Some thoughts on NetApp’s acquisition of Solidfire

Yesterday, NetApp announced that they have entered into a definitive agreement to acquire Solidfire for $875M in an all cash transition. Having spent more than 7 years at NetApp, I thought, I would provide my perspective on the deal .

As we all know, NetApp had a 3-way strategy around Flash. First, All-Flash FAS for customers looking to get the benefits of data-management feature rich ONTAP but with better performance and at a lower latency. Second, E-Series for customers looking to use applications side features with a platform that delivered raw performance and third FlashRay for customers looking for something designed from the grounds up for flash that can utilize the denser, cheaper flash media to deliver lower cost alternative with inline space efficiency and data management features.

The Solidfire acquisition is the replacement for the FlashRay portion of the strategy. The FlashRay team took forever to get a product out of the door and then surprisingly couldn’t even deliver on HA. The failure to deliver on FlashRay is definitely alarming as NetApp had some quality engineers working on it. Solidfire gives NetApp faster time (?) to market (relatively speaking). Here is why I think Solidfire made the most sense for NetApp –

  • Solidfire gives NetApp arguably a highly scalable block based product (at least on paper). Solidfire’s Fiber Channel approach is a little funky but let’s ignore it for now.
  • Solidfire is one of the vendors out there that has native integration with cloud which plays well with NetApp’s Data Fabric vision.
  • Solidfire is only the second flash product out there designed from the grounds-up that can do QoS. I am not a fan as you can read here but they are better than the pack. (You know which is the other one – Tintri hybrid and all-flash VMstores with a more granular per-VM QoS of course)
  • Altavault gives NetApp a unified strategy to backup all NetApp products. So the All-Flash no longer has to work with SnapVault or ONTAP functionalities. Although the field teams would like to see tighter integration with SnapManager etc. Since most of the modern products make good use of APIs, it should not be difficult. (One of the key reasons why NetApp wanted to develop an all-flash product internally was that they wanted it to work with ONTAP – You are not surprised. Are you?)
  • Solidfire has a better story than some of the other traditional all-flash vendors out there around Service Providers which is a big focus within NetApp.
  • Solidfire’s openness around using Element OS with any HW and not just Dell and Cisco (that they can use today). I want to add here that from what I have gathered, Solidfire has more control over what type of HW one can use and its not as open as some of the other solutions out there.
  • And yes, Solidfire would have been much cheaper than other more established alternatives out there making the deal sweeter.

I would not go into where Solidfire as a product misses the mark. You can find those details around the internet. Look here and here.

Keeping technology aside, one of the big challenges for NetApp would be execution at the field level. The NetApp field sales team always leads with ONTAP and optimization of ONTAP for all-flash would make it difficult for the Solidfire product to gain mindshare unless there is a specific strategy put in place by leadership to change this behavior. Solidfire would be going from having sales team that woke up everyday to sell and create opportunity for the product to a team that historically hasn’t sold anything other than ONTAP. Hopefully, NetApp can get around this and execute on the field. At least that’s what Solidfire employees would be hoping for.

What’s next for NetApp? I can’t remember but I think someone on twitter or a blog or podcast mentioned that NetApp may go private in the coming year(s). Although it sounds crazy but I think its the only way for companies like NetApp/EMC to restructure and remove the pressure of delivering on the top line growth especially with falling storage costs, improvement in compute hardware, move towards more software centric sales, utility based pricing model and cloud.

From a Tintri standpoint, the acquisition doesn’t change anything. We believe that flash is just a medium and products like Solidfire, Pure Storage, XtremeIO or any product that uses LUNs and Volumes as the abstraction layer have failed to grab an opportunity to bring a change of approach for handling modern workloads in the datacenter. LUNs and Volumes were designed specifically for physical workloads and we have made them to work with virtual workloads through overprovisioning and constant baby-sitting. Flash just throws a lot of performance at the problem and contributes to overprovisioning. Whether customers deploy a Solidfire or a Pure Storage or a XtremeIO, there will be no change. It would just delay the inevitable. So pick your widget based on the incumbent in your datacenter or based on price.

If you want to fix the problem, remove the pain of constantly managing & reshuffling storage resources and make storage invisible then talk to Tintri.

Contact us and we will prove that we will drive down CAPEX (up to 5x), OPEX (up to 52x) and save you time with the VM-aware storage.

Screen Shot 2015-12-22 at 11.41.09 AM

While you are at it don’t forget to check out our Simplest Storage Guarantee here .

Screen Shot 2015-12-22 at 11.41.22 AM

Cheers..

@storarch

 

 

What’s New in All-Flash?

Today, Tintri announced the Tintri VMstore T5000 All-Flash series—the world’s first all-flash storage system that lets you work at the VM level—leading a launch that includes Tintri OS 4.0, Tintri Global Center 2.1 and VMstack, Tintri’s partner-led converged stack. Since its inception in 2008, Tintri has delivered differentiated and innovative features and products for next-generation virtualized datacenters. And we’re continuing the trend with the game-changing All-Flash VM-Aware Storage (VAS).

Other all-flash vendors claim all-flash can be a solution for all workloads—a case of “if all you have is a hammer then everything looks like a nail.” Or, they’ll argue that all-flash can augment hybrid deployments, with the ability to pin or move entire LUNs and volumes.

launchtimeline_tintri

But not all workloads in a LUN or volume may have the same needs for flash, performance and latency. So just as we’ve reinvented storage over the past four years, Tintri’s ready to reinvent all-flash. Here’s how:

  • No LUNs. Continuing the Tintri tradition, the T5000 series eliminates LUNs and volumes, letting you focus on applications. We’re welcoming VMs to the all-flash space across multiple hypervisors.
  • Unified management. Aside from standalone installations, the T5000 series can also augment the T800, and vice-versa. Admins can now manage VMs across hybrid-flash and all-flash platforms in a single pool through Tintri Global Center (TGC), with full integration.
  • Fully automated policy-based infrastructure through TGC, with support from vDisk-granular analytics and VM-granular self-managed service groups.

With access to vDisk-granular historical performance data, SLAs and detailed latency information, customers can decide which workloads can benefit from all-flash vs hybrid-flash—especially when our hybrid-flash delivers 99-100% from flash.

But we hear you, storage admins: you want to go into the weeds. Surprise—we’re happy to help. Here’s what else the T5000 series can offer you:

  • Space savings from inline dedupe, compression, cloning and thin provisioning.
  • NVDIMMs, NTB, 10G and more of the latest hardware advancements.
  • Enterprise reliability exceeding 99.999% uptime.
  • Scale of up to 112,000 VMs, 2.3PB and up to 5.4M IOPs (random 60:40 R:W, 8K) in a single TGC implementation.  (These are real-life numbers, not 100% read numbers.)
  • VM-granular snapshots, cloning and replication.
  • vDisk-level Dynamic QoS to eliminate noisy neighbors and ensure peak performance.
  • VM-level Manual QoS to setup performance SLAs through Min and Max IOPs.
  • vDisk (VMDKs, VHDs)-level data synchronization across VMs for test and dev or any operations requiring periodic copying of data.
  • VM-level replication, backup and transfer between Hybrid Flash and All-Flash systems.
  • VM-granular performance analytics with end-to-end latency visualization that includes host, network, storage, contention and throttle latency.

Today, Tintri continues our solid roadmap of business-relevant innovations in storage for modern workloads. We changed the game for hybrid-flash—and we’re doing it again for all-flash.

Cheers,
@storarch

The need for a Game Changer in All-Flash Storage

The all-flash space has been abuzz lately with a slew of vendors announcing new developments:

  • Solidfire announced new nodes, a software-only implementation (which oddly comes without complete hardware freedom) and a new program around its Flash Forward guarantee.
  • Pure Storage announced an update to its Flash Array lineup and a program around Evergreen Storage.
  • HP announced its 20K 3PAR line up, basically a hardware refresh.
  • EMC announced software updates to XtremeIO and a lot of other flashy stuff in ScaleIO and DSSD (typical of EMC to think ahead and have multiple bets).
  • NetApp re-launched All-Flash FAS with new pricing to complement the rich data services that ONTAP brings to the table, and has been pounding its chest about how ONTAP is the best thing to happen to all-flash arrays.

(Time will tell what happens to Flashray which is apparently being positioned in a different category (cheaper, simpler to use). Going by my experience, it’ll be a tough sell internally to move sales teams away from selling ONTAP, especially now that they have an optimized All-Flash FAS. (They should thank Gartner for that.) Against popular belief, NetApp has had different products for different workloads in its portfolio (FAS, StorageGrid, E-Series, AltaVault, Flashray) but where it has suffered in my opinion is educating and convincing the NetApp field sales teams to sell anything other than ONTAP. The problem is made worse by loyal NetApp customers who want everything to work with or within ONTAP.)

The Theme

If we look at most of the announcements, we see a unifying theme: Bigger, Faster, Cheaper and Better. This mostly results from new HW technologies (compute), increasing flash capacities and reduction in the price of flash. From a software standpoint, the newer products are catching up to add all the functionalities that traditional products have had. Traditional products (like HP 3PAR, NetApp FAS) are optimizing the code for flash and taking advantage of their already existing data services and application integrations. From a hardware standpoint, eventually every vendor will catch up to each other as they adopt the newer hardware.

Where is the Differentiator?

If we compare the All-Flash offerings from various vendors, most of them have similar features: dedupe, compression, snapshot, clones, replication, LUN/volume-based QoS and some sort of application and cloud integration. Every vendor only does one feature or another better and they struggle to find a big differentiator. When that happens, it’s marketing that starts to innovate more than engineering, and we start seeing messages like this:

  • We provide better space savings (6x vs. 5x) (yes, that’s around 10% better)
  • Our space savings technology never goes post-process (okay, but the other vendor is 10% better for savings)
  • We provide Evergreen Flash (marketing spin on a creative sales rep doing something at the time of a refresh – made even easier by flash)
  • Our Flash Forward program is unique in the industry (another marketing spin)
  • We are the only vendor that provides cloud integration (not true)
  • Designed from the ground up for flash (flash is a medium and traditional products can be optimized for flash—but faster performance/response times or longevity of flash doesn’t necessarily need a ground-up design in all cases. I am saying this even though the Flash layer and spinning drives have a completely different block layout on the Tintri VMstore with the flash layer designed specifically with Flash in mind)
  • We have the cheapest flash solution (when nothing works, talk price)

Running out of ideas?

It’s like everyone is running out of ideas. None of these vendors have taken a “completely different” approach—and their product can be better than others’ only for a limited time. Eventually, everyone will catch up to each other. If you take the same road your competitors do, your results can’t be much different.

But we can’t expect traditional vendors to take a different approach, unless they’re developing a new product without any baggage. But younger product companies definitely have a chance to be different. Still, most of these younger companies have taken a safe approach based on 30-year-old constructs and abstractions that are not required in the modern datacenter—mainly LUNs, volumes that have challenges associated with them. These constructs worked great for some of the traditional workloads but they require a lot of assumptions to be made for architecting storage in a modern datacenter (RAID Group size, Block Size, Queue Depths, LUN/Volume sizes, Number of LUNS/Volumes, number of workloads per LUN/Volume, grouping based on data protection needs etc.). Modern workloads are no longer tied to LUNs/Volumes which also poses a huge problem especially for architectures that are designed with these constructs in mind.

Now, because the traditional vendors and the younger vendors used the same approach, it has become a contest between the two – Traditional vendors are trying to optimize their product for flash, and newer vendors are trying to add functionality to match up to that of traditional vendors. As I see it, the scale is heavier on the traditional vendor side as far as storage with a traditional approach is concerned—because instead of changing the game, the younger vendors decided to play the game of traditional vendors.

 

Innovation focussed on Storage MediaNeed to be Different, not Better

Historically, the startups that make a difference are the ones that take a different approach. Data Domain, for example, defined a new model for backups. Even NetApp took a filesystem approach to storage (for file and block), enabling a completely different implementation of technologies like snapshot, clones, dedupe (primary storage) etc. Now everyone has started to have some sort of filesystem layer, and have caught up to the extent where the lines are all blurred out. NetApp is feeling the pressure now, but it took a long time for vendors to get there. There are many other examples, including ones even outside the storage industry (think Uber, Airbnb, Facebook).

While starting out different is great, it is important for any vendor to stay different and keep reinventing itself (through acquisition or innovation) based on changing needs. They should not get bogged down by a “things are working well, why change anything?” mentality.

Being different changes the possibilities and gives a chance for products to stand out. It allows companies to change the game and the table stakes. It allows companies to ‘change the experience’ which is what we use to evaluate any product.

As far as the all-flash market is concerned, there is a need for a product with a different approach. A product that can change the game and bring new possibilities. The need is for something designed from the ground up for the modern datacenter (and modern applications), rather than something that is just designed from the ground up for flash. Flash is just a medium, and mediums change. It’s Flash today, it may be something else tomorrow.

Cheers,

@storarch

Improving Storage QoS Accuracy and Performance based Chargeback/Showback

A few weeks back, I wrote a series of blog posts (Part 1, Part 2, Part 3) on how Tintri simplifies chargeback/showback for service providers (SPs). With the release of manual quality of service (QoS) per virtual machine (VM) and the introduction of normalized IOPS, Tintri has made that value proposition for SPs even better.

Tintri Storage QoS

As we all know, Tintri is the only storage platform that has an always-on dynamic QoS service that ensures QoS at a vDisk level. As part of this new functionality, Tintri customers can manually configure QoS at a VM level.

QoS on Tintri systems is implemented on normalized IOPS (more on this below) and customers can configure min and/or max settings for individual VMs. The minimum setting guarantees performance when the system is under contention (when you are more than 100% on the Performance Reserves bar) and the maximum setting allows an upper limit on performance for the VM. The new latency visualization gets an enhancement as well with the support for contention and throttle latency visualizations that ensure that QoS doesn’t become a liability.

Screen Shot 2015-04-23 at 9.15.01 PM

If you want to read more about QoS, head over to the blog post here. There is also a great video posted here.

Normalized IOPS

Normalized IOPS are measured at a granularity of 8K by a reporting mechanism that translates standard IOPS into 8K IOPS. This helps create a single scale to measure the performance of various VMs/applications. So, in addition to reporting the standard IOPS per VM/vDisk, the VMstore also reports normalized IOPS for the VMs. So how does the Tintri VMstore report Normalized IOPS? Here are a few examples –

If an application/VM is doing 1000 IOPS @ 8K block size, the VMstore would report it as 1000 Normalized IOPS. Similarly the Normalized IOPs for an application doing 1000 IOPs @ 16K block size would be reported as 2000 Normalized IOPs. Taking a few more examples –

1000 IOPS @ 12K would be equal to 2000 Normalized IOPS as well (rounding off to nearest 8K)

and 1000 IOPS @ 32K would be reported as 4000 Normalized IOPS

Why use normalized IOPS?

  • As we all know, different applications have different block sizes. Normalized IOPS allows us to understand the real workload generated by various applications and help create an apples-to-apples comparison between applications.
  • It also makes QoS predictable. When we set up QoS using normalized IOPS, we know exactly what the result will be, instead of getting a skewed result because of the block size of the application.
  • It gives one single parameter for SPs to implement performance-based chargeback/showback. So, instead of considering IOPS, block size, and throughput, and then trying to do some sort of manual reporting and inconsistent chargeback/showback, the SPs get the measurements out of the box.

Let’s use an example to see how SPs can take advantage of the new functionality.

Screen Shot 2015-04-23 at 9.13.41 PM

In the above screenshot, we have three VMs and we can see the IOPS and Normalized IOPS for each of these VMs. If we look at just the IOPS, we would be inclined to think that the VM SatSha_tingle is putting the highest load on the system, and that it is 2.7x the VM SatSha_tingle-02. But if we look at the Normalized IOPS, we know the real story. The VM SatSha_tingle-02 is almost 1.5x of SatSha_tingle. This is also reflected in the reserves allocated by the system to the VMs under Reserve%.

In a SP environment, without the normalized IOPS, the SP would either end up charging less for SatSha_tingle-02, or would have to look at block size and do some manual calculation to understand the real cost of running the VM. But with Normalized IOPS, the SP can standardize on one parameter for charging based on performance and get more accurate and more predictable with its chargeback/showback.

Since Normalized IOPS are also used for setting up QoS, SPs can now guarantee predictable performance to its customers through implementation of min and max IOPS-based QoS. With Normalized IOPS, the SPs now have four different ways to chargeback/showback on Tintri systems: Provisioned space, Used space, Reserves and min/max Normalized IOPS. Each of these ways bring more accuracy and predictability to any SPs chargeback/showback model that directly affects their Profitability.

Cheers,

@storarch

The industry is validating Tintri – Another one comes through

Last few weeks have been great in terms of industry recognition of how Tintri has been approaching the storage problem for virtualized workloads.

First, VVOLs go GA and validates the approach Tintri took 7 years back with VMstore in terms of removing the boundaries around LUNs and Volumes in virtualized environments and come out with a product that delivered VM centric Storage Platform around 4 years back. The result is 4 years of product maturity (and 4 years of lead) based on real world deployments.

Now we have Pure Storage announce an integration with VMTurbo that allows customers to use VMTurbo in combination with Pure Storage to automate the movement of VMs from one LUN to the other based on various conditions including performance and latency.

What does this tell us?

Continue reading

FY16 , VVols and Tintri’s Financial Differentiation

vSphere 6.0 is GA and Tintri announced support for vSphere 6.0, VVols and VMware Integrated Openstack along with a plugin for vRealize Operations (vROPs) at PEX this week. We also finished our FY in January and will be off to our Sales Kick Off next week. FY15 was a great year with tremendous growth and record QTRs for Tintri. Tintri continues to lead the way with a product designed from the grounds up for both Flash and Virtualization. With vSphere 6.0 we would bring all the goodness that customer’s love about VMstore to VVols including some of the key differentiators that would separate us from the pack –

  • 99-100% IO from flash
  • VM granular operations
  • VM granular visibility and latency visualization
  • Per VM/VVol analytics
  • Automatics Per VM partitioning of Storage resources (Performance Reserves) based on the analytics
  • QoS and Performance Fair share at a VM level (there are a lot more exciting things coming in this space. Stay Tuned for an update on this….)
  • Latency Visualization across the infrastructure (Host, Network, Storage). We are going to add more to this in the coming weeks … stay tuned
  • 1M VVols per VMstore
    • With VVols implementation, a VM may need as low as 5 VVols and as high as 100s of VVols (with snapshot, clones etc.) and a 1000 VM install would require 10s of Thousands to 100s of thousands VVols.
  • VM Granular Automation
  • Ability to Manage, Monitor and analyze up to 112,000 VMs from a single pane of glass

The VVol race that the storage Vendors are starting now was won by Tintri four years back. If you would be evaluating VVols in the coming weeks/months, you should definitely read this blog here to understand what you should ask from your storage vendor when it comes to VVols.

Tintri from the beginning focused on using software to drive innovation and one of the key differentiators about the technology is its ability to deliver 99-100% IO from flash, which is driven by our software unlike all-flash vendors that use Brute Force to deliver performance. The advantage is that Tintri can address a broad spectrum of workloads at a very low cost.

Workload Breakup

What it means is that unlike an All-Flash solution where $/IOP is low and $/GB is high or a hybrid solution where $/IOP is high and $/GB is low, Tintri brings both $/GB and $/IOP at low levels without over depending on Space Savings (Dedup & Compression), therefore delivering a better $/workload at a very high density.

$/GB

Our focus on Virtualization continues to help us differentiate and bring new Virtualization & Cloud Centric functionality faster to the market. The result is a platform that is 5-10x cheaper on CAPEX, 60x cheaper on OPEX and highly scalable.

Cheers..

@storarch

Why Tintri’s milestone of 200,000 VMs and 16PB of Storage is bigger than you think?

Yesterday we announced a significant milestone of 200,000 VMs deployed on Tintri with close to 16PB addressed by these VMs.

Now, these numbers may not look big on their own, but they become really interesting when you combine it with the fact we have doubled the number of VMs in last 6 months and that capacity numbers are for VMs experiencing sub-ms performance. All of this has come at the cost of incumbent storage providers where Tintri beat Modern & Traditional Storage Vendors in process.

Tintri brought a revolutionary Storage platform in 2011 designed for Flash just to run VMs and vDisks. The idea was to have a storage platform that was designed with Virtualization in mind and not Physical Workloads. To date, Tintri VMstore is the only external, best-of-breed platform that has laser focus on Virtualization. The General Purpose Platforms (Traditional & Modern, Flash & Hybrid) continue to focus on Physical workloads even as the customers are moving towards 100% virtualization.=

Where Tintri continues to have edge across multiple Hypervisors is the vDisk level visibility of workloads as compared to General Purpose Platforms that have no idea about what happens at the Hypervisor layer.

One of the drawbacks of this is the IO blender effect that everyone talks about with no effort to provide any solution except throwing flash at it. Tintri is the only platform that addresses it, delivering high performance, sub-ms response times, vDisk granular isolation, predictability, analytics across the infrastructure and per VM data services.

VMware VVOLs is the step in the right direction but it is just an enabler for one hypervisor and it’ll depend upon a vendor on what functionalities it brings to the storage platforms. With all our experience in managing and understanding VMs, Tintri is committed to bring all the goodness that the customers have experienced on the VMstore and much more to VVOLs. And only Tintri would be able to provide customers a choice of deploying VMs either with VVOLs or with an open implementation like NFS without compromising on functionality.

How will we maintain this growth, as the base gets bigger?

Tintri has a solid roadmap. Our focus on Virtualization allows us to bring better functionality around Virtualization & Cloud, much faster to the market. We don’t have to try to be good for all workloads as other General Purpose Platforms and in process compromise everywhere. We are the best Storage Platform for Virtualization & Cloud and would continue to be so for a long time.

If you want to experience all-flash performance for all your virtualized applications (not just the critical ones) at 1/4th of the cost of an over-provisioned flash array (through over-sold dedup and compression) with all the analytics, auto-tuning, VM granular goodness and isolation that our customers are experiencing, I would encourage you to contact your Tintri Rep or your preferred partner. If you plan to attend VMworld, we are going to have big presence there. You can book a Private meeting with Tintri or attend one of our sessions. See details here.

Cheers..

@storarch