August 2015 – Silverton Consulting

#VMworld2015 day 1 announcements

It seemed like today was all about the cloud and cloud native apps. Among the many announcements, VMware announced two key new capabilities: VMware integrated containers and the ~~Python~~ Photon Platform.

Containers running on VMware

VMware vSphere Integrated Containers is an implementation of containers that runs natively under vSphere. The advantage of this solution is that now when developers fire up a multi-container app, each container now exists as a separate VM under vSphere and can be managed, monitored and secured just like any other VM in the environment. Previously a multi-container app would be one VM per container engine containing potentially many containers running under the single VM. But with vSphere Integrated Containers, the container engine and the light weight Linux kernel (~~Python~~ Photon OS) are now integrated into the ESX hypervisor so each container runs as a native VM. Integrated containers is an follow on to a combination of Project Bonneville, Project ~~Python~~ Photon (OS) and Instant clones. Recall with Instant Clones one can spin up a clone of a VM in less than a second and its memory footprint is 0MB.
~~Python~~ Photon Platform takes container execution to a whole new level, with a new deployment of a hypervisor tailor made to run containers (not VMs). With the ~~Python~~ Photon Platform one natively runs container frameworks underneath the platform. ~~Python~~ Photon Platform consists of ~~Python~~ Photon Machine which is ~~Python~~ Photon OS (lightweight Linux Kernel distro) & the new Microvisor (new light weight hypervisor for container hardware calls) and ~~Python~~ Photon Controller which is a distributed control plane and management API. With ~~Python~~ Photon Platform one can manage 100K to Millions of containers, running under 1000s of container frameworks.

Over time ~~Python~~ Photon Platform is intended to be open sourced. VMware also announced a bundling of Pivotal Cloud Foundry with the ~~Python~~ Photon Platform so as to better run cloud native apps implemented in Cloud Foundry. But the ultimate intent is to provide support for Google Kubernetes, Apache Mesos and any other container framework that comes out.

So now you can run your Docker container apps or any other container app solution in two different ways. One depends on vSphere standard management platform and runs container apps as a standard VMs. The other takes a completely green field approach and runs container frameworks natively in a ground up new hypervisor solution with a new management solution altogether that scales.

The advantage of ~~Python~~ Photon is that it scales to extreme, cloud level types of application environments. ~~Python~~ Photon is intended to run cloud-native apps.

vCloud Air extensions

One of the other major things that VMware demoed today was moving a VM from on premises to vCloud Air and back again – a real crowd pleaser. One VMware Exec said that after MIT had convinced them they needed to be able to move apps from on premises to the cloud for dev-test apps. They then turned around and decided they wanted to move dev-test activity back to their onprem environment and instead wanted to move their production to vCloud Air.

They demoed both capabilities using vMotion to move a VM to vCloud Air and using it again to move it back. The nice thing about all this is that all the security and other attributes of the VM can move to the cloud and back again along with the VM. All the while the VM continued to operate, with no disruption to execution. They mention that it could potentially take hours to move the data for the VM.

There were a number of other capabilities announced today including EVO SDDC (EVO: RACK reborn) which includes a new datacenter management solution. Customers can now roll in a rack of servers and have EVO SDDC manage them and deploy software defined data center on them in a matter of hours. Within EVO SDDC you can have application domains which span racks of servers but provide isolation and management multi-tennancy.

NSX 6.2 was also discussed and essentially is key to extending your networking from on premises to vCloud Air. With NSX 6.2 local routing, micro segmentation security and app firewalls can be configured locally and then be “extended” to the vCloud Air environment.

Lots of moving parts here and I probably missed some key components to these solutions and didn’t cover any of them well enough other than to give a feel for what they are.

But one thing is clear, VMware’s long term strategy is to take your native, on premises VMs to vCloud Air and back again as well as if your Dev-Ops group or any other BU wants to use containers to implement cloud apps, VMware has you covered coming and going.

Comments?

3D NAND, how high can it go?

Posted on August 28, 2015 by Ray in Data density, SSD storage, Strategic Inflection Points

I was at the Flash Memory Summit a couple of weeks ago and a presenter (from Hynix, I think) got up and talked about how 3D NAND was going to be the way forward for all NAND technology. I always thought we were talking about a handful of layers. But on the slide he had what looked to be a skyscraper block with 20-40 layers of NAND.

Currently shipping 3D NAND

It seems all the major NAND fabs are shipping 30+ layer 3D NAND. Samsung last year said they were shipping 32-layer 3D (V-)NAND, Toshiba announced earlier this year that they had 48-layer 3D NAND. Hynix is shipping 36-layer 3D NAND. Micron-Intel is also shipping 32-layer 3D NAND. Am I missing anyone?

Samsung also said that they will be shipping a 32GB, 48-layer V-NAND chip later this year. Apparently, Samsung is also working on 64-layer V-NAND in their labs and are getting good results. In an article on Samsung’s website they mentioned the possibility of 100 layers of NAND in a 3D stack.

The other NAND fabs are also probably looking at adding layers to their 3D NAND but aren’t talking as much about it.

Earlier this year on a GreyBeards on Storage Podcast we talked with Jim Handy, Director at Objective Analysis on what was going on in NAND fabrication. Talking with Jim was fascinating but one thing he said was that with 3D NAND, building a hole with the right depth, width and straight enough was a key challenge. At the time I was thinking a couple of layers deep. Boy was I wrong.

How high/deep can 3D NAND go?

On the podcast, Jim said he thought that 3D NAND would run out of gas around 2023. Given current press releases, it seems NAND fabs are adding ~16 layers a year to their 3D-NAND.

So if 32 to 48 layers is todays 3D-NAND and we can keep adding 16 layers/year through 2023 that’s 8 years *16 layers or an additional 128 layers to the 32 to 48 layers currently shipping. With that rate we should get to 160 to 176 layer 3D NAND chips. And if 48 layers is 32GB then we maybe we could see ~+100GB 3D NAND chips.

This of course means that there is no loss in capacity as we increase layers. Also that the industry can continue to add 16 layers/year to 3D-NAND chips.

I suppose there’s one other proviso, that nothing else comes along that is less expensive to fabricate while still providing ever increasing capacity of lightening fast, non-volatile storage (see a recent post on 3D XPoint NVM technology).

Photo Credit(s):

Flash’s only at 5% of data storage

Posted on August 14, 2015 by Ray in Energy efficiency, Internet of Things, Market dynamics, Mobile computing, SSD storage, Storage, Storage performance, Strategy, System effectiveness, Visionary leadershp

We have been hearing for years that NAND flash is at price parity with disk. But at this week’s Flash Memory Summit, Darren Thomas, VP Storage BU, Micron said at his keynote that NAND only store 5% of the bits in a data center.

Darren’s session was all about how to get flash to become more than 5% of data storage and called this “crossing the chasm”. I assume the 5% is against yearly data storage shipped.

Flash’s adoption rate

Darren, said last year flash climbed from 4% to 5% of data center storage, but he made no mention on whether flash’s adoption was accelerating. According to another of Darren’s charts, flash is expected to ship ~77B Gb of storage in 2015 and should grow to about 240B Gb by 2019.

If the ratio of flash bits shipped to data centers (vs. all flash bits shipped) holds constant then Flash should be ~15% of data storage by 2019. But this assumes data storage doesn’t grow. If we assume a 10% Y/Y CAGR for data storage, then flash would represent about ~9% of overall data storage.

Data growth at 10% could be conservative. A 2012 EE Times article said2010-2015 data growth CAGR would be 32% and IDC’s 2012 digital universe report said that between 2012 and 2020, data will double every two years, a ~44% CAGR. But both numbers could be talking about the world’s data growth, not just data center.

How to cross this chasm?

Geoffrey Moore, author of Crossing the Chasm, came up on stage as Darren discussed what he thought it would take to go beyond early adopters (visionaries) to early majority (pragmatists) and reach wider flash adoption in data center storage. (See Wikipedia article for a summary on Crossing the Chasm.)

As one example of crossing the chasm, Darren talked about the electric light bulb. At introduction it competed against candles, oil lamps, gas lamps, etc. But it was the most expensive lighting system at the time.

But when people realized that electric lights could allow you to do stuff at night and not just go to sleep, adoption took off. At that time competitors to electric bulb did provide lighting it just wasn’t that good and in fact, most people went to bed to sleep at night because the light then available was so poor.

However, the electric bulb higher performing lighting solution opened up the night to other activities.

What needs to change in NAND flash marketing?

From Darren’s perspective the problem with flash today is that marketing and sales of flash storage are all about speed, feeds and relative pricing against disk storage. But what’s needed is to discuss the disruptive benefits of flash/NAND storage that are impossible to achieve with disk today.

What are the disruptive benefits of NAND/flash storage, unrealizable with disk today.

Real time analytics and other RT applications;
More responsive mobile and data center applications;
Greener, quieter, and potentially denser data center;
Storage for mobile, IoT and other ruggedized application environments.

Only the first three above apply to data centers. And none seem as significant as opening up the night, but maybe I am missing a few.

Also the Wikipedia article cited above states that a Crossing the Chasm approach works best for disruptive or discontinuous innovations and that more continuous innovations (doesn’t cause significant behavioral change) does better with Everett Roger’s standard diffusion of innovation approaches (see Wikepedia article for more).

So is NAND flash a disruptive or continuous innovation? Darren seems firmly in the disruptive camp today.

Comments?

Photo Credit(s): 20-nanometer NAND flash chip, IntelFreePress’ photostream

A new storage benchmark – STAC-M3

Posted on August 7, 2015August 7, 2015 by Ray in Data analytics, Disk storage, SSD storage, Storage performance

A week or so ago I was reading a DDN press release that said they had just published a STAC-M3 benchmark. I had never heard of STAC or their STAC-M3 so thought I would look them up.

STAC stands for Securities Technology Analyst Center and is an organization dedicated to testing system solutions for the financial services industries.

What does STAC-M3 do

It turns out that STAC-M3 simulates processing a time (ticker tape or tick) log of security transactions and identifyies the maximum and weighted bid along with various other statistics for a number (1%) of securities over various time periods (year, quarter, week, and day) in the dataset. They call it high-speed analytics on time-series data. This is a frequent use case for systems in the securities sector.

There are two versions of the STAC-M3 benchmark: Antuco and Kanaga. The Antuco version uses a statically sized dataset and the Kanaga uses more scaleable (varying number of client threads) queries over larger datasets. For example, the Antuco version uses 1 or 10 client threads for their test measurements whereas the Kanaga version scales client threads, in some cases, from 1 to 100 threads and uses more tick data in 3 different sized datasets.

Good, bad and ugly of STAC-M3

Access to STAC-M3 reports requires a login but it’s available for free. Some details are only available after you request them which can be combersome.

One nice thing about the STAC-M3 benchmark information is that it provides a decent summary of the amount of computational time involved in all the queries it performs. From a storage perspective, if one were to take this and just analyze the queries with minimal or light computation that come closer to a pure storage workload than computationally heavy queries.

Another nice thing about the STAC-M3 is that it in some cases it provides detailed statistical information about the distribution of metrics, including mean, median, min, max and standard deviation. Unfortunately, the current version of the STAC-M3 does not provide these statistics for the computational light measures that are of primary interest to me as a storage analyst. It would be very nice to see some of their statistical level reporting be adopted by SPC, SPECsfs or Microsoft ESRP for their benchmark metrics.

STAC-M3 also provides a measure of storage efficiency, or how much storage it took to store the database. This is computed as the reference size of the dataset divided by the amount of storage it took to store the dataset. Although this could be interesting most of the benchmark reports I examined all had similar numbers for storage efficiency 171% or 172%.

The STAC-M3 benchmark is a full stack test. That is it measures the time from the point a query is issued to the point the query response is completed. Storage is just one part of this activity, computing the various statistics is another part and the database used to hold the stock tick data is another aspect of their test environment. But what is being measured is the query elapsed time. SPECsfs2014 has also recently changed over to be a full stack test, so it’s not that unusual anymore.

The other problem from a storage perspective (but not a STAC perspective) is that there is minimal write activity during any of the benchmark specific testing. There’s just one query that generates a lot of storage write activity all the rest are heavy read IO only.

Finally, there’s not a lot of description of the actual storage and server configuration available in the basic report. But this might be further detailed in the Configuration Disclosure report which you have to request permission to see.

STAC-M3 storage submissions

As it’s a stack benchmark we don’t find a lot of storage array submissions. Typical submissions include a database running on some servers with SSD-DAS or occasionally a backend storage array. In the case of DDN it was KX system’s kdb 3.2 database, with Intel Enterprise Edition servers for Lustre, with 8 Intel based DDN EXAscaler servers, talking to a DDN SFA12KX-40 storage array. In contrast, a previousr submission used an eXtremeDB Financial Edition 6.0 database running on Lucera Compute™ (16 Core SSD V2, Smart OS) nodes.

Looking back over the last couple of years of submissions (STAC-M3 goes back to 2010), forstorage arrays, aside from the latest DDN SFA12KX-40, we find an IBM FlashSystem 840, NetApp EF550, IBM FlashSystem 810, a couple of other DDN SFA12K-40 storage solutions, and a Violin V3210 & V3220 submission. Most of the storage array submissions were all-flash arrays, but the DDN SFA12KX-40 is a hybrid (flash-disk) appliance.

Some metrics from recent STAC-M3 storage array runs

In the above chart, we show the Maximum MBPS achieved in the year long high bid (YRHIBID) extraction testcase. DDN won this one handily with over 10GB/sec for its extraction result.

However in the next chart, we show the Mean Response (query elapsed) Time (in msec.) for the query that extracts the Year long High Bid data extraction test (YRHIBID). In this case the IBM FlashSystem 810 did much better than the DDN or even the more recent IBM FlashSystem 840.

Unexpectedly, the top MBPS storage didn’t achieve the best mean response time for the YRHIBID query. I would have thought the mean response time and the maximum MBPS would show the same rankings. Not clear to me why this is, it’s the mean response time not minimum or maximum. Although the maximum response time would show the same rankings. An issue with the YRHIBID is that it doesn’t report standard deviation, median or minimum response time results. Having these other metrics might have shed some more light on this anomaly but for now this is all we have.

If anyone knows of other storage (or stack) level benchmarks for other verticals please let me know and I would be glad to dig into them to see if they provide some interesting viwes on storage performance.

Comments?

Photo Credit(s): Stock market quotes in newspaper by Andreas Poike