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

My public speaking experience

It can be a bit of a hassle; working on cool projects as a contractor and finding the time to take days off to visit and/or present at a VMworld, VMUG or other industry events. And that is next to putting in the hours to co-write some pretty awesome books if I may say so myself.

Busy but fun times! However, it is really important to me to keep attending industry events. I genuinely love to visit and present as I really see it as a investment in myself and our community. Meeting new people is always fun and interesting, and listening in on sessions is very educational. While doing so, I get the chance to practise public speaking.

The article by Duncan Epping (http://www.yellow-bricks.com/2018/03/08/confessions-of-a-vmug-speaker-the-prequel-speakerfail/) made me recap and think about my experiences with public speaking so far.

The First Time

It’s only been 2 years since I’ve started to (co-)host presentations. It was the NLVMUG in 2016. I can relate to the excess of rehearsing as Duncan described in his article. I was pretty psyched but mostly nervous to present at a VMUG. I talked in front of customers a lot, but public speaking felt like a totally different ballgame.

But there I was, presenting in front of peers. Looking back at the recordings, there are so many points I want to improve on. And the best way to learn and improve is to do it more often. Around that time, Frank and I started writing our Host Deep Dive book. We got the chance to present some of the content at both VMworlds in 2016.

I remember that VMworld US 2016 was the second or third time I was on stage, but the first time not speaking native tongue. We had a big room and something in the range of 800 registrants! Once we walked to our room, Oceanside D, we witnessed a large amount of people waiting to get into the room. I managed to film the part when they opened the doors:

Very cool to witness, but a little bit scary as well. I kicked of the introductions only to stumble on the very first sentences and had trouble pronouncing our own session title. Talking about #speakerfail. Once I was up to do my part, the nerves settled and I had a lot of fun presenting. Afterwards, people who attended the session were positive and we scored a top-10 session which was awesome!

Since then, I had the chance to do several VMUGs with Frank next to the NLVMUG and both VMworlds again in 2017. We presented at the German, London, Italy and the Nordic VMUG.

Moral of the this short write-up;

If I can do it, you most certainly can!

I talked to a lot of people who want to present at a VMUG or other events, but it looks like they worry far too much to go through with it. It’s okay to be nervous, but don’t let it get you. It’s that thing about stepping outside your comfort zone and into the zone where the magic happens… Presenting is a great opportunity to share your knowledge and experience, and in the process, put your name on the charts.

Upcoming Schedule

Hopefully, I’ll get the chance to present at VMworld 2018. Two session are submitted, session ID 1738 and 1735. Pretty cool as one session will be together with a lead-engineer who works on Network DRS within VMware!

With the support of the VMUG organization and our friends at Rubrik, we will attend the Indianapolis VMUG at the 10th of July. Attending and presenting at one of the largest US based VMUGs will be a very good experience.

Also, the VMUG at Prague on the 24th of May is on the schedule, really looking forward to that one!

There are some other opportunities that are work in progress.

To Conclude

I honestly hope that my experience can encourage others to take the leap of faith and contribute at an upcoming VMUG. Think about that project you’re working on and the design choices you made for it to succeed. Or what about that issue you ran into and solved. All very good content to convey to our VMware community.

Like the Nike campaign launched in 1988 stated; Just do it!!

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