Going into the last day of #VFD3, I was a bit cranky, missing my Child Partition, and strict though her protocols be, the Supervisor Module spouse back home.
But #TFD delegates don’t get to feel sorry for themselves so I put on my big boy pants, and turned my thoughts to VMTurbo.
“What the hell is a VM Turbo,” I asked myself as I walked in the meeting room and took a good hard look at the VMTurbo guys.
Two of them were older gentlemen, one was about my age. The two older guys had Euro-something accents; one was obviously Russian. I made with the introductions and got a business card from one of them. It listed an address in New Jersey or New York or something. Somewhere gritty, industrial and old no doubt, the inverse of Silicon Valley.
As I moved to my seat, there was some drama between the VMTurbo presenters and Gestalt’s Tom Hollingsworth who, even though he’s a CCIE, seems to really enjoy playing SVGA Resolution Cop. “The online viewers aren’t going to be able to see your demo at 1152×800,” Tom said. “You need to go 1024×768 to the projector” he nagged.
“But but….” the VMTurbo guys responded, fiddling with some setting which caused the projected OS X desktop to disappear and be replaced by a projector test pattern. At that point everyone’s attention shifted, once again, to the stupid presentation Mac book and its malfunctioning DisplayPort-VGA converter dongle*
Sitting now, I sighed: So this was how #VFD3 was going to end: A couple of European sales guys had flown out from the east coast to California, probably hoping to catch some sunshine after pitching a vmturbo to us, but now Deputy SVGA and the Mac Book’s stupid dongle were getting in their way.
Great! I thought as I sat down.
And then I was blown away for the next 2.5 hours.
VMTurbo isn’t a bolt-on forced induction airflow device for your 2u host, rather, it’s a company co-founded four years ago by some brainy former EMC scientists, both of whom were now standing before me. The Russian guy, Yuri Rabover, has a PhD in operating systems, and the CEO, Shmuel Kliger, has a PhD in something sufficiently impressive.
The product they were pitching is called Operations Manager (yes, yet another OpsMan), which is unfortunate because the generic name doesn’t help this interesting product stand out from the pack….this is operations management, true, but with an economics engine, real life reporting on cost/benefits and an opportunity cost framework that seems pretty ingenious to me.
Yeah I said economics. As in animal spirits and John Maynard Keynes, the road to serfdom & Frederic Hayek, Karl Max & Das Kaptial vs Milton Friedman, ‘Merica and childhood lemonade stands…that kind of economics.
And I’m not exaggerating here; they opened the meeting talking about economics! They told us to step back and imagine our vertical stack at every stage -from LUN to switch to hypervisor to cpu to user-facing app- as a marketplace in which resources are bought, sold, and consumed, in which there is limited supply & unpredctable demand, in which certain resources are scarce & therefore valuable while others are plentiful and therefore cheap. There’s even a consumers/producers slider; your “maker” filer produces 30,000 IOPS, but your “taker” users are consuming 25,000. Abuse & overuuse of the modern Type 1 Hypervisor akin to over-grazing the commons with your sheep, a Tragedy of the vCommons, if you will.
Someone stop me, I’m having too much fun.
You get the idea: the whole virtualization construct is a market economy.
I can’t speak for the other delegates, but I was enraptured partly because it seemed to validate my post on Pareto efficiency & Datacenter spending as right-tracked & thoughtful rather than the ravings of a crazy man and partly because it’s a framework I’ve gotten used to operating under my entire IT career.
But that’s just me nerding out and getting some feel-good confirmation bias. Is this even a useful & practical way to think of your IT resources? Is VMTurbo’s premise solid or crazy?
I’d argue it’s a pretty solid premise & a good way to frame your virtualization infrastructure. We already do it in IT: I bet you ‘budget’ IOPS, bandwidth, CPU & memory to meet herky-jerky demand, amid expectations for the availability and performance of those resources. That’s kind of our job, especially in the SMB space, where companies buy the server, storage, and network guy for the price of one systems guy, right?
So what VMTurbo’s OpsMan actually do? Some pretty cool things.
- VMTurbo’s Yuri Rabover whiteboards my pain : between the user & my spindles, wherein lies the problem?
OpsMan allows you to put a high value/mission critical designation on a user-facing application. And with that information, the economic engine takes over and with OpsMan’s visibility all the way from your user-facing VM to your old 7200 rpm spinning platters, it’s going to central-plan the animal spirits out of your stack and spit out some recommendations to you, which you can then, in the words of one of the VMTurbo guys, “Hit the recommendations button and this red thing goes to green.”**
Ahh who doesn’t like green icons indicating health and balance? Of course, achieving that isn’t very hard; just give as much resources as you can to every VM you have and you’ll get green. The nag emails will go away, and all will be well.
For awhile anyway.
Any rookie button pusher can give VMs what they want and make things green (answer: always more), but it takes wisdom and discernment to give VMs what they actually need to accomplish their task yet avoid the cardinal sin of over-provisioning which leads inevitably to a Ponzi scheme-style collapse of your entire infrastructure.
Therein lies the rub and VMTurbo says it can put some realistic $$ and statistics around that decision, not only dissuading you from over-provisioning a VM, but giving you an opportunity cost for those extra resources you’re about to assign.
Sure it’s tempting to add 10vCPU & 32GB of RAM to that critical SQL cluster, especially if it gets the accounting department off your back. But VMTurbo’s OpsMan sees the stack from top to bottom and it can caution you that adding those resources to SQL will degrade the performance of your XenApp PoS farm, for instance, or it might suggest you add some disk to another stack.
Neat stuff.
VMTurbo, essentially, says it can do your job (especially in the SMB space) better than you can, freeing you up from fire fighting & panicked ssh sessions to check the filer’s load to more important things, like DevOps or script-writing or whatever you fancy I suppose.
And when its done having its way with your stack, when the output from your vEconomy is incredibly larger than the input, when you’ve arrived at #VirtualizationGlory and there’s no more left to give, the VMTurbo guys say OpsMan can give you a report the CFO can read and understand, a report that says, “Here thar be performance, but no farther without CapEx, yarr.”
For me in Hyper-V & SMB land, where SCOM is a cruel & unpredictable, costly mistress and the consultant spend is meager, VMTurbo feels like a solid & well thought out product. For VMware, OpenStack shops? I’m unclear if VCOPS does something similar to OpsMan, but man did VMTurbo’s presentation get my VMware colleagues talking. Highly recommend you set aside an hour and watch the discussion at Tech Field Day’s youtube site.
All in all not a bad way to end #VFD3: getting challenged to think of virtualized systems as economies by some very sharp engineers from Europe, one of whom learned operating system design in Soviet Russia, where the virtualization sequence is decidedly v2p, but the thinking, understanding, and perhaps execution are first rate. I’ll know more on the execution side when I put this in my lab.
I hereby dub the VMTurbo guys Philosopher Kings of Virtualization for taking a unique and thoughtful approach.
Ping them if: You operate in environments where IT spend is limited, or you want to get the most out of your hardware
Set Outlook reminder for when: No need to wait. With solid VMware support, some flattering & nice things but also real products for Hyper-V, and KVM/Xen support, Open Stack soon, VMTurbo pleases
Send to /dev/null if: You have virtually unlimited hardware capex to spend and play with. If so, congrats.
Other Links/Reviews/Thoughts from #VFD3 Delegates:
* Sidenote: Still floored that one can’t escape dongle technology dysfunction even in Silicon Valley
**You can even automate VMTurbo’s recommendations, which the company says a great many of its customers do, a remark that caused a bit of discomfort among the #VFD3 crew.
Wilson.tech 
4 thoughts on “#VFD3 Day 3 : VMTurbo wants to vStimulate your vEconomy”