Deduplication – By the Numbers

Atlantis HyperScale appliances come with effective capacities of 12TB, 24TB and 48TB depending on the model that is deployed. These capacities are what we refer to as effective capacity, i.e., the available capacity after in-line de-duplication that occurs when data is stored onto HyperScale Volumes. HyperScale Volumes always de-duplicate data first before writing data down to the local flash drives. This is what is known as in-line deduplication which is very different from post-de-duplication which will de-duplicate data after it is written down to disk. The latter incurs storage capacity overhead as you will need the capacity to store the data before the post-process de-duplication is able to then de-duplicate. This is why HyperScale appliances only require three SSDs per node to provide the 12TB of effective capacity at 70% de-duplication.

Breaking it down

HyperScale SuperMicro CX-12
Number of nodes 4
Number of SSDs per node 3
SSD capacity 400GB
Usable flash capacity per node 1,200GB
Cluster RAW flash capacity 4,800GB
Cluster failure tolerance 1
Usable flash capacity per cluster 3,600GB
Effective capacity with 70% dedupe 12,000GB


Data Reduction Table

De-Dupe Rate (%)

Reduction Rate (X)







































Formula for calculating Reduction Rate

Taking the capacity from a typical HyperScale appliance of 3,600GB, this will give 12,000TB of effective capacity.


HyperScale provides a guarantee of 12TB per CX-12 appliance, however some workloads such as DEV/TEST private clouds and stateless VDI workloads could see as much as 90% data reduction. That’s 36,000GB of effective capacity. Do the numbers yourself, in-line de-duplication eliminates the need for lots of local flash drives or slower high capacity SAS or SATA drives. HyperScale runs the same codebase as USX and as such utilizes RAM to perform the in-line de-duplication which eliminates the need for add-in hardware cards or SSDs as staging capacity for de-duplication.

For more information please visit this site


Introducing Atlantis HyperScale

What is it?

A hyper-converged appliance running pre-installed USX software on either XenServer or VMware vSphere and on the hardware of your choice – Lenovo, HP, SuperMicro and Cisco.

How is it installed?

HyperScale comes pre-installed by Atlantis Channel Partners. HyperScale runs exactly the same software as USX, however HyperScale is installed automatically from USB key by the Channel Partner. When it is delivered to your datacenter, it is a simple 5 step process to get the HyperScale appliance ready to use.

Watch the video.

Step 1

Step 2

Step 3

Step 4

Step 5


What do you get?

The appliance is ready to use in about 30 minutes with three data stores ready for use. You can of course create more volumes and also attach and optimize external storage such as NAS/SAN in addition to the local flash devices that come with the appliance.

Atlantis HyperScale Server Specifications
Server Specifications Per Node CX-12 CX-24 CX-48 (Phase 2)
Server Compute Dual Intel E5-2680 v3
Hypervisor VMware vSphere 5.5 or Citrix XenServer 6.5
Memory 256-512 GB 384-512 GB TBD
Networking 2x 10GbE & 2x 1GbE
Local Flash Storage 3x 400GB Intel 3710 SSD 3x 800GB Intel 3710 SSD TBD
Total All-Flash Effective Capacity (4 Nodes)* 12 TB 24 TB 48 TB
Failure Tolerance 1 node failure (FTT=1)
Number of Deployed Volumes 3
IOPs per Volume More than 50,000 IOPs
Latency per Volume Less than 1ms
Throughput per Volume More than 210 MB/s

Key Differentiators vs other Hyper-converged Offerings

Apart from lower cost (another post to follow) or you can read this post from Chris Mellor from The Register, HyperScale runs on exactly the same codebase as USX. USX has advanced data services that provide very efficient data reduction and IO acceleration patented technology. For a brief overview of the Data Services please see this video.



Number of nodes = 4

SSDs per node = 3

SSD capacity = 400GB

Usable capacity per node = 1200GB

Usable capacity per appliance with FTT=1 = 3,600GB

Effective capacity with 70% de-duplication = 12,000GB


USX 2.1 Whats New?

USX 2.1 is now available and has some minor improvements over previous versions. There are some major milestones and some minor improvements that are part of this release.

USX Volume Dashboard
USX Volume Dashboard

Major milestones:

  1. VMware support for USX on the VMware HCL, the VMware KB is in this link.
  2. VMware support for Atlantis NAS VAAI Plugin, the VMware Compatibility Guide for USX is in this link.
    • The Atlantis NAS VAAI Plugin is now officially supported as VMwareAccepted: VIBs with this acceptance level go through verification testing, but the tests do not fully test every function of the software. The partner runs the tests and VMware verifies the result. Today, CIM providers and PSA plugins are among the VIBs published at this level. VMware directs support calls for VIBs with this acceptance level to the partner’s support organization.
    • Atlantis NAS VAAI Plugin can now be installed using VMware Update Manager.

Minor improvements:

  1. Added Incremental Backups for SnapClones for Simple Volumes (VDI use cases).
  2. Added Session Timeout – A new preference was added so that you can configure the number of minutes that a session can be idle before it is terminated.
  3. Added vCenter hierarchy view for Mount and Unmount of Volumes.
  4. Added new Volume Dashboard that shows availability & status reporting improvements, including colour codes for various conditions, all of which roll up to an redesigned volume dashboard that provides an overview of a volume’s configuration, resource use, and health
  5. Improved Status Updates.
  6. Added Active Directory and LDAP Authentication to USX Manager.
  7. Added option to have one node failure for USX clusters of up to 5 nodes. Previously this was up to 4 nodes.
  8. REST API to support changing the USX database server.

Coming to VMworld US? Get yourself a VVOL compliant all software storage array

This article details all of my and Atlantis’ activities at VMworld US. Read more to get an introduction of what we will be doing and announcing and a sneak peek at our upcoming technology roadmap that solves some of the major business issues concerning performance, capacity and availability today. It is indeed going to be a VMworld with ‘no limits’ and one of the great innovations that we will be announcing is Teleport. More on this later!

Teleport your files
No limits with Teleport

I’ll be at in San Francisco from Saturday 23rd August until Thursday 28th August where I’ll be representing the USX team and looking after the Hands on Labs, running live demos and having expert one on ones at the booth. Come and visit to learn more about USX and how I can help you get more performance and capacity out of your VMware and storage infrastructure. I’d love to hear from you.

Where can you find me?

Atlantis is a Gold sponsor this year with Hands on Labs, a booth and multiple speaking sessions. Read on to find out what we’ll be announcing and where you can find my colleagues and me.

Booth in the Exhibitor Hall

I’ll mostly be located at booth 1529, you can find me and my colleagues next to the main VMware booth, just head straight up pass the HP, EMC, NetApp and Dell stands and come speak to me on how USX can help you claim more performance and capacity from these great enterprise storage arrays.

Speak to me about USX data services and I’ll show you some great live demos on how you can reclaim up to 5 times your storage capacity and gain 10 times more performance out of your VMware environment.

Here’s one showing USX as storage for vCloud Director in a Service Provider context and also for Horizon View.

If that’s not enough then come and speak to me about some of these great innovations:

  • If you’ve been waiting for a VVOL compliant all software vendor to try VVOLs with vSphere 6 beta then wait no more.
  • VMware VVOL Support – all of your storage past, present and future instantly become VVOL compliant with USX.
  • Teleport – the vMotion of the storage world which gives you the ability to move VMs, VMDKs and files between multiple data centers and the cloud in seconds to improve agility (if you’re thinking its Storage vMotion, trust me it is not).
  • And more….
Location in Solutions Exchange


We have three breakout sessions this year, two of them with our customers UHL and Northim Bank where Dave Rose and Erick Stoeckle respectively will take you through how they use USX in production.

The other breakout session is focused on VVols, VASA, VSAN and USX Data Services and will be delivered by our CTO and Founder Chetan Venkakesh (@chetan_). If you have not had the pleasure to hear Chetan speak before, then please don’t miss this opportunity. The guy is insane and uses just one slide with one picture to explain everything to you. He is a great storyteller and you shouldn’t miss it – even if it’s just for the F bombs that he likes to drop.

Chetan will also do a repeat 20-minute condensed session in the Solutions Exchange for a brain dump of Atlantis USX Data Services. Don’t miss this! Chetan will take you through the great new technology in the Atlantis kitbag.

Session Title Speaker(s) When Where
STP3212 – Unleashing the Awesomeness of the SDDC with Atlantis USX Chetan Venkatesh – Founder and CTO, Atlantis Computing Tuesday, Aug 26, 11:20 AM – 11:40 AM Solutions Exchange Theater Booth 1901
INF2951-SPO – Unleashing SDDC Awesomeness with Atlantis USX: Building a Storage Infrastructure for Tier 1 VMs with vVOLS, VASA, VSAN and Atlantis USX Data Services Chetan Venkatesh – Founder and CTO, Atlantis Computing Wednesday, Aug 27, 12:30 PM – 1:30 PM Somewhere in the Moscone (TBC)
EUC2654 – UK Hospital Switches From Citrix XenApp to VMware Horizon Saving £2.5 Million and Improving Patient Care Dave Rose – Head of Design authority, UHL
Seth Knox – VP Products, Atlantis Computing
Wednesday, Aug 27, 1:00 PM – 2:00 PM Somewhere in the Moscone (TBC)
STO2767 – Northrim Bank and USX Erick Stoeckle , Northrim Bank
Nishi Das – Director of Product Management, ILIO USX, Atlantis Computing Inc.
Thursday, Aug 28, 1:30 PM – 2:30 PM Somewhere in the Moscone (TBC)

Hands on Labs

You can find the hands on labs in the Hands on Labs hall, I’ll also be here to support you if you’re taking this lab. The Atlantis USX HOL is titled:

HOL-PRT-1465 – Build a Software-based Storage Infrastructure for Tier 1 VM Workloads with Atlantis USX Data Services.

This HOL consists of three modules, each of which can be taken separately or one after the other.

Modules 1 and 2 are read and click modules where you will follow the instructions in the lab guide and create the USX constructs using the Atlantis USX GUI.

Module 3 however uses the Atlantis USX API browser to quickly perform the steps in Module 1 with some JSON code.

All three modules will take you approximately an hour and a half to complete.

I had an interesting time writing this lab which was a balancing exercise in working with the limited resources assigned to my Org VDC. Please provide feedback on this lab if you can, it’ll help with future versions of this HOL. Just tweet me at @hugophan. Thanks!

Note that performance will be an issue because we are using the VMworld Hands on Labs hosted on Project NEE/OneCloud. This is a vCloud Director cloud in which the ESXi servers that you will see in vCenter are actually all virtual machines. Any VMs that you run on these ESXi servers will themselves be what we call nested VMs. In some cases you could actually see 2 more or nested levels. How’s that for inception? Just be aware that the labs are for a GUI, concept and usability feel and not for performance.

If you want to see performance, come to our booth!

VMware Hands on Labs with 3 layers of nested VMs!

Hands on Labs modules

Module #


Module Title

Atlantis USX – Deploying together with VMware VSAN to deliver optimized local storage

Module Narrative

Using Atlantis USX, IT organizations can pool VSANs with existing shared storage, while optimizing it with Atlantis USX In-Memory storage technology to boost performance, reduce storage capacity and provide storage services such as high availability, fast cloning and unified management across all datacenter storage hardware.The student will be taken through how to build a Hybrid virtual volume that optimizes VMware VSAN allowing it to delver high performing virtual workloads from local storage.

  • Build an USX Capacity Pool using the underlying VMware VSAN datastore
  • Build an USX performance pool from local server RAM
  • Build a Hybrid USX virtual volume suitable for running SQL Server
  • Present the Atlantis USX virtual volume to ESX over NFS

Module Objectives
Development Notes

A customer has built a resilient datastore from local storage using VSAN. This is then pooled by Atlantis USX to provide the Deduplication and I/O optimization that server workloads require. A joint whitepaper of this solution has already been written here:
Estimated module duration: 45 minutes


Module #


Module Title

Atlantis USX – Build In Memory Storage

Module Narrative

With Atlantis USX In-Memory storage optimization, processing computationally extensive analytics becomes easier and more cost effective allowing for an increased amount of data being processed per node and reduced the time to complete these IO intensive jobs, workloads may include Hadoop, Splunk, MongoDB.During this lab the student will be taken through how to build an Atlantis USX virtual volume using local server memory.

  • Build an USX Performance Pool aggregating server RAM from a number of ESX hosts.
    • Log into the web based management interface, and connect it the vCenter hosting the ESX infrastructure
    • Export the memory from the three ESX hosts onto the network using Atlantis aggregation technology.
    • Combine the discrete RAM resource into a protected performance pool with the Pool creation wizard.
  • Build an In-Memory virtual volume suitable for running a big data application
    • Run through the Create Virtual Volume wizard selecting In-Memory and deploying the In-Memory Virtual Volume
  • Present the Virtual Volume (datastore) to ESX over NFS.
    • Add the newly created datastore into ESX.

Module Objectives
Development Notes

The use case for this lab is increasing application performance by taking advantage of the storage optimization features in Atlantis USX.Estimated module duration: 30 minutes


Module #


Module Title

Atlantis USX – Using the RESTful API to drive automation and orchestration to scale a software-based storage infrastructure

Module Narrative

Atlantis USX has a powerful set of RESTful APIs. This module will give you insight into those APIs by using them to build out a Virtual Volume. In this module you will:

  • Connect to the USX API browser and review the available APIs
  • Create a Capacity and Memory Pool with the API
  • Create a Virtual Volume with the API

Module Objectives
Development Notes

The intent of this lab is to provide an example of how to use the Atlantis USX RESTful API to deploy USX at scale.Estimated module duration: 15 minutes


Oculus giveaway! See the reality in software defined storage

That’s right! I’ll be giving some of these away at the booth, make sure you stop by to see the new reality in software defined storage!

You can also pick up some of the usual freebies like T-shirts, pens, notepads etc.

There are also Google Glasses, Chromecasts, quad copters and others. We’re also working on something special. Watch this space.

Live Demos at the Booth

Come and speak to me and my colleagues to learn how USX works. We will be running live demos of the following subjects:

  • USX – Storage Consolidation for any workload on any storage.
  • USX – Database Performance Acceleration.
    • Run Tier-1 workloads on commodity hardware.
    • Run Tier-1 high performance workloads on non all-flash or hybrid storage arrays.
  • USX – All Flash Hyper-Converged with SuperMicro/IBM/SANdisk.
  • USX – Teleport (think vMotion for VMs, VMDKs and files over long distances and high latency links). Come talk to me for a live demo.
Beam me up Scotty!
  • USX Tech Preview – Cloud Gateway – using USX data services with AWS S3 as primary storage.
  • USX – VDI on USX on VSAN.
  • VDI – NVIDIA 3D Graphics.

Atlantis Events

SF Giants Game

SF Giants Game, Mon, Aug 25th at 19:00. Please contact your Atlantis Representative or ping me a note if you haven’t received an invite.

USX Partner Training & Breakfast, Wed, Aug 27th at 08:00. Please contact your Atlantis Representative or ping me a note if you’re an Atlantis Partner but have not received an invite.

Let’s meet up!

If you’re at VMworld or in the SF Bay area then let’s meet up and expand our networks.

Event Date Hours Event Name Where Register
Sat, Aug 23rd 19:00 – 22:00 VMworld Community Kickoff Johnny Foley’s, 243 O’Farrell Street
Sun, Aug 24th 13:00 – 16:00 #Opening Acts City View at Metreon
Sun, Aug 24th 15:00 – 17:00 #v0dgeball Charity Tournament SOMA Rec Center – Corner of Folsom and 6th Streets
Sun, Aug 24th 16:00 – 19:00 VMworld Welcome Reception Solutions Exchange, Moscone Center n/a
Sun, Aug 24th 20:00 – 23:00 #VMunderground City View at Metreon
Mon, Aug 25th 19:00 – 23:00 #vFlipCup VMworld Community TweetUp Folsom Street Foundry
Tues, Aug 26th 16:30 – 18:00 Hall Crawl Solutions Exchange, Moscone Center n/a
Tues, Aug 26th 19:00 – 22:00 #VCDX, #vExpert Party E&O Restaurant & Lounge, 314 Sutter St Invite only
Tues, Aug 26th 20:00 – 23:00 #vBacon Ferry Building, 1 Sausalito
Wed, Aug 27th 17:00 – 19:00 VMware vCHS Tweetup 111 Minna
Wed, Aug 27th 19:00 – 22:00 VMworld Party Moscone Center n/a

Can’t meet up?

Follow me and my colleagues on Twitter for live updates during VMworld and send us messages and questions, we’d love to hear from you.

Hugo Phan @hugophan

Chetan Venkakesh @chetan_

Seth Knox @seth_knox

Mark Nijmeijer @MarkNijmeijerCA

Gregg Holzrichter @gholzrichter

Toby Colleridge @tobyjcol

Is Atlantis USX the future of Software Defined Storage?

More informative info on #USX and a great write-up from Storage Swiss. - The Home of Storage Switzerland

Software Defined Storage (SDS) has certainly caught the attention of IT planners looking to reduce the cost of storage by liberating them from traditional storage hardware lock-in. As SDS evolves the promise of lower storage CAPEX, increased deployment and architecture flexibility, paired with lower OPEX through decreased complexity may emerge from suppliers of this technology. Atlantis USX looks to lead this trend, claiming to deliver all-flash array performance for half the cost of a traditional SAN.

Atlantis USX Architecture

From an architectural perspective, USX has the same roots as Atlantis’s VDI solution, except that it’s focused on virtual server workloads instead of virtual desktops. As part of the enhancements for server virtualization, USX has added the ability to pool any storage resource between servers (SAN, NAS, Flash, RAM, SAS, SATA), it’s added data protection to ensure reliability in case of a host failure and has built its own high availability…

View original post 1,335 more words

Atlantis USX Data Services with Hyper-Converged Architecture – Web Scale, Virtual Volumes & In-line Deduplication

Atlantis USX has some very cool technology which I’ve had the pleasure to ‘play’ with over the past few weeks. In these series of posts I’ll attempt to cover the various technologies within the Atlantis USX stack.

The key technologies in the Atlantis USX In-Memory Data Services are:

  1. Inline IO and Data de-duplication
  2. Content aware IO processing
  3. Compression
  4. Fast Clone
  5. Storage Policies
  6. Thin Provisioning

This post focuses on Inline IO and Data de-duplication (or just dedupe for short) and Fast Clone and how these rich data services enable a hyper converged solution to outperform enterprise storage arrays.


Why would you use Atlantis USX?

The best way to approach this is to look at some use cases: Crazy as it seems, Atlantis USX delivers All-Flash Array performance but also gives five times the capacity of traditional storage arrays. Doing this with 100% software, no hardware appliances, and true software defined storage with software, enabling true web-scale architecture.

The majority of storage vendors today either do one of the other, not both. So you could end up with storage silos where IOPS are provided by an all-flash array and capacity is provided by a traditional SAN.


USX Use Cases

The three key Atlantis USX messages are:

  • Why buy more storage when you can do more with the storage you already have
    • Get up to 5X the capacity out of your existing storage array
    • Avoid buying any new storage hardware for the next 5 years
    • Reduce storage costs by up to 75%


    Use cases: Storage capacity running out in your current arrays.

    • Don’t buy another disk tray or array, free up capacity by leveraging Atlantis USX Inline Deduplication.
    • Get more capacity out of your all-flash array purchase – all-flash arrays (AFA) provide great performance but not great capacity, get 5X more capacity by using USX on-top of your AFA.



  • Accelerate the performance of your existing storage array
    • Deliver all-flash performance to applications with your existing storage at a fraction of the cost
    • Works with any storage system type – SAN, NAS, Hybrid, DAS


    Use cases: Current storage arrays not providing enough IOPS to your applications – place USX in front of your array and gain all-flash performance by using RAM from your hypervisor to accelerate and optimize the IO.


  • Build hyper-converged systems INSTANTLY without buying any new hardware
    • With RAM, local disk (SSD/SAS/SATA) or VMware VSAN on your existing servers
    • Don’t replace your servers of choice with alternative appliances
    • Use blade servers for hyper-converged infrastructure

    Use cases: Leverage existing investment in your compute estate by using USX to pool and protect local RAM and DAS to create a hyper-converged solution which can leverage both the DAS and any shared storage resources already deployed, including traditional SAN/NAS and VMware VSAN. Also use your preferred server architecture for hyper-converged, USX allows you to use both blade and rack server form factors due to the reduction in the number of disks required.


What if I want to do all of the above, all at the same time?

Well yes you can. And yes Duncan, we are doing this today (

You can get the benefits of rich data services coupled with crazy fast storage and in-line deduplication enabling immediate capacity savings today.


What is Inline IO and Data de-duplication?

In short, it is the ability to dedupe data blocks and therefore IO operations before those blocks and IO operations reach the underlying storage. Atlantis USX reduces the load on the underlying storage by processing IO using the distributed in-memory technology within Atlantis USX.

To demonstrate this, the blue graph below represents IOPS provided by USX to VMs. The red graph represents the actual IOPS that USX then sends down to the underlying storage (if it needs to). [The red graph would be for IO operations that are required for unique writes, however I won’t go into detail about that here in this post.]

Conversely, the same graphs can be used to show data de-duplication, just replace the IOPS metric on the y-axis with Capacity Utilization (GB) and you will also see the same savings in the red graph. Atlantis USX uses in-memory in-line de-duplication to offload IOPS from the underlying storage and to reduce consumed capacity on the underlying storage. I’ll show you how this works in the following labs below.


Examples in the lab

Let’s see some of these use cases in action in the lab.

Lab setup

  • 3 x SuperMicro servers installed with vSphere 5.5 U1b with 32GB RAM, 1 x SSD, 1 x SATA and some shared storage (which is not in use in this post) presented from an all-flash array (violin memory) and SAN (Nexenta) both over iSCSI.
  • Local direct attached storage (DAS) pooled, protected and managed by Atlantis USX.

Use Case 1: Building hyper-converged using Atlantis USX for VDI

In this use case I’ve created a hyper-converged system using the three servers and pooling the local SSDs as a performance pool and the local SATA drives as a capacity pool.

Memory is not used as a performance pool due to the servers only having 32GB of RAM. In a real world deployment you can of course use RAM as the performance pool and not require any SSDs altogether. I’ll use RAM in another blog post.

In the vSphere Client, these disks are shown as local VMFS5 data stores.

Pooling Local Resources

What USX then does is pool the SSDs into a Performance Pool and the SATA disks into a Capacity Pool.

Performance Pools

Atlantis USX pools the SSDs into a Performance Pool to provide performance. Performance Pools provide redundancy and resiliency to the underlying resources. In this example, where we are only using three servers, the RAW capacity provided by the SSDs are 120 x 3 = 360, however due to the Performance Pool providing redundancy, the actual usable capacity will be 66% of this, so 240GB is usable. This is the minimum configuration for a 3-node vSphere cluster. If you had a 4-node cluster then you will have the option to deploy a Performance Pool with a ‘RAID-10’ configuration. This will then give you 480GB RAW and 240GB usable. It’s really up to you to define how local resources are protected by Atlantis USX and by adding more nodes to your vSphere cluster and/or more local resources you can create hyper-converged infrastructure which is truly web scale.

Side note 1: an aside on web scale

Atlantis USX can pool, protect and manage multiple vCenter Servers and their resources. vCenter Servers can manage thousands of vSphere ESXi hosts. You can even create a Virtual Volume from resources which span over multiple ESXi servers, which are not in the same vSphere Cluster and not managed by the same vCenter Server. Heck, you can even use USX to provide the rich data services through Virtual Volumes which use multiple vsanDatastores (VMware VSAN). What I’m trying to say is that your USX Virtual Volume is not restricted to a vCenter construct and as such is free to roam as it is in essence decoupled from any underlying hardware. More on Virtual Volumes later.

Roaming Free
Roaming Free

Back to Capacity Pools

Atlantis USX pools the SATA disks into a Capacity Pool to provide capacity. Capacity Pools also provide redundancy and resiliency to the underlying resources. In this example, where we are only using three servers, the RAW capacity provided by the SATA disks are 1000 x 3 = 3000, however due to the Capacity Pool providing redundancy, the actual usable capacity will be 66% of this, so 2000GB is usable.

The resources from the Performance Pool and Capacity Pool are then used to carve out resources to Virtual Volumes.

Side note 2: a quick introduction to Atlantis USX Virtual Volumes

The concept of a Virtual Volume is not new, it was proposed by VMware back in 2012 ( and in more detail by Duncan here ( but since then has not really had the engineering focus that it deserves until now ( The concept is very straightforward – your application should not be dependent on the underlying storage for its storage needs.

Virtual Volumes is all about making the storage VM-centric – in other words making the VMDK a first class citizen in the storage world” – Cormac Hogan

Your application should be able to define its own set of requirements and then the storage will configure itself to accommodate the application. Some of these requirements could be:

  • The amount of capacity
  • The performance – IOPS and latency
  • The level of availability – backup and replication
  • The isolation level – single virtual volume container just for this application or shared between multiple applications of a similar workload

With Atlantis USX, Virtual Volumes have a storage policy which defines those exact requirements. Atlantis USX will provide the rich data services for the virtual volumes which can then be consumed by the application at the request of an Application Owner. Enabling self-service storage request and management for an application without waiting for a storage admin to calculate the RAID level and getting your LUN two weeks later. Is this still happening?

An Atlantis USX Virtual Volume is created from some memory from the hypervisor, some resource from the Performance Pool and some resource from the Capacity Pool. The Atlantis USX rich data services – inline data deduplication and content aware IO processing happens at the Virtual Volume level. The Virtual Volume is then exported by Atlantis USX as NFS or iSCSI (today. Object and CIFS very soon) either to the underlying hypervisor as a datastore or directly to the application. Think of a Virtual Volume as either a) an application container or b) a datastore – all with the storage policy characteristics as explained above and of course supporting all of the lovely vSphere, Horizon View, vCloud, VCAC features that you’ve come to love and depend on:

  • HA
  • DRS
  • vMotion
  • Fault Tolerance
  • Snapshots
  • Thin Provisioning
  • vSphere Replication
  • Storage Profiles
  • Linked Clones
  • Fast Provisioning
  • VAAI

Back to creating Virtual Volumes from Pools

In our example here, the maximum size for one Virtual Volume would be constructed from 240GB from the Performance Pool and 2000GB from the Capacity Pool. However, to take advantage of Atlantis USX in-memory I/O optimization and de-duplication, you would create multiple Virtual Volumes, one for a particular workload type. Doing so will make the most out of the Atlantis USX Content Aware IO Processing engine.

Let’s configure a single Virtual Volume for a VDI use case. I’ll create a Virtual Volume with just 100GB from the Capacity Pool and 5GB from the Performance Pool. We will then deploy some Windows 8 VMs into this Virtual Volume and see the Atlantis USX in-memory data deduplication and content aware IO processing in action.

Here’s our Virtual Volume below, configured from 100GB of resilient SATA and just 5GB of resilient SSD. Note that VAAI integration is supported and for NFS the following primitives are currently available: ‘Full File Clone’ and ‘Fast File Clone/Native Snapshot Support’.

[Dear VMware, how about a new ‘Drive Type’ label named ‘In-Memory’, ‘USX’, ‘Crazy Fast’?]

As you can see the datastore is empty. Very empty. The status graphs within USX currently show no IO offload and no deduplication. There’s nothing to dedupe and no IO to process.


Let’s start using this datastore by cloning a Windows 8 template into it. We will immediately see deduplication savings on the full clone after it is copied to our new virtual volume.


Here’s our new template, cloned from the ‘Windows 8.1 Template’ template above which is now located on the new usx-hyb-vol1 virtual volume.


The same graph below shows that for just that single workload, USX has been able to perform data de-duplication by 18%.


Let’s jump into Horizon View and create a desktop pool and use Full Clones for any new desktops, I’ll use the template named win8-template-on-usx as the base template for the new desktop pool and our new virtual volume usx-hyb-vol1 as the datastore.


Let’s see what happens when we deploy one new virtual machine via a full clone with Horizon View which uses an Atlantis USX Virtual Volume. Hint: The clone happens almost instantly due to the VAAI Full Clone offload to USX. We will also see the deduplication ratio increase and IO offload will also increase.


The Full Clone completes in about 9 seconds. Happy days!


The deduplication has increased to 63%! With just two VMs on this datastore – the template win8-template-on-usx and the first VM usx-vdi1.


Taking a look with the vSphere Client datastore browser again, we now see two VMs in the virtual volume which are both full VMs, not linked clones.


Two Full VMs, only occupying 8.9GB.


Let’s now go ahead and deploy an additional 5 VMs using Horizon View.


All five new VMs are provisioned pretty much instantly as shown in the vSphere Client Recent Tasks pane.


Checking the Atlantis USX status graphs again, the deduplication ratio has increased to 88%.


And we now see 6 Full Clones and the template in the datastore but still just consuming 10.57GB.


Additionally because the workloads are pretty much exactly the same, with all six VMs deployed and running in the usx-hyb-vol1 Virtual Volume and with Atlantis USX in-memory Content Aware IO processing, IO and data de-duplication, the IO Offload is pretty much at 100%. This will decrease accordingly as users start using the virtual desktops and more unique data is created but Atlantis USX will always try to provide all IO from the Performance Pool (RAM, Flash or SSD).


No storage blog post is complete without an Iometer test

Let’s do a VDI Iometer profile with 80% writes, 20% reads at 80% random with 4k blocks using the guide from Jim (


Here’s the result:

55k IOPS (fifty five thousand IOPS!) and pretty much negligible read and write latency on just three vSphere ESXi hosts. To put that into context, if I deployed one hundred Windows 8 VDI desktops into that Virtual Volume, each desktop (and therefore user) would basically have 550 IOPS. You can read more about IOPS per user in this post by Brian Madden ( To put this IOPS number into further context, that Virtual Volume is configured to use just 10GB of RAM from the hypervisor, 5GB of SSD and 100GB (of which only 10.57GB is in use, which is a 88% capacity saving) of super slow SATA disks in total over the three vSphere ESXi hosts. If you want more IOPS, you just need to create more Virtual Volumes or add more ESXi hosts to scale out the hyper-converged solution.

In other words… crazy performance on hyper converged architecture with just a few off-the shelf disks on a few servers. No unicorns or magic in Atlantis USX, just pure speed and space savings. BOOM!



To summarize, Atlantis USX is a software-defined storage solution that delivers the performance of an All-Flash Array at half the cost of traditional SAN or NAS. You can pool any SAN, NAS or DAS storage and accelerate its performance, while at the same time consolidating storage to increase storage capacity by up to five times. With Atlantis USX, you can avoid purchasing additional storage for more than five years, meet the performance needs of any application without buying hardware, and transition from costly shared storage systems to lower cost hyper-converged systems based on direct-attached storage as I’ve demonstrated here.

In part 2. I’ll use local RAM instead of SSDs and in part 3. I’ll demonstrate how Atlantis USX can be used to get more capacity and IOPS from your current storage array.

Accelerating SDDC at Atlantis Computing

Sometimes an opportunity comes along that is just too damn exciting to pass.

This is a short post on my latest move to Atlantis Computing from Canopy Cloud. My new role is primarily with the USX team to help drive the adoption of USX into large Enterprises and Service Providers. USX is Atlantis Computing’s newest technology which does for server workloads what ILIO did for EUC. Quite simply my job is to make USX a success. I’ll be helping the virtualization community understand Atlantis Computing’s USX and ILIO technologies, working with customers and partners and also with our technology partners, such as VMware, NetApp, VCE, Fusion-IO and IBM. Even though USX is new, the technology is based on ILIO which has been shipping since 2009 and is powering the largest VDI deployments in the world.

Today was officially my first day and it was a pretty interesting one. It started with a customer meeting with a large bank in London and then to BriForum, both in a listening capacity but I couldn’t help myself and ended up talking  about both ILIO and USX to some techies at the bank and then some people that came to the stand at BriForum. There is definitely hot interest with using RAM to accelerate storage in both EUC and server workloads.

Atlantis Computing’s ILIO and USX technologies are truly software defined and in simple terms enables the in-line optimisation of both IOPS and capacity BEFORE the IOPS and blocks hits the underlying storage. For example the blue graph represents IOPS to the storage array for 200 VDI VMs without ILIO, the red graph represents IOPS to the same storage array with ILIO, a saving of 80%.


In addition because storage is deduped in-line, there is also massive capacity savings on the underlying storage too. Dedupe occurs in-line, there is no requirement for dedupe to blocks written to disk as data is deduped before being written to disk, hence no overhead caused by a dedupe job on the storage processor or spindles.

In-line de-duplication is not the only capability within the Atlantis Computing technology, some of the others are:



I won’t go into each one in this post, I’ll save that for another day. I’m very excited with my new role at a new company and hope to blog a lot more often as I learn more about Atlantis Computing and of course storage virtualization and optimisation in general.

If you want to read more, some of these resources help explain the tech. Oh and we offer a completely free ILIO license for use in POCs/Lab environments, be sure to check it out!