Again this year, I had a lot of fun roaming around VMworld 2016 US with my iRig Mic, which does a solid job at keeping out the ambient noise that is typical at such conferences.
You'll see me visit unprepared folks, who I asked for permission to record moments before the camera was rolling.
I spent much of Monday and Tuesday learning stuff, and most of Wednesday enjoying talking to hundreds of people at my live SuperServer demo/Q&A session, so I had very limited time to get these informal interviews done. New York VMUG co-leader Ariel Sanchez and Matt Crape kindly watched my SuperServers for a bit while I went off and did these recordings, what a nice thing of them to offer to do. I greatly appreciate it.
I wasn't able to arrange time with QNAP when visiting their booth briefly, and I never even made it to Synology's booth this year. I also didn't see any storage stuff at Intel, but admittedly was rushing, as the entire exhibitor area was closing up soon. I also failed to get footage from my NVIDIA booth visit, but I now have some contacts that will come in handy in the future.
...you can accelerate your VMs. You can accelerate per VM level, so you can decide you want all your VMs or a subset of your VMs...takes about 15 minutes to install the product, and if you're not seeing the results you want, it's very easy to take the product out too.
...We're really focused on caching in RAM. We support SSDs, but it's a tiered cache where we put the hottest data in RAM, and we evict stuff we can't fit into RAM into the SSD. The reason we're so good at RAM caching is we do inline deduplication of our cache space...what that means is...you might give it 10 gigs of RAM, but we're going to make it look like a lot more than that, we can make it look like 40 or 80 gigs of RAM.
...If you don't have server-side SSDs, there's no hardware, so we can send you a link to the software, you can install it in your home lab or in production at work, and get you up and running without any additional hardware.
...We recently announced our 7100 platform, it's a drive that's available in both a U.2 and a M.2 form factor. It's a 22110, it's got full power loss protection, and it's on about 50 to 60% way through getting on to the VMware HCL at this point in time.
...It's meant to be on the vSAN list for the caching tier layer, and we also have an interation that can be in the capacity tier if you choose to use it that way.
...This first iteration yes, our next generation product will have 22110 and 2280, it's also about capacity, getting up to 2TB takes a lot of room.
We do plan to certify all those models and put it on the VMware HCL as time permits. We will schedule them to put it on to the queue, as soon as we are back from VMworld.
This next clip isn't quite an interview, but it's what I'd ask Anton about anyway, had I had a chance to chat with him. Thought you might enjoy this clip, especially given I just recently wrote about ReFS here.
This clip is from VMworld 2016 US:
Veeam Availability Suite 9.5 Deep Dive [SDDC9461-SPO]
- Anton Gostev, VP, Product Management, Veeam Software
- Doug Hazelman, VP Product Strategy, Veeam Software
by Gostev » Tue Sep 06, 2016 1:02 am
Indeed, support for "deduplicating" encrypted backups is really the killer feature of our ReFS integration, and this is something neither external deduplicating storage nor Windows Server dedupe are able to do (and will never be able to). This is really a game changer, especially for Cloud Connect service providers.
- Between Windows Server 2016 TPv3 and TPv4 we moved from ReFS version 2.0 to 3.0
Jan 13 2016 by Didier Van Hoye at Working Hard In IT