Short lived VM (Mayflies) research yields surprising scheduling benefit

Last semester, Alex Hirschfeld (my son) did a simulation to explore the possible efficiency benefits of the Mayflies concept proposed by Josh McKenty and me.

Mayflies swarming from Wikipedia

In the initial phase of the research, he simulated a data center using load curves designed to oversubscribe the resources (he’s still interesting in actual load data).  This was sufficient to test the theory and find something surprising: mayflies can really improve scheduling.

Alex found an unexpected benefit comes when you force mayflies to have a controlled “die off.”  It allows your scheduler to be much smarter.

Let’s assume that you have a high mayfly ratio (70%), that means every day 10% of your resources would turn over.  If you coordinate the time window and feed that information into your scheduler, then it can make much better load distribution decisions.  Alex’s simulation showed that this approach basically eliminated hot spots and server over-crowding.

Here’s a snippet of his report explaining the effect in his own words:

On a system that is more consistent and does not have a massive virtual machine through put, Mayflies may not help with balancing the systems load, but with the social engineering aspect, it can increase the stability of the system.

Most of the time, the requests for new virtual machines on a cloud are immutable. They came in at a time and need to be fulfilled in the order of their request. Mayflies has the potential to change that. If a request is made, it has the potential to be added to a queue of mayflies that need to be reinitialized. This creates a queue of virtual machine requests that any load balancing algorithm can work with.

Mayflies can make load balancing a system easier. Knowing the exact size of the virtual machine that is going to be added and knowing when it will die makes load balancing for dynamic systems trivial.

Are VMs becoming El Caminos? Containers & Metal provide new choices for DevOps

I released “VMS ARE DEAD” this post two weeks ago on DevOps.com.  My point here is that Ops Automation (aka DevOps) is FINALLY growing beyond Cloud APIs and VMs.  This creates a much richer ecosystem of deployment targets instead of having to shoehorn every workload into the same platform.

In 2010, it looked as if visualization had won. We expected all servers to virtualize workloads and the primary question was which cloud infrastructure manager would dominate. Now in 2015, the picture is not as clear. I’m seeing a trend that threatens the “virtualize all things” battle cry.

IMG_20150301_170558985Really, it’s two intersecting trends: metal is getting cheaper and easier while container orchestration is advancing on rockets. If metal can truck around the heavy stable workloads while containers zip around like sports cars, that leaves VMs as a strange hybrid in the middle.

What’s the middle? It’s the El Camino, that notorious discontinued half car, half pick-up truck.

The explosion of interest in containerized workloads (I know, they’ve been around for a long time but Docker made them sexy somehow) has been creating secondary wave of container orchestration. Five years ago, I called that Platform as a Service (PaaS) but this new generation looks more like a CI/CD pipeline plus DevOps platform than our original PaaS concepts. These emerging pipelines obfuscate the operational environment differently than virtualized infrastructure (let’s call it IaaS). The platforms do not care about servers or application tiers, their semantic is about connecting services together. It’s a different deployment paradigm that’s more about SOA than resource reservation.

On the other side, we’ve been working hard to make physical ops more automated using the same DevOps tool chains. To complicate matters, the physics of silicon has meant that we’ve gone from scale up to scale out. Modern applications are so massive that they are going to exceed any single system so economics drives us to lots and lots of small, inexpensive servers. If you factor in the operational complexity and cost of hypervisors/clouds, an small actual dedicated server is a cost-effective substitute for a comparable virtual machine.

I’ll repeat that: a small dedicated server is a cost-effective substitute for a comparable virtual machine.

I am not speaking against virtualize servers or clouds. They have a critical role in data center operations; however, I hear from operators who are rethinking the idea that all servers will be virtualized and moving towards a more heterogeneous view of their data center. Once where they have a fleet of trucks, sports cars and El Caminos.

Of course, I’d be disingenuous if I neglected to point out that trucks are used to transport cars too. At some point, everything is metal.

Want more metal friendly reading?  See Packet CEO Zac Smith’s thinking on this topic.

Research showing that Short Lived Servers (“mayflies”) create efficiency at scale [DATA REQUESTED]

Last summer, Josh McKenty and I extended the puppies and cattle metaphor to limited life cattle we called “mayflies.” It was an attempt to help drive the cattle mindset (I think of it as social engineering, or maybe PsychOps) by forcing churn. I’ve come to think of it a step in between cattle and chaos monkeys (see Adrian Cockcroft).

While our thoughts were on mainly ops patterns, I’ve heard that there could be a real operational benefit from encouraging this behavior. The increased turn over in the environment improves scheduler optimization, planned load drains and coping with platform/environment migration.

Now we have a chance to quantify this benefit: a college student (disclosure: he’s my son) has created a data center emulation to see if Mayflies help with utilization. His model appears to work.

Now, he needs some real world data, here’s his request for assistance [note: he needs data by 1/20 to be included in this term]:

Hello!

I am Alexander Hirschfeld, a freshman at Rose-Hulman Institute of Technology. I am working on an independent study about Mayflies, a new idea in virtual machine management in cloud computing. Part of this management is load balancing and resource allocation for virtual machines across a collection of servers. The emulation that I am working on needs a realistic set of data to be the most accurate when modeling the results of using the methods outlined by the theory of mayflies.

Mayflies are an extension of the puppies verses cattle approach to machines, they are the extreme version of cattle as they have a known limited lifespan, such as 7 days. This requires the users of the cloud to build inherently more automated and fault-resistant applications. If you could send me a collection of the requests for new virtual machines(per standard unit of time and their requested specs/size), as well as an average lifetime for the virtual machines (or a graph or list of designated/estimated life times), and a basic summary of the collection of servers running the virtual machines(number, ram, cores), I would be better able to understand how Mayflies can affect a cloud.

Thanks,
Alexander Hirschfeld, twitter: @d-qoi

Needless to say, I’m really excited about the progress on demonstrating some the impact of this practice and am looking forward to posting about his results in the near future.

If you post in the comments, I will make sure you are connected to Alex.

OpenCrowbar v2.1 Video Tour from Metal to OpenStack and beyond

With the OpenCrowbar v2.1 out, I’ve been asked to update the video library of Crowbar demos.  Since a complete tour is about 3 hours, I decided to cut it down into focused demos that would allow you to start at an area of interest and work backwards.

I’ve linked all the videos below by title.  Here’s a visual table on contents:

Video Progression

Crowbar v2.1 demo: Visual Table of Contents [click for playlist]

The heart of the demo series is the Annealer and Ready State (video #3).

  1. Prepare Environment
  2. Bootstrap Crowbar
  3. Add Nodes ♥ Ready State (good starting point)
  4. Boot Hardware
  5. Install OpenStack (Juno using PackStack on CentOS 7)
  6. Integrate with Chef & Chef Provisioning
  7. Integrate with SaltStack

I’ve tried to do some post-production so limit dead air and focus on key areas.  As always, I value content over production values so feedback is very welcome!

2015, the year cloud died. Meet the seven riders of the cloudocalypse

i can hazAfter writing pages of notes about the impact of Docker, microservice architectures, mainstreaming of Ops Automation, software defined networking, exponential data growth and the explosion of alternative hardware architecture, I realized that it all boils down to the death of cloud as we know it.

OK, we’re not killing cloud per se this year.  It’s more that we’ve put 10 pounds of cloud into a 5 pound bag so it’s just not working in 2015 to call it cloud.

Cloud was happily misunderstood back in 2012 as virtualized infrastructure wrapped in an API beside some platform services (like object storage).

That illusion will be shattered in 2015 as we fully digest the extent of the beautiful and complex mess that we’ve created in the search for better scale economics and faster delivery pipelines.  2015 is going to cause a lot of indigestion for CIOs, analysts and wandering technology executives.  No one can pick the winners with Decisive Leadership™ alone because there are simply too many possible right ways to solve problems.

Here’s my list of the seven cloud disrupting technologies and frameworks that will gain even greater momentum in 2015:

  1. Docker – I think that Docker is the face of a larger disruption around containers and packaging.  I’m sure Docker is not the thing alone.  There are a fleet of related technologies and Docker replacements; however, there’s no doubt that it’s leading a timely rethinking of application life-cycle delivery.
  2. New languages and frameworks – it’s not just the rapid maturity of Node.js and Go, but the frameworks and services that we’re building (like Cloud Foundry or Apache Spark) that change the way we use traditional languages.
  3. Microservice architectures – this is more than containers, it’s really Functional Programming for Ops (aka FuncOps) that’s a new generation of service oriented architecture that is being empowered by container orchestration systems (like Brooklyn or Fleet).  Using microservices well seems to redefine how we use traditional cloud.
  4. Mainstreaming of Ops Automation – We’re past “if DevOps” and into the how. Ops automation, not cloud, is the real puppies vs cattle battle ground.  As IT creates automation to better use clouds, we create application portability that makes cloud disappear.  This freedom translates into new choices (like PaaS, containers or hardware) for operators.
  5. Software defined networking – SDN means different things but the impacts are all the same: we are automating networking and integrating it into our deployments.  The days of networking and compute silos are ending and that’s going to change how we think about cloud and the supporting infrastructure.
  6. Exponential data growth – you cannot build applications or infrastructure without considering how your storage needs will grow as we absorb more data streams and internet of things sources.
  7. Explosion of alternative hardware architecture – In 2010, infrastructure was basically pizza box or blade from a handful of vendors.  Today, I’m seeing a rising tide of alternatives architectures including ARM, Converged and Storage focused from an increasing cadre of sources including vendors sharing open designs (OCP).  With improved automation, these new “non-cloud” options become part of the dynamic infrastructure spectrum.

Today these seven items create complexity and confusion as we work to balance the new concepts and technologies.  I can see a path forward that redefines IT to be both more flexible and dynamic while also being stable and performing.

Want more 2015 predictions?  Here’s my OpenStack EOY post about limiting/expanding the project scope.

Ironic + Crowbar: United in Vision, Complementary in Approach

This post is co-authored by Devanda van der Veen, OpenStack Ironic PTL, and Rob Hirschfeld, OpenCrowbar Founder.  We discuss how Ironic and Crowbar work together today and into the future.

Normalizing the APIs for hardware configuration is a noble and long-term goal.  While the end result, a configured server, is very easy to describe; the differences between vendors’ hardware configuration tools are substantial.  These differences make it impossible challenging to create repeatable operations automation (DevOps) on heterogeneous infrastructure.

Illustration to show potential changes in provisioning control flow over time.

Illustration to show potential changes in provisioning control flow over time.

The OpenStack Ironic project is a multi-vendor community solution to this problem at the server level.  By providing a common API for server provisioning, Ironic encourages vendors to write drivers for their individual tooling such as iDRAC for Dell or iLO for HP.

Ironic abstracts configuration and expects to be driven by an orchestration system that makes the decisions of how to configure each server. That type of orchestration is the heart of Crowbar physical ops magic [side node: 5 ways that physical ops is different from cloud]

The OpenCrowbar project created extensible orchestration to solve this problem at the system level.  By decomposing system configuration into isolated functional actions, Crowbar can coordinate disparate configuration actions for servers, switches and between systems.

Today, the Provisioner component of Crowbar performs similar functions as Ironic for operating system installation and image lay down.  Since configuration activity is tightly coupled with other Crowbar configuration, discovery and networking setup, it is difficult to isolate in the current code base.  As Ironic progresses, it should be possible to shift these activities from the Provisioner to Ironic and take advantage of the community-based configuration drivers.

The immediate synergy between Crowbar and Ironic comes from accepting two modes of operation for OpenStack: bootstrapping infrastructure and multi-tenant server allocation.

Crowbar was designed as an operational platform that seeds an OpenStack ready environment.  Once that environment is configured, OpenStack can take over ownership of the resources and allow Ironic to manage and deliver “hypervisor-free” servers for each tenant.  In that way, we can accelerate the adoption of OpenStack for self-service metal.

Physical operations is messy and challenging, but we’re committed to working together to make it suck less.  Operators of the world unite!

Physical Ops = Plumbers of the Internet. Celebrating dirty IT jobs 8 bit style

I must be crazy because I like to make products that take on the hard and thankless jobs in IT.  Its not glamorous, but someone needs to do them.

marioAnalogies are required when explaining what I do to most people.  For them, I’m not a specialist in physical data center operations, I’m an Internet plumber who is part of the team you call when your virtual toilet backs up.  I’m good with that – it’s work that’s useful, messy and humble.

Plumbing, like the physical Internet, disappears from most people’s conscious once it’s out of sight under the floor, cabinet or modem closet.  And like plumbers, we can’t do physical ops without getting dirty.  Unlike cloud-based ops with clean APIs and virtual services, you can’t do physical ops without touching something physical.  Even if you’ve got great telepresence, you cannot get away from physical realities like NIC and SATA enumeration, BIOS management and network topology.  I’m delighted that cloud has abstracted away that layer for most people but that does not mean we can ignore it.

Physical ops lacks the standardization of plumbing.  There are many cross-vendor standards but innovation and vendor variation makes consistency as unlikely as a unicorn winning the Rainbow Triple Crown.

493143-donkey_kong_1For physical ops, it feels like we’re the internet’s most famous plumber, Mario, facing Donkey Kong.  We’ve got to scale ladders, jump fireballs and swing between chains.  The job is made harder because there’s no half measures.  Sometimes you can find the massive hammer and blast your way through but that’s just a short term thing.

Unfortunately, there’s a real enemy here: complexity.

Just like Donkey Kong keeps dashing off with the princess, operations continue to get more and more complex.  Like with Mario, the solution is not to bypass the complexity; it’s to get better and faster at navigating the obstacles that get thrown at you.  Physical ops is about self-reliance and adaptability.  In that case, there are a lot of lessons to be learned from Mario.

If I’m an internet plumber then I’m happy to embrace Mario as my mascot.  Plumbers of the internet unite!