ScaleIO Is Not Your Father’s SDS

Disclaimer: I recently attended Storage Field Day 13.  My flights, accommodation and other expenses were paid for by Tech Field Day and Pure Storage. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

 

I’ve written about ScaleIO before (here and here), but thought it might be useful to deliver a basic overview of what ScaleIO actually is and what it can do. You can see Dell EMC’s Storage Field Day presentation video here and you can grab a copy of my rough notes from here.

 

ScaleIO Overview

What is it?

In a nutshell, it’s a software-defined storage product that leverages captive server storage at scale.

 

Benefits

According to Dell EMC, the useful life of ScaleIO is perpetual.

  • Deploy once
  • Grow incrementally
  • No data migration
  • Rolling upgrades
  • Perpetual software licenses

 

ScaleIO Vision and Architecture

Core, Fundamental Features of ScaleIO

Configuration Flexibility

  • Hyperconverged and/or 2-layers

Highly scalable

  • 100s / 1000s of nodes

High performance / low footprint

  • Performance scales linearly
  • High I/O parallelism
  • Gets the maximum from flash media
  • Various caching options (RAM, flash)

Platform agnostic

  • Bare-metal: Linux / Windows
  • Virtual: ESX, XEN, KVM, Hyper-V

Any network

  • Slow, fast, shared, dedicated, IPv6

Flash and Magnetic

  • SSD, NVMe, PCI or HDD
  • Manual and automatic multi-tiering

Elastic / flexible / multi-tenancy

  • Add, move, remove nodes or disks “on the fly”
  • Auto-balance

Various partitioning schemes:

  • Protection-domains
  • Storage pools
  • Fault sets
  • Seamlessly move assets from one partition to another
  • QoS – bandwidth/IOPS limiter

Resilient

  • Distributed mirroring
  • Fast auto many-to-many rebuild
  • Extensive failure handling / HA
  • Background disk scanner

Secure

  • AD/LDAP, RBAC integration
  • Secure cluster formation and component authentication
  • Secure connectivity with components, secure external client communication
  • D@RE (SW, followed by SED*)

Ease of management & operation

  • GUI, CLI, REST, OpenStack Cinder, vSphere plugin and more
  • Instant maintenance mode
  • NDU

Competent Snapshots

  • Writeable, no hierarchy limits
  • Large consistency groups
  • Automatic policies*

Thin-provisioning

Space-efficient layout*

  • Fine-grain snapshots and thin-provisioning*
  • Compression*

*Soon

 

Two-ways

You can use ScaleIO in a hyperconverged configuration and a “two-layer” configuration. With hyperconverged, you can run:

  • Application and storage in the same node, where  ScaleIO is yet another application running alongside other applications
  • Asymmetric nodes, where nodes may have a different # of spindles, etc

You can also run ScaleIO in a two-layer configuration

  • app-only nodes can access ScaleIO volumes
  • app+storage – hyperconverged nodes

 

Components

ScaleIO Components

  • ScaleIO Data Client (SDC) exposes shared block volumes to the application (block device driver)
  • ScaleIO Data Server (SDS) owns local storage that contributes to the ScaleIO storage pool (daemon/service)

SDS and SDC in the same host

  • Can live together
  • SDC serves the I/O requests of the resident host applications
  • SDS serves the I/O requests of various SDCs

 

Volume Layout, Redundancy and Elasticity

A volume appears as a single object to the application.

Volume Layout (No Redundancy)

  • Chunks (1MB) are spread across the cluster in a balanced manner
  • No hot spots, no I/O splitting

2-Copy Mirror Scheme

Free and Spare Capacity

  • Free and reserved space scattered across the cluster

 

Fast, balanced and smart rebuild

Forwards Rebuild

  • Once disk/node fails – the rebuild load is balanced across all the cluster partition disks/nodes -> faster and smoother rebuild

Backwards Rebuild

  • Smart and selective transition to “backwards” rebuild (re-silvering), once a failed node is back alive
  • Short outage = small penalty

 

Elasticity, Auto-rebalance

Add: one may add nodes or disks dynamically -> the system automatically rebalances the storage

  • Old volumes can use the wider striping
  • No extra exposure
  • Most minimal data transferred

Remove: One may remove nodes / disks dynamically -> the system automatically rebalances the storage

  • Minimal data transferred in a many to many fashion

Combination: The same rebalance plan could handle additions and removals simultaneously

 

Conclusion and Further Reading

I’ve spoken to a range of people in the industry, from customers to Dell EMC folks to competitive vendors, and one thing that gets raised constantly is that Dell EMC are offering both ScaleIO and VMware vSAN. If you’ve been following along at home, you’ll know that this isn’t the first time Dell EMC have offered up products that could be seen as competing for the same market share. But I think they’re doing different things and are aimed at different use cases. My second favourite Canadian Chad Sakac explains this better than I would here.

Put this software on the right hardware (the key to any successful software defined storage product) and you’ve got something that can deliver very good block storage performance across a range of use cases. If you want to know more, Dell EMC have a pretty handy architecture overview document you can get here, and you can download a best practice white paper from here. You can also access a brief introduction to ScaleIO here (registration required). But the best bit is you can download ScaleIO for free from here.

ScaleIO.Next promises to deliver a range of new features, including space efficient storage and NVMe support. I’m curious to see the market uptake has been given the accessibility of the software. I’d also like to see what the uptake has been given the availability of ScaleIO-ready nodes based on Dell PowerEdge hardware. In any case, if you’ve got some spare tin, I recommend taking ScaleIO for a spin.

Dell EMC’s Isilon All-Flash Is Starting To Make Sense

Disclaimer: I recently attended Storage Field Day 13.  My flights, accommodation and other expenses were paid for by Tech Field Day and Pure Storage. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

 

I’ve written about Dell EMC Isilon All-Flash before (here and here). You can see Dell EMC’s Storage Field Day presentation video here and you can grab a copy of my rough notes from here.

 

The Problem?

Dell EMC’s Isilon (and OneFS) has been around for a while now, and Dell EMC tell us it offers the following advantages over competing scale-out NAS offerings:

  • Single, scalable file system;
  • Fully symmetric, clustered architecture;
  • Truly multi-protocol data lake;
  • Transparent tiering with heterogeneous clusters; and
  • Non-disruptive platform and OneFS upgrades.

While this is most likely true, the world (and its workloads) are changing. To this end, Dell EMC have been working with Isilon customers to address some key industry challenges, including:

  • Electronic Design Automation – 7nm and 3D Chip designs;
  • Life Sciences – population-scale genomics;
  • Media and Entertainment – 4K Content and Distribution; and
  • Enterprise – big data and analytics.

 

The Solution?

To cope with the ever-increasing throughput requirements, Dell EMC have developed an all-flash offering for their Isilon range of NAS devices, along with some changes in their OneFS operating environment. The idea of the “F” series of devices is that you can “start small and scale”, with capacities ranging from 72TB – 924TB (RAW) in 4RU. Dell EMC tell me you can go to over 33PB in a single file system. From a performance perspective, Dell EMC say that you can push 250K IOPS (or 15GB/s) in just 4RU and scale to 9M IOPS. These are pretty high numbers, and pointless if your editing workstation is plugged into a 1Gbps switch. But that’s generally not the case nowadays.

One of the neater resilience features that Dell EMC discussed was that the file system layout is “sled-aware” (there are 5 drive sleds per node and 20 sleds per 4RU chassis) meaning that a given file uses one drive per sled, allowing for sled removal for service without data unavailability, with these being treated as temporarily-offline drives.

 

Is All-Flash the Answer (Or Just Another Step?)

I’ve been fascinated with the storage requirements (and IT requirements in general) for media and entertainment workloads for some time. I have absolutely no real-world experience with these types of environments, and it would be silly for me to position myself as any kind of expert in the field. [I am, of course, happy for people working in M&E to get in touch with me and tell me all about what they do]. What I do have is a lot of information that tells me that the move from 2K to 4K (and 8K) is forcing people to rethink their requirements for high bandwidth storage in the ranges of capacities that studios are now starting to look at.

Whilst I was initially a little confused around the move to all-flash on the Isilon platform, the more I think about it, the more it makes sense. You’re always going to have a bunch of data hanging around that you might want to keep on-line for a long time, but it may not need to be retrieved at great speed (think “cheap and deep” storage). For this, it seems that the H (Hybrid) series of Isilon does the job, and does it well. But for workloads where large amounts of data need to be processed in a timely fashion, all-flash options are starting to make a lot more sense.

Is an all-flash offering the answer to everything? Probably not. Particularly not if you’re on a budget. And no matter how much money people have invested in the movie / TV show / whatever, I can guarantee that most of that is going to talent and content, not infrastructure. But there’s definitely a shift from spinning disk to Flash and this will continue as Flash media prices continue to fall. And then we’ll wonder how we ever did anything with those silly spinning disks. Until the next magic medium comes along. In the meantime, if you want to take OneFS for a spin, you can grab a copy of the version 8.1 simulator here. There’s also a very good Isilon overview document that I recommend you check out if that’s the kind of thing you’re into.

Dell EMC’s in the Midst of a Midrange Resurrection

Disclaimer: I recently attended Storage Field Day 13.  My flights, accommodation and other expenses were paid for by Tech Field Day and Pure Storage. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

 

Dell EMC presented on their Unity range of midrange storage at Storage Field Day 13 recently. You can see video of the presentation here, and download my rough notes from here.

 

We’re Talking About Unity, Man

All of the Software

Dell EMC have been paying attention to their customers, and all of the software for Unity is now included:

  • Block, File or VVol
  • Snapshots and AppSync Basic
  • Replication (including RecoverPoint Basic)
  • Inline compression
  • D@RE
  • AV enabler
  • QoS
  • Cloud Tiering
  • Unisphere (now running on HTML-5, die Java, die!)

There’s no need to go hunting for licenses or enablers like we had to in the VNX and CLARiiON days. This is a good thing, and tells me a lot about Dell EMC’s willingness to listen to customers when they say they want this stuff to be simple to consume without a bunch of extra costs.

 

Architecture

Dell EMC tell us that the Unity array is built on an active-active, fully redundant, dual node architecture. I can’t confirm whether this is the case or not, but I’m fairly sure that it’s an improvement on the ALUA days of yore. The Unity is also really a unified design now, with file, block or VMware Virtual Volume storage sharing the same pool of storage. Again, this is a significant improvement over the somewhat cludgy “Unified” approach that EMC took with the VNX range of arrays.

Dell EMC claim that the Unity array takes “10 minutes to install and 30 minutes to production”. I’m not sure how I feel about these numbers, and I’m not sure I’d make purchasing decisions based on how long it takes me to put some storage in a rack. Heck, I’ve worked in environments where it takes 2 hours to fill out the change request forms to deploy the arrays, and another 4 days to get these activities approved. I guess it’s nice to know that at the end of that administrative pain you could jam this gear in a rack pretty quickly and focus on other, more interesting activities.

Dell EMC are positioning the Unity as “compact and powerful: cloud integrated 500TB all-flash in 2RU”. Not unlike the Mazda3, you get a lot in a fairly compact form factor. And you likely won’t pay huge amounts for it either. Cloud integrated means a lot of things to a lot of people, but Dell EMC have been paying attention to what the likes of Pure Storage and Nimble Storage have been doing, and have delivered a pretty cool offering in CloudIQ, and I’m optimistic that the rest of Dell EMC’s tools will be following suit, if they haven’t already.

 

The Midrange Isn’t Dead

Okay, people weren’t actually saying that midrange is dead. But sometimes it feels like the focus has been on a lot of other things, like super scale out, hyper-object storage and terribly sexy, high-end all flash storage that runs to a large number of petabytes and connects directly into a port at the base of the end user’s skull. Added to that Dell EMC have had to do some careful balancing of product portfolios, and doing a pretty decent job of selling the benefits of both the Unity and SC series. I’ve had exposure to both products over time, and can see the good in each line of products. It’s not unreasonable to expect that they’ll merge in the future, but when this future will be is anyone’s guess. When Unity initially launched it felt a bit rushed (you can read my coverage here and here). Dell EMC have been working pretty hard to smooth out some of the roughness and bring to market some cool features that were missing in the first iteration of the product.

I’ve been fond of midrange arrays for a long time. The damn things tend to just run, and you can’t walk into most data centres without bumping into some kind of midrange array. Sometimes, midrange is really all you need to get the job done. And there’s no shame in that either. We’re also seeing a bunch of features that were traditionally considered “high-end” being implemented further down the stack. This should only be considered a good thing.

 

Further Reading

You can download the Unity Simulator here, and read my thoughts on Dell EMC’s midrange update from Dell EMC World 2017 here. You can also grab a copy of the Dell EMC Unity VSA from here.

 

Dell EMC World 2017 – Wrap-up and Link-o-rama

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

Here’s a quick post with links to the other posts I did surrounding Dell EMC World 2017, as well as links to other articles I found interesting.

 

Product Announcements

Here’re the posts I did covering the main announcements from the show.

Dell EMC Announces VMAX Enhancements

Dell EMC Announces Midrange Storage Line Enhancements

Dell EMC Announces XtremIO “X2”

Dell EMC Announces Isilon Update (with cameo from ECS)

Dell EMC (Pre-)Announces ScaleIO 3.0

 

Event-Related

Here’re the posts I did during the show. These were mainly from the media sessions I attended.

Dell EMC World 2017 – Monday General Session Notes

Dell EMC World 2017 – Michael Dell Q & A (and more!)

Dell EMC World 2017 – Dell Technologies Cloud Strategy Session Notes

Dell EMC World 2017 – Tuesday General Session Notes

Dell EMC World 2017 – Michael Dell Q & A – Part 2

Dell EMC World 2017 – storage.58 – Isilon.Next: Raising the Bar on Performance & Archive Use Cases Notes

Dell EMC World 2017 – storage.43 – Dell EMC Unity: Performance Analysis Deep Dive Notes

Dell EMC World 2017 – (Fairly) Full Disclosure

 

Other Links

Here’re some articles about the show written by people I know or follow (or both). They’re worth checking out (both the articles and the people).

Jon Klaus

Viva Las Vegas: See you at Dell EMC World 2017!

Workforce Transformation at Dell EMC World 2017

 

Brett Johnson

Dell EMC World 2017: All wrapped up

 

Dave Henry

Virtustream Launches Cloud Offering Designed for Healthcare

Summary of Monday’s Announcements at Dell EMC World 2017

 

Sam Shouse

ScaleIO 3.0

 

Greg Schulz

Dell EMC World 2017 Day One news announcement summary

Dell EMC Azure Stack Hybrid Cloud Solution

 

Preston de Guise

Dell EMC Integrated Data Protection Appliance

 

Chad Sakac

Dell EMC World 2017: ScaleIO 3.0!

Dell EMC World 2017: Ready Node-a-palooza!

Dell EMC World 2017: VDI Complete–Ready Bundle!

Dell EMC World 2017: RedHat Ready Bundle Update!

Dell EMC World 2017: Azure Stack Update!

Dell EMC World 2017: VxRack FLEX Updates!

Dell EMC World 2017: Cloud FLEX–I can’t believe we’re doing this!

Dell EMC World 2017: XC Series Updates!

Dell EMC World 2017: VxRail and VxRack SDDC Updates!

 

Dell EMC Announcements

Here are some of the posts from Dell EMC covering the major product announcements.

Dell EMC VMAX 950F: Raises Bar for High-End All Flash Storage

New Dell EMC PowerEdge: Bedrock of the Modern Data Center

Introducing XtremIO X2 – Next Generation All-Flash Array

Flexible Consumption Models—Transforming How IT Invests for the Future

New Dell EMC SC5020 Storage Array Offers Lowest $/GB

Dell EMC Integrated Data Protection Appliance – Innovation Without Compromise

Dell EMC Advances Data Center Grade Software-Defined Storage with ScaleIO.Next

Simplify IT Transformation with Next Gen Dell EMC Unity All-Flash Systems

Bigger. Badder. More Powerful. Dell EMC Just Reinvented #1 Scale-Out NAS Platform in the Industry

 

Conclusion

I had a hectic but enjoyable week. I would have liked the time to get to more of the technical sessions, but being given access to some of the top executives in the company was pretty neat too. Thanks again to Dell EMC (particularly Mark Browne and Sarah Vela) for having me along for the ride. Now, please enjoy this really blurry picture of Gwen Stefani.

Dell EMC World 2017 – Tuesday General Session Notes

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

These are my very rough noted from the Tuesday General Session at Dell EMC World 2017. You’ll see that they’re mainly dot points. Ideas to take away and think about if you will.

Karen Quintos takes the stage.

“IT Transformation Realized Awards” (video) – Winners are AIG, citi, Columbia Sportswear, Express Scripts, Jaguar Land Rover, Molina Healthcare.

Jeremy Burton takes the stage (Jeff Clarke can’t make it today)

  • What’s changed since 1987? A whole lot of stuff
  • Work’s not a place, it’s an activity
  • 42% of millennial will quit their job if they use substandard tech

Latitude 7285 2-in-1 with wireless charging. Available from June 1 in the US.

  • It’s not just about the tech though. People are interested in consuming PCs as a service.
  • Security – 95% of breaches occur at the endpoint
  • Technology improves by 10X every 5 years

(video)

Ken Black (Nike VP of Digital Design Transformation)

  • Creation and collaboration
  • How do you get the idea in the designer’s head out and into a product that you can consume?

Sarah Burkhart (PM, Dell Canvas)

  • VR and AR estimated to be a $35B business by 2025

Brian Mullins (CEO, @DAQRI)

  • Design hardware and software to bring augmented reality everywhere

Andy Rhodes (VP and GM of IoT)

  • IMS Evolve and Dell EMC
  • Dell EMC want to help you build the infrastructure to help you transform your workforce.

Pat Gelsinger takes the stage (@pgelsinger)

  • VMware do “real” magic – changing the world, changing the quality of people’s lives
  • Pendulum swinging – mainframe, minicomputer, client server, IoT, etc
  • Need to take control of the edge
  • IoT – plethora of edge devices, producing an extraordinary amount of data
  • VMware Pulse IoT Center – AirWatch, vROps, NSX
  • Manage, monitor and secure
  • Real-time visibility
  • VMware – addressing customers’ most complex challenges
  • And device, any app, any cloud

The core challenge is having to stitch together silos of innovation – there are too many point solutions to manage

VMware Workspace ONE – Consumer simple, enterprise secure

  • The power of HCI
  • VDI Complete – Dell EMC, VMware, Dell Technologies [High five from @sakacc]
  • Rent-A-Center – rental place
  • 14G brings out the best in vSAN
  • Dell EMC VxRack SDDC
  • VMware Cloud Foundation Momentum
  • VMware cross-cloud architecture
  • Demo of VMware on AWS
  • Pivotal and VMware
  • “Developer-ready infrastructure”

Bill Cook (President and COO, Pivotal) joins Pat on stage

Key Trends – enterprises are changing business models based on shift to cloud-native applications

  • Mobile devices and connectivity
  • Near-free computing costs
  • Global scale of operations
  • Ubiquity of embedded sensors

Speed to deployment

  • Developer – increase feature velocity, decrease spend
  • Operator – increase service levels, decrease cost
  • “You’ll be up and running in days – not weeks or months”
  • Digital transformation: “Tech is breaking out of tech”

Some interesting ideas in this session. 3.5 stars.

Dell EMC World 2017 – (Fairly) Full Disclosure

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

Here are my notes on gifts, etc, that I received as a conference attendee at Dell EMC World 2017. This is by no stretch an interesting post from a technical perspective, but it’s a way for me to track and publicly disclose what I get and how it looks when I write about various things. I’m going to do this in chronological order, as that was the easiest way for me to take notes during the week. While everyone’s situation is different, I took 5 days of training / work time to be at this event (thanks to my employer for being on board).

 

Sunday

My employer paid for my taxi to BNE airport. I flew Qantas economy class to LAX and then American Airlines to LAS. The flights were paid for by Dell EMC. Plane food was consumed on the flight. It was a generally good experience, lack of sleep notwithstanding. I stayed at the Palazzo Hotel. This was covered by Dell EMC as well.

 

Monday

I attended a vExpert / Dell EMC Elect kickoff breakfast held at the Palazzo. I had bacon, sausage and eggs, juice, coffee. Remarkably, the bacon was cooked properly, not burnt to a crisp like the Americans seem to prefer. I also picked up a great VCSA VSAN t-shirt. Thanks a bunch to VMware (and Gina Rosenthal in particular) for organising this.

I then attended press / media / influencer sessions at the conference. I picked up a Dell EMC branded 2500Ma portable battery and a bottle of water. Sarah Vela gave me a New Balance Dell EMC branded backpack and one of those useful water bottles that aren’t made of crappy plastic. For lunch I had steak, chicken and salad and another bottle of water. Dell EMC hosted a “Press, Analyst & Influencer Reception” at the pool at the Palazzo. I had some shrimp and sushi and a couple of Stella Artois beers. I also picked up a black fedora (they were giving them out for some kind of activity that I didn’t get to stay for). If it survives the trip home my eldest daughter will love it. I had dinner at Morel’s Steakhouse courtesy of ActualTech Media. I had a few Firestone PIVO beers, the filet mignon and fancy french fries, and some profiteroles for dessert.

 

Tuesday

Breakfast for press / media / influencers was held in the Solutions Expo. I had some coffee, fruit, a breakfast burrito and a bottle of water. I had lunch in the press area. This consisted of some potato salad, pasta and short ribs. Good stuff. I had a briefing with some folks from the Dell EMC Midrange team and they kindly gave me an 8GB USB stick. We had an influencer reception organised by Sarah Vela at Velveteen Rabbit and I had a few Sierra Nevada Summerfest lagers and some hors-d’oeuvres. It was a pretty cool place.

I then took a Lyft with Howard Marks and Bob Plankers (paid for by Howard) to Lotus of Siam for dinner with 20 other people. Bob bought me a large bottle of Singha while we waited in the bar for our table to be ready. We then had a variety of Thai dishes (including garlic prawns) and I had a few more Singha beers. This was paid for by a number of people (Andy Banta of NetApp, Gina Rosenthal from VMware, with Hugo Patterson from Datrium contributing the lion’s share). I then caught a Lyft back to my hotel with Howard (courtesy, once again, of Howard) and turned in for the night.

 

Wednesday

Breakfast was in the media area. It was sausage, bacon, scrambled eggs, yoghurt, orange juice and coffee. I had lunch in the media area (sensing a theme here) consisting of chicken and salad. I picked up some stuff in the Solutions Expo, including a Brocade-sponsored NVMe over Fibre Channel for Dummies book, a Cisco | Dell EMC tote bag, a Dell EMC water bottle, a Dell EMC “phone holder” and a Dell EMC World shopping bag. Not a lot of swag this year, but this aligns with my reluctance to seek it out and Dell EMC’s (and other companies’) reluctance to hand it out. Dell EMC ran a customer appreciation reception that I attended from 5 – 7pm. I had a few Shiner Light Blonde beers at this event, some prawns, and some goat’s cheese croquettes.

I was lucky enough to grab dinner at Table 10 with Edward Halteky, Brett Johnson, Alastair Cooke and Michael Davis. I had some calamari, fries (wedges) and two Firestone Walker IPA beers. vBrownBag was kind enough to pick up the tab. By the time we’d finished dinner it was almost time for the Customer Appreciation Party (featuring Gwen Stefani) to get started. We made our way to the venue and listened to Gwen pump out the hits. I had a couple of Stella Artois beers there.

 

Thursday

I skipped breakfast but did pick up 3 Dell EMC World long sleeve shirts from the lounge. Lunch at was at Public House with Michael Davis, Gina Rosenthal, Brett Johnson and Alastair Cooke. I had a hamburger, french fries and a Las Vegas Lager. We split the bill 5 ways. I then went to the final session of the conference, had a bottle of water, grabbed my bags and made my way to Las Vegas International in a cab. The taxi ride was covered by my employer.

 

Dell EMC World 2017 – storage.43 – Dell EMC Unity: Performance Analysis Deep Dive Notes

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

Here are my rough notes from the #storage.43 session. This was presented by Keith Snell and went through a lot of useful scenarios.

 

Introduction

Three uses for performance data

1. Health check

  • Performance metrics provide the ability to determine operating efficiency of the system in servicing requests.
  • Independent to block or file activity, the storage processors and disks are common contributors to performance that give us a first look at system health

2. Capacity Planning

  • Checking current resource utilisation
  • Can we incrementally add workload to existing resources?
  • Can we add hardware and workload to the system?

3. Troubleshooting

  • Object specific performance metrics provide the capability to isolate and identify areas of concern

 

Sample Period

Performance data can be presented with different sample periods – “so what?”

The larger the sample period the more “averaged” the data is

  • Reduces chance to view burst activity
  • Duration of bursts will dictate accuracy of displayed data

Performance dashboard might look different depending on time period viewed

  • Dashboard is minimum 60 second samples but can go up to 4 hours per sample (variation in performance will be averaged the sample frequency being displayed)

For the most accurate and customisable performance analysis, post processing performance archives is recommended

 

Performance Metrics and Where to Find Them

Object Unisphere Dashboard / uemcli Archive
Storage Processor Utilisation (average) Utilisation (average and per core)
LUN Response Time, IOPS, MB/s, queue Utilisation, response time, IOPS, MB/s, queue
Disk IOPS, MB/s, Service Time, queue Utilisation, IOPS, MB/s, queue
Ports IOPS, requests, MB/S IOPS, requests, MBPS
File Systems IOPS, MB/s, IO size IOPS, MB/s, IO size
FAST Cache Dirty ratio None (future)
  • Utilisation, response time and MB/s are key quality of service indicators
  • Utilisation at LUN and disk layer is available from archive data

 

Performance Dashboard

The performance dashboard is primarily used for viewing performance data from the historical database, and can be used to determine the health of the system

Time selection options customisable – time available goes back 90 days.

Sample period available

  • 60 seconds = up to 3 days of data
  • 300 seconds = up to 14 days of data
  • 3600 seconds = up to 28 days of data
  • 14400 seconds = up to 90 days of data

System level statistics

  • Port IOPS and MB/s
  • Flash LUN Statistics
  • SAS LUN Statistics
  • LUN I/O size and MB/s
  • Host I/O Limits

In Performance dashboard area of the Unity Unisphere interface.

 

UEMCLI

uemcli options for historical data

Available metrics for historical viewing

uemcli -d <IP> -u <user> -p <pwd> /metrics/metric -availability historical show

Lists all available metrics, ~77 in total.

Sample period available

  • 60 seconds = up to 3 days of data
  • 300 seconds = up to 14 days of data
  • 3600 seconds = up to 28 days of data
  • 14400 seconds = up to 90 days of data
uemcli -d <IP> -u <user> -p <pwd> /metrics/value/hist -path sp.*.storage.lun.*.totalcallsrate show -from "2017-05-10 14:25:00" -count 360 -interval 60 -output csv
uemcli -d <IP> -u <user> -p <pwd> /metrics/value/hist -path sp.*.storage.lun.*.responsetime show -from "2017-05-10 14:25:00" -count 360 -interval 60 -output csv


uemcli options for real time

Available metrics for historical viewing

uemcli -d <IP> -u <user> -p <pwd> /metrics/metric -availability real-time show

Lists all available metrics, ~580 in total.

uemcli syntax for real-time commands

/metrics/value/rt -path <value> show -interval <value> [{-period <value> | -to <value> | -count <value>} [-summary]] [-flat] [-output {nvp | csv | table [-wrap]}] [{brief | -detail}]
uemcli -d <IP> -u <user> -p <pwd> /metrics/value/rt -path sp.*.storage.lun.*.readsRate,sp.*.storage.lun.*.writesRate show -interval 30

We pick a longer interval than the minimum 5 as it can be challenging to compute / display multiple LUNs’ data in real time.

 

Performance Archives

Archives contain 1 hour of data in a SQL database format

  • Each archive is aligned to the top of the hour (e.g. coverage of 3pm to 4pm, and 4pm to 5pm)
  • Filename is data and time referenced to the start time of the archive (UTC time)
  • Partial archives are readable self contained SQL database files
  • Repository contains a minimum of 48 archives (covering 2 days of high definition performance data)

As of Unity OE 4.2, archives can be retrieved in the UI

  • Retrieving archives is currently possible via WinSCP

You can look at the structure of the archive with DB Browser for SQL Lite

  • https://www.sqlite.org/download.html
  • Export requires data manipulation to evaluate timestamp details from an offset of epoch time (also per second samples for metrics like I/O, MB, calls, etc, Object names have to be mapped to user objects where possible with embedded tables).

 

Unity Performance Archive Dump

Options

  • 1 to multiple archives
  • Output to csv format (2 variants of formatting)
  • Timesteps
  • Equated per second metrics
  • Ongoing development

Still in development. Email upad@dell.com to get early access via this.

What do I do with dumped csv data?

 

Excel

If your timestamp doesn’t show seconds, you can select column A and change format

  • Add :ss to show seconds for each sample

After selecting the entire sheet by clicking in the top corner, select insert pivot chart. That will default to the whole table.

 

Summary

  • Multiple performance data options for viewing, collection and analysis
  • Unity best practices for performance referenced for health status
  • Sample period considerations with different methods to look at data
  • Issue isolation and possible solutions considered, engaging Host I/O Limits, and rebalancing of load using dynamic pool expansion.

Keith also very kindly did a condensed version of this session for vBrownBag. You can check it out here. All in all a great way to finish of the conference. 5 stars.

Dell EMC World 2017 – storage.58 – Isilon.Next: Raising the Bar on Performance & Archive Use Cases Notes

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

Here are my rough notes from the #storage.58 session. This was presented by John Har and covered the H and A series Isilon hardware.

 

Isilon Overview

Isilon: the true scale out NAS

Has been around for 15 years

  • Single scalable namespace
  • 18TB to 65PB, 1GB/s to 140GB/s
  • Distributed filesystem across cluster, up to 144 nodes
  • No bottlenecks, no hotspots
  • Easy to manage, no RAID, LUNs or multiple FS to manage
  • Up to 89% storage efficiency

 

Transparent, optimised storage tiering

  • Reduce capital expense
  • Optimise storage
  • Transparent to users and applications
  • Flexible admin defined policies
  • Deduplication

Cloud tiering to ECS, Azure, AWS, virtustream, etc

 

Enterprise Grade Data Protection and Management

  • SnapshotIQ – Fast, efficient data backup and recovery
  • SyncIQ – Fast and flexible asynchronous replication for disaster recovery protection
  • SmartConnect – Policy-based client failover with load balancing
  • SmartLock – Policy-based compliance and WORM data protection
  • SmartDedupe – Data deduplication to reduce storage requirements and costs
  • SmartPools – Policy-based automated tiering
  • SmartQuotas – Quota management and thin provisioning
  • InsightIQ – Performance monitoring and reporting to manage storage resources
  • CloudPools – Seamlessly tier cold or frozen data to a choice of public or private cloud options
  • Access Zones – Secure separation of data for different groups or users

 

New generation architecture

  • Drive sleds future-proofed to support other drives such as NVMe
  • Compute “suitcases” – performance / cost optimised
  • Use either with IB or Ethernet (one or the other) – Isilon still owns / qualifies the back-end networking
  • Non-disruptive migration will be possible too (from InfiniBand to Ethernet)

 

Streaming image/video workflows Everywhere

Typical requirements

  • >1GB/s sequential read/write
  • GB-TB sized datasets
  • Low, stable latency <2ms

Example: M&E 4K uncompressed workflows

  • Post-production and visual effects flow
  • 5-100 artists & editors, 5K – 10K core render farm
  • 1.2GB/s per 4K uncompressed stream (73GB/min)
  • Sometimes cache on clients – data management headache

 

Solution: Work directly off Isilon

  • H600 and F800 optimised for many 1-2GB/s streams
  • Can edit and create effects directly off of H600
  • Eliminate dedicated edit storage and data movements
  • Seamless tiering with archive in same cluster – transparent to clients

Why not just use ECS for archive? ECS is great for geo-distributed, PB scale. Isilon ideal for the same site.

 

High IOPS Workloads

IOPS-intensive design, distribution, and search

Typical requirements

  • Millions of small temporary files
  • Heavy on creates and deletes
  • Metadata intensive

Example: EDA Design

Intensive, multi-staged chip design process

  • Thousands of files created (checkout)
  • Millions of temp files created
  • Simulation and verification testing
  • Millions of files deleted

10s to 100s of concurrent projects

 

Solution: Performance and density with Generation 6

  • F800 or H600 can simplify the performance tier for active design projects
  • H500 / H400 / A200 can be recent projects or DR site
  • A200 / A2000 can provide TBs to PBs of deep archive

 

Archive – You never know when you’ll need that again

Typical requirements

  • 10s – 100s of PB
  • Online and few seconds of latency
  • Moderate read throughput when data needed

 

Example: Population-scale genomics

  • Per million people – 80PB of whole genome data
  • “Variant calling” to extract population-scale insights using traditional HPC or newer Hadoop methods
  • Need performant, deep archives

 

Solution: Generation 6

H-series for single namespace of active processing

  • H600 for continuous ingest, transfers, intense HPC
  • H500/H400 for researchers

A2000 for deep archives in same namespace or separate site. Continue to tier further down to ECS for geo-collaboration

 

Closing Thoughts

  • H-series and A-series are future-proofed in performance and capacity to grow your business
  • Isilon Generation 6 delivers the optimal mix of performance, capacity and densities for every part of your workflows, new and existing
  • Existing Isilon benefits continue: single namespace, scalability and simplicity
  • Seamless data lake to Dell EMC ECS and public cloud for colder archives
  • Looking at how to replace the backup accelerators (A100)

Very useful session. 4.5 stars.

 

Dell EMC World 2017 – Michael Dell Q & A – Part 2

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

I attended an APJ-specific Q & A with Michael Dell. If find these things fascinating because they generally highlight (at least to me) how much of a grip on both the business and technology side MD has. It also reminds me that the poor guy must get a lot of silly questions every single day of the week. Also, blurry photos? I’ve got you covered.

CIOs in India are asking to delivery business value every day. How is Dell responding in terms of the new acquisition models in terms of mid-market and enterprise?

MD: You don’t do IT for fun. You do it to be more productive, enable growth. You can’t do anything without IT though. Companies are having to re-imagine their business. IT Transformation. Workforce transformation – not everything is being done with the mobile phone. But there was a “defocus” on things like PCs. They got old. Productivity fell. Having the lowest cost PC doesn’t retrain or attract good talent. And it all has to be secure. The role of IT in business has never been greater than before.

You said that HPE were shrinking their way to success last year. Has your opinion changed?

MD: We’re continuing to grow. We’ve made some big, bold choices about our business. Customers have been positive. Strong momentum in APJ.

Compare now and 5 years from now – what will be the biggest changes? And how will you do it? And what market segments do you want to win that you haven’t? 

MD: 5 years, 10 years. The SDDC will become the de facto standard. SDN is starting to emerge. Storage virtualisation is well advanced. Enables moving the focus up to the application level. Emergence of 5G cellular network. Expect it to be a global phenomenon. It’s not about phone calls. It’s about data. Low latency will lead to different kind of distributed computing. IoT, plus AI and machine learning and deep learning – it’s going to be amazing. Building the company around these new requirements. Every industry is having to re-imagine itself given this access to data. The art of the possible. Scared of new entrants showing up without that baggage too. It’s changed a lot in the last 5 – 10 years.

Which market segments?

MD: We’re focussed on infrastructure. We want to be the essential infrastructure company for the fourth industrial revolution. Pivotal is creating new kind of infrastructure for the cloud-native world. Not going to do everything, lots of partnerships and alliances.

There was a PC era, there was a smartphone era. What’s the next big thing in consumer world?

MD: From the perspective of the consumer, it will be easier to tell you what we’re not going to do. We’re not really a company that is mostly focussed on the consumer. If you’re going to sell PCs to business, the individual consumer must love them. We’re focussed on data centre, enterprise. Don’t expect voice-activated gadgets to manage your home from us.

In the run up to the merger, the company divested some software assets. Increasingly IT is all about software-defined. How are you going to continue innovating? When do you see a time when IT is a utility, if at all?

MD: Our SW business is much larger than before. We got rid of Quest, but we bought EMC (RSA, Pivotal, etc). What you saw on stage today were a lot of software products. VMware is a massively successful software company. Pivotal is a company that has created a whole ethos to create software. As for utility models, we talked about Cloud Flex program on the first day. People moving to pay by usage model. We’re happy to embrace that.

US tech giants often leave AU, etc off the guest list for major announcements. Will all this stuff be available in AU? If not, why not?

MD: We operate in 180 countries, we don’t do everything everywhere. We have a tiered approach. Australia happens to be one of those countries we focus on first. We have a global business in nature. You can expect the vast majority of this stuff to be available all over the world.

We’ve been hearing good stories about the merger. Any struggles?

MD: We’re quite happy with the way the combination has come together. Customers have observed we’ve made a lot of progress over the last 8 months. The biggest surprise was that there weren’t a lot of surprises. I don’t have a lot of complaints. Customer demand is quite strong. Integration with VMware has gone extremely well. Pivotal and VMware co-operating. Commitments from global SIs, customers. Customers would rather buy everything from one company. Humbled by reaction from customers. Over half of the mission-critical data in the world stored on Dell EMC.

Post-merger, how will the big Dell tech centres in Malaysia evolve?

MD: These centres are very important to us. Incredibly bullish about long-term growth opportunities in Asia. Big part of our past, present, and our future.

You want consumers to love the product. Why did you let Apple “flood” the market with Apple machines that people aspire to own?

MD: Apple’s marketshare recently reached a 5 year low. Our’s is a 5 year high. We aspire to have our marketshare go up.

A lot has been said about India as a big market. How big is India as a market for Dell? What are your plans for India?

MD: Was our third largest market. When combined with EMC and VMware, it wasn’t anymore. India continues to grow. Broad range of activities for Dell technologies. It’s a great place, important and will continue to be.

 

Interesting session. 4 stars.

 

Dell EMC World 2017 – Dell Technologies Cloud Strategy Session Notes

Disclaimer: I recently attended Dell EMC World 2017.  My flights, accommodation and conference pass were paid for by Dell EMC via the Dell EMC Elect program. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

I attended a media and influencer session covering Dell EMC’s Cloud Strategy. Unfortunately I wasn’t able to stay for the entire session, but I thought these notes might be useful for folks out there interested in Dell EMC’s approach to this somewhat hot topic.

 

Cloud Strategy Overview

Jeremy Burton comes on stage. “I’m very much the warmup act”. Talks briefly about Dell’s application-centric view of the world:

  • Mission-critical applications – IO intensive, requiring guarantees of resiliency
  • General-purpose applications
  • Cloud-native applications

It’s a short rehash of David Goulden’s deck from yesterday – you can find my coverage of that here.

 

Cloud Strategy Discussion

There’s then a panel, moderated by Matt Baker (Senior Vice President, Strategy and Planning, Dell EMC), and comprised of:

 

What have we learned from customers over the past decade?

DG: “Cloud isn’t a place, it’s where you’re doing things. ITaaS – that’s the simple definition. Then the whole IT landscape is moving to a cloud operating model. Always have to marry it back to customers’ applications. You need to have applications that enhance the business. Take customers on the journey.

PG: The pieces are really coming together. Virtualised compute, SDDC, CloudFoundation putting the pieces together. Converged and HCI. Validated designs and EHC. We have all the layers at a component level through to a complete integrated solution for private cloud that can be extended to the public cloud. University example where they’re operating 50/50 public and private. Announced integration of vRealize with virtustream. It’s now all realisable.
Developers are ultimately the end consumers of cloud.

JW: New set of workloads are happening. E.g. Bosch. IoT? NSX helped them, as did vSphere, EHC and PCF.
Rodney, you created a public cloud for demanding environments? How?

RR: Determined that the last thing the world needed was another sub-scale AWS. Solved a different engineering problem. Modernising the applications will happen eventually. No reason you can’t use automation and true cloud multi-tenancy for these applications. Break resources into highly granular components. Run higher utilisation per host, allowing pricing power of a public cloud. Still use throughput control providing latency guarantees.

 

What about the notion of locality? Flexible consumption options? What’s its role?

DG: Logical extension of cloud operating model. IT should be able to buy its infrastructure based on use too. Traditional models of acquisition and ownership are being challenged.

PG: NSX, heavily favoured subscription model. Huge bias that on-premises is perpetual. That is changing.
NSX is a perfect match for solving stumbling blocks to cloud adoption. Can I talk for an hour about this? We’ve seen an inflection point. Ability to move networking functions into software. Integral part of what they’re doing.

JW: NSX integration is important in PCF. Figuring out this stuff is hard. NSX-T being integrated with PCF. Vital to application / platform approach.

PG: Cloud has been a leader in modern application development aspects.

JW: We thought we wanted cloud, what we really wanted was cloud applications.

 

What about the notion of community clouds. What role do verticals play in what you’re doing at virtustream?

RR: Mission-critical applications in cloud is relatively new space. Moniker associated with SAP, but run 1000s of applicationss. Starting to “verticalise” – introducing a healthcare vertical. “Hybrid-washing is the new cloud-washing”. Mission critical in the cloud will be a $25-30B segment. Federal, public sector …

 

[Questions from the floor]

Where does DevOps fit in?

JW: Continuous ops, deployment, update. Took an app-centric view of developers infrastructure.

PG: Developers wouldn’t go to a devops conference. They’re not motivated to be operations people. They want to automate stuff to get out of the business of ops. PCF is built for Day 2 operations. Developer to Operations is measured in minutes. Home Depot, Comcast operating at scale.

 

What are you thinking about public clouds? You’re competing and working with them? Where do they really fit?

PG: Lead partners for Pivotal are AWS, IBM, Azure and Google. Cross-cloud strategy is helping them embrace the energy. The right answer is a hybrid, multi-cloud strategy moving forward. Are you going to bet on one cloud only?

 

Cost dynamics of that approach? Want to reduce the friction across those environments.

DG: Dell EMC will be the provider of the infrastructure. Be the company that solutions across Dell Technologies (e.g. EHC). On-premises marketplace is a huge opportunity.  As much cooperative as it is competitive.

PG: No one else has these relationships with the big providers.

RR: We get this a lot. It’s all about the use case. There are certain workloads that make the most sense to be placed in a hyper scale public cloud.

 

If I’m a developer for a new application today, I care about APIs and data, not infrastructure. We’re still playing with old technology – VMs / containers. Nothing like server less has emerged in the private space.

JW: The PCF paradigm – here’s the code I want to run, the services I want to bind it to. Bringing Spring CloudFunction to the Pivotal stack.

PG: Our objective is to make infrastructure frictionless, regardless of location.
David was talking about differences between SMB and Enterprise. Given the differences, how are you guys approaching SMB from a cloud perspective. And how are they using it?

PG: Some SMB customers think they’re just not at scale, so they don’t want to run infrastructure. Powerful GTM for Dell. Certain industries, it’s just not going to happen. Not one size fits all.

RR: Market segmentation will play significantly here.

 

People can be irrational. Enterprises are looking for a straightforward solution. What you’re collectively proposing may seem complex. What do you think?

PG: Initial uptake of public cloud was based on easy, not cost. We’ve now finished the easy stack in private. What’s my business model? Industry constraints? Cost options? Now you can pick the best of both.

RR: If you’re going to have a holistic solution, it is a challenge to simplify the message. Large business is where the technical idealist goes to die.

DG: It’s not a terribly complicated matrix. You might just use Enterprise Hybrid Cloud and public cloud. In each of these segments, there are complete solutions.

MB: It’s been much simplified, and we want to show you as an audience the complete solution. Partners and sales people make the choice a bit simpler when working with customers. Far simpler than it has been in the past.

 

Where do you think Boomi fits in this?

JW: PCF integration just announced.

DG: Haven’t met a customer who doesn’t need it.

RR: Working with Boomi to integrate with virtustream blueprint technologies and integrating into virtustream platform

And that’s a wrap. I unfortunately missed the customer discussion between Tom Roloff (Senior Vice President, Business & IT Transformation) and Ted Newman (Head of Cloud Services, Royal Bank of Scotland) and the “Cloud Strategy Realized” panel with:

 

Conclusion

Everyone says cloud (of whatever type) is hard. And they’re right. A few people made a big point about the focus on private cloud by Dell EMC in one of the keynotes this week. I think they’re missing the point though. Amazon will always tell you that public is best. And probably by 2025 when most applications are cloud-native, this will absolutely be true. But in the meantime, there are a shedload of enterprises and small businesses running legacy applications that don’t necessarily translate well to public cloud infrastructure. Or they can be serviced more efficiently in a private cloud scenario. I don’t have a problem with this approach at all. Dell EMC aren’t stupid. They have virtustream, and they’re working mighty hard to make sure their hybrid story is a good one. People get this idea that vendors have to be everything to everyone and when that doesn’t happen, they seem to get a bit upset. Public cloud is clearly a solid way forward for a lot of companies and their applications, but it’s not the only one. Just like not everyone is going to be a hyperscaler, not everyone is going to go all in on public cloud. I’m okay with that. And Dell EMC may change their mind next year too. If you’re looking an alternative viewpoint, you could have a look at this article on El Reg. In any case, the part of the session I attended was informative. 4 stars.