Technology:Unpacked

In this week’s episode, Chris catches up with Stan Stevens, Director of Software Product Marketing at Hitachi Vantara to talk about updates to Hitachi Ops Center. Ops Center is the storage management platform for administering Hitachi VSP storage products. Stan discusses new features (including Ops Center Protector and support for VSP E990), and provides a view on what to expect in the future.

Ops Center is divided into four main components – Administrator for provisioning and systems management; Analyser for AIOps functionality, including problem resolution; Automator for workflow automation and Protector for data protection and backup. As Stan explains in this discussion, Ops Center aims to augment existing customer processes and tools, rather than be a replacement for them.

One interesting aspect of the use of a single management platform is the ability to provide the same automation and provisioning process across solutions that are designed for enterprise and midrange. This provides the opportunity to optimise data placement without having to change management processes.

More details on the Ops Center portfolio can be found here – https://www.hitachivantara.com/en-us/products/it-operations-management/ops-center.html

Elapsed Time: 00:33:12

Timeline

* 00:00:00 – Intros* 00:01:00 – Quick recap on Hitachi’s structure * 00:02:54 – What is Ops Center? * 00:04:40 – What are the components of Ops Center? * 00:07:30 – What’s the strategy with Ops Center? * 00:10:30 – Ops Center will expose APIs to integrate with existing frameworks * 00:11:50 – Workflows and automation templates are included in the platform * 00:16:52 – Storage administration is changing – higher level management * 00:19:20 – 160 million data points collected in 24 hours – AIOps * 00:21:00 – What’s new – Protector – backup to cloud/object 7 E990 support * 00:23:55 – Ops Center offers standardisation of management platforms * 00:28:00 – How does backup to cloud work? 00:30:00 – Future, what’s coming next? * 00:31:58 – Wrap up

Related Podcasts & Blogs

* #154 – Hitachi Vantara VSP E990 NVMe Midrange Appliance with Colin Gallagher* #125 – Hitachi Next 2019: Ops Center* #103 – Data Management and DataOps with Hitachi Vantara

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #v06o.

This week, Chris and Martin dig deeper into storage media and look at magneto-resistive RAM, commonly known as MRAM in this conversation with Joe O’Hare, Director of Distribution and Product Marketing at Everspin Technologies.

MRAM is a persistent memory technology that uses resistance to determine the state of data. Everspin, the leading provider of MRAM technologies offers two product types – Toggle and Spin Transfer Torque. These two solutions provide different characteristics of endurance and scaling, but both offer low latency reads and writes at around 35 nanoseconds.

MRAM is already finding uses in embedded solutions, where Toggle offers opportunities for IoT and industrial devices. With a relatively low level of scalability, Toggle isn’t likely to migrate to the enterprise. Instead, STT provides greater scalability with the trade-off of reduced endurance (although we should say, nowhere near the poor endurance levels of NAND flash). Today, we already see STT MRAM embedded in IBM FlashCore drives as a replacement for super-capacitors.

This conversation is interesting as it highlights the complementary nature of technologies like MRAM in improving the capabilities of existing persistent storage technologies. You can learn more at www.everspin.com.

Elapsed Time: 00:32:25

Timeline

* 00:00:00 – Intros* 00:01:15 – Persistent memory and MRAM – what is it?* 00:02:45 – MRAM has high endurance – like DRAM* 00:03:15 – MRAM needs to offer low latency* 00:05:45 – What are the two types of MRAM?* 00:08:15 – 35 nanosecond read/write cycle on MRAM* 00:11:00 – Toggle offers much greater endurance than STT* 00:14:45 – STT products are already in enterprise drives* 00:16:15 – IBM uses MRAM in FlashCore devices* 00:18:00 – Could MRAM make SMR and QLC/PLC drives more efficient? * 00:20:15 – MRAM will also be used on SmartNICs* 00:22:30 – What non-enterprise application are there for MRAM? * 00:23:15 – MRAM will be embedded in SoCs and ASICs* 00:26:30 – MRAM will comply with the SPI interface* 00:28:30 – What does the future hold? * 00:30:45 – Wrap Up

Related Podcasts & Blogs

* What are SCM and PM?* The Expanding Storage Hierarchy* #141 – Building Storage Systems of the Future

Joe’s Bio

Joe has had a rewarding career working in the semiconductor industry at companies such as TI, Lucent Microelectronics, Agere Systems and now Everspin Technologies. He has held a variety of engineering, marketing and executive positions with a focus on developing products for the storage industry, both magnetic and solid state.  As marketing director at Everspin Technologies, Joe is leading the effort to define and launch a new class of MRAM memory that is targeted at storage and industrial applications where performance and persistence are featured. 

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #2dst.

This week we continue with the discussion on midrange storage platforms with a more in-depth look at PowerStore and other recent announcements. PowerStore is the new Dell midrange platform that’s expected to replace XtremIO, SC Series and Unity. We learned more on the platform from Dell earlier in the week (see the links in related episodes).

This episode looks to unpack some of the detail with reference to the wider storage market. Will AppsON be a success? What does it mean to have an integrated hypervisor? Could PowerStore run in the public cloud? All questions we get to in this episode.

Looking at the market in general, is there now a move towards single storage operating systems and platforms? Have we finally seen a degree of standardisation and rationalisation? Listen to find out!

Elapsed Time: 00:47:02

Timeline

* 00:00:00 – Intros* 00:01:05 – 12 months since our previous speculation on midrange * 00:02:00 – Was Trident the PowerStore project?* 00:05:15 – Containerisation and virtualisation in PowerStore* 00:07:00 – It’s not Tanzu!* 00:08:25 – Doesn’t virtualisation impact performance?* 00:10:50 – Can any vendor use the PCIe acceleration in ESXi 6.7U2? * 00:12:30 – What other midrange announcements have there been? * 00:15:15 – Dell has expanded it’s storage portfolio (again)* 00:16:50 – Does cost sensitivity preclude only all-flash in midrange? * 00:18:55 – Is midrange the new “enterprise”?* 00:24:00 – What has happened to NVMe-oF startups?* 00:29:25 – Is PowerStore a “challenger” product?* 00:31:20 – Is scale-out really needed today?* 00:35:00 – How will ESXi be accessed by the customer in PowerStore X? * 00:36:30 – Could PowerStoreOS run in the public cloud?* 00:38:50 – PowerStoreOS could run better on VMware on AWS* 00:40:00 – Will all vendors go single storage operating system?* 00:44:45 – Wrap up

Related Podcasts & Blogs

* #157 – Introduction to Dell PowerStore* #90 – Dell EMC’s Enterprise NVMe Strategy with Vince Westin* #138 – Storage Predictions for 2020* #102 – May Midrange Madness with Chris Mellor* Dell Technologies Unveils PowerStore Midrange.NEXT

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #ndi0.

In this sponsored episode, Chris and Martin look at the newly announced midrange storage platform from Dell Technologies. PowerStore is a new all-flash midrange storage solution that offers both scale-up and scale-out capabilities. As we find out in the discussion with Dan Cummins and Devon Reed, this is only one aspect of the new technology. Through a feature called AppsOn, customers can run their own applications on a native ESXi hypervisor.

In building a new storage platform, how did Dell Technologies leverage the assets already in the portfolio? We find out that XtremIO, SC Series and Unity all provided inspiration for the new solution, although the design and code is completely new.

AppsOn represents an interesting approach in running local applications. Whilst we’ve seen this kind of solution before (EMC tried it on VMAX3), this time the target includes Edge applications where benefits can be gained from local pre or post processing.

While we covered lots about the internals of the system, we didn’t manage to cover the migration process (which is integrated with existing platforms) or the new purchasing models. We hope to cover these in a future episode.

You can find more on PowerStore, including the virtual tour and interactive demo referenced at the end of the podcast through this link: https://www.delltechnologies.com/en-gb/storage/powerstore-storage-appliance.htm

Elapsed Time: 00:39:22

Timeline

* 00:00:00 – Intros* 00:02:00 – What is PowerStore?* 00:02:55 – Does this consolidate existing platforms into one?* 00:04:00 – PowerStore addresses needs for new media and functionality* 00:05:25 – How does PowerStore leverage Dell storage IP?* 00:07:15 – PowerStore uses container-based technology* 00:12:10 – PowerStore offers scale-up & scale-out* 00:17:55 – Midrange represents a hugely diverse market* 00:20:30 – PowerStore offers use cases for edge* 00:23:00 – What is AppsOn?* 00:24:50 – How is ESXi exposed to the end user?* 00:27:20 – What modifications to ESXi have been made?* 00:35:45 – Could we expect to see new storage services in PowerStore? * 00:37:25 – PowerStore is available today!* 00:38:00 – Wrap Up

Devon’s Bio

Devon Reed is Senior Director of product management for mid-range and entry storage at Dell Technologies. A two-decade veteran of the IT industry, Devon is responsible for the product strategy and roadmap for the Dell EMC PowerStore, Unity and Unity XT families, the SC Series, and PowerVault.

Dan’s Bio

Daniel Cummins is a Senior Distinguished Engineer at Dell Technologies and Chief Architect for Dell EMC midrange & entry systems. Daniel is responsible for defining, incubating, and driving new storage product architectures and technology innovations for midrange storage products.

Related Podcasts & Blogs

* #90 – Dell EMC’s Enterprise NVMe Strategy with Vince Westin* #99 – Dell Technologies World 2019 in Review* #102 – May Midrange Madness with Chris Mellor* Dell Technologies Unveils PowerStore Midrange.NEXT

In this episode, returning guest Douglas Fallstrom from Hammerspace takes Chris and Martin through the details of the Hammerspace global file system platform. The solution is software-defined, running either on virtual machines or in the public cloud. Customers can choose to leave data on existing hardware platforms and simply abstract the data into the Hammerspace platform, or use block storage to build out a distributed file system.

The ability to abstract the physical placement of data from metadata allows customers to choose exactly how to manage their content. Traditional storage platforms have implemented data protection or other management features at the system or hardware level. With Hammerspace, this can now be applied directly to individual files through policies.

Extensible and rich metadata also allows workflow to be applied to data in ways that couldn’t achieved before. Douglas highlights some examples in the recording, including customers with over 100 billion files.

You can find more information on the Hammerspace platform at https://hammerspace.com/ or watch the Tech Field Day recordings at https://techfieldday.com/companies/hammerspace/. Follow Hammerspace on Twitter at https://twitter.com/Hammerspace_Inc and Douglas at https://twitter.com/dfsweden.

Elapsed Time: 00:42:20

Timeline

* 00:00:00 – Intros* 00:02:45 – Hammerspace is an SDS solution, VMs or the cloud* 00:04:10 – Hammerspace can use existing data in place or block storage* 00:06:25 – How is existing data put under Hammerspace management? * 00:09:30 – Hammerspace supports multi-protocol – NFS & SMB* 00:11:00 – Metadata management is a key differentiator in Hammerspace* 00:16:00 – Does Hammerspace use underlying physical storage attributes?* 00:20:25 – Protection is assigned at the data level, not storage* 00:23:00 – Searches generate no I/O load on the underlying storage platform* 00:28:10 – What type of data is deployed on the Hammerspace platform?* 00:32:15 – What if I want to take Hammerspace out of the environment?* 00:36:00 – Migration is one use-case for the Hammerspace platform * 00:37:00 – What container-based support does Hammerspace offer? * 00:39:30 – What is the lightbulb moment?  Demos! * 00:41:00 – Wrap Up

Transcript

Related Podcasts & Blogs

* #152 – Global File System Concepts* #150 – Myriad File Systems* #75 – It’s ILM All Over Again with Chris Mellor* SFD7 – Primary Data and Data Virtualisation

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #lwfj.

In this edition of the podcast, Chris chats to Chadd Kenney, VP and Chief Technologist at Clumio. Clumio is a SaaS data protection company that has recently expanded to support Office 365 environments. This discussion covers background on Clumio, how data protection for cloud should work and some specifics of the Clumio implementation.

Looking deeper at the way in which the Clumio platform works, data from protected environments (such as VMware vSphere) lands directly on S3. This allows the solution to scale up to support thousands of concurrent backups, without needing to know that customers have increased their backup requirements.

In line with many similar offerings, Clumio now protects Office 365 data. It’s worth remembering that SaaS-based applications typically don’t provide any data protection capabilities, so customers need to put in place their own backup.

You can find out more about Clumio at https://clumio.com/

Elapsed Time: 00:30:32

Timeline

* 00:00:00 – Intros * 00:01:20 – Clumio now supports Office 365 * 00:03:25 – Protect data were it resides to avoid egress charges * 00:05:30 – Don’t run backup 24/7 (unless you need it) * 00:06:00 – SaaS backup provides air gap protection against ransomware * 00:09:20 – Define policy once and apply consistently everywhere * 00:11:05 – Backup administrators have huge power in enterprises * 00:13:00 – Leaping to cloud without a backup strategy is risky * 00:15:05 – Data is becoming more loosely coupled from the application * 00:19:20 – What is the Clumio consumption model? * 00:21:00 – Where does customer data sit? * 00:22:55 – How do you scale for unknown customer demand? * 00:23:45 – Clumio writes directly to S3 * 00:28:00 – Why protect Office 365 data? * 00:29:35 – Wrap Up

Related Podcasts & Blogs

* Backup Agents – Good or Bad?* Backup is Your Responsibility – Even in Public Cloud* Backup as a Service

Chadd’s Bio

Chadd Kenney is the Vice President and Chief Technologist at Clumio. Chadd has 20 years of experience in technology leadership roles, most recently as Vice President of Products and Solutions for Pure Storage. Prior to that role, he was the Vice President and Chief Technology Officer for the Americas helping to grow the business from zero in revenue to over a billion. Chadd also spent 8 years at EMC in various roles from Field CTO to Principal Engineer. Chadd is a technologist at heart, who loves helping customers understand the true elegance of products through simple analogies, solutions use cases, and a view into the minds of the engineers that created the solution.

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #6rcw.

Today, Hitachi Vantara announced the VSP E990, a midrange all-NVMe storage appliance. The new solution, available immediately, offers up to 5.8 million IOPS, I/O latency as low as 64µs with up to 64PB effective capacity. In this episode, Chris Evans chats remotely to Colin Gallagher about the new platform.

VSP E990 extends the existing solutions in the VSP family, from the F350 up to the 5000 series enterprise-class solutions. The “E” denotes NVMe – other platform models have “F” (flash) and “G” (general) designations. The quoted 64µs latency figure is lower than the VSP 5000 announced at NEXT last year (see the previous podcast recording on this). As a dual-controller array, E990 provides slightly better performance, shaving 6µs off the 5100 latency figures.

VSP E990 is based on the SVOS storage operating system used across all Hitachi VSP storage solutions. This provides consistency and standardisation for inter-family replication and management. VSP E990 incorporates Intelligent Data Reduction with a 4:1 “sight unseen” guarantee. The solution is also “SCM Ready”.

Chris talks to Colin about the evolution of the midrange market. As enterprise requirements change, mid-market solutions are becoming more important than ever. With this announcement, Hitachi Vantara is introducing EverFlex, a range of consumption models from purchase to “as a service”.

You can read more on the technical aspects of the E990 announcement on Colin’s blog. Here’s a link to the VSP E990 data sheet.

Elapsed Time: 00:35:41

Timeline

* 00:00:00 – Intros * 00:57:00 – What is the VSP E990? * 00:03:49 – E990 is NVMe only * 00:04:36 – E990 is 64µs compared to 70µs with VSP 5000 * 00:07:30 – SVOS runs across all platforms for consistent management * 00:09:00 – What is Intelligent Data Reduction? * 00:14:05 – What is “SCM Ready”? * 00:18:40 – What protocol support will there be? * 00:21:10 – How does the E990 fit into the portfolio? * 00:25:25 – Is the midrange market the growth storage market? * 00:28:35 – Hitachi OpsCenter 10.1 supports VSP E990 * 00:31:36 – EverFlex from Hitachi Vantara introduces new consumption models * 00:34:16 – Wrap Up

Transcript

Related Podcasts & Blogs

* #123 – Hitachi Next 2019: VSP 5000* #144 – Introduction to Storage as a Service* Hitachi Vantara Introduces VSP 5000 Series Storage Arrays

Colin’s Bio

Colin is Vice President for Digital Infrastructure Product Marketing at Hitachi Vantara where he leads product marketing for storage systems, storage software, and converged/hyper-converged solutions. Over his 25-year career he has lead marketing and product management team teams at several major storage companies. Colin has a passion for telling compelling stories about technical products that help customers solve both business...

As we head towards week 4 of lockdown in the UK, Chris and Martin reflect on the personal changes in their daily routines, as well as the implications on businesses. This has been a time for dusting off old skills (like DNS/DHCP configurations) and finding new uses for Raspberry Pis and Arduinos.

Working from home has placed significant focus on Zoom, where the attack vector for “zoombombing” has resulted in some organisations (like schools) temporarily moving away from the platform. We’re seeing the inevitability of short-term scaling, for Zoom and Microsoft with Teams.

Are cloud vendors struggling with capacity? There have been reports of delays in instance provisioning and constraints on free and educational accounts. But things aren’t all bad. Cohesity has announced another $250m in funding and since recording, VAST Data has received a $100m C-round.

How should companies be optimising in these times? The COVID-19 restrictions provide the impetus to look again at optimisation of storage platforms and virtual machine allocations. However, a quick dash to the public cloud could lead some organisations to introduce technical debt that will need resolution later.

Here’s a link to TinkerCad, mentioned by Martin.

Elapsed Time: 00:34:00

Timeline

* 00:00:00 – Intros* 00:01:00 – Martin learns the violin – almost….* 00:02:00 – Spending time redoing home IT* 00:04:30 – How many Raspberry PIs do you have?* 00:06:35 – Shortage of laptops and webcams * 00:07:10 – Zoom under pressure* 00:10:30 – Random LinkedIn connections * 00:11:40 – In-person events for 2021 already being cancelled * 00:12:50 – Will old-style networking events come back? * 00:15:00 – Vendors could learn a lot from traditional media * 00:16:27 – Are cloud vendors struggling with capacity? * 00:19:02 – Cohesity raises $250m in the current market * 00:21:00 – What tech optimisations should we be looking at? * 00:23:20 – Estate maintenance is having to change * 00:23:37 – BC/DR needs a review * 00:26:00 – What are the implications of moving workloads to the cloud? * 00:28:42 – What will cloud migrations look like in the current environment? * 00:32:00 – Wrap Up

Related Podcasts & Blogs

* Weekend Lab Work: DHCP Servers* Weekend Lab Work: DNS Servers* #149 – Coronavirus 2.0* #146 – Coronavirus and Impacts on the Technology Industry

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #rqrp.

This week, Chris and Martin are joined by Douglas Fallstrom, SVP Product & Operations at Hammerspace, as the conversation on global file systems continues. Hammerspace has developed a global file system platform that caters for geographic data dispersion and sits above traditional storage.

In this podcast episode, Douglas explains some of the challenges of stretching data over distance – typically latency and getting effective throughput. When metadata and data are abstracted in a file system, these issues can be mitigated – global data sharing doesn’t imply a need for global locking. This separation of the control and data planes is probably the most important takeaway from this episode and one we’re likely to see replicated across the storage industry.

You can learn more about Hammerspace at https://hammerspace.com/ or follow them on Twitter at https://twitter.com/hammerspace_inc. Alternatively, wait a couple of weeks and we’ll have a more detailed interview with Douglas that digs into the product a bit more.

Oh and if you’re wondering about the name – here’s where it comes from – https://en.wikipedia.org/wiki/Hammerspace

Elapsed Time: 00:33:26

Timeline

* 00:00:00 – Intros* 00:02:10 – Quick introduction to Hammerspace * 00:03:45 – Are global and parallel file systems different? * 00:07:00 – Global file systems allow “stretching” of data to global locations * 00:08:15 – Data consistency across locations is really important * 00:09:35 – Data copying can change or delete ACLs from data * 00:10:30 – What are the use-cases for global file systems? * 00:14:00 – Global sharing doesn’t imply or need global locking * 00:19:00 – With metadata, data can appear to be present without physically being there * 00:23:00 – Many data sources only change portions of file content * 00:26:30 – How does AI or ML allow physical data to be better managed? * 00:31:30 – Should we be moving file/object and away from block storage? * 00:32:45 – Wrap Up

Related Podcasts & Blogs

* #150 – Myriad File Systems* #92 – Introduction to Elastifile with Jerome McFarland* #116 – Fixing Gaps in Cloud Storage with Andy Watson

Copyright (c) 2016-2020 Storage Unpacked. No reproduction or re-use without permission. Podcast episode #0xaq.

In this episode, Martin and Chris are joined in conversation by Alex Chircop, CEO at StorageOS. The company has announced StorageOS V2.0, a significant evolution in their storage platform, built for containers using containers.

As this episode explains, the version 2.0 release of StorageOS enhances scalability and resiliency, with a strong focus on features needed for enterprise adoption. Each volume presented to a container now has a “mini-brain” to implement much more distributed application awareness.

Availability is increased through the use of Delta Sync, a new technology to ensure data volumes are recovered to a consistent state within as short a time as possible. Security has also been a big focus, with data encrypted at rest and in transit. APIs all now use authentication and there’s an internal certificate authority to mitigate the complexity of certificate management.

StorageOS is free for the first 500GB and delivered through the freemium model. Platform documentation can be found here – https://docs.storageos.com/docs/

More information on the v2.0 announcement is here in this press release and blog post. Alex references the self-evaluation guide, which can be found here along with details to register for the 500GB free access.

Alex references the CNCF storage landscape white paper developed by the CNCF Storage SIG. A copy can be found here.

Elapsed Time: 00:36:50

Timeline

* 00:00:00 – Intros* 00:01:00 – KubeCon postponed to August* 00:02:22 – What is StorageOS?* 00:05:35 – StorageOS builds in data resiliency* 00:08:25 – Container storage requires more application awareness * 00:10:15 – StorageOS scores workloads to manage physical data placement* 00:11:30 – There’s no dependency on a specific container platform* 00:13:50 – Container storage is changing the assumptions about storage requirements * 00:15:10 – What is new in StorageOS version 2? * 00:17:15 – The adoption of containers is adapting the development of StorageOS * 00:20:00 – Consistent deterministic performance is essential, even with component fluctuations  * 00:22:10 – Version 2 introduces more flexible federated capabilities 00:23:00 – StorageOS now includes much greater embedded encryption & security controls * 00:25:30 – How do customers upgrade from StorageOS v1 to v2? * 00:28:00 – What experiences and feedback is there from customers? * 00:30:10 – Storage is becoming part of the application workflow process * 00:34:45 – Call to action – where can users find more?

Transcript

Related Podcasts & Blogs

* #35 – The Spectre of Meltdown with Alex Chircop* #139 – Storage Predictions for 2020 (Part II)* Building Data Storage with Containers