A few months into the gluster acquisition by Red Hat …

… just received a note indicating that our Gluster Reseller contract was voided, and that we would be seeing a new partner portal for Red Hat Storage coming soon where we could apply again for reseller status.

Hmmm ….

Reading over the information I saw on the Red Hat storage platform, it looks like they are going full on appliance route, which diminishes the value we can potentially add to the platform, and removes much of the differentiation we can do at the stack level (better kernels, up to date drivers, tweaked/tuned drivers/OS, …). Actually, their focus looks like it was laid out in pretty good detail … they are looking to make these effectively “sealed” type appliances.

I think the rationale for this is competition from Oracle, and to some degree it makes sense. But it also changes what we can and cannot do with Gluster. I have a sense that the 3.2.5 release may be one of the last public code drops … this is a hunch, I have no real information one way or another.

I suspect that work on *BSD and Solaris will be wound down (at least in the context of integrating patches for this). I don’t think we will see gluster as a separate product or tarball or … going forward.

I hope I am wrong, but to a degree, this makes sense as a strategy. Acquire a company, and monetize the product, by removing many of the other channels that it could be used with. Unfortunately for us, we got caught up in the newly non-sanctioned use cases. Its being packaged more for a Dell, or another large white box provider to throw storage together.

So 3.2.5 might be the last really publicly available system. Yeah, it is open source, and I am sure you can get it. But its going to be tightly tied to the Red Hat platform. Which isn’t a bad thing, but as a company that works hard at differentiating by replacing and tuning underperforming portions of the stack, mebbe this isn’t as good for us.

Gonna have to think about this somewhat. Some customers have been nervous about this going forward, and I’ve done all I can to get them to wait and see before acting. These changes I don’t see making them less nervous … actually more.

Again, hoping I am wrong. But I have a pretty good history of not being wrong.

Viewed 63922 times by 7198 viewers


7 thoughts on “A few months into the gluster acquisition by Red Hat …

  1. No, 3.2.5 will not be the last public release. AFAIK Red Hat doesn’t close up *any* of the code it acquires, and continues to underwrite the gluster.org upstream community. In fact, plenty of post-3.2.5 code is already in the public GitHub and Gerrit repositories.

    I’ll just say one more thing, as both a Red Hat associate and a gluster.org community leader: if there ever *is* a move to close up the code, I will fork it myself. I just don’t expect that to happen.

  2. This post is wrong on so many levels. What you’re witnessing is a distinction being made between what is available via Gluster.org and what is available via Red Hat Storage. The appliances to which you refer are available from Red Hat. From GlusterFS, you’ll be able to do whatever you want, within the constraints of the GPL v3.

    We have no desire to choke off access to Gluster. In fact, we’re doing quite the opposite – we’re creating a global user and developer community around GlusterFS, hosted on gluster.org. This will all be explained and made clear in our webinar on the subject on January 26 – http://www.redhat.com/webinars/?zPage=2012-01-26-The-future-of-gluster-dot-org-a-roadmap

    You can keep track of all new developments at gluster.org

  3. @Jeff

    Thanks for the note. I am glad to hear this. I would understand a strategy to close it up to prevent Oracle from potentially gaining more value from the acquisition than Red Hat. It wouldn’t actually be a bad strategy either. Well, for Red Hat. Not so much for us.

    This said, we’ve got some IP bits we’ve been developing that would have (as one particular interface instance) a translator layer. I’ve been reading your docs from a few months ago (wow … close to a year ago now …) about how to develop a translator. I didn’t want to lose this option, and I didn’t want to fork.

    I am glad to hear it will remain open. Looking at what Oracle did with the kernel patch folks … yeah … caused me to worry. I know, Red Hat != Oracle.

    @John Mark

    I am sorry ??? Whats wrong with expressing a concerned opinion? I accept your statement as to seeing the Red Hat Storage vs Gluster.org distinction, but this isn’t being communicated well (at least to us). Gluster.org has been around quite a while, and I’ve been a strong supporter of Gluster since the 2.0 days, and playing with it since before 1.3 days.

  4. Joe, are you planning to publish that translator code some time soon? Since the acquisition we’re back down to one company with employees writing translators, and I’m desperately trying to increase that number. For example, I’m at FUDcon right now doing just that. If you or someone else at $dayjob wanted to participate in that effort, that would be awesome.

  5. @Jeff

    The translator is a layer to talk to our IP bits. We will likely have a lower end implementation of our IP up in “short order”, and then I’ve got to get some of the proof of correctness done (think massive sets of unit and system tests). The interface translator was going to steal heavily from one in use now, and once we are done with it, we’ll push it back. Might even do it as we develop it, so we can get comments/critiques.

    I can talk more after we get some paperwork filed.

  6. Joe,

    I was caught by surprise, as I couldn’t see how you reached those conclusions. The letter in question must have been rather poorly worded, as it should have included at the very least the basic plan for the GlusterFS project.

    In any case, I’m happy to answer any questions you may have about GlusterFS or refer you to the proper channels for Red Hat Storage.


  7. @Jeff

    Oddly I think the translator scaffold we are most likely to abuse^H^H^H^H^Hwork with is the stripe translator. Might be fun for me to fix this anyway so its faster. We have a number of use cases for the system where faster would be better. I did see Amar commit something to Fuse that should make for O_DIRECT files to work better, which would help some of our other cases.


    I don’t have the letter in front of me, but it wasn’t “hey thanks for supporting us, new programs are coming, we are terminating this one and will start another one soon, so watch this space.” It read more along the lines of “stop selling GlusterFS IMMEDIATELY, and when(if) we create a new parter program around this, we may notify you if we want you to apply.”

    Put another way, it read a great deal like “thanks, now don’t let the door hit you in the ass on the way out.” This is why I noted what I did in our offline conversations. I am concerned, that there is a reasonable probability of the thing I am concerned with occurring.

Comments are closed.