VMware and Microsoft have collaborated to validate and support the functionality and performance scalability of SQL Server 2017 on vSphere-based Linux VMs. The results of that work show SQL Server 2017 for Linux installs easily and has great performance within VMware vSphere virtual machines. VMware vSphere is a great environment to be able to try out the new Linux version of SQL Server and be able to also get great performance.
Back in March, I published a performance study of SQL Server performance with vSphere 6.5 across multiple processor generations. Since then, Intel has released a brand-new processor architecture: the Xeon Scalable platform, formerly known as Skylake.
Our team was fortunate enough to get early access to a server with these new processors inside – just in time for generating data that we presented to customers at VMworld 2017.
Each Xeon Platinum 8180 processor has 28 physical cores (pCores), and with four processors in the server, there was a whopping 112 pCores on one physical host!
Docker containers are growing in popularity as a deployment platform for enterprise applications. However, the performance impact of running these applications in Docker containers on virtualized infrastructures is not well understood. A new white paper is available that uses the open source Weathervane performance benchmark to investigate the performance of an enterprise web application running in Docker containers in VMware vSphere 6.5 virtual machines (VMs). The results show that an enterprise web application can run in Docker on a VMware vSphere environment with not only no degradation of performance, but even better performance than a Docker installation on bare-metal.
Weathervane is used to evaluate the performance of virtualized and cloud infrastructures by deploying an enterprise web application on the infrastructure and then driving a load on the application. The tests discussed in the paper use three different deployment configurations for the Weathervane application.
VMs without Docker containers: The application runs directly in the guest operating systems in vSphere 6.5 VMs, with no Docker containers.
VMs with Docker containers: The application runs in Docker containers, which run in guest operating systems in vSphere 6.5 VMs.
Bare-metal with Docker containers: The application runs in Docker containers, but the containers run in an operating system that is installed on a bare-metal server.
The figure below shows the peak results achieved when running the Weathervane benchmark in the three configurations. The results using Docker containers include the impact of tuning options that are discussed in detail in the paper.
Some important things to note in these results:
The performance of the application using Docker containers in vSphere 6.5 VMs is almost identical to that of the same application running in VMs without Docker.
The application running in Docker containers in VMs outperforms the same application running in Docker containers on bare metal by about 5%. Most of this advantage can be attributed to the sophisticated algorithms employed by the vSphere 6.5 scheduler.
The results discussed in the paper, along with the results of previous investigations of Docker performance on vSphere, show that vSphere 6.5 is an ideal platform for deploying applications in Docker containers.
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.
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.
We have just published a new whitepaper on the performance of Oracle databases on vSphere 6.5 monster virtual machines. We took a look at the performance of the largest virtual machines possible on the previous four generations of four-socket Intel-based servers. The results show how performance of these large virtual machines continues to scale with the increases and improvements in server hardware.
Oracle Database Monster VM Performance on vSphere 6.5 across 4 generations of Intel-based four-socket servers
In addition to vSphere 6.5 and the four-socket Intel-based servers used in the testing, an IBM FlashSystem A9000 high performance all flash array was used. This array provided extreme low latency performance that enabled the database virtual machines to perform at the achieved high levels of performance.
Some similar tests with Microsoft SQL Server monster virtual machines were also recently completed on vSphere 6.5 by my colleague David Morse. Please see his blog post and whitepaper for the full details.
Achieving optimal SQL Server performance on vSphere has been a constant focus here at VMware; I’ve published past performance studies with vSphere 5.5 and 6.0 which showed excellent performance up to the maximum VM size supported at the time.
Since then, there have been quite a few changes! While this study uses a similar test methodology, it features an updated hypervisor (vSphere 6.5), database engine (SQL Server 2016), OLTP benchmark (DVD Store 3), and CPUs (Intel Xeon v4 processors with 24 cores per socket, codenamed Broadwell-EX).
With Storage I/O Control (SIOC), vSphere 6.5 administrators can adjust the storage performance of VMs so that VMs with critical workloads will get the I/Os per second (IOPS) they need. Admins assign shares (the proportion of IOPS allocated to the VM), limits (the upper bound of VM IOPS), and reservations (the lower bound of VM IOPS) to the VMs whose IOPS need to be controlled. After shares, limits, and reservations have been set, SIOC is automatically triggered to meet the desired policies for the VMs.
A recently published paper shows the performance of SIOC meets expectations and successfully controls the number of IOPS for VM workloads.
VMware recently announced the general availability of vSphere 6.5. Among the many new features in this release are some DRS specific ones like predictive DRS, and network-aware DRS. In vSphere 6.5, DRS also comes with a host of performance improvements like the all-new VM initial placement and the faster and more effective maintenance mode operation.
If you want to learn more about them, we published a new white-paper on the new features and performance improvements of DRS in vSphere 6.5. Here are some highlights from the paper: