back to article Tintri: We have ZERO interest in adding compute to storage

Under new CEO Ken Klein, hybrid array startup Tintri is sticking to its virtualised server-centric networked storage knitting and embracing the cloud as a third tier cold storage vault. Currently a VMware-focused storage supplier using VMware storage abstractions, such as virtual machines (VMs) and virtual disks instead of …


This topic is closed for new posts.
  1. Anonymous Coward
    Anonymous Coward


    Yeah. The guys make it sound so glossy (the world of marketing, right) but at the end of the day it's just serving NFS stores to vCenter, and pulling vCenter stats into their GUI for graphical analysis. Each Tintri box is an NFS store. Have 10 Tintri boxes, that's 10 individual stores. Nothing too clever there (although they do have a piece of software where you can see all 10 stores in one GUI).

    Also I believe Tegile announced (but probably not released, as is the way with Tegile) the ability to do per-VM analysis in their box in the last 6 months.

    As soon as VVOLs is released from VMware, there will be no value differentiation of VM-centric or VM-management between these guys and every other storage vendor in the market, regardless of the presentation layer being iSCSI, FC or NFS IMO.

    I guess this is why they're quickly trying to position themselves as a cloud player with KVM, and with alternative private cloud hypervisors like Hyper-V... this would require a bigger re-engineer of the entire platform though as that would require SMB 3.0 rather than NFS.

    1. @storarch

      Re: NFS...

      Tintri Employee here -

      Well, if it was so easy to do it on NFS then why are the other vendors that are into General purpose storage still waiting for VMware to bring out VVols? How about other hypervisors? Functionality is just one small part of the VM aware storage for which VVol will act as an enabler and won't just change the underlying storage architecture. There are a lot of other aspects of a VM aware storage. Traditional NFS implementations consider everything as files. There is no VM awareness there. Everyone still wants to do general purpose storage (fileshares, homedirectories, physical workloads, content), so there is no way they would optimize their storage for VMs. Even if they do and let go their traditional customers, it'll need a complete rewrite (bringing SMB to the storage is much easier than that). And we all know what it takes to rewrite a traditional storage system. If you want to get some more ideas on why VVol is just an enabler read the blog post here

      1. Anonymous Coward
        Anonymous Coward

        Re: NFS...

        Your blog -- TL;dr (except the very end --

    2. Anonymous Coward
      Anonymous Coward

      Re: NFS...

      As a happy consumer of Tintri, I can say that you are dead wrong. I have used bog-standard NFS datastores, delivered by NetApp, and VMFS datastores, delivered by EMC. What Tintri brings to the table are performance and simplicity. It's dead simple to stand up and provision a Tintri (half an hour from unboxing to serving data--try doing that with a NetApp!), and Tintri's approach to hybrid storage has given us high performance at an order of magnitude less per IOPS. If Tintri storage has a weakness, it's probably in the area of sustained sequential throughput, which will cause the SATA drives to start working hard, which will not give the best performance. On the other hand, unlike most mainstream vendors, heavy load to the disks doesn't cause the performance for the whole device to keel over, in my experience. Unlike with both NetApp and EMC arrays, I have not been able to create a load profile which causes all the VMs on a Tintri to stall, although I'm sure it can be done.

      VVOLs may address the issue. I have no idea, although I do see that they've been in the works for a couple of years and still have not emerged. From what I can tell, though, the VVOL concept relies on tight integration between the hypervisor layer and the underlying storage, using the hypervisor to perform storage optimization. I can see the appeal, and it's quite possible that VMware will, in fact, steal Tintri's lunch with this move, but time will tell. The challenge to VMware will be successfully integrating a broad portfolio of storage products in a fashion that is stable and maximally performant, whereas all Tintri has to do is work well with a few hypervisors, a much less daunting technical task. That said, I'm not sure that Tintri will gain a significant foothold in the cloud; it depends whether they can compete on price with the bulk storage that cloud providers use. Your typical cloud provider probably doesn't have much use for a vendor's "secret sauce;" they'd much rather make their own.

    3. Anonymous Coward
      Anonymous Coward

      Re: NFS...

      > Also I believe Tegile announced (but probably not released, as is the way with Tegile) the ability to do per-VM analysis in their box in the last 6 months.

      It's the Tegile troll. He has come (anonymously of course) to collect his Troll toll. Just disclose if you are with the company or their PR agency.

  2. Cthugha

    VVOL's to the rescue

    Roadmap to fix all, yeah for roadmaps......

  3. Nate Amsden

    way late to the party

    Other vendors have supported open stack, KVM etc for years, Tintri is the late comer here not the other folks. I still firmly believe once VVOLs come out tintri will lose their only edge and they'll end up being someone like Pillar or XIO.

    I have a friend or two at Tintri and have had a few long discussions with him on the tech. Their platform has it's use cases but it's pretty limited. Application aware they are not, they are VMware hypervisor aware. Wake me when they integrate with actual applications like Oracle, MSSQL, MySQL(haven't seen anyone integrate with that myself), Exchange, SAP etc etc(looking at their website now I see no indication they are very VM-centric). Wake me when they allow you to take a snapshot of a data set and send that snapshot to another VM(AFAIK you can't do this with VMFS hence my own heavy use of raw device maps for databases - see

    They have interesting tech but nothing that interests me personally. I want something much more flexible and agnostic. Last I spoke to my friend over there he said Tintri still did not allow NFS exports directly to guest operating systems, they were VMware-only. So now they are adding KVM ..make the storage platform flexible enough to do more things. At the time(about a year ago) he said there wasn't much interest in being more flexible, more agnostic. I have to assume that is because they didn't have enough resources to do it so they stuck to what they did best (probably a good idea).

    But adding compute to storage has always been a stupid idea, whoever came up with the concept needs to be taken out back and shot. It's one of those things where when I hear it I really don't have a response, my brain just can't think of how someone could come up with such a incredibly stupid concept to begin with. Now if the system is built from the ground up ala Simplivity and that Nuatix people I think that is different, though I still think both of their approaches are too limited and feel that they will at some point offer a storage-only version of their platform for better scalability(& margins - I've said this before on el reg). The combined platform will be fine for real small SMBs, there's no point in combining such a system for larger scale your too limited with fixed units for scaling. Sometimes you need to scale compute, other times storage, sometimes both, forcing the customer to do both every time is not an efficient way of operating.

    I'll be happy with 3PAR for a while yet myself(mission critical storage anyway). They are killing it in the mid range these days and their stuff is only getting better. The core technology folks from 3PAR are still very much leading the march and are heavily shielded by the head of HP storage (ex-3PAR CEO) to do what they do best.

This topic is closed for new posts.