110: GreyBeards talk FMS2020 wrap up with Jim Handy, General Director of Objective Analysis

This months it’s back to storage and our annual wrap-up on the Flash Memory Summit Conference with Jim Handy, General Director of Objective Analysis. Jim’s been on our show 5 times before and is a well known expert on NAND and SSDs (as well as DRAM and memory systems). Jim also blogs at TheSSDGuy.com and TheMemoryGuy.com just in case you want to learn more.

FMS went virtual this year and had many interesting topics including how computational storage is making headway in the cloud, 3D QLC is hitting the enterprise with PLC on the way, and for a first at FMS, a talk on DNA storage (for more information on this, see our podcast with CatalogDNA). Jim’s always interesting to talk with to help us understand where the NAND-SSD industry is headed. Listen to the podcast to learn more.

Jim mentioned that the major NAND vendors are all increasing the number of layers for their 3D NAND, and it continues to scale well. Most vendors are currently shipping ~100 layer NAND, with Micron doing more than that. And vendor roadmaps are looking at the possibility of 200 layers or more. Jim doesn’t think anyone knows how high it can go.

Another advantage of 3D NAND is it can be used to make bigger bit cells and thus have better endurance. From Jim’s perspective more electrons per cell means a better more resilient bit cell.

Many vendors in the nascent persistent memory industry were all hoping that NAND would stop scaling at some point and they would be able to pick up the slack. But NAND manufacturers found 3D and scaling hasn’t stopped at all. This has relegated most persistent memory vendors to a small niche market with the exception of Intel (and Micron).

Jim said that Intel is losing money on Optane every year, ~$5B so far. But Intel knows that chip profitability is tied to economies of scale, volumes matter. With enough volume, Optane will become cheap enough to manufacture that they will make buckets of money from it.

Interestingly, Jim said that DRAM scaling is slowing down. That means there may be an even bigger market for something close to DRAM access speeds, but with increased density and lower cost. Optane seems to fit that description very well.

Jim also mentioned that computational storage is starting to see some traction with public cloud vendors. Computational storage adds generic compute power to inside an SSD which can be used to perform storage intensive functions out at the SSD rather than transferring data into the CPU for processing. This makes sense where a lot of data would need to be transferred back and forth to an SSD and where computational cycles are just as cheap out on the SSD as in the server. For example, for data compression, search, and video transcoding, computational storage can make a lot of sense. (See our podcast with NGD systems for more informaiton).

In contrast, Open-Channel SSDs are making dumb SSDs, or SSDs without any flash translation layer or other smarts needed to make NAND work as persistent storage bin the enterprise. There’s a small group of system providers that want to perform all this functionality at a global scale (or across multiple SSDs) rather than at the local, SSD drive level.

Another topic that hit it’s stride this year at FMS2020 was Zoned Name Spaces (ZNS). ZNS partitions an SSD into separately addressable segments, to allow higher performing sequential (write) access within those zones. As SSD capacity has increased, IO activity has sky-rocketed and this has led to an “IO blender” effect. Within an IO blender, it’s impossible to understand which IO is following a sequential pattern and which is not. ZNS is intended to solve that probplem

With ZNS SSDs, IOs doing sequential access can have their own partition and that way the SSD can understand its sequential IO and act accordingly. It turns out that sequential writes to NAND can perform much, much faster than random writes.

ZNS was invented for SMR (shingled magnetic recording) disks, because these overwrote portions of other tracks (like roof shingles, tracks on SMR disks overlap). We had heard about ZNS at FMS2019 but had thought this just a better way to share access to a single SSD, by carving it up into logical (mini-)volumes. Jim said that was also a benefit but the major advantage is being able to understand sequential IO and write to the SSD more effectively.

We talked some on the economics of NAND flash, disk and tape as storage media. Jim and I see this continuing a trend that’s been going on for years, where NAND storage cost $/GB ~10X more than disk capacity, and disk storage costs $/GB ~10X more than tape capacity. All three technologies continue their relentless pursuit of increasing capacity but it’s almost like train tracks, all three $/GB curves following one another into the future.

On the other hand, high RPM disk seems to have died, and been replaced with SSDs. Disk manufacturers have seen unit declines but the # GB they are shipping continues to increase. Contrary to a number of AFA system providers, disk is not dead and is unlikely to die anytime soon.

Finally, we discussed DNA storage and it’s coming entry into the storage market. It’s all a question of price of the drive and media technology, size of the mechanism (drive?) and read and write access times. At the moment all these are coming down but are not yet competitive with tape. But given DNA technology trends, there doesn’t appear to be any physical barrier that’s going to stop it from becoming yet another storage technology in the enterprise, most likely at a 10X $/GB cost advantage over tape…

Jim Handy, General Director, Objective Analysis

Jim Handy of Objective Analysis has over 35 years in the electronics industry including 20 years as a leading semiconductor and SSD industry analyst. Early in his career he held marketing and design positions at leading semiconductor suppliers including Intel, National Semiconductor, and Infineon.

A frequent presenter at trade shows, Mr. Handy is known for his technical depth, accurate forecasts, widespread industry presence and volume of publication.

He has written hundreds of market reports, articles for trade journals, and white papers, and is frequently interviewed and quoted in the electronics trade press and other media. 

He posts blogs at www.TheMemoryGuy.com, and www.TheSSDguy.com

109: GreyBeards talk SmartNICs & DPUs with Kevin Deierling, Head of Marketing at NVIDIA Networking

We decided to take a short break (of sorts) from storage to talk about something equally important to the enterprise, networking. At (virtual) VMworld a month or so ago, Pat made mention of developing support for SmartNIC-DPUs and even porting vSphere to run on top of a DPU. So we thought it best to go to the source of this technology and talk with Kevin Deierling (TechSeerKD), Head of Marketing at NVIDIA Networking who are the ones supplying these SmartNICs to VMware and others in the industry.

Kevin is always a pleasure to talk with and comes with a wealth of expertise and understanding of the technology underlying data centers today. The GreyBeards found our discussion to be very educational on what a SmartNIC or DPU can do and why VMware and others would be driving to rapidly adopt the technology. Listen to the podcast to learn more.

NVIDIA’s recent acquisition of Mellanox brought them Mellanox’s NIC, switch and router technology. And while Mellanox, and now NVIDIA have some pretty impressive switches and routers, what interested the GreyBeards was their SmartNIC technology.

Essentially, SmartNICS provide acceleration and offload of data handling needs required to move data around an enterprise network. These offload services include at a minimum, encryption/decryption, packet pacing (delivering gadzillion video streams at the right speed to insure proper playback by all), compression, firewalls, NVMeoF/RoCE, TCP/IP, GPU direct storage (GDS) transfers, VLAN micro-segmentation, scaling, and anything else that requires real time processing to perform at line speeds.

For those who haven’t heard of it, GDS transfers data from storage directly into GPU memory and from GPU memory directly to storage without any CPU cycles or server memory involvement, other than to set up the transfer. This extends NVMeoF RDMA tech to/from storage and server memory, to GPUs. That is, GDS offers a RDMA like path between storage and GPU memory. GPU to/from server memory direct interface already exists over the PCIe bus.

But even with all the offloads and accelerators above, they can also offer an additional a secure enclave outside the TPM in the CPU, to better isolate security sensitive functionality for a data center. (See DPU below).

Kevin mentioned multiple times that the new unit of computation is no longer a server but rather is now a data center. When you have public cloud, private cloud and other systems that all serve up virtual CPUs, NICs, GPUs and storage, what’s really being supplied to a user is a virtual data center. Cloud providers can carve up their hardware and serve it to you any way you want or need it. Virtual data centers can provide a multitude of VMs and any infrastructure that customers need to use to run their workloads.

Kevin mentioned by using SmartNics, IT or cloud providers can return 30% of the processor cycles (that were being spent doing networking work on CPUs) back to workloads that run on CPUs. Any data center can effectively obtain 30% more CPU cycles and increased networking speed and performance just by deploying SmartNICs throughout all the servers in their environment.

SmartNICs are an outgrowth of Mellanox technology embedded in their HPC InfiniBAND and high end Ethernet switches/routers. Mellanox had been well known for their support of NVMeoF/RoCE to supply high IOPs/low-latency IO activity for NVMe storage over Ethernet and before that their InfiniBAND RDMA technologies.

As Mellanox came out with their 2nd Gen SmartNIC they began to call their solution a “DPU” (data processing unit), which they see forming part of a “holy trinity” underpinning the new data center which has CPUs, GPUs and now DPUs. But a DPU is more than just a SmartNIC.

All NVIDIA SmartNICs and DPUs are based on Mellanox’s BlueField cards and chip technology. Their DPU uses BlueField2 (gen 2 technology) chips, which has a multi-core ARM engine inside of it and memory which can be used to perform computational processing in addition to the onboard offload/acceleration capabilities.

Besides adding VMware support for SmartNICs, PatG also mentioned that they were porting vSphere (ESX) to run on top of NVIDIA Networking DPUs. This would move the core VMware’s hypervisor functionality from running on CPUs, to running on DPUs. This of course would free up most if not all VMware Hypervisor CPU cycles for use by customer workloads.

During our discussion with Kevin, we talked a lot about the coming of AI-ML-DL workloads, which will require ever more bandwidth, ever lower latencies and ever more compute power. NVIDIA was a significant early enabler of the AI-ML-DL with their CUDA API that allowed a GPU to be used to perform DL network training and inferencing. As such, CUDA became an industry wide phenomenon allowing industry wide GPUs to be used as DL compute engines.

NVIDIA plans to do the same with their SmartNICs and DPUs. NVIDIA Networking is releasing the DOCA (Data center On a Chip Architecture) SDK and API. DOCA provides the API to use the BlueField2 chips and cards which are the central techonology behind their DPU. They have also announced a roadmap to continue enhancing DOCA, as they have done with CUDA, over the foreseeable future, to add more bandwidth, speed and functionality to DPUs.

It turns out the real problem which forced Mellanox and now NVIDIA to create SmartNics was the need to support the extremely low latencies required for NVMeoF and GDS IO.

It wasn’t clear that the public cloud providers were using SmartNICS but Kevin said it’s been sort of a widely known secret that they have been using the tech. The public clouds (AWS, Azure, Alibaba) have been deploying SmartNICS in their environments for some time now. Always on the lookout for any technology that frees up compute resources to be deployed for cloud users, it appears that public cloud providers were early adopters of SmartNICS.

Kevin Deierling, Head of Marketing NVIDIA Networking

Kevin is an entrepreneur, innovator, and technology executive with a proven track record of creating profitable businesses in highly competitive markets.

Kevin has been a founder or senior executive at five startups that have achieved positive outcomes (3 IPOs, 2 acquisitions). Combining both technical and business expertise, he has variously served as the chief officer of technology, architecture, and marketing of these companies where he led the development of strategy and products across a broad range of disciplines including: networking, security, cloud, Big Data, machine learning, virtualization, storage, smart energy, bio-sensors, and DNA sequencing.


Kevin has over 25 patents in the fields of networking, wireless, security, error correction, video compression, smart energy, bio-electronics, and DNA sequencing technologies.

When not driving new technology, he finds time for fly-fishing, cycling, bee keeping, & organic farming.

This image has an empty alt attribute; its file name is Subscribe_on_iTunes_Badge_US-UK_110x40_0824.png
This image has an empty alt attribute; its file name is play_prism_hlock_2x-300x64.png
This image has an empty alt attribute; its file name is Spotify_Logo_CMYK_Black-1024x307.png


108: GreyBeards talk DNA storage with David Turek, CTO, Catalog DNA

The Greybeards get off the beaten (enterprise) path this month, to see what lies ahead with a discussion on DNA storage. David Turek, CTO, Catalog DNA (@CatalogDNA) is a long time IBMer that had been focused on HPC systems at IBM but left and went to Catalog DNA to pursue the commercialization of DNA storage, an “emerging” technology. CatalogDNA is a company out of Boston that had recently closed a round of funding and are focused on bringing DNA storage out into the world of IT.

David was a pleasure to talk and has lot’s of knowledge on HPC and enterprise data center solutions. He also has a good grasp of what it will take to bring DNA storage to market. Keith has had some prior experience with DNA technologies in BioPharma so could talk in more detail about the technology and its ecosystem. [We’re trying out a new format, let us know what you think; The Eds.]

Ray has written about DNA storage in his RayOnStorage Blog, most recently in April of this year and May of last year. It’s been an ongoing blog topic of his for almost a decade now. When Ray was interviewed about the technology he thought it interesting but had serious obstacles with read and write latencies and throughput as well as the size of the storage device.

Well CatalogDNA seems to have got a good handle on write throughput and are seriously working on the rest.

However, DNA storage’- volumetric density was always of exceptional. Early on in the podcast, David mentioned that DNA storage was 6 orders of magnitude (1 million times) more dense in bytes/mm**3 than magnetic tape today. An LTO8 tape device stores 12TB (uncompressed) in a tape cartridge, 14.2 in**3 (230.3 cm**3) or roughly 845GB/in**3 (52GB/cm**3). One million times this, would be 12EB in the same volume.

The challenge with LTO8, disk or SSD storage today is at some point you have to move the data from one device to a more modern device. This could be every 3-5 years (for disk or SSD) or 25-30 years for tape. In either case, at some point IT would need to incur the cost and time to move the data. Not much of a problem for 100TB or so but when you start talking PB or EB of data, it can be a never ending task.

DNA storage

David mentioned Catalog uses “synthetic DNA” in their storage. This means the DNA it uses is designed to be incompatible with natural DNA such that it wouldn’t work in a cell. It has stops or other biological mechanisms to inhibit it’s use in nature. Yes it uses the same sugars, backbones, and other chemistry of biologically active DNA, but it has been specifically modified to inhibit its use by normal cellular machinery. 

DNA storage has a number of unique capabilities :

  • It can be made to last forever, by being dried out (dessicated) and encased in a crystal and takes 0 power/energy to be stored for eons.
  • It can be cheaply and easily replicated, almost an infinite number of times, for only the cost of chemical feedstock, chemical interactions and energy. Yes, this may take time but the process scales up nicely. One could make 2 copies in first cycle, 4 in the 2nd, 8 in the 3rd, etc and by doing this it would only take 20 cycles to create a million copies. If each cycle takes 10 minutes, in 3:20, you could have a million copies of 1EB of data.
  • It can be easily searched for target information. This involves fabricating a DNA search molecule and inserting it into the storage solution. Once there it would match up with the DNA segment that held your key. And of course, the search molecule and the data could be replicated to speed up any search process.
  • We already mentioned the extreme density advantage above.

Speed of DNA storage access

David said they can already write Catalog DNA storage in MB/sec.

The process they use to write is like a conveyer belt which starts off with a polyethylene sheet (web actually). Somewhere, the digital data comes in, is chunked and transformed into DNA strand (25-50 base pairs) molecules or dots. The polyethylene sheet rolls into a machine that uses multiple 3D print heads to deposit dots (the DNA strand data chunks) at web points. This machine/process deposits 100K or more of these dots onto the web. The sheet then moves to the next stage where the DNA molecules are scraped off and drained into a solution. Then a wet process occurs which uses chemistry to make the DNA more readable and enables the separate DNA molecules to connect into a data strand. Then this data strand goes into another process where it gets reduced in volume and so that it is more stable.

If needed, one can add another step that dries out or desiccates the data strand into even a smaller volume which can then be embedded into a crystalline structure which could last for centuries.

David compared the DNA molecules (data chunks) to Legos, only they are the same pieces in a million different colors Each piece represents some segment of data bits/bytes. Using chemistry and proprietary IP each separate DNA molecule self organizes (connects) into a data strand, representing the information you want to store.

Reading DNA involves, off the shelf, DNA sequencers. The one Catalog currently uses is the Oxford NanoPore device, but there are others. David didn’t say how fast they could read DNA data. But current DNA reading devices destroy the data. So making replicas of the data would be required to read it.

David said their current write device is L shaped with one leg about 14’ (4.3m) long and the other about 12’ (3.7m) long with each leg being about 3’ (0.9m) wide.

Searching EB of data in minutes?!

DNA strands can be searched (matched) using a search molecule and inserting this into the storage solution (that holds the data strands). Such a molecule will find a place in the data that has a matching (DNA) data element and I believe attach itself to the data strand.

For example, lets say you had recorded all of a country’s emails for a month or so and you wanted to search them for the words, “bomb”, “terrorist”, “kill”, etc. One could create a set of search molecules, replicate them any number of times (depending on how quickly you wanted to search the data and how many matches you expected), and insert them into a data pool with multiple data strands that stored the email traffic.

After some time, you’d come back and your search would be done. You’d need to then extract the search hits, and read out the portion of the data strands (emails) that matched. I’m guessing extraction would involve some sort of (wet) chemical process or filtration.

State of Catalog DNA storage

David mentioned that as a publicity stunt they wrote the whole Wikipedia onto Catalog DNA storage. The whole Wikipedia fit into a cylinder about the height of a big knuckle on your hand and in a width smaller than a finger. The size of the whole Wikipedia, with complete edit history is 10TB uncompressed and if they stored all the edit versions plus its media such as images, videos, audio and other graphics, that would add another 23TB (as of end of 2014), so ~33TB uncompressed.

David believes in 18 months they could have a WORM (write once, read many times) data storage solution that could be deployed in customer data centers which would supply immense data repositories in relatively small solution containers.

CatalogDNA is currently in a number of PoCs with major corporations (not labs or universities) to show how DNA storage technology can be used to solve problems.

David believes that at some point they will be able to make compute engines entirely of DNA. At that point, one could have a combined compute and storage (HCI-like) DNA server using the same technology in a solution. And as mentioned previously, one could replicate from one DNA server & storage to a million DNA servers & storage in just 20 cycles. How’s that for scale out.


David Turek, CTO Catalog DNA

Dave Turek is Catalog’s Chief Technology Officer. He comes to Catalog from IBM where he held numerous executive positions in High Performance Computing and emerging technologies.

He was the development executive for the IBM SP program which produced the first commercially successful massively parallel system; he started IBM’s Linux Cluster business; launched an early offering in Cloud computing called Deep Computing Capacity on Demand; produced the Roadrunner system, the world’s first petascale computer; and was responsible for IBM’s exascale strategy which led to the deployment of the Summit and Sierra systems at Oak Ridge and Lawrence Livermore National Laboratories respectively.

David has been invited to testify to Congress on numerous occasions regarding the future of computing in the US and has helped establish technical collaborations with universities, businesses, and government agencies around the world.

This image has an empty alt attribute; its file name is Subscribe_on_iTunes_Badge_US-UK_110x40_0824.png
This image has an empty alt attribute; its file name is play_prism_hlock_2x-300x64.png
This image has an empty alt attribute; its file name is Spotify_Logo_CMYK_Black-1024x307.png


107: GreyBeards talk MinIO’s support of VMware’s new Data Persistence Platform with AB Periasamy, CEO MinIO

Sponsored by:

The GreyBeards have talked with Anand Babu (AB) Periasamy (@ABPeriasamy), CEO MinIO, before (see 097: GreyBeards talk open source S3… episode). And we also saw him earlier this year, at their headquarters for Storage Field Day 19 (SFD19) where AB gave a great discussion of what they were doing and how it worked (see MinIO’s SFD18 presentation videos).

The podcast runs ~26 minutes. AB is very technically astute and always a delight to talk with. He’s extremely knowledgeable about the cloud, containerized applications and high performing S3 compatible object storage. And now with MinIO and vSAN Data Persistence under VCF Tanzu, very knowledgeable about the virtualized IT environment as well. Listen to the podcast to learn more. [We’re trying out a new format placing the podcast up front. Let us know what you think; The Eds.]


VMware VCF vSAN Data Persistence Platform with MinIO

Earlier this month VMware announced a new capability available with the next updates of vSAN, vSphere & VCF called the vSAN Data Persistence Platform. The Data Persistence Platform is a VMware framework designed to integrate stateful, independent vendor software defined storage services in vSphere. By doing so, VCF can provide API access to persistent storage services for containerized applications running under Tanzu Kubernetes (k8s) Grid service clusters.

At the announcement, VMware identified three object storage and one (Cassandra) database technical partners that had been integrated with the solution.  MinIO was an object storage, open source partner.

VMware’s VCF vSAN Data Persistence framework allows vCenter administrators to use vSphere cluster infrastructure to configure and deploy these new stateful storage services, like MinIO, into namespaces and enables app developers direct k8s API access to these storage namespaces to provide persistent, stateful object storage for applications. 

With VCF Tanzu and the vSAN Data Persistence Platform using MinIO, dev can have full support for their CiCd pipeline using native k8s tools to deploy and scale containerized apps on prem, in the public cloud and in hybrid cloud, all using VCF vSphere.

MinIO on the Data Persistence Platform

AB said MinIO with Data Persistence takes advantage of a new capability called vSAN Direct which gives vSAN almost JBOF types of IO control and performance. With MinIO vSAN Direct, storage and k8s cluster applications can co-reside on the same ESX node hardware so that IO activity doesn’t have to hop off host to be performed. In addition, can now populate ESX server nodes with lots (100s to 1000s?) of storage devices and be assured the storage will be used by applications running on that host.

As a result, MinIO’s object storage IO performance on VCF Tanzu is very good due to its use of vSAN Direct and MinIO’s inherent superior IO performance for S3 compatible object storage.

With MinIO on the VCF vSAN Data Persistence Platform, VMware takes over all the work of deploying MinIO software services on the VCF cluster. This way customers can take advantage of MiniO’s fully compatible S3 object storage system operating in their VCF cluster. For app developers they get the best of all worlds, infrastructure configured, deployed and managed by admins but completely controllable, scaleable and accessible through k8s API services.

If developers want to take advantage of MinIO specialized services such as data security or replication, they can do so directly using MinIOs APIs, just like they would when operating bare metal or in the cloud.

AB said the VMware development team was very responsive during development of Data Persistence. AB was surprised to see such a big company, like VMware, operate with almost startup like responsiveness. Keith mentioned he’s seen this in action as vSAN has matured very rapidly to a point of almost feature parity, with just about any storage system out there today .

With MinIO object storage, container applications that need PB of data, now have a home on VCF Tanzu. And it’s as easily usable as any public cloud storage. And with VCF Tanzu configuring and deploying the storage over its own infrastructure, and then having it all managed and administered by vCenter admins, its simple to create and use PB of object storage.

MinIO is already the most popular S3 compatible object storage provider for applications running in the cloud and on prem. And VMware is easily the most popular virtualization platform on the planet. Now with the two together on VCF Tanzu, there seems to be nothing in the way of conquering containerized applications running in IT as well.

With that, MinIO is available everywhere containers want to run, natively available in the cloud, on prem and hybrid cloud or running with VCF Tanzu everywhere as well.


AB Periasamy, CEO MinIO

AB Periasamy is the CEO and co-founder of MinIO. One of the leading thinkers and technologists in the open source software movement,

AB was a co-founder and CTO of GlusterFS which was acquired by RedHat in 2011. Following the acquisition, he served in the office of the CTO at RedHat prior to founding MinIO in late 2015.

AB is an active angel investor and serves on the board of H2O.ai and the Free Software Foundation of India.

He earned his BE in Computer Science and Engineering from Annamalai University.


This image has an empty alt attribute; its file name is Subscribe_on_iTunes_Badge_US-UK_110x40_0824.png
This image has an empty alt attribute; its file name is play_prism_hlock_2x-300x64.png
This image has an empty alt attribute; its file name is Spotify_Logo_CMYK_Black-1024x307.png


106: Greybeards talk Intel’s new HPC file system with Kelsey Prantis, Senior Software Eng. Manager, Intel

We had talked with Intel at Storage Field Day 20 (SFD20), about a month ago. At the virtual event, Intel’s focus was on their Optane PMEM (persistent memory) technology. Kelsey Prantis (@kelseyprantis), Senior Software Engineering Manager, Intel was on the show and gave an introduction into Intel’s DAOS (Distributed Architecture Object Storage, DAOS.io) a new HPC (high performance computing, super computers) file system they developed from scratch to use leading edge, Intel technologies, and Optane PMEM was one of them.

Kelsey has worked on LUSTRE and other HPC file systems for a long time now and came into the company from the acquisition of Whamcloud. Currently, she manages the development team working on DAOS. DAOS is a new HPC object storage file system which is completely open source (available on GitHub).

DAOS was designed from the start to take advantage of NVMe SSDs and Optane PMEM. With PMEM, current servers can support up to 20TB of memory. Besides the large memory sizes, Optane PMEM also offers non-volatile memory and byte addressability (just like DRAM). These two characteristics opens up new functionality that allows DAOS to move beyond legacy, block oriented, storage architectures that have been the only storage solution for HPC (and the enterprise) for decades now.

What’s different about DAOS

DAOS uses PMEM for all metadata and for storing small files. HPC IO has always focused on heavy bandwidth (IO using large blocks) oriented but lately newer applications have emerged, such as AI/ML/DL, data analytics and others, that use smaller files/blocks. Indeed, most new HPC clusters and supercomputers are deploying almost as many GPUs as CPUs in their configurations to support AI activities.

The problem is that these newer applications typically consume much smaller files. Matt mentioned one HPC client he worked with was processing small batches of seismic data, to predict, in real time, earthquakes that were happening around the world.

By using PMEM for metadata and small files, DAOS can be much more responsive to file requests (open, close, delete, status) as well as provide higher performing IO for small files. All this leads to a much better performing system for the new HPC workloads as well as great sustainable performance for the more traditional large file workloads.

DAOS storage

DAOS provides a cluster storage system that can be configured with from 1 (no data protection), but more normally 3 nodes (with data protection) at a minimum to 512 nodes (lab tested). Data protection in DAOS is currently based on mirroring data and can use from 0 to the number of nodes in a cluster as data mirrors.

DAOS system nodes are homogeneous. That is they all come with the same amount of PMEM and NVMe SSDs. Note, DAOS doesn’t support disk drives. Kelsey mentioned DAOS node hardware can be tailored to suit any particular application environment. But they typically require an average of 6% of overall DAOS system capacity in PMEM for metadata and small file activity.

DAOS current supports their own API, POSIX, HDFS5, MPIIO and Apache Spark storage protocols. Kelsey mentioned that standard POSIX uses a pessimistic conflict resolution mode which leads to performance bottlenecks during parallel access. In contrast, DAOS’s versos of POSIX uses optimistic conflict resolution, which means DAOS starts writes assuming there’s no conflict, but if one occurs it handles the conflict in real time. Of course with all the metadata byte addressable and in PMEM this doesn’t take up a lot of (IO) time.

As mentioned earlier, DAOS data protection uses mirror-replicas. However, unlike most other major file systems, DAOS mirroring can be done at the object level. DAOS internally is an object store. Data organization on DAOS starts at the pool level, underneath that is data containers, and then under that are objects. Any object in DAOS can have its own mirroring configuration. DAOS is working towards supporting Erasure Coding as another form of data protection for a future release.

DAOS performance

There’s a new storage benchmark that was developed specifically for HPC, called the IO500. The IO500 benchmark simulates a number of different HPC workloads, measures performance for each of them, and computes an (aggregate) performance score to rank HPC storage systems.

IO500 ranks system performance using two lists: one is for any sized configuration that typically range from 50 to 1000s of nodes and their other list limits the configuration to 10 nodes. The first performance ranking can sometimes be gamed by throwing more hardware into a cluster. The 10 node rankings are much harder to game this way and from our perspective, show a fairer comparison of system performance.

As presented (virtually) at ISC 2020, DAOS took the top spot on the IO500 any size configuration list and performed better than 2X the next best solution. And on the IO500 10 node list, Intel’s DAOS configuration, Texas Advanced Computing (TAC) DAOS configuration, and Argonne Nat Labs DAOS configuration took the top 3 spots and had 3X better performance than the next best, non-DAOS storage system.

The Argonne National Labs has already stated that they will be using DAOS in their new HPC system to be deployed in the near future. Early specifications for storage at the new Argonne Lab required support for 230PB of data and 25TB/sec of bandwidth.

The podcast ran ~43 minutes. Kelsey was great to talk with and very knowledgeable about HPC systems and HPC IO in particular. Matt has worked at Argonne in the past so understood these systems better than I. Sadly, we lost Matt’s end of the conversation about 1/2 way into the recording. Both Matt and I thought that DAOS represents the birth of a new generation of HPC storage. Listen to the podcast to learn more.


This image has an empty alt attribute; its file name is Spotify_Logo_CMYK_Black-1024x307.png

This image has an empty alt attribute; its file name is play_prism_hlock_2x-300x64.png
This image has an empty alt attribute; its file name is Subscribe_on_iTunes_Badge_US-UK_110x40_0824.png

Kelsey Prantis, Senior Software Engineering Manager, Intel

 Kelsey Prantis heads the Extreme Storage Architecture and Development division at Intel Corporation. She leads the development of Distributed Asynchronous Object Storage (DAOS), an open-source, low-latency and high IOPS object store designed from the ground up for massively distributed Non-Volatile Memory (NVM).

She joined Intel in 2012 with the acquisition of Whamcloud, where she led the development of the Intel Manager for Lustre* product.

Prior to Whamcloud, she was a software developer at personal genomics and biotechnology company 23andMe.

Prantis holds a Bachelor’s degree in Computer Science from Rochester Institute of Technology