Home > Blogs > VMware VROOM! Blog

New White Paper: Fast Virtualized Hadoop and Spark on All-Flash Disks – Best Practices for Optimizing Virtualized Big Data Applications on VMware vSphere 6.5

A new white paper is available showing how to best deploy and configure vSphere 6.5 for Big Data applications such as Hadoop and Spark running on a cluster with fast processors, large memory, and all-flash storage (Non-Volatile Memory Express storage and solid state disks). Hardware, software, and vSphere configuration parameters are documented, as well as tuning parameters for the operating system, Hadoop, and Spark.

The best practices were tested on a 13-server cluster, with Hadoop installed on vSphere as well as on bare metal. Workloads for both Hadoop (TeraSort and TestDFSIO) and Spark Machine Learning Library routines (K-means clustering, Logistic Regression classification, and Random Forest decision trees) were run on the cluster. Configurations with 1, 2, and 4 VMs per host were tested as well as bare metal. Among the 4 virtualized configurations, 4 VMs per host ran fastest due to the best utilization of storage as well as the highest percentage of data transfer within a server. The 4 VMs per host configuration also ran faster than bare metal on all Hadoop and Spark tests but one.

Here are the results for the TeraSort suite:

And for Spark Random Forest decision trees:

Here are the best practices cited in this paper:

Reserve about 5-6% of total server memory for ESXi; use the remainder for the virtual machines.
Do not overcommit physical memory on any host server that is hosting Big Data workloads.
Create one or more virtual machines per NUMA node.
Limit the number of disks per DataNode to maximize the utilization of each disk: 4 to 6 is a good starting point.
Use eager-zeroed thick VMDKs along with the ext4 or xfs filesystem inside the guest.
Use the VMware Paravirtual SCSI (pvscsi) adapter for disk controllers; use all 4 virtual SCSI controllers available in vSphere 6.5.
Use the vmxnet3 network driver; configure virtual switches with MTU=9000 for jumbo frames.
Configure the guest operating system for Hadoop performance including enabling jumbo IP frames, reducing swappiness, and disabling transparent hugepage compaction.
Place Hadoop master roles, ZooKeeper, and journal nodes on three virtual machines for optimum performance and to enable high availability.
Dedicate the worker nodes to run only the HDFS DataNode, YARN NodeManager, and Spark Executor roles.
Run the Hive Metastore in a separate MySQL database.
Set the YARN cluster container memory and vcores to slightly overcommit both resources
Adjust the task memory and vcore requirement to optimize the number of maps and reduces for each application.

All details are in the paper.

DRS Lens – A new UI dashboard for DRS

1 Reply

DRS Lens provides an alternative UI for a DRS enabled cluster. It gives a simple, yet powerful interface to monitor the cluster real time and provide useful analyses to the users. The UI is comprised of different dashboards in the form of tabs for each cluster being monitored.

Continue reading →

The Extreme Performance Series at VMworld 2017

Continue reading →

Introducing VMmark3: A highly flexible and easily deployed benchmark for vSphere environments

1 Reply

VMmark 3.0, VMware’s multi-host virtualization benchmark is generally available here. VMmark3 is a free cluster-level benchmark that measures the performance, scalability, and power of virtualization platforms.

VMmark3 leverages much of previous VMmark generations’ technologies and design. It continues to utilize a unique tile-based heterogeneous workload application design. It also deploys the platform-level workloads found in VMmark2 such as vMotion, Storage vMotion, and Clone & Deploy. In addition to incorporating new and updated application workloads and infrastructure operations, VMmark3 also introduces a new fully automated provisioning service that greatly reduces deployment complexity and time.

Continue reading →

NEW VMworld 2017 Bootcamp – vSphere Advanced Performance Design, Configuration and Troubleshooting

6 Replies

New this year for VMworld 2017 in Las Vegas, we will be offering a pre-VMworld bootcamp focused on vSphere platform performance. Specific SQL and Oracle bootcamps will still be offered, but we have had many requests for a workload agnostic program. This bootcamp will enable you to confidently support all your virtual workloads and give you an opportunity to directly interact with VMware Performance Engineering.

Continue reading →

Introducing TPCx-HS Version 2 – An Industry Standard Benchmark for Apache Spark and Hadoop clusters deployed on premise or in the cloud

2 Replies

Since its release on August 2014, the TPCx-HS Hadoop benchmark has helped drive competition in the Big Data marketplace, generating 23 publications spanning 5 Hadoop distributions, 3 hardware vendors, 2 OS distributions and 1 virtualization platform. By all measures, it has proven to be a successful industry standard benchmark for Hadoop systems. However, the Big Data landscape has rapidly changed over the last 30 months. Key technologies have matured while new ones have risen to prominence in an effort to keep pace with the exponential expansion of datasets. One such technology is Apache Spark.

According to a Big Data survey published by the Taneja Group, more than half of the respondents reported actively using Spark, with a notable increase in usage over the 12 months following the survey. Clearly, Spark is an important component of any Big Data pipeline today. Interestingly, but not surprisingly, there is also a significant trend towards deploying Spark in the cloud. What is driving this adoption of Spark? Predominantly, performance.

Today, with the widespread adoption of Spark and its integration into many commercial Big Data platform offerings, I believe there needs to be a straightforward, industry standard way in which Spark performance and price/performance could be objectively measured and verified. Just like TPCx-HS Version 1 for Hadoop, the workload needs to be well understood and the metrics easily relatable to the end user.

Continuing on the Transaction Processing Performance Council’s commitment to bringing relevant benchmarks to the industry, it is my pleasure to announce TPCx-HS Version 2 for Spark and Hadoop. In keeping with important industry trends, not only does TPCx-HS support traditional on premise deployments, but also cloud.

I envision that TPCx-HS will continue to be a useful benchmark standard for customers as they evaluate Big Data deployments in terms of performance and price/performance, and for vendors in demonstrating the competitiveness of their products.

Tariq Magdon-Ismail

(Chair, TPCx-HS Benchmark Committee)

Additional Information: TPC Press Release

Oracle Database Performance on vSphere 6.5 Monster Virtual Machines

Weathervane, a benchmarking tool for virtualized infrastructure and the cloud, is now open source.

6 Replies

Weathervane is a performance benchmarking tool developed at VMware. It lets you assess the performance of your virtualized or cloud environment by driving a load against a realistic application and capturing relevant performance metrics. You might use it to compare the performance characteristics of two different environments, or to understand the performance impact of some change in an existing environment.

Weathervane is very flexible, allowing you to configure almost every aspect of a test, and yet is easy to use thanks to tools that help prepare your test environment and a powerful run harness that automates almost every aspect of your performance tests. You can typically go from a fresh start to running performance tests with a large multi-tier application in a single day.

Weathervane supports a number of advanced capabilities, such as deploying multiple independent application instances, deploying application services in containers, driving variable loads, and allowing run-time configuration changes for measuring elasticity-related performance metrics.

Weathervane has been used extensively within VMware, and is now open source and available on GitHub at https://github.com/vmware/weathervane.

The rest of this blog gives an overview of the primary features of Weathervane.

Continue reading →

DRS Cluster Resource Management with Reservation and Shares

1 Reply

Resource management in vSphere is very robust and sophisticated. It provides settings like reservation, limits and shares (a.k.a. RLS), which can be applied on virtual machines (VMs) and resource pools. These settings can be used as knobs to isolate resources, prioritize them, or to guarantee availability of resources to VMs in a cluster. Our customers have often asked about how these settings impact availability of resources for a VM.

Recently we published a white paper based on our study, to explain how reservation and shares can impact resource availability for VMs when they are applied on VMs versus when they are applied on resource pools. In the paper, we also share some general guidelines on when and how these settings can be used.

from VMware's performance team