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

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

103: GreyBeards talk scale-out file and cloud data with Molly Presley & Ben Gitenstein, Qumulo

Sponsored by:

Ray has known Molly Presley (@Molly_J_Presley), Head of Global Product Marketing for just about a decade now and we both just met Ben Gitenstein (@Qumulo_Product), VP of Products & Solutions, Qumulo on this podcast. Both Molly and Ben were very knowledgeable about the problems customers have with massive data troves.

Molly has been on our podcast before (with another company, see: GreyBeards talk HPC storage with Molly Rector, CMO & EVP, DDN ). And we have talked with Qumulo before as well (see: GreyBeards talk data-aware, scale-out file systems with Peter Godman, Co-founder & CEO, Qumulo ).

Qumulo has a long history of dealing with customer issues with data center application access to data, usually large data repositories, with billions of small or large files, they have accumulated over time. But recently Qumulo has taken on similar problems in the cloud as well.

Qumulo’s secret has always been to allow researchers to run their applications wherever their data resides. This has led Qumulo’s software defined storage to offer multiple protocol access as well as a completely native, AWS and GCP cloud version of their solution.

That way customers can run Qumulo in their data center or in the cloud and have the same great access to data. Molly mentioned one customer that creates and gathers data using SMB protocol on prem and then, after replication, processes it in the cloud.

Qumulo Shift

Ben mentioned that many competitive storage systems are business model focused. That is they are all about keeping customer data within their solutions so they can charge for capacity. Although Qumulo also charges for capacity, with the new Qumulo Shift service, customer can easily move data off Qumulo and into native cloud storage. Using Shift, customers can free up Qumulo storage space (and cost) for any data that only needs to be accessed as objects.

With Shift, customers can replicate or move on prem or in the cloud Qumulo file data to AWS S3 objects. Once in S3, customers can access it with AWS native applications, other applications that make use of AWS S3 data, or can have that data be accessible around the world.

Qumulo customers can select directories to Shift to an AWS S3 bucket. The Qumulo directory name will be mapped to a S3 bucket name and each file in that directory will be copied to an S3 object in that bucket with the same file name.

At the moment, Qumulo Shift only supports AWS S3. Over time, Qumulo plans to offer support for other public cloud storage targets for Shift.

Shift is based on Qumulo replication services. Qumulo has a number of patents on replication technology that provides for sophisticated monitoring, control and high performance for moving vast amounts of data.

How customers use Shift

One large customer uses Qumulo cloud file services to process seismic data but then makes the results of that analysis available to other clients as S3 objects.

Customers can also take advantage of AWS and other applications that support objects only. For example, AWS SageMaker Machine Learning (ML) processes S3 object data. Qumulo customers could gather training data as files and Shift it to S3 objects for ML training.

Moreover, customers can use Shift to create AWS S3 object backups, archives and DR repositories of Qumulo file data. Ben mentioned DevOps could also use Qumulo Shift via APIs to move file data to S3 objects as part of new application deployment.

Finally, using Shift to copy or move file data to AWS S3, makes it ideal for collaboration by researchers, analysts and just about other entity that needs access to data.

The podcast ran ~26 minutes. Molly has always been easy to talk with and Ben turned out also to be easy to talk with and knew an awful lot about the product and how customers can use it. Keith and I enjoyed our time with Molly and Ben discussing Qumulo and their new Shift service. 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 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

Ben Gitenstein, VP of Products and Solutions, Qumulo

Ben Gitenstein runs Product at Qumulo. He and his team of product managers and data scientists have conducted nearly 1,000 interviews with storage users and analyzed millions of data points to understand customer needs and the direction of the storage market.

Prior to working at Qumulo, Ben spent five years at Microsoft, where he split his time between Corporate Strategy and Product Planning.

Molly Presley, Head of Global Product Marketing, Qumulo

Molly Presley joined Qumulo in 2018 and leads worldwide product marketing. Molly brings over 15 years of file system and archive technology leadership experience to the role.

Prior to Qumulo, Molly held executive product and marketing leadership roles at Quantum, DataDirect Networks (DDN) and Spectra Logic.

Presley also created the term “Active Archive”, founded the Active Archive Alliance and has served on the Board of the Storage Networking Industry Association (SNIA).

0101: Greybeards talk with Howard Marks, Technologist Extraordinary & Plenipotentiary at VAST

As most of you know, Howard Marks (@deepstoragenet), Technologist Extraordinary & Plenipotentiary at VAST Data used to be a Greybeards co-host and is still on our roster as a co-host emeritus. When I started to schedule this podcast, it was going to be our 100th podcast and we wanted to invite Howard and the rest of the co-hosts to be on the call to discuss our podcast. But alas, the 100th Greybeards podcast came and went, before we could get it done. So we decided to refocus this podcast back on VAST Data.

We talked with Howard last year about VAST and some of this podcast covers the same ground (see last year’s podcast with Howard on VAST Data) but I highlighted below different aspects of their product that we also discussed.

For starters, VAST just finalized a recent round of funding, which if I recall, valued them at over $1B USD, or yet another data storage unicorn.

VAST is a scale out, disaggregated, unstructured data platform that takes advantage of the economics of QLC SSD (from Intel) combined with the speed of 3D XPoint storage class memory (Optane SSD, also from Intel) to support customer data. Intel is an investor in VAST.

VAST uses mutliple front end (controller) servers, with one or more HA NVMe drive module(s) connected via a dual infiniband or 100Gbps Ethernet RDMA cluster interconnect. The HA NVMe drive module has two (IO modules) adapter cards, one for each connection that takes IO and data requests and transfers them across a PCIe bus which connects to QLC and Optane SSDs. They also have a Mellanox (another investor) switch on their backend with a (round robin) DNS router to connect hosts to their storage (front-end) servers.

Each backend HA NVMe drive module has 12 1.5TB Optane U.2 SSDs and 44 15.4TB QLC SSDs, for a total of 56 drives. Customer data is first written to Optane and then destaged to QLC SSD.

QLC has the advantage of being 4 bits per cell (for a lower $/GB stored) but it’s endurance or drive writes/day (dw/d)) is significantly worse than TLC. So VAST has had to work to increase QLC endurance in their system.

Natively, QLC offers ~0.2 dw/d when doing random 4K writes. However, if your system does 128KB sequential writes, it offers 4.0 dw/d. VAST destages data from Optane SSDs to QLC in 1MB chunks which both optimizes endurance and reduces garbage collection write amplification within the drive.

Howard mentioned their frontend servers are stateless, i.e., maintain no state information about any IO activity going on. Any IO state information is maintained by their system in Optane SSDs. Each server maintains a work log (like) structure on Optane that describes what they are doing in support of host IO and other activities. That way, if one front end server goes down, another one can access its log and take over its activity.

Metadata is also maintained only on Optane SSDs. Howard called their metadata structure a V-tree (B-tree). VAST mirrors all meta-data and customer data to two Optane SSDs. So if one Optane SSD goes down, its pair can be used to continue operations.

In last years podcast we talked at length about VAST data protection and data reduction capabilities so we won’t discuss these any further here.

However, one thing worth noting is that VAST has a very large RAID (erasure code protection) stripe. Data is written to the QLC SSDs in a VAST designed, locally decodable erasure coding format.

One problem with large stripes is rebuild time. VAST’s locally decodable parity codes help with this but the other thing that helps is distributing rebuild IO activity to all front end servers in the system.

The other problem with large stripe sizes is garbage collection. VAST segregates customer data by “temporariness” based on their best guess. In this way all data in one stripe should have similar lifetimes. When it’s time for stripe garbage collection, having all temporary data allows VAST to jettison the whole stripe (or most of it) rather than having to collect and re-write old stripe data to another new stripe.

VAST came out supporting NFSv3 and S3 object storage protocols, Their next release adds support for SMB 2.2, data-at-rest encryption and snapshotting to an external S3 store. As you may recall SMB is a stateful protocol. In VAST’s home grown, SMB implementation, front end servers can take over SMB transactions from other failed servers, without having to fail the whole transaction and start over again.

VAST uses a fail in place, maintenance policy. That is failed SSDs are not normally replaced in customer deployments, rather blocks, pages, or SSDs are marked as failed and the spare capacity available in the drive enclosure is used to provide space for any needed rebuilt data.

VAST offers a 10 year maintenance option where the customer keeps the same storage for 10 full years. That way customers don’t have to migrate data from one system to another until their 10 years are up.

The podcast runs a little under 44 minutes. Howard and I can talk forever. He is always a pleasure to talk with as well as extremely knowledgeable about (VAST) storage and other industry solutions.  The co-hosts and I had a great time talking with him again. Listen to the podcast to learn more.

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

Howard Marks, Technologist Extraordinary and Plenipotentiary, VAST Data, Inc.

Howard Marks brings over forty years of experience as a technology architect for hire and Industry observer to his role as VAST Data’s Technologist Extraordinary and Plienopotentary. In this role, Howard demystifies VAST’s technologies for customers and customer requirements for VAST’s engineers.

Before joining VAST, Howard ran DeepStorage an industry test lab and analyst firm. An award-winning speaker, he has appeared at events on three continents including Comdex, Interop and VMworld.

Howard is the author of several books (all gratefully out of print) and hundreds of articles since Bill Machrone taught him journalism at PC Magazine in the 1980s.

Listeners may also remember that Howard was a founding co-Host of the Greybeards-on-Storage Podcast.

93: GreyBeards talk HPC storage with Larry Jones, Dir. Storage Prod. Mngmt. and Mark Wiertalla, Dir. Storage Prod. Mkt., at Cray, an HPE Enterprise Company

Supercomputing Conference 2019 (SC19) is coming to Denver next week and in anticipation of that show, we thought it would be a good to talk with some HPC storage group. We contacted HPE and given their recent acquisition of Cray, they offered up Larry and Mark to talk about their new ClusterStor E1000 storage system.

There are a number of components that go into Cray supercomputers and besides the ClusterStor, Larry and Mark mentioned their new SlingShot cluster interconnect which is Ethernet based with significant enhancements to congestion handling. But the call focused on ClusterStor.

What is ClusterStor

ClusterStor, is a Lustre file system hardwareappliance. Lustre has always been popular with the HPC crowd as it offered high bandwidth file services. But Lustre often took a team of (PhD) scientists to configure, deploy and run properly because of all the parameters that had to be setup for optimum performance.

Cray’s ClusterStor was designed to make configuring, deploying and running Lustre a lot simpler with a GUI and system defaults that provided an optimal running environment. But if customers still want access to all Lustre features and functionality, all the Lustre parameters can still be tweaked to personalize it.

What sort of appliance

The ClusterStore team has created a Lustre storage appliance using two systems, a 2U-24 NVMe SSD system and a 4U-106 disk drive system. Both systems use PCIe Gen 4 buses which offer 2X the bandwidth of Gen 3 and NVMe Gen 4 SSDs. Each ClusterStore E1000 appliance comes with 2 servers for HA and the storage behind it.

Larry said the 2U NVMe Gen 4 appliance offers 80GB/sec of read and 60GB/sec of write data bandwidth. And a full rack of these, could support ~2.5TB/sec of data bandwidth. One TB/sec seems like an awful lot to the GreyBeards, 2.5TB/sec, out of this world.

We asked if it supported InfiniBAND interconnects? Yes, they said it supports the latest generation of InfiniBAND but it also offers Cray’s own (SlingShot) Ethernet interconnect, unusual for HPC environments. And as in any Lustre parallel file system, servers accessing storage use Lustre client software.

ClusterStor Data Services

But on the backend, where normally one would see only LDISKFS for backend storage, ClusterStor also offers ZFS. Larry and Mark said that LDISKFS is faster but ZFS offers more functionality like snapshots and data compression.

Many of the Top 100 & Top 500 supercomputing environments are starting to deploy ML DL (machine learning-deep learning) workloads along with their normal HPC activities. But whereas HPC work has historically depended on bandwidth to read, write and move large files around, ML DL deals with small files and needs high IOPS. ClusterStor was designed to satisfy both high bandwidth and high IOPS workloads.

In previous HPC Lustre flash solutions, customers had to deal with the complexity of where to place data, such as on flash or on disk. But with net ClusterStor E1000, the system can do all this for you. That is it will move data from disk to flash when it sees an advantage to doing so and move it back again when that advantage is gone. But, just as with Lustre configuration parameters above, customers can still pre-stage data to flash.

The other challenge for HPC environments is extreme size. Cray and others are starting to see requirements for Exascale (exabyte, 10**18) byte) storage systems. In fact, Cray has a couple of ClusterStor E1000 configurations of 400PB or more already, As these systems age they may indeed grow to exceed an exabyte.

With an exabyte of data, systems need to support billions of files/inodes and better metadata services and indexing. ClusterStor offers optimized inode indexing and search to enable HPC users to quickly find the data they are looking for. Further, ClusterStor offers, data at rest encryption and supports virtual file systems, for multi-tenancy.

With a ZFS backend, ClusterStor can supply data compression and snapshots. Cray has tested ZFS compression on HPC scientific ( mostly already application compressed) data and still see ~30% reduction is storage footprint. At an exabyte of storage 30% can be a significant cost reduction

The podcast ran long, ~46 minutes. Larry and Mark had a good knowledge of the HPC storage space and were easy to talk with. Matt’s an old ZFS hand, so wanted to take even more about ZFS. I had a good time discussing ClusterStor and Lustre features/functionalit and how the HPC workloads are changing. Listen to the podcast to learn more. [The podcast was recorded on November 6th, not the 5th as mentioned in the lead in, Ed.]

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

Larry Jones, Director Storage Product Management

Larry Jones is a director of storage product management for Cray, a Hewlett Packard Enterprise company.

Jones previously held senior product management roles at Seagate, DDN and Panasas.

Mark Wiertalla, Director Storage Product Marketing

Mark Wiertalla is a product marketing director for Cray, a Hewlett Packard Enterprise company.

Prior to Cray, Wiertalla held product manager roles at EMC and SGI.