How Soon Is Now?

This is one of those posts that is really just a loose collection of thoughts that have been bouncing around my head recently regarding software lifecycles. I’m not a software developer, merely a consumer. It’s not supported by any research and should be treated as nothing more than opinion. It should also not be used to justify certain types of behaviour. If this kind of hippy-dippy stuff isn’t for you, I’ll not be offended if you ignore this article. I also apologise for the lack of pictures in this one.

 

Picture This

I’ve been doing a lot of work recently with various enterprises using unsupported versions of software. In this particular case, the software is Windows 2003. The fact that Windows 2003 reached its end of extended support this time two years ago is neither here nor there. At least, for the purposes of this article it doesn’t matter. The problem for me isn’t the lack of support of this operating system as I don’t spend a lot of time directly involved in OS support nowadays. Rather, the problem is that vendors tell me that any software running on that platform is not supported either, as the OS may be the cause of issues I encounter and Microsoft won’t help them anymore. This is a perfectly valid position from a support point of view, as software companies are invariably very careful about ensuring the platform they run on is supported by the platform vendor. Commercially, it’s not a great look in the marketplace to be selling old stuff – it’s just not as sexy.

 

So What’s Your Point?

There’re a few things at play here that I want to explore a bit. I’ll reiterate that these are likely poorly expressed opinions at best, so please bear with me.

Stop Telling Me About Your App Store

The technology software vendors love to talk about their “app store capabilities”, particularly when it comes to cool new things like cloud. We’re all relatively happy to accept a rapid development and update cycle for our phones, and we want to pick out the services we need from a web page and deploy them quickly. Why can’t we do that with enterprise software? Well, you can up to a point. But there’s a metric shit tonne of work that needs to be done organisationally before most shops are really ready to leverage that capability. There, I’ve said it. I don’t think you can right the words Agile and DevOps in your proposals and magically be at that point. I’m not saying that there’s no value in these movements – I think they’re definitely valuable – but I still maintain there’s work to be done. As an aside, go and read The Phoenix Project. I don’t care if you’re in ops or not, just read it. It’s very cheap on Kindle. No I don’t get a cut.

What If It Breaks?

Enterprises don’t like to update their software platforms because they are inordinately afraid that something will break. To the average neckbeard, this is no big deal. We’ll reach for the backups (hehe), roll back the change and try to work out what happened so that it doesn’t happen again. But in enterprises, they aren’t the ones making the decisions. Their neck isn’t on the block if something goes wrong. It’s some middle manager you’ve never heard of in charge of a particular division within the company whose sole purpose is to support whatever business function this particular bit of software services. And the last guy who really understood anything about this critical software left the company seven years ago. And it was a bit of off the shelf software that was heavily customised and lightly documented. And so people have been clinging to this working version of the software on a particularly crusty platform for a very long time. And they are so very scared that your upgraded platform, besides causing them a lot of testing work, will break things in the environment that no one understands (and fewer still will be able to fix). I’ve worked in these environments a lot during the past 15 – 20 years. At times I’ve considered finding new employment rather than be the bunny pushing the buttons on the upgrade of Widget X to Widget X v2 for fear that something spectacularly bad happens. You think I’m exaggerating? There’s a whole consulting industry built around this crap.

But You Said This Was The Best Ever Version

When I lived in customer land, I had any number of vendors tell me about their latest versions of the their products, explaining, somewhat breathlessly, just how good this particular version was. And how much better than the old version it was. And how I should upgrade before my current support runs out. I have this conversation frequently with customers:

Me: “Version 7 of Super Software is coming to end of support life, you’ll need to upgrade to Version 7.8”

Customer: “But what’s changed that Version 7 won’t do what I need it to do anymore?”

Me: “Nothing. But we won’t support it because the platform is no longer supported”

Customer “…”

I know there are reasons, like end of support for operating systems, that mean that it just doesn’t make sense, fiscally speaking, to keep supporting old version of products. I also understand that customers are usually given plenty of notice that their favourite version of something is coming up to end of support. I still feel that we’re a little too focused on fast development of software (and improvements, of course), without always considering just how clunky some organisations are (and how difficult it can be to get the right resources in place to upgrade line of business applications). Granted, there are plenty of places who deal just fine with rapid release cycles, but large enterprises do not. And what is it that one day suddenly stops a bit of software from working? If my version goes end of support tomorrow, what changes from a technical perspective? Nothing, right? Yes and no. Nothing has changed with the version you’re running, but chances are you’re two major revisions behind the current one. I bet there’ve been a bunch of new features (some of which might be useful to you) introduced since that version came out. You can also guarantee that you’ll be in something of a bad way when new security flaws are discovered either in your old software or the old platform, because the vendors won’t be rushing to help you. It will be “best effort” if you’re lucky.

 

But You Don’t Understand My Business

It may be startling for some in the tech community to discover, but 99% of companies in the world are not focused (primarily) on matters of an IT nature. It doesn’t matter that major vendors get up on stage at their conferences and talk about how every company is an IT company. The simple fact is that most companies still treat IT as an expense, not an enabler. When vendors come along and decide that the software they told you was awesome two years ago is now terrible and you should really burn it with fire, you’re generally not going to be impressed. Because it’s possible that you’re going to have to pay to upgrade that software. And it’s very likely it’s going to cost you in terms of effort to get the software upgraded. But if your business is focused on putting beer in bottles and the current version of software is doing that for you, why should you change? On the flip side of this, software companies have demonstrated over time that it’s very hard to generate consistent revenue from net new customers. You need to keep the current ones upgrading (and paying) regularly as well. It has also been explained to me (as both a customer and integrator) that software companies are not charities. So there you go.

 

What’s The Answer Then, Smarty?

No idea. Enterprise IT is hard. It always has been. It may not be in the future. But it is right now. And software companies are still doing what software companies have always done, for good and bad reasons. I really just wanted to put some thoughts down on paper that reflected my feeling that enterprise IT is hard. And we shouldn’t always criticise people just because they’re not running the latest iteration of whatever we’re selling them.

Okay, fine. The answer is to try and keep within support where you can. And minimise your exposure in the places where you can’t. Is that what you wanted to hear? I thought so.

Enterprise IT is hard.

Storage Field Day 7 – Day 3 – Maxta

Disclaimer: I recently attended Storage Field Day 7.  My flights, accommodation and other expenses were paid for by Tech Field Day. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

For each of the presentations I attended at SFD7, there are a few things I want to include in the post. Firstly, you can see video footage of the Maxta presentation here. You can also download my raw notes from the presentation here. Finally, here’s a link to the Maxta website that covers some of what they presented.

 

Company Overview

Yoram Novick, CEO of Maxta, took us through a little of the company’s history and an overview of the products they offer.

Founded 2009, Maxta “maximises the promise of hyper-convergence” through:

  • Choice;
  • Simplicity;
  • Scalability; and
  • Cost.

They currently offer a buzzword-compliant storage platform via their MxSP product, while producing hyper-converged appliances via the MaxDeploy platform. They’re funded by Andreessen Horowitz, Intel Capital, and Tenaya Capital amongst others and are seeking to “[a]lign the storage construct with the abstraction layer”. They do this through:

  • Dramatically simplified management;
  • “World class” VM-level data services;
  • Eliminating storage arrays and storage networking; and
  • Leveraging flash / disk and capacity optimization.

 

Solutions

MaxDeploy is Maxta’s Hyper-Converged Appliance, running on a combination of preconfigured servers and Maxta software. Maxta suggest you can go from zero to running VMs in 15 minutes. They offer peace of mind through:

  • Interoperability;
  • Ease of ordering and deployment; and
  • Predictability of performance.

MxSP is Maxta’s Software-Defined Storage product. Not surprisingly, it is software only, and offered via a perpetual license or via subscription. Like a number of SDS products, the benefits are as follows:

  • Flexibility
    • DIY – your choice in hardware
    • Works with existing infrastructure – no forklift upgrades
  • Full-featured
    • Enterprise class data services
    • Support latest and greatest technologies
  • Customised configuration for users
    • Major server vendors supported
    • Proposed configuration validated
    • Fulfilled by partners

 

Architecture

MaxtaMaxDeployArchitecture

The Maxta Architecture is built around the following key features:

Data Services

  • Data integrity
  • Data protection / snapshots / clones
  • High availability
  • Capacity optimisation (thin / deduplication / compression)
  • Linear scalability

Simplicity

  • VM-centric
  • Tight integration with orchestration software / tools
  • Policy based management
  • Multi-hypervisor support (VMware, KVM, OpenStack integration)

What’s the value proposition?

  • Maximise choice – any server, hypervisor, storage, workload
  • Maximise IT simplicity – manage VMs, not storage
  • Maximise Cost Savings – standard components and capacity optimisation
  • Provide high levels of data resiliency, availability and protection

I get the impression that Maxta thought a bit about data layout, with the following points being critical to the story:

  • Cluster-wide capacity balancing
  • Favours placement of new data on new / under-utilised disks / nodes
  • Periodic rebalancing across disks / nodes
  • Proactive data relocation

 

Closing Thoughts and Further Reading

I like Maxta’s story. I like the two-pronged  approach they’ve taken with their product set, and appreciate the level of thought they’ve put into their architecture. I have no idea how much this stuff costs, so can’t say whether it represents good value or no, but on the basis of the presentation I saw I certainly think they’re worth looking at if you’re looking to get into either mega-converged appliances or buzzword-storage platforms. You should also check out Keith’s preview blog post on Maxta here, while Cormac did a great write-up late last year that is well worth checking out.

 

OT: Sometimes a Mac problem needs a Windows solution

I have a Logitech 1000i all-in-one remote control. Good for me you say. Good for me I say too. But recently I wanted to update the remote via the Harmony Remote Software. I’ve recently updated my iMac to OS X 10.6.3, and made the silly error of updating to the latest version of the Harmony software – version 7.7.0. The software works fine, but it just doesn’t update the remote. There’s even a KB article about it. And I tried all of the steps, but nothing would get it working. And do you know how I resolved the issue? I uninstalled and reinstalled the same version of the software. That’s right, I had to do the sort of thing that I had been doing on my PC for years. Ridiculous. And I don’t know who’s to blame, but I don’t like it.