vSphere Host Resources Deep Dive: Part 3 – VMworld

In my previous post, I mentioned the part 3 of the Host Deep Dive session at VMworld 2018. The ‘3’ is because we ran the part 1 and 2 at VMworld 2016 and 2017. We had the chance to try a new way of discussing Host Resources settings by the way of creating levels of performance tuning. The feedback we received will test-driving this session at the London and Indianapolis VMUG, was really positive.

As we always stated, the out-of-the-box experience of VMware vSphere is good enough for 80-90% of common virtual infrastructures. We like to show how you can gradually increase performance and reduce latency with advanced vSphere tuning. That’s why we came up with the Pyramid of Performance Optimization. Delivering the content this way allows for better understanding on when to apply certain optimizations. We will start with the basics and work our way up to settings to squeeze out the maximum performance of vSphere ESXi hosts.

Due to session time constrains, we will focus on compute (CPU and Memory) and virtual Networking. The following pyramids contain the subjects about content we will discuss in our session.

Pyramid of Performance Optimization – Compute:


Pyramid of Performance Optimization – Networking:

We will go trough all these levels in detail. We very much look forward to VMworld and hope to see you there! Be sure to reserve your seat for this session!

The following VMworld sessions are all based on the Deep Dive series:

  • vSphere Clustering Deep Dive, Part 1: vSphere HA and DRS [VIN1249BU]
  • vSphere Clustering Deep Dive, Part 2: Quality Control with DRS and Network I/O Control [VIN1735BU]
  • vSphere Host Resources Deep Dive: Part 3 [VIN1738BU]

Read More

Clustering Deep Dive Book – released + logo!

Yesterday we finally were able to share the news that our new VMware vSphere 6.7 Clustering Deep Dive book is released.

Countless hours has gone into it; researching, writing content, updating content, discussing a lot, creating the cover designs, creating a logo, having fun!
It was my second time as a co-author after releasing the Host Deep Dive book last year with Frank. I am humbled that I got to work with two of the most regarded individuals in our vCommunity. What these guys did for making the daily life easier for everybody working with VMware solutions, is incredible.

Also, a big thank you to all our reviewers, people who helped realizing this release and Chris Wahl for writing an inspiring foreword.

Clustering Deep Dive

I am a big fan of the previous releases of the Clustering Deep Dive series. When thinking about that, back in 2010-11, the first release helped me a lot to fully understand all clustering constructs. One might say it helped to fuel my enthusiasm for working with VMware vSphere.

Couple years fast forward and here I am working together with Duncan and Frank on the latest release. A big thank you to them for letting me get onboard and be part of this amazing series! As there are a lot of changes since the 5.1 release, we hope this book can help you getting a thorough understanding about all VMware vSphere 6.7 clustering features. The new version of the Clustering Deep Dive covers vSphere HA, DRS, Storage DRS, Storage I/O Control and Network I/O Control. In the last chapter of the book, we bring all the theory together and apply it to create a stretched cluster configuration.

Where Duncan worked on the HA parts and Frank on the DRS parts, I primarily focussed on the Quality Control parts. I feel that these features are often enabled or disabled without really understanding how they can help you managing and enforcing quality control. At least, that is my experience with them. While knewing high-level what NIOC and SIOC are all about, a deeper understanding can lead to new insights on their impact and how to use them. We feel that this addition to the book helps to gain these insights.

Logo & VMworld sessions

The idea is to provide you with a vSphere Resource kit to fully understand all features from the hardware components and everything involved all the way up to the vSphere clustering service on top of that.

Host Deep Dive book + Clustering Deep Dive book = vSphere Resource kit

The following VMworld sessions are all based on the Deep Dive series:

  • vSphere Clustering Deep Dive, Part 1: vSphere HA and DRS [VIN1249BU]
  • vSphere Clustering Deep Dive, Part 2: Quality Control with DRS and Network I/O Control [VIN1735BU]
  • vSphere Host Resources Deep Dive: Part 3 [VIN1738BU]

Now the Host Deep Resources Deep Dive, Part 3 might be a slightly confusing title. It is part 3 because we already did Part 1 at VMworld 2016 and Part 2 in 2017. We will bring a new awesome way of delivering host resources knowledge in that session. More on that later.

With the arrival of the new Clustering Deep Dive book, we came up with a new logo to accompany the Host Deep Dive logo. There will be a limited number of shirts + stickers (pushing for on-time delivery) that we will bring with us to VMworld. We will give some away in our sessions so make sure to attend!

 

Read More

FREE vSphere 6.5 Host Resources Deep Dive E-Book

In June of this year, Frank and I published the vSphere 6.5 Host Resources Deep Dive, and the community was buzzing. Twitter exploded, and many community members provided rave reviews.

This excitement caught Rubriks attention, and they decided to support the community by giving away 2000 free copies of the printed version at VMworld. The interest was overwhelming, before the end of the second signing session in Barcelona we ran out of books.

A lot of people reached out to Rubrik and us to find out if they could get a free book as well. This gave us an idea, and we sat down with Rubrik and the VMUG organization to determine how to cater the community.

We are proud to announce that you can download the e-book version (PDF only) for free at rubrik.com. Just sign up and download your full e-book copy here.

 

Spread the word! And if you like, thank @Rubrik and @myVMUG for their efforts to help the VMware community advance.

 

A quick impression of the buzz at the Rubrik booth at VMworld:

Read More

TCP Segmentation Offload in ESXi explained

TCP Segmentation Offload (TSO) is the equivalent to TCP/IP Offload Engine (TOE) but more modeled to virtual environments, where TOE is the actual NIC vendor hardware enhancement. It is also known as Large Segment Offload (LSO). But what does it do?

When a ESXi host or a VM needs to transmit a large data packet to the network, the packet must be broken down to smaller segments that can pass all the physical switches and possible routers in the network along the way to the packet’s destination. TSO allows a TCP/IP stack to emit larger frames, even up to 64 KB, when the Maximum Transmission Unit (MTU) of the interface is configured for smaller frames. The NIC then divides the large frame into MTU-sized frames and prepends an adjusted copy of the initial TCP/IP headers. This process is referred to as segmentation.

When the NIC supports TSO, it will handle the segmentation instead of the host OS itself. The advantage being that the CPU can present up to 64 KB of data to the NIC in a single transmit-request, resulting in less cycles being burned to segment the network packet using the host CPU. To fully benefit from the performance enhancement, you must enable TSO along the complete data path on an ESXi host. If TSO is supported on the NIC it is enabled by default.

The same goes for TSO in the VMkernel layer and for the VMXNET3 VM adapter but not per se for the TSO configuration within the guest OS. To verify that your pNIC supports TSO and if it is enabled on your ESXi host, use the following command: esxcli network nic tso get. The output will look similar the following screenshot, where TSO is enabled for all available pNICs or vmnics.

(more…)

Read More

Virtual Networking: Poll-mode vs Interrupt

The VMkernel is relying on the physical device, the pNIC in this case, to generate interrupts to process network I/O. This traditional style of I/O processing incurs additional delays on the entire data path from the pNIC all the way up to within guest OS. Processing I/Os using interrupt based mechanisms allows for CPU saving because multiple I/Os are combined in one interrupt. Using poll mode, the driver and the application running in the guest OS will constantly spin waiting for an I/O to be available. This way, an application can process the I/O almost instantly instead of waiting for an interrupt to occur. That will allow for lower latency and a higher Packet Per Second (PPS) rate.

An interesting fact is that the world is moving towards poll-mode drivers. A clear example of this is the NVMe driver stack.

The main drawback is that the poll-mode approach consumes much more CPU time because of the constant polling for I/O and the immediate processing. Basically, it consumes all the CPU you offer the vCPUs used for polling. Therefore, it is primarily useful when the workloads running on your VMs are extremely latency sensitive. It is a perfect fit for data plane telecom applications like a Packet GateWay (PGW) node as part of a Evolved Packet Core (EPC) in a NFV environment or other real-time latency sensitive workloads.

Using the poll-mode approach, you will need a pollmode driver in your application which polls a specific device queue for I/O. From a networking perspective, Intel’s Data Plane Development Kit (DPDK) delivers just that. You could say that the DPDK framework is a set of libraries and drivers to allow for fast network packet processing.

Data Plane Development Kit (DPDK) greatly boosts packet processingperformance and throughput, allowing more time for data plane applications. DPDK can improve packet processing performance by up to ten times. DPDK software running on current generation Intel®Xeon® Processor E5-2658 v4, achieves 233 Gbps (347 Mpps) of LLC forwarding at 64-byte packet sizes. Source: http://www.intel.com/content/www/us/en/communications/data-planedevelopment-kit.html

DPDK in a VM

Using a VM with a VMXNET3 network adapter, you already have the default paravirtual network connectivity in place. The following diagram shows the default logical paravirtual device connectivity.

(more…)

Read More

Why we chose vSAN for our business critical apps

Looking at the IT infrastructure at several production sites within my customer’s organization, we quickly noticed IT infrastructure components (mainly compute and storage related) that were not up to par from an availability and performance perspective. The production sites all run local business critical ERP application workloads that are vital to the business processes. After researching and discussing a lot, I proposed my customer a new blueprint. The blueprint consists of a new compute and storage baseline for the site local datacenters. The idea was to create a platform that allows for a higher availability and more performance while reducing costs.

We researched the possibility to step away from the traditional storage arrays and move towards a Hyper Converged Infrastructure (HCI) solution. Because IT is not the main business of the company, we were trying to keep things as simple as possible. We defined several ‘flavors’ to suit each production location to its needs. For example, the small sites will be equipped with a ROBO setup, the medium sites with a single datacenter cluster and the large factories are presented a stretched cluster solution. A stretched cluster setup will allow them to adhere to the stated availability SLA in the event of a large scale outages on the plant for their most important applications that do not offer in-application clustering/resiliency.

Benefits

Since my customer is running VMware solutions in all of its datacenters, VMware vSAN was the perfect fit. It allows the customer to lean on the already in-house VMware knowledge while being able to move towards less FTE for managing the storage backend. Implementing stretched clusters on multiple sites using storage arrays can be a daunting task. And although there are prerequisites, implementing VMware vSAN is implemented fairly easy, even if you opt for a stretched cluster configuration. This allowed for very short time from the moment of receiving hardware to a fully operational vSphere and vSAN cluster. Because the customer is in the process of renewing its IT infra for a number of sites, it really helps to tell the business we can deliver within weeks rather than months.

Using the VMware vSAN ready nodes allowed us to exceed the required storage capacity and performance requirements while being more cost efficient in comparison to traditional storage arrays. As management loves lowered costs, both capex and opex, HCI was the way to go. From a manageability point-of-view, it is a big plus that all VMware datacenters and (vSAN) clusters are managed from a centralized VMware vCenter UI. Another plus was the savings in rack units as those are scarce in some site-local datacenters.

(more…)

Read More