Tag Archives: disaggregation

Disaggregation and Composability vital for AI/DL models to scale

By | | , , , , , , , , , , , , , , , , , , , , , , , ,
Leave a comment

New generations of applications and workloads like AI/DL (Artificial Intelligence/Deep Learning), and HPC (High Performance Computing) are breaking the seams of entrenched storage infrastructure models and frameworks. We cannot continue to scale-up or scale-out the storage infrastructure to meet these inundating fluctuating I/O demands. It is time to look at another storage architecture type of infrastructure technology – Composable Infrastructure Architecture.

Infrastructure is changing. The previous staid infrastructure architecture parts of compute, network and storage have long been thrown of the window, precipitated by the rise of x86 server virtualization almost 20 years now. It triggered a tsunami of virtualizing everything, including storage virtualization, which eventually found a more current nomenclature – Software Defined Storage. Both storage virtualization and software defined storage (SDS) are similar and yet different and should be revered through different contexts and similar goals. This Tech Target article laid out both nicely.

As virtualization raged on, converged infrastructure (CI) which evolved into hyperconverged infrastructure (HCI) went fever pitch for a while. Companies like Maxta, Pivot3, Atlantis, are pretty much gone, with HPE® Simplivity and Cisco® Hyperflex occasionally blipped in my radar. In a market that matured very fast, HCI is now dominated by Nutanix™ and VMware®, with smaller Microsoft®, Dell EMC® following them.

From HCI, the attention of virtualization has shifted something more granular, more scalable in containerization. Despite a degree of complexity, containerization is taking agility and scalability to the next level. Kubernetes, Dockers are now mainstay nomenclature of infrastructure engineers and DevOps. So what is driving composable infrastructure? Have we reached the end of virtualization? Not really.

Evolution of infrastructure. Source: IDC

It is just that one part of the infrastructure landscape is changing. This new generation of AI/ML workloads are flipping the coin to the other side of virtualization. As we see the diagram above, IDC brought this mindset change to get us to Think Composability, the next phase of Infrastructure.

Continue reading →

The burgeoning world of NVMe

By | | , , , , , , , , , , , , , , , , ,
1 Comment

When I wrote this article “Let’s smoke this storage peace pipe” 5 years ago, I quoted:

“NVMe® and NVM®eF‰, as it evolves, can become the Great Peacemaker and bringing both divides and uniting them into a single storage fabric.“

I envisioned NVMe® and NVMe®oF™ setting the equilibrium at the storage architecture level, finishing the great storage fabric into one. This balance in the storage ecosystem at the storage interface specifications and language-protocol level has rapidly unifying storage today, and we are already seeing the end-to-end NVMe paths directly from the PCIe bus of one host to another, via networks over Ethernet (with RoCE, iWARP, and TCP flavours) and Fibre Channel™. Technically we can have an end point device, example a tablet, talking the same NVMe language to its embedded storage as well as a cloud NVMe storage in an exascale storage far, far away. In the past, there were just too many bridges, links, viaducts, aqueducts, bypasses, tunnels, flyovers to cross just to deliver a storage command, or a data in a formats, encased and encoded (and decoded) in so many different ways.

Colours in equilibrium, like the rainbow

Simple basics of NVMe®

SATA (Serial Attached ATA) and SAS (Serial Attached SCSI) are not optimized for solid state devices. besides legacy stuff like AHCI (Advanced Host Controller Interface) in SATA, and archaic SCSI-3 primitives in SAS, NVM® has so much to offer. It can achieve very high bandwidth and support 65,535 I/O queues, each with a queue depth of 65,535. The queue depth alone is a massive jump compared to SAS which has a queue depth limit of 256.

A big part of this is how NVMe® handles I/O processing. It has a submission queue (SQ) and a completion queue (CQ), and together they are know as a Queue Pair (QP). The NVMe® controller handles tens of thousands at I/Os (reads and writes) simultaneously, alerted to switch between each SQ and CQ very quickly using the MSI or MSI-X interrupt. Think of MSI and MSI-X as a service bell, a hardware register that informs the NVM® controller when there are requests in the SQ, and informs the hosts that there are completed requests in the CQ. There will be plenty of “dings” by the MSI-X service register but the NVMe® controller can perform it very well, with some smart interrupt coalescing.

NVMe I/O processing

NVMe® 1.1, as I recalled, used to be have 3 admin commands and 10 base commands, which made it very lightweight compared to SCSI-3. However, newer commands were added to NVMe® 2.0 specifications included command sets fo key-value operations and zoned named space.

Continue reading →

Storageless shan’t be thy name

By | | , , , , , , , , , , , , , , , , , , , ,
2 Comments

Storageless??? What kind of a tech jargon is that???

This latest jargon irked me. Storage vendor NetApp® (through its acquisition of Spot) and Hammerspace, a metadata-driven storage agnostic orchestration technology company, have begun touting the “storageless” tech jargon in hope that it will become an industry buzzword. Once again, the hype cycle jargon junkies are hard at work.

Clear, empty storage containers

Clear, nondescript storage containers

It is obvious that the storageless jargon wants to ride on the hype of serverless computing, an abstraction method of computing resources where the allocation and the consumption of resources are defined by pieces of programmatic code of the running application. The “calling” of the underlying resources are based on the application’s code, and thus, rendering the computing resources invisible, insignificant and not sexy.

My stand

Among the 3 main infrastructure technology – compute, network, storage, storage technology is a bit of a science and a bit of dark magic. It is complex and that is what makes storage technology so beautiful. The constant innovation and technology advancement continue to make storage as a data services platform relentlessly interesting.

Cloud, Kubernetes and many data-as-a-service platforms require strong persistent storage. As defined by NIST Definition of Cloud Computing, the 4 of the 5 tenets – on-demand self-service, resource pooling, rapid elasticity, measured service – demand storage to be abstracted. Therefore, I am all for abstraction of storage resources from the data services platform.

But the storageless jargon is doing a great disservice. It is not helping. It does not lend its weight glorifying the innovations of storage. In fact, IMHO, it felt like a weighted anchor sinking storage into the deepest depth, invisible, insignificant and not sexy. I am here dutifully to promote and evangelize storage innovations, and I am duly unimpressed with such a jargon.

Continue reading →

Scaling new HPC with Composable Architecture

By | | , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
2 Comments

[Disclosure: I was invited by Dell Technologies as a delegate to their Dell Technologies World 2019 Conference from Apr 29-May 1, 2019 in the Las Vegas USA. Tech Field Day Extra was an included activity as part of the Dell Technologies World. My expenses, travel, accommodation and conference fees were covered by Dell Technologies, the organizer and I was not obligated to blog or promote their technologies presented at this event. The content of this blog is of my own opinions and views]

Deep Learning, Neural Networks, Machine Learning and subsequently Artificial Intelligence (AI) are the new generation of applications and workloads to the commercial HPC systems. Different from the traditional, more scientific and engineering HPC workloads, I have written about the new dawn of supercomputing and the attractive posture of commercial HPC.

Don’t be idle

From the business perspective, the investment of HPC systems is high most of the time, and justifying it to the executives and the investors is not easy. Therefore, it is critical to keep feeding the HPC systems and significantly minimize the idle times for compute, GPUs, network and storage.

However, almost all HPC systems today are inflexible. Once assigned to a project, the resources pretty much stay with the project, even when the workload processing of the project is idle and waiting. Of course, we have to bear in mind that not all resources are fully abstracted, virtualized and software-defined whereby you can carve out pieces of the hardware and deliver a percentage of that resource. Case in point is the CPU, where you cannot assign certain clock cycles of CPU to one project and another half to the other. The technology isn’t there yet. Certain resources like GPU is going down the path of Virtual GPU, and into the realm of resource disaggregation. Eventually, all resources of the HPC systems – CPU, memory, FPGA, GPU, PCIe channels, NVMe paths, IOPS, bandwidth, burst buffers etc – should be disaggregated and pooled for disparate applications and workloads based on demands of usage, time and performance.

Hence we are beginning to see the disaggregated HPC systems resources composed and built up the meet the diverse mix and needs of HPC applications and workloads. This is even more acute when a AI project might grow cold, but the training of AL/ML/DL workloads continues to stay hot

Liqid the early leader in Composable Architecture

Continue reading →

Disaggregation or hyperconvergence?

By | | , , , , , , , , , , , , , , , , , , , , ,
1 Comment

[Preamble: I have been invited by  GestaltIT as a delegate to their TechFieldDay from Oct 17-19, 2018 in the Silicon Valley USA. My expenses, travel and accommodation are covered by GestaltIT, the organizer and I was not obligated to blog or promote their technologies presented at this event. The content of this blog is of my own opinions and views]

There is an argument about NetApp‘s HCI (hyperconverged infrastructure). It is not really a hyperconverged product at all, according to one school of thought. Maybe NetApp is just riding on the hyperconvergence marketing coat tails, and just wanted to be associated to the HCI hot streak. In the same spectrum of argument, Datrium decided to call their technology open convergence, clearly trying not to be related to hyperconvergence.

Hyperconvergence has been enjoying a period of renaissance for a few years now. Leaders like Nutanix, VMware vSAN, Cisco Hyperflex and HPE Simplivity have been dominating the scene, and touting great IT benefits and eliminating IT efficiencies. But in these technologies, performance and capacity are tightly intertwined. That means that in each of the individual hyperconverged nodes, typically starting with a trio of nodes, the processing power and the storage capacity comes together. You have to accept both resources as a node. If you want more processing power, you get the additional storage capacity that comes with that node. If you want more storage capacity, you get more processing power whether you like it or not. This means, you get underutilized resources over time, and definitely not rightsized for the job.

And here in Malaysia, we have seen vendors throw in hyperconverged infrastructure solutions for every single requirement. That was why I wrote a piece about some zealots of hyperconverged solutions 3+ years ago. When you think you have a magical hammer, every problem is a nail. 😉

In my radar, NetApp and Datrium are the only 2 vendors that offer separate nodes for compute processing and storage capacity and still fall within the hyperconverged space. This approach obviously benefits the IT planners and the IT architects, and the customers too because they get what they want for their business. However, the disaggregation of compute processing and storage leads to the argument of whether these 2 companies belong to the hyperconverged infrastructure category.

Continue reading →