YES – VM + Containers can be faster than Bare Metal!

Pat Gelsinger, VMware CEO, said that VM managed Containers could be 8% faster than bare metal during the VMworld keynote (@kitcolbert). On the surface, this comment defies logic: bare metal should be the theoretical limit for performance like the speed of light. While I don’t know the specifics of his test case, the claim of improved performance is credible.  Let’s explore how.

RackN specializes in bare metal workloads so let me explain how it’s possible in the right cases that containers in VMs benchmark faster than containers alone.

The crux of the argument comes down to two factors:

  1. Operating systems degrade when key resources are depleted
  2. CPUs are optimized for virtualization (see NUMA architecture)

Together, these factors conspire to make VMs a design necessity on large bare metal systems.

A large RAM and CPU core system can become saturated with container workloads even in the 10s of containers. In these cases, the performance cost for operating system to manage resources starts to take away from the performance. Since typical hypervisor hosts have a lot of resources, the risk of over saturation is very high.

The solution on high resource hosts is to leverage a hypervisor to partition the resources into multiple operating system instances. That eliminates over saturation and improves throughput for the host. We’re talking about 10 vms with 10 containers instead of 1 host with 100 containers.

In addition to simple partitioning, most CPUs are optimized for virtualization. That means that they can run multiple virtualization operating systems on the same host with minimal overhead.  The non-virtualized host does not get to leverage this optimization.

Due to these factors AND with the right tuning, it would be possible to demonstrate improved container performance for hosts that were optimized for running a hypervisor. The same would not hold true for systems that are size optimized for only container workloads. Since the container optimized machines are also much cheaper, the potential performance gain is likely an not a good ROI.

While bare metal will eventually come; this strange optimization reinforces why we expect to see hypervisors continue to be desired in container deployments for a long time.

0 comments on “Podcast with Zach Smith talking Bare Metal and AWS Training Wheels”

Podcast with Zach Smith talking Bare Metal and AWS Training Wheels

Joining this week’s L8ist Sh9y Podcast is Zach Smith, CEO of Packet and long-time champion of bare metal hardware. Rob Hirschfeld and Zach discuss the trends in bare metal, the impact of AWS changing the way developers view infrastructure, and issues between networking and server groups in IT organizations.

Topic                                                            Time (Minutes.Seconds)

Introduction                                                       0.0 – 0.43
History of Packet                                               0.43 – 1:38
Why Public Cloud Bare Metal                         1.38 – 2.10
Price Points Metal vs VM                                 2.10 – 3.08
Intro Compute to Non-Data Center People 3.08 – 4:27
RackN early Customer                                      4.27 – 5.41
Managing non-Enterprise Hardware             5.41 – 7.45
Cloud has forever changed IT Ops                 7.45 – 10.20
Making Hardware Easier                                 10.20 – 12.35
Continuous Integration (CI)                            12.35 – 14.37
Customer Story w/ Terraform                        14.47 – 16.08
SRE, DevOps and Engineering Thinking     16.08 – 16:49
Most extreme Metal Pipelines                        16.49 – 18.02
Coolest New Hardware in Use                        18.02 – 19.28
How order metal and add to data center     19.28 – 22.47
RackN and the Switch                                       22.47 – 24.39
Edge Computing Break Enterprise IT           24.39 – 25.16
DevOps Highlights for Today                          25.16 – 27.01
Post Provision Control in Open Source          27.01 – 30.03
Data Centers in early 2000’s                            30.03 – 31.27
Nov 1 in NYC: Cloud Native in DataCenter   31.27 –  END

Podcast Guest: Zach Smith, CEO Packet

Zachary has spent his last 16 years building, running and fixing public cloud infrastructure platforms.  As the CEO of Packet, Zachary is responsible for the company’s strategic product roadmap and is most passionate about helping customers and partners take advantage of fundamental compute and avoid vendor lockin.  Prior to founding Packet, Zachary was an early member of the management team at Voxel, a NY-based cloud hosting company sold to Internap in 2011, that built software to automate all aspects of hosting datacenters.  He lives in New York City with his wife and 2 young children. Twitter @zsmithnyc