Hike blogging: 07-17-2017

by Robin Harris on Monday, 17 July, 2017

Hike blogging has been on hiatus for several reasons, including no good pictures, packing up for a short move, too much rain – it’s monsoon time now – and I’ve been getting back to biking as well.

But this morning got out at 630 on to the Twin Buttes/Hog Heaven/Hog Wash loop. It’s about 4.5 miles, with about 370 feet of vertical.

The Hog Heaven portion is a double black diamond mountain bike trail. Given that I find it a little hairy on foot, I can’t imagine how skilled – or crazy – you have to be to bike it.

But the views were fabulous in the early morning light. Here’s one:

Click to enlarge.

The StorageMojo take
Let me know if you come to town. It’s a beautiful place and well worth a visit. Happy to recommend hikes and places to go in town for food, wine, music, and art.

Courteous comments welcome, of course.


Flash Memory Summit next month

by Robin Harris on Monday, 17 July, 2017

StorageMojo’s crack analyst team will be attending next months Flash Memory Summit. The dates are August 8-10, at the Santa Clara Convention Center.

Wasn’t able to attend last year, but the 2015 summit was the best storage show I’d seen in years. Flash is where the action is, with NVRAM coming along as well.

I’ve got a couple of meetings scheduled, but if your company is doing something early stage, I’d like to talk to you. Comment below to set up a meeting. I won’t publish invites.

The StorageMojo take
With flash products moving into maturity, StorageMojo is really interested in NVRAM technologies and in how they are affecting system architectures. Especially interested in emerging concepts.

Courteous comments welcome, of course.


The moving target problem

by Robin Harris on Tuesday, 11 July, 2017

With the news that Toshiba has developed 3D quad-level cell flash with 768Gb die capacity, I’m reminded of the moving target problem. This is a problem whenever a new technology seeks to carve out a piece of an existing technology’s market.

Typically, a startup seeks funding based on producing a competitive product in, say, two years. Good analysis will allow for the fact that competition will improve, typically based on then-current improvement trends.

Often two things happen to derail the projections. The most likely is that the new product development cycle slips out, so when the product ships it is up against another 6-18 months of incumbent improvement.

But sometimes the pace of incumbent improvement rises, so even if the newtech meets its schedule projections – when does THAT ever happen? – it is still facing a tougher competitor than planned.

Disk vs flash
Flash had this problem for a couple of decades with disk. In the early 90s I bought an HP Omnibook 300 and forked over another $400 for a 10MB Compact Flash card to replace the power hungry disk. Some flash proponents probably hoped this was the beginning of a trend.

But it was not to be. Disk vendors discovered how to increase bit density on a regular basis, and disk capacities and areal densities started rising at ≈40% a year. They also built rugged 2.5″ drives for the burgeoning notebook market, and invested in power-saving technologies.

That helped keep flash at bay for another 15 years.

But finally, the flash cost-per-bit dropped below that of DRAM, and the floodgates opened. Flash won the smartphone market, which powered investment in huge fabs, and soon flash prices were dropping faster than disks.

But the key was that flash found niches that disks could not serve. And when one of those niches exploded into industry-altering size, the economics of critical mass and mass production kicked in.

I’ve been following NVRAM with great interest for years. That’s partly due to interest in what it could mean for system architecture, but also for its potential as a substitute for flash.

While it’s clear that the NAND flash cost advantage is good for the next decade, it’s also clear that flash has been shoehorned into applications – such as caches – for which it is suboptimal. NVRAM will encroach around the edges of the flash market, not the heart.

MRAM, for example, is already doing a good business in the automotive and mil-spec sectors, because it is really tough. Diablo’s current hybrid NVDIMMs – combo DRAM and flash – could certainly benefit from a pure NVRAM solution if the price was right.

The key is that NVRAM’s sweet spot is well away from flash’s cost-per-bit and density sweet spots. A fact that Toshiba’s announcement exemplifies.

The StorageMojo take
Watching how flash and NVRAM interact in the marketplace over the next decade will be instructive for students of technology diffusion. The two technologies are close in some ways, but differ dramatically in others, so simple flash out/NVRAM in stories are will be the exception.

That also ignores the potential creativity of architects and engineers as they explore the capabilities of new kinds of NVRAM. Or the potential for a new class of devices that drive NVRAM adoption, as the smartphone drove flash.

In any case the calculus of the moving target will remain. To the nimble go the spoils.

Courteous comments welcome, of course.


Why startups fail

by Robin Harris on Wednesday, 21 June, 2017

A great piece at CB Insights. They collected the failure stories of 101 startups and then broke those failures into 20 categories.

Spoiler alert!
Here are the top 10 reasons for failure, as compiled by CB Insights.

Click to enlarge.

What I find interesting is that 8 of the top 10 reasons are marketing related.

  • No market need.
  • Get outcompeted.
  • Pricing, cost issues.
  • Poor product.
  • Need, lack, business model.
  • Poor marketing.
  • Ignore customers.
  • Product mis-timed.

Across the cultural divide
Tech founders tend to be techies, and techies tend to have a problem with folks of the sales/marketing persuasion. One problem is that many marketing people don’t really understand the technology they are marketing, which means they can’t be full partners to the tech team.

Another problem is that marketing people tend to be well-versed in the arts of persuasion. If the marketer takes a position, especially in regards to technology they don’t appreciate, they can easily steer the startup in the wrong direction.

Plus, every techie has a story where they’ve felt misled by a sales or marketing person, and that anger or regret can bleed into professional relationships in a startup.

Finally, techies rarely have a handle on what to look for in their marketing hires. Based on more than 35 years experience, StorageMojo has a suggestion.

The StorageMojo take
My sympathies are with the engineers when it comes to their feelings about marketing. As I said in the link above:

They’d get flayed for every decommit and slip. They’d sweat blood figuring out solutions to hundreds of subtle problems.

Then, after 2 to 3 years of effort, they’d deliver the product to marketing and, all too often, watch their hard work go for naught.

Maybe marketing missed some key features. Didn’t position the product properly. Training failed to equip the field. Mis-pricing. Tougher competition than expected.

That last paragraph captures many of the issues that CB Insights survey did. Which shouldn’t be a surprise.

Startups exist to sell a product. Development is only a means to that end.

Courteous comments welcome, of course. Disclosure: I offer services to help startups with every phase of product development.


A transaction processing system for NVRAM

by Robin Harris on Monday, 19 June, 2017

Adapting to NVRAM is going to be a lengthy process. This was pointed out by a recent paper. More on that later.

Thankfully, Intel wildly pre-announced 3D XPoint. That has spurred OS and application vendors to consider how it might affect their products.

As we saw with the adoption of SSDs, it takes time to unravel the assumptions built into products. Take databases: they spent decades optimizing for hard drives, and when SSDs came along many of those optimizations became detrimental.

Durable transactions
On the face of it it shouldn’t be that hard. You want a durable transaction, you have persistant NVRAM. Are we good here?


In a paper published by Microsoft Research, DUDETM: Building Durable Transactions with Decoupling for Persistent Memory, the authors (Mengxing Liu, Mingxing Zhang, Kang Chen, Xuehai Qian, Yongwei Wu, Jinglei Ren) go into the issues:

While persistent memory provides non-volatility, it is challenging for an application to ensure correct recovery from the persistent data on a system crash, namely, crash consistency. A solution . . . is using crash-consistent durable transaction[s]. . . .

Most implementations of durable transactions enforce crash consistency through logging. However, the. . . dilemma between undo and redo logging is essentially a trade-off between update redirection cost and persist ordering cost.

The authors make a bold claim:

[O]ur investigation demonstrates that it is possible to make the best of both worlds while supporting both dynamic and static transactions. The key insight of our solution is decoupling a durable transaction into three fully asynchronous steps.

To create a fully decoupled transaction system for NVRAM, the researchers made three key design decisions.

  • A single, shared, cross-transaction shadow memory.
  • An out of the box Transaction Memory.
  • A redo log as the only way to transfer updates from shadow memory to persistent memory.

These design choices enabled building an ACID transaction in three decoupled, asynchronous, steps.

  • Perform: execute the transaction in a shadow memory, and produce a redo log for the transaction.
  • Persist: flush the redo log of each transaction to persistent memory in an atomic manner.
  • Reproduce: modify original data in persistent memory according to the persisted redo log.

The paper is lengthy and a recommended read for those professionally interested in transaction processing on NVRAM. But here’s their performance summary.

Our evaluation results show that DUDETM adds guarantees of crash consistency and durability to TinySTM by adding only 7.4% ∼ 24.6% overhead, and is 1.7× to 4.4× faster than existing works Mnemosyne and NVML.

The StorageMojo take
As we’ve seen with the transition from hard drives to SSDs, unwinding decades of engineered-in assumptions in the rest of stack is a matter of years, not months. There’s the issue of rearchitecting basic systems, such as transaction processing, or databases, and then the hard work of stepwise enhancement of those new architectures as we gain knowledge about how they intersect with the new technology and workloads.

There are going to be many opportunities for startups that focus on NVRAM. The technology is coming quickly and with more technology diversity – there are several types of NVRAM already available, with more on the way, and each has different trade-offs – which means that the opportunities for creativity are legion.

Courteous comments welcome, of course.


A distributed fabric for rack scale computing

by Robin Harris on Monday, 12 June, 2017

After years of skepticism about rack scale design (RSD), StorageMojo is coming around to the idea that could will work. It’s still a lab project, but researchers are making serious progress on the architectural issues.

For example, in a recent paper, XFabric: A Reconfigurable In-Rack Network for Rack-Scale Computers Microsoft Researchers Sergey Legtchenko, Nicholas Chen, Hugh Williams, Daniel Cletheroe, Antony Rowstron, and Xiaohan Zhao, discuss

. . . a rack-scale network that reconfigures the topology and uplink placement using a circuit-switched physical layer over which SoCs perform packet switching. To satisfy tight power and space requirements in the rack, XFabric does not use a single large circuit switch, instead relying on a set of independent smaller circuit switches.

The network problem
My concerns around RSD have always centered on the network. It’s obvious that Moore’s Law is making more powerful and efficient Systems on a Chip (SoCs) more attractive. And flash has eliminated many issues around storage, particularly power, cooling, weight, and density – while cost is steadily improving.

Which leaves the network. Network bandwidth is much more costly than internal server bandwidth, and, due to the bursty nature of traffic, much more likely to constrain overall system performance.

Which, in a nutshell, is the business justification for hyperconverged infrastructure: blocks of compute, memory & storage using cheap internal bandwidth; with Ethernet interconnecting the blocks. But today we can have a couple of thousand microservers in a rack.

Now if we could only figure out how to network them at reasonable cost and performance. Traditional Top-of-Rack (ToR) switches are costly and don’t scale well.

Higher server density requires a redesign of the in-rack network. A fully provisioned 40 Gbps network with 300 SoCs would require a ToR switch with 12 Tbps of bisection bandwidth within a rack enclosure which imposes power, cooling and physical space constraints.

Fully distributed networks are much cheaper, but inflexible. That’s why HPE’s Moonshot uses three network topologies, one for ingress/egress traffic, multi-hop for storage and a 2D torus fabric for in-rack traffic.

The XFabric answer
With XFabric the MR team decided to split the difference.

. . . XFabric uses partial reconfigurability. It partitions the physical layer into a set of smaller independent circuit switches such that each SoC has a port attached to each partition. Packets can be routed between the partitions by the packet switches embedded in the SoCs. The partitioning significantly reduces the circuit switch port requirements enabling a single cross point switch ASIC to be used per partition. This makes XFabric deployable in a rack at reasonable cost.

Of course, you then have to deal with the fact that the fabric is not fully configurable. Which is the XFabric secret sauce.

XFabric uses a novel topology generation algorithm that is optimized to generate a topology and determine which circuits should be established per partition. It also generates the appropriate forwarding tables for each SoC packet switch. The algorithm is efficient, and XFabric can instantiate topologies frequently, e.g. every second at a scale of hundreds of SoCs, if required.

The team modeled XFabric on a test bed and the results were stunning:

The results show that under realistic workload assumptions, the performance of XFabric is up to six times better than a static 3D-Torus topology at rack scale. We also show it provides comparable performance to a fully reconfigurable network while consuming five times less power.

The StorageMojo take
With the work being done on PCIe fabrics, I/O stack routing, composable infrastructure, and resiliance in distributed storage, we are reaching a critical mass of basic research that points to a paradigm-busting architecture for RSD. In 10 years today’s state-of-the-art hyperconverged systems will look like a Model T Ford sitting next to a LaFerrari Aperta.

A key implication of RSD is that it will favor warehouse scale systems. That’s good news for cloud vendors.

But if RSD is as configurable as the current products and research suggests, it will also find a home in the enterprise. The tension that exists today between object storage in the cloud and object storage in the enterprise will govern enterprise adoption.

But that’s a topic for another post.

Courteous comments welcome, of course.

{ 1 comment }

Infinidat sweetens All Flash Array Challenge

June 6, 2017

In response to yesterday’s StorageMojo post on Infinidat, Brian Carmody of Infinidat tweeted: Robin, Verde Valley is a great organization. @INFINIDAT will donate $10K for every Infinidat Challenge customer who mentions your blog post. — Brian Carmody (@initzero) June 5, 2017 Thanks, Brian! The StorageMojo take Verde Valley Sanctuary is a fine organization that StorageMojo […]

0 comments Read the full article →

Infinidat’s sweet AFA challenge

June 5, 2017

StorageMojo has observed, many times, that great marketing of a mediocre product beats mediocre marketing of a great product all the time. Thus it is always of interest when someone comes up with an innovative marketing wrinkle. That’s what Infinidat has done with their Faster than all flash challenge. Their claim is that their system […]

5 comments Read the full article →

Hike blogging: Devils Creek Road

June 3, 2017

Taking a vacation from the usual slog in NoAZ. I’m some 60 miles north of Seattle, working on my rain tan. The weatherman claims we’ll break 70 degrees sometime during my visit, but I’m not counting on it. Occasional patches of blue sky remind me of what is possible, if not likely. Took a 4.5 […]

0 comments Read the full article →

Routing the I/O stack

May 30, 2017

Lots of energy around the concept of Rack Scale Design (Intel’s nomenclature) in systems design these days. Instead of depositing a cpu, memory, I/O, and storage on a single motherboard, why not have a rack of each, interconnected over a high-bandwidth, low-latency network – PCIe is favored today – and use software to define bundles […]

6 comments Read the full article →

Liqid’s composable infrastructure

May 8, 2017

The technology wheel is turning again. Yesterday it was converged and hyperconverged infrastructure. Tomorrow it’s composable infrastructure. Check out Liqid a software-and-some-hardware company that I met at NAB. The software – Element – enables you to configure custom servers from hardware pools of compute, network, and, of course, storage. I met Liqid co-founder Sumit Puri […]

1 comment Read the full article →

NAB 2017 storage roundup

May 4, 2017

Spent two days at the annual National Association of Broadcasters (NAB) confab in Las Vegas. With 4k video everywhere, storage was a hot topic as well. Here’s what caught my eye. Object storage – often optimized for large files – continues to be a growth area. Scality, Dynamic Data Pool, Object Matrix, HGST, Data IO, […]

0 comments Read the full article →

Is NetApp still doomed?

April 20, 2017

A reader wrote to ask for the StorageMojo take on NetApp now, as opposed to the assessment in How doomed is NetApp? two years ago. Q3 had some good news for NetApp. In their latest 10Q filing, they noted that while revenues for the first 9 months of the year were down 3%, for the […]

2 comments Read the full article →

Spin Transfer Technologies: next up in the MRAM race

April 19, 2017

MRAM technology is hot. I’ve written about Everspin – they’ve been shipping for years and just IPO’d – and now I’d like to introduce Spin Transfer Technologies. They’ve kept a low profile – they AREN’T shipping, are sampling protos, and they do have some nice Powerpoints. I spoke to their CEO, Barry Hoberman, and the […]

2 comments Read the full article →

Sizing the overconfig effect on the array market

March 30, 2017

For decades customers routinely overconfigured storage arrays to get performance. Customers bought the most costly hard drives – 15k SAS or FC – at huge markups. Then they’d short stroke the already limited capacity of these high cost drives – turning a 900GB drive into a, say, 300GB drive – in order to goose IOPS […]

3 comments Read the full article →