @DevOpsSummit at 20th Cloud Expo, Jeffrey Scheaffer, GM and SVP, Continuous Delivery Busine...
In order to meet the rapidly changing demands of today’s customers, companies are continually forced to redefine their business strategies in order to meet these needs, stay relevant and continue to see profitable growth. IoT deployment and development is integral in this transformation, and today businesses are increasingly seeing the value of investing their resources into IoT deployments. These technologies are able increase ROI through projects such as connecting supply chains or enabling sm...
SYS-CON Events announced today that CollabNet, a global leader in enterprise software development, release automation and DevOps solutions, will be a Bronze Sponsor of SYS-CON's 20th International Cloud Expo®, taking place from June 6-8, 2017, at the Javits Center in New York City, NY. CollabNet offers a broad range of solutions with the mission of helping modern organizations deliver quality software at speed. The company’s latest innovation, the DevOps Lifecycle Manager (DLM), supports Value S...
SYS-CON Events announced today that Peak 10, Inc., a national IT infrastructure and cloud services provider, 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. Peak 10 provides reliable, tailored data center and network services, cloud and managed services. Its solutions are designed to scale and adapt to customers’ changing business needs, enabling them to lower costs, improve performance and focus intern...
A strange thing is happening along the way to the Internet of Things, namely far too many devices to work with and manage. It has become clear that we'll need much higher efficiency user experiences that can allow us to more easily and scalably work with the thousands of devices that will soon be in each of our lives. Enter the conversational interface revolution, combining bots we can literally talk with, gesture to, and even direct with our thoughts, with embedded artificial intelligence, whic...
Everywhere we turn in our industry we can find strong opinions about the direction, type and nature of cloud’s impact on computing and business. Another word that is used in every context in our industry is “hybrid.” In his session at 20th Cloud Expo, Alvaro Gonzalez, Director of Technical, Partner and Field Marketing at Peak 10, will use a combination of a few conceptual props and some research recently commissioned by Peak 10 to offer a real-world consideration of how the various categories of...
SYS-CON Events announced today that Super Micro Computer, Inc., a global leader in compute, storage and networking technologies, 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. 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/...
With major technology companies and startups seriously embracing Cloud strategies, now is the perfect time to attend @CloudExpo | @ThingsExpo, June 6-8, 2017, at the Javits Center in New York City, NY and October 31 - November 2, 2017, Santa Clara Convention Center, CA. Learn what is going on, contribute to the discussions, and ensure that your enterprise is on the right path to Digital Transformation.
Multiple data types are pouring into IoT deployments. Data is coming in small packages as well as enormous files and data streams of many sizes. Widespread use of mobile devices adds to the total. In this power panel at @ThingsExpo, moderated by Conference Chair Roger Strukhoff, panelists will look at the tools and environments that are being put to use in IoT deployments, as well as the team skills a modern enterprise IT shop needs to keep things running, get a handle on all this data, and deli...
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.
In his opening keynote at 20th Cloud Expo, Michael Maximilien, Research Scientist, Architect, and Engineer at IBM, will motivate why realizing the full potential of the cloud and social data requires artificial intelligence. By mixing Cloud Foundry and the rich set of Watson services, IBM's Bluemix is the best cloud operating system for enterprises today, providing rapid development and deployment of applications that can take advantage of the rich catalog of Watson services to help drive insigh...