This was a ridiculous amount of fun… and a first – Chad’s World was live at EMC World 2011. This was a ridiculously stupid attempt – Wade and I are not good actors, and normally need many takes to do anything right :-) Our hope was that while it could be an epic #FAIL, at least it would be a fun & irreverent way to wrap up EMC World, and open up for the Fray.
For what it’s worth – as much as this is a gas, I want people to know that while I’m an exec at EMC, more importantly I’m a dude who puts his pants on one leg at a time – just a normal guy who happens to be a passionate nerd. Our marketing geniuses (and they are geniuses) thought this would be a funny way to entertain and educate on stuff EMC is doing, and leverage my Canadian-ness and the fact that yup, I do have a large home lab in my basement :-) I’m also completely willing to make an ass out of myself, which seems to be a pre-requisite for something like this!
A big thank you to the customers – first for being EMC, VMware, Cisco customers, and also for being such good sports to join us and share their killer stories!
- Jonathan Visser @ Morris Hosital
- Chris Kudlick @ Morris James, LLP
- Mike Hurst & Rael Mussell @ Credit Acceptance Corp
- Tom Pearson @ Loves Country Stores
- Kyle Berger @ Alvarado Independent School District
- Haim Inger @ CLAL Insurance
- Brendan McGowan @ Safe Systems
Their stories of how they are using our technologies together are just amazing. Frankly – I think they make the show worth watching.
Also a big thank you to VMware, Cisco, Intel, Wyse and Molson’s for all supporting the event!
Click on the picture below to get to the streaming video (all Chad’s World episodes are at www.emc.com/chadsworld), and read on past the break if you want the “insider scoop” of what was going on behind the scenes.
Also – here’s a bunch of pictures of the event (including some behind the scenes)
For people wanting the “behind the scenes” (ergo what was REALLY going on as we’re on stage), read on…
Here’s a behind the scenes list of “things to know” as you’re watching (the background factoids will hopefully make it more fun :-)
- During the opening – you can’t see all the photos, but we had fun with that. YES that’s really me sitting in Joe Tucci’s office. YES, that’s really Pam Buote (Joe’s Exec Admin) kicking Wade and I out (she’s very nice). YES, that’s really us trying to get on the private jet.
- During the opening – those are the REAL flying Elvii. I wanted to jump out of the plane (I could do it tandem), but on the day of filming (which was saturday) it was so windy, there was no jumping. I’m now jonesing to have another go…
- That Cadillac burned about a half tank between Boulder City and Las Vegas :-)
- There is not much that is as much fun as rolling down the Vegas strip in an old Cadillac with 4 other people, all dressed as Elvis. I would HIGHLY recommend it.
- Literally, we finished the rehearsal SECONDS before people started to come into the room. And it was a DISASTER. I had Jeremy Burton (EMC CMO) come up to me and say “ok, this is going to be an epic disaster, so… just roll with it”
- None of the demos worked in rehearsal – so just remember while watching, Wade and I – we’re thinking to ourselves at each of those points “is this going to work?”. In the end, EVERYTHING worked – which I have to say is a miracle (and there’s a lot of vSpecialists to thank for that) :-)
- In Chapter 2, we demo VPLEX Geo with a Google-Maps mashup doing vMotion, which is really cool. I’m going to do a longer post on the topic of the latest on stretched clusters and vmotion over distance (and Scott Lowe talked about it also here) – but am waiting for the other shoe to drop (you’ll know it when it happens). Short version: today, stretched clusters are supported in sync distances only. VMotion support boundaries are gated by host-to-host and vCenter-to-host latencies and networking layer 2 adjacencies.
- Also in Chapter 2, we demoed a very funky solution for HPCC workloads driven by a customer (Purdue). NOTE: this is 100% real, but 100% NOT AVAILABLE, and not on any committed roadmap. That customized vmkernel (developed by EMC and VMware together) has a modified vSphere snapshot mechanism that enables complete synchronicity of vSphere memory and VMDK snapshots across a large number of virtual machines (a coordinated, programmatic pause/snap/resume), and also dramatic improvements of the time to take snapshots and also to resume. I think this would be something useful in many use cases, so am lobbying to have it in future vSphere releases. Also, there REALLY is a vVPLEX – a virtual machine that we can instantiate in a remote datacenter and then present storage as if it were local. This is something that will likely see the light of day, but will take some time. The innovations that are public are just the tip of the iceberg.
- In Chapter 3, we demoed an Isilon cluster being constructed live, and then firing up boatloads of VMs. In the background, Nick Weaver and Chris Horn were furiously firing stuff up on the VMware side to create VMs, but Wade and I borked the timing – we were going WAY to fast :-) After about 10 minutes, the 10 Isilon nodes were added, giving us more than 130TB of storage, and we were close to the 1000 VM’s spawned off mark (using Nick’s VM-spawning tools he made for his crazy “VMs as DNA evolving” experiment). BUT – I think the funnier part is this: Fred Nix (the big guy) ASKED to be sprayed with the CO2 fire extinguisher! I had him do it to me in return after the show and he’s not kidding – it’s REALLY cold. But – what adds that little “behind the scenes” bit on this is that Fred’s finger got mashed when inserting the Isilon nodes – and there was blood dripping down the front of the cabinets :-) So, as I’m spraying him – just know that he’s missing the tip of a finger – and yet he just rolls with it – because that’s the kind of guy Fred (@VCEMonk) is. Fred – you ROCK!
- What am I referring to when I talk about different NFS behavior in “future vSphere releases”? It’s not NFS v4.x or pNFS (though I’m not saying those won’t exist in the future), but rather than there will be new ways to leverage DNS round-robin to distribute single-TCP-session connections across IPs in future vSphere releases that will help. More on this (obviously) in the future.
- Also in Chapter 3, you can’t see it on camera but during the “stunt crew” period (done to try to “gag up” the folks coming on stage to build the cluster), one of the vSpecailists squirts water all over my face… that’s the stuff you can see on my shirt for the rest of the episode.
- In Chapter 4 – the workload was running on the VNX when Wade is disassembling it. The point is a profound one, which is that only VNX has a SSD-based extension of cache that is persistent on failure. The workload was a SQL Server instance running swingbench. The “speedometer” UI is something Nick whipped up because otherwise it was hard to read on the screen. Once again, Wade and I had our timing wrong (remember – no real rehersal :-), but amazing that it worked. There was one pause between Wade and I because the sequence was supposed to start with Wade inserting SSDs, but we never put the SSDs on stage :-)
- In Chapter 5 – YES, I’ve had a ton of questions about this – the PX6 is actually booting all those 100 clients, and YES, this is something that really works. As I expected, there is a need for “small” VDI deployments in the >100 client range. I wouldn’t recommend it for much more than that. Also a consideration – the PX6 is supported like an SMB product (you can get premium support) – this isn’t a technical thing, but don’t expect a support model like the 4hr MTTR you would see on a VNX. The UCS C-series is running ESX, vCenter and a future version of View.
- In chapter 5 a little sidebar – I really resent that we are, in effect, a sexist industry. There is a completely imbalanced set of males and females in the tech industry and that sadly is reflected at conferences, and even in my team. As the proud papa of two girls, I want them to be whatever they want to be. I’ve been driving hard for diversity on my team, and so cringed a little when Heather volunteered to be the one to boot all the systems. The last thing I want is to reinforce that she’s a “Vanna White”. So – let it be noted (as I tried to note), Heather Boegemann is a vSpecialist ROCKSTAR. She knows EMC and VMware inside and out – and can out-geek anyone. Yeah!
- A bit of a flub in Chapter 5 – the reason that Heather ran back on stage with the Cius is the Cius we on stage completely freaked out RIGHT before we went on stage, so I expected it to be a brick throughout that bit (note that it was a rock for weeks in advance – just one of those “demo demon” things). Literally in the minutes running up to that point in the live show, Dave Robertson and Rick Scherer ran over to Cisco’s booth, grabbed another Cius, and worked with Cisco to set it all up. So, a little impromptu miracle – THANK YOU to Dave, Rick, Heather and Cisco!
Thanks again to all who helped, and a big thank you to VMware, Cisco, Intel, Wyse and Molson – and most of all – a huge shout out to all those VMware/EMC customers who make the world go round! ….So, should we do another live Chad’s World?
I want a Chad Bobblehead doll!
Posted by: Elliot Fliesler | June 01, 2011 at 02:53 PM