Category Archives: Composable Infrastructure

AI and the Data Factory

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

When I first heard of the word “AI Factory”, the world was blaring Jensen Huang‘s keynote at NVIDIA GTC24. I thought those were cool words, since he mentioned about the raw material of water going into the factory to produce electricity. The analogy was spot on for the AI we are building.

As I engage with many DDN partners and end users in the region, week in, week out, the “AI Factory” word keeps popping into conversations. Yet, many still do not know how to go about building this “AI Factory”. They only know they need to buy GPUs, lots of them. These companies’ AI ambitions are unabated. And IDC predicts that worldwide spending on AI will double by 2028, and yet, the ROI (returns on investment) remains elusive.

At the ground level, based on many conversations so far, the common theme is, the steps to begin building the AI Factory are ambiguous and fuzzy to most. I like to share my views from a data storage point of view. Hence, my take on the Data Factory for AI.

Are you AI-ready?

We have to have a plan but before we take the first step, we must look at where we are standing at the present moment. We know that to train AI, the proverbial step is, we need lots of data. Deep Learning (DL) works with Large Language Models (LLMs), and Generative AI (GenAI), needs tons of data.

If the company knows where they are, they will know which phase is next. So, in the AI Maturity Model (I simplified the diagram below), where is your company now? Are you AI-ready?

Simplified AI Maturity Model

Get the Data Strategy Right

In his interview with CRN, MinIO’s CEO AB Periasamy quoted “For generative AI, they realized that buying more GPUs without a coherent data strategy meant GPUs are going to idle out”. I was struck by his wisdom about having a coherent data strategy because that is absolutely true. This is my starting point. Having the Right Data Strategy.

In the AI world, from a data storage guy, data is the fuel. Data is the raw material that Jensen alluded to, if it was obvious. We have heard this anecdotal quote many times before, even before the AI phenomenon took over. AI is data-driven. Data is vital for the ROI of AI projects. And thus, we must look from the point of the data to make the AI Factory successful.

Continue reading →

Preliminary Data Taxonomy at ingestion. An opportunity for Computational Storage

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

Data governance has been on my mind a lot lately. With all the incessant talks and hype about Artificial Intelligence, the true value of AI comes from good data. Therefore, it is vital for any organization embarking on their AI journey to have good quality data. And the journey of the lifecycle of data in an organization starts at the point of ingestion, the data source of how data is either created, acquired to be presented up into the processing workflow and data pipelines for AI training and onwards to AI applications.

In biology, taxonomy is the scientific study and practice of naming, defining and classifying biological organisms based on shared characteristics.

And so, begins my argument of meshing these 3 topics together – data ingestion, data taxonomy and with Computational Storage. Here goes my storage punditry.

Data Taxonomy in post-injection 

I see that data, any data, has to arrive at a repository first before they are given meaning, context, specifications. These requirements are different from file permissions, ownerships, ctime and atime timestamps, the content of the ingested data stream are made to fit into the mould of the repository the data is written to. Metadata about the content of the data gives the data meaning, context and most importantly, value as it is used within the data lifecycle. However, the metadata tagging, and preparing the data in the ETL (extract load transform) or the ELT (extract load transform) process are only applied post-ingestion. This data preparation phase, in which data is enriched with content metadata, tagging, taxonomy and classification, is expensive, in term of resources, time and currency.

Elements of a modern event-driven architecture including data ingestion (Credit: Qlik)

Even in the burgeoning times of open table formats (Apache Iceberg, HUDI, Deltalake, et al), open big data file formats (Avro, Parquet) and open data formats (CSV, XML, JSON et.al), the format specifications with added context and meanings are added in and augmented post-injection.

Continue reading →

And great AI starts with good Data Management

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

Processing data has become more expensive.

Somewhere, there is a misconception that data processing is cheap. That stems from the well-known pricings of the capacities of public cloud storage that are a fraction of cents per month. But data in storage has to be worked upon, and has to be built up and protected to increase its value. Data has to be processed, moved, shared, and used by applications. Data induce workloads. Nobody keeps data stored forever and never be used again. Nobody buys storage just for capacity alone.

We have a great saying in the industry. No matter, where the data moves, it will land in a storage. So, it is clear that data does not exist in ether. And yet, I often see how little attention and prudence and care, when it comes to data infrastructure and data management technologies, the very components that are foundational to great data.

Great data management for Great AI

AI is driving up costs in data processing

A few recent articles drew my focus into the cost of data processing.

Here is one posted by a friend on Facebook. It is titled “The world is running out of data to feed AI, experts warn.”

My first reaction was, “How can we run out of data“? We have so much data in the world today that the 175 zettabytes predicted by IDC when we reach 2025 might be grossly inaccurate. According to Exploding Topics, it is estimated that we create 328.77TB of data per day, 120 zettabytes per year. While I cannot vouch for the accuracy of the numbers, the numbers are humongous.

Continue reading →

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 →

Project COSI

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

The S3 (Simple Storage Service) has become a de facto standard for accessing object storage. Many vendors claim 100% compatibility to S3, but from what I know, several file storage services integration and validation with the S3 have revealed otherwise. There are certain nuances that have derailed some of the more advanced integrations. I shall not reveal the ones that I know of, but let us use this thought as a basis of our discussion for Project COSI in this blog.

Project COSI high level architecture

What is Project COSI?

COSI stands for Container Object Storage Interface. It is still an alpha stage project in Kubernetes version 1.25 as of September 2022 whilst the latest version of Kubernetes today is version 1.26. To understand the objectives COSI, one must understand the journey and the challenges of persistent storage for containers and Kubernetes.

For me at least, there have been arduous arguments of provisioning a storage repository that keeps the data persistent (and permanent) after containers in a Kubernetes pod have stopped, or replicated to another cluster. And for now, many storage vendors in the industry have settled with the CSI (container storage interface) framework when it comes to data persistence using file-based and block-based storage. You can find a long list of CSI drivers here.

However, you would think that since object storage is the most native storage to containers and Kubernetes pods, there is already a consistent way to accessing object storage services. From the objectives set out by Project COSI, turns out that there isn’t a standard way to provision and accessing object storage as compared to the CSI framework for file-based and block-based storage. So the COSI objectives were set to:

  • Kubernetes Native – Use the Kubernetes API to provision, configure and manage buckets
  • Self Service – A clear delineation between administration and operations (DevOps) to enable self-service capability for DevOps personnel
  • Portability – Vendor neutrality enabled through portability across Kubernetes Clusters and across Object Storage vendors

Further details describing Project COSI can be found here at the Kubernetes site titled “Introducing COSI: Object Storage Management using Kubernetes API“.

Standardization equals technology adoption

Standardization means consistency, control, confidence. The higher the standardization across the storage and containerized apps industry, the higher the adoption of the technology. And given what I have heard from the industry over these few years, Kubernetes, to me, even till this day, is a platform and a framework that are filled and riddled with so many moving parts. Many of the components looks the same, feels the same, and sounds the same, but might not work out the same when deployed.

Therefore, the COSI standardization work is important and critical to grow this burgeoning segment, especially when we are rocketing towards disaggregation of computing service units, resources that be orchestrated to scale up or down at the execution of codes. Infrastructure-as-Code (IAC) is becoming a reality more and more with each passing day, and object storage is at the heart of this transformation for Kubernetes and containers.

Continue reading →

I built a 6-node Gluster cluster with TrueNAS SCALE

By | | , , , , , , , , , , , , , , , , , , , , , , ,
10 Comments

I haven’t had hands-on with Gluster for over a decade. My last blog about Gluster was in 2011, right after I did a proof-of-concept for the now defunct, Jaring, Malaysia’s first ISP (Internet Service Provider). But I followed Gluster’s development on and off, until I found out that Gluster was a feature in then upcoming TrueNAS® SCALE. That was almost 2 years ago, just before I accepted to offer to join iXsystems™, my present employer.

The eagerness to test drive Gluster (again) on TrueNAS® SCALE has always been there but I waited for SCALE to become GA. GA finally came on February 22, 2022. My plans for the test rig was laid out, and in the past few weeks, I have been diligently re-learning and putting up the scope to built a 6-node Gluster clustered storage with TrueNAS® SCALE VMs on Virtualbox®.

Gluster on OpenZFS with TrueNAS SCALE

Before we continue, I must warn that this is not pretty. I have limited computing resources in my homelab, but Gluster worked beautifully once I ironed out the inefficiencies. Secondly, this is not a performance test as well, for obvious reasons. So, this is the annals along with the trials and tribulations of my 6-node Gluster cluster test rig on TrueNAS® SCALE.

Continue reading →

Computational Storage embodies Data Velocity and Locality

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

I have been earnestly observing the growth of Computational Storage for a number of years now.  It was known by several previous names, with the name “in-situ data processing” stuck with me the most. The Computational Storage nomenclature became more cohesive when SNIA® put together the CMSI (Compute Memory Storage Initiative) some time back. This initiative is where several standards bodies, the major technology players and several SIGs (special interest groups) in SNIA® collaborated to advance Computational Storage segment in the storage technology industry we know of today.

The use cases for Computational Storage are burgeoning, and the functional implementations of Computational Storage are becoming vital to tackle the explosive data tsunami. In 2018 IDC, in its Worldwide Global Datasphere Forecast 2021-2025 report, predicted that the world will have 175 ZB (zettabytes) of data. That number, according to hearsay, has been revised to a heady figure of 250ZB, given the superlative rate data is being originated, spawned and more.

Computational Storage driving factors

If we take the Computer Science definition of in-situ processing, Computational Storage can be distilled as processing data where it resides. In a nutshell, “Bring Compute closer to Storage“. This means that there is a processing unit within the storage subsystem which does not require the host CPU to perform processing. In a very simplistic manner, a RAID card in a storage array can be considered a Computational Storage device because it performs the RAID functions instead of the host CPU. But this new generation of Computational Storage has much more prowess than just the RAID function in a RAID card.

There are many factors in Computational Storage that make a lot sense. Here are a few:

  1. Voluminous data inundate the centralized architecture of the cloud platforms and the enterprise systems today. Much of the data come from end point devices – mobile devices, sensors, IoT, point-of-sales, video cameras, et.al. Pre-processing the data at the origin data points can help filter the data, reduce the size to be processed centrally, and secure the data before they are ingested into the central data processing systems
  2. Real-time processing of the data at the moment the data is received gives the opportunity to create the Velocity of Data Analytics. Much of the data do not need to move to a central data processing system for analysis. Often in use cases like autonomous vehicles, fraud detection, recommendation systems, disaster alerts etc require near instantaneous responses. Performing early data analytics at the data origin point has tremendous advantages.
  3. Moore’s Law is waning. The CPU (central processing unit) is no longer the center of the universe. We are beginning to see CPU offloading technologies to augment the CPU’s duties such as compression, encryption, transcoding and more. SmartNICs, DPUs (data processing units), VPUs (visual processing units), GPUs (graphics processing units), etc have come forth to formulate a new computing paradigm.
  4. Freeing up central resources with Computational Storage also accelerates the overall distributed data processing in the whole data architecture. The CPU and the adjoining memory subsystem are less required to perform context switching caused by I/O interrupts as in most of the compute/storage architecture today. The total effect relieves the CPU and giving back more CPU cycles to perform higher processing tasks, resulting in faster performance overall.
  5. The rise of memory interconnects is enabling a more distributed computing fabric of data processing subsystems. The rising CXL (Compute Express Link™) interconnect protocol, especially after the Gen-Z annex, has emerged a force to be reckoned with. This rise of memory interconnects will likely strengthen the testimony of Computational Storage in the fast approaching future.

Computational Storage Deployment Models

SNIA Computational Storage Universe in 2019

Continue reading →

Time to Conflate Storage with Data Services

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

Around the year 2016, I started to put together a better structure to explain storage infrastructure. I started using the word Data Services Platform before what it is today. And I formed a pictorial scaffold to depict what I wanted to share. This was what I made at that time.

Data Services Platform (circa 2016)- Copyright Heoh Chin Fah

One of the reasons I am bringing this up again is many of the end users and resellers still look at storage from the perspective of capacity, performance and price. And as if two plus two equals five, many storage pre-sales and architects reciprocate with the same type of responses that led to the deteriorated views of the storage technology infrastructure industry as a whole. This situation irks me. A lot.

Continue reading →

How well do you know your data and the storage platform that processes the data

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

Last week was consumed by many conversations on this topic. I was quite jaded, really. Unfortunately many still take a very simplistic view of all the storage technology, or should I say over-marketing of the storage technology. So much so that the end users make incredible assumptions of the benefits of a storage array or software defined storage platform or even cloud storage. And too often caveats of turning on a feature and tuning a configuration to the max are discarded or neglected. Regards for good storage and data management best practices? What’s that?

I share some of my thoughts handling conversations like these and try to set the right expectations rather than overhype a feature or a function in the data storage services.

Complex data networks and the storage services that serve it

I/O Characteristics

Applications and workloads (A&W) read and write from the data storage services platforms. These could be local DAS (direct access storage), network storage arrays in SAN and NAS, and now objects, or from cloud storage services. Regardless of structured or unstructured data, different A&Ws have different behavioural I/O patterns in accessing data from storage. Therefore storage has to be configured at best to match these patterns, so that it can perform optimally for these A&Ws. Without going into deep details, here are a few to think about:

  • Random and Sequential patterns
  • Block sizes of these A&Ws ranging from typically 4K to 1024K.
  • Causal effects of synchronous and asynchronous I/Os to and from the storage

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 →