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

105: Greybeards talk new datacenter architecture with Pradeep Sindhu, CEO & Co-founder, Fungible

Neither Ray nor Keith has met Pradeep before, but Ray was very interested in Fungible’s technology. Turns out Pradeep Sindhu, CEO and Co-founder, Fungible has had a long and varied career in the industry starting at Xerox Parc, then co-founding and becoming chief scientist at Juniper, and now reachitecting the data center with Fungible. Pradeep mentioned this at the end of the podcast, he has always been drawn to hard problems with the potential to open up immense possibilities. What he did at Juniper and what he is planning to accomplish with Fungible both fit that pattern.

Today, in a typical data center, we have servers, networking and storage equipment all connected through a fabric. But from Pradeep’s perspective none of it works well in support of data centric computing. What we have today is operating like changing a screw with a pliers. But if there existed some hardware that can execute data centric computing (or to follow the metaphor, a screw driver) well, the data center would operate much more efficiently, with more performance and better resource use.

Fungible was founded in 2015 with the idea that the industry is moving to a data centric computing paradigm and today’s data center is ill equipped to take IT there.

What is data centric computing

The IT industry has been moving to a new type of computing, that is focused on short bursts of CPU activity with relatively small packets of data coming off the network (from sensors/outside world, from storage, from other servers, etc.). Those workloads are often transient, short lived, are intended to be performed quickly and may not leave any persistent state.

We can see this in the emergence of micro-services architectures with Docker and k8s containers. But you don’t have to be using containers. It’s also present in machine learning where the update cycle of the neural network (with accelerators) takes lot’s of small bursts of computation while it consumes lots of small data items (pictures, text documents, ticker/status logs, etc. ).

Furthermore, the move to commodity hardware has taken the same x86/ARM core CPUs and used them to execute these small bursts of computation. And for some of these operations that may still make sense. But when the data center uses these same cores to perform data path packet processing. It bogs down the network. It consumes a lot of power, adds overhead (higher latencies), leads to packet loss, injects network jitter and a host of other problems.

So, in order to get the data packets to where they need to be with out those problems, networking endpoints need to be changed out to something designed to support data path critical workloads. Pradeep calls these data path critical work items “run to complete” code.

The critical question is what proportion of IT workloads are “data centric’ vs. not. While it might not be that high today, Pradeep and Fungible are betting that it’s going to be getting much higher over time. If we look at hyper-scalars today they are the forefront of this computing paradigm change and much of their workloads are moving to containerized execution.

The DPU enables data centric computing

Fungible plans to add a DPU that supports a power efficient, “run-to-complete” programming engine to the data center. By using DPUs, they can create a true fabric (using IPoE) that’s low latency, low jitter, lossless and provides full cross-sectional bandwidth.

The problem as Pradeep sees it is that the X86 and ARM cores are just not made to execute run-to-comple workloads well and this is required to provide a true fabric. Whereas Fungible has designed the DPU from the start to execute run-to-complete work.

Pradeep sees the data center of tomorrow utilizing JBoF(lash) & JBoD(isk) boxes with DPU(s) in front of them providing storage server services (block, file and object), JBoGP(Us) or JBoFP(GAs) boxes with DPU(s) in front of them providing accelerator/graphics server services, and compute boxes with DPU(s) and x86/ARM cores with DRAM-Optane PMEM in them providing CPU server and client services. All the DPUs together in a cluster would in total provide true fabric services.

Essentially, the DPUs would take over all data path operations and the storage, GPUS, CPUs would handle everything else. In effect, segregating data path and control path services in the data center.

Greenfield, brownfield or both

Keith and I both assumed this would be great for a green field deployments. But,. Pradeep said it’s designed to be incrementally added to servers, JBoFs, JBoDs, JBoGs/JBoFPs and start providing data path services within current data center fabric environments. Even as the rest of the data center remain unchanged.

At some point we talked about the programming model of the DPU. The DPU offers a bring your own Linux OS that can be programmed in any language you choose. But the critical, data-path functionalityi is coded in “C” to run as fast and as efficiently as possible.

Fungible has designed this hardware themselves. We didn’t get to talk about how they plan to market their product to the data center.

Pradeep also said to stay-tuned, and they were just about to announce their first product offering based on the DPU.

The podcast ran ~38 minutes. Pradeep, given his education and experience, is a very knowledgeable individual about the data center environment today. He’s certainly one of the most interesting IT tecnologist we have talked with in a while on the GreyBeards podcast. To say what Fungible is trying to do is aggressive and bold is an understatement. But Pradeep feels this is the only way forward to liberate the data center from its data path chains today. Both Keith and I thought we needed at least another hour or so to truly understand what they are doing and where they are going with it. 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

Pradeep Sindhu, CEO and Co-Founder, Fungible

Pradeep Sindhu is CEO and Co-Founder of Fungible, a Santa Clara-based startup providing at-scale, next-generation solutions for the data center, cloud and IT industries. He has been at the forefront of the network and processing industry for over three decades.

As the co-founder and CTO of Juniper Networks, he played a central role in the architecture, design and development of Juniper’s M40 router – the M series was the first of its kind, offering the industry true decoupling of the control plane and the forwarding plane.

Prior to Juniper, he was a Principal Scientist and Distinguished Engineer at the Computer Science Lab at Xerox’s Palo Alto Research Center (PARC) pushing the envelope on what silicon could do for networking and processing.

He is passionate about new ways to support our growing data-centric world with the right combination of hardware and software to build the infrastructure our future needs.

104: GreyBeards talk new cloud defined (shared) storage with Siamak Nazari, CEO Nebulon

Ray has known Siamak Nazari (@NebulonInc), CEO Nebulon for three companies now but has rarely had a one (two) on one discussion with him. With Nebulon just emerging from stealth (a gutsy move during the pandemic), the GreyBeards felt it was a good time to get Siamak on the show to tell us what he’s been up to. Turns out he and Nebulon decided it was time to completely rethink/rearchitect shared storage for the new data center.

At his prior company, Siamak spent a lot of time with many customers discussing the problems they had dealing with the complexity of managing, provisioning and maintaining multiple shared storage arrays. Somewhere in all those discussions Siamak saw this as a problem that needed a radical solution. If we could just redo shared storage from the ground up, there might be a solution to all these problems.

Redefining shared storage

Nebulon’s new approach to shared storage starts with an SPU card which replaces SAS RAID cards in a server. But instead of creating SAS RAID groups, the SPU creates a shareable, enterprise class, pool of storage across a throng of servers.

They call a collection of servers with SPUs, Cloud Defined Storage (CDS) and it creates a Nebulon nPod. An nPod essentially consists of multiple servers with SPU cards, with or without attached SSD storage, that are provisioned, managed and monitored via the cloud. Nebulon nPod servers are elements or nodes of a shared storage pool across all interconnected SPU servers in a data center.

In an SPU server with local (SAS, SATA, NVMe) SSD storage, the SPU creates an erasure coded pool of storage which can be used to serve (SAS) LUNs to this or any other SPU attached server in the nPod. In a SPU server without local SSD storage, the SPU provides access to any other SPU server shared storage in the nPod. Nebulon nPods only works with flash storage, it doesn’t support spinning media.

The SPU can supply boot storage for its server. There’s no need to have the CPU running OS code to use nPod shared storage. Yes, the SPU needs power and an active PCIe bus to work, but the functionality of an SPU doesn’t require an operational OS to work. The SPU provides a SAS LUN interface to server CPUs.

Each SPU has dual port access to an inter-cluster (25GbE) interconnect that connects all SPUs to the nPod. The nPod inter-cluster protocol is proprietary but takes advantage of standard TCP/IP services across the network with standard 25GbE switching.

The SPU firmware insures that it stays connected as long as power is available to the server. Customers can have more than one SPU in a server but these would be used for more IO performance. Each SPU also has 32GB of NVRAM for caching purposes and it’s also used for power fail fault tolerance.

In the unlikely case that the server and SPU are completely down (e.g. power outage), clients can still access that SPUs data storage, if it was mirrored (see below). When the SPU server comes back up, it will be resynched with any data that had been changed.

Other Nebulon storage features

Nebulon supports data-at-rest encryption, compression and deduplication for customer data. That way customer data is never in plain text as it travels across the nPod or even within the server from the SPU to SSD storage. Also any customer data written to an nPod can be optionally mirrored and as noted above, is protected via erasure coding.

The SPU also supports snapshotting of customer LUN data. So clients can take copies of LUNs and use these for backups, test, dev, etc. SPUs also support asynchronous or synchronous replication between nPods. For synchronous replication and mirrored data, the originating host only sees the IO complete after the data has been received at the target SPU or nPod.

Metadata for the nPod that defines LUN configurations and which server has LUN data is kept across the cluster in each SPU. But metadata on the location of user data within a server is only kept in that server’s SPU.

We asked Siamak whether nPods support SCM (storage class memory). He said not yet, but they’re looking at SCM NVMe storage for use as a potential metadata and data cache for SPUs.

Nebulon Application Centric storage

All the above storage features are present in most enterprise class storage systems. But what sets Nebulon apart from all other shared storage arrays is that their control plane is entirely in the cloud. That is customers point their browser to Nebulon’s control plane and use it to configure, provision and manage the nPod storage pool. Nebulon supports application templates that can be used to configure nPod storage to support standardized applications, such as VMware VMs, MongoDB, persistent storage for K8S containers, bare metal Linux apps, etc.

With the nPod’s control plane in the cloud it makes provisioning, managing and monitoring storage services much more agile. Nebulon can literally roll out new control plane updatesy to their install base on an almost daily basis. Just like any other cloud based or SAAS application. Customers receive the updated nPod control plane functionality by simply refreshing their browser page.

Nebulon’s GoToMarket

Near the end of our podcast, we asked Siamak about how Nebulon was going to access the market. Nebulon’s goto market is to use server OEMs. That is, they have signed agreements with two (and working on a third) server vendors to sell SPU cards with Nebulon control plane access.

During server purchases, customers configure their servers but now along with SAS RAID card options they will now see an Nebulon SPU option. OEM server vendors will bundle SPU hardware and Nebulon control plane access along with all other server components such as CPU’s, SSDs, NICs, etc, This way, the customer will receive a pre-installed SPU card in their server and will be ready to configure nPod LUNs as soon as the server powers on in their network.

Nebulon will go GA in the 3rd quarter.

The podcast ran ~43 minutes. Siamak has always been a pleasure to talk with and is very knowledgeable about the problems customers have in today’s data center environments. Nebulon has given him and his team the way to rethink storage and address these serious issues. Matt and I had a good time talking with Siamak. 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

Siamak Nazari, CEO Nebulon

Siamak Nazari is the CEO and Co-founder of Nebulon. Siamak has over 25 years of experience working on distributed and highly available systems.

In his position as HPE Fellow and VP, he was responsible for setting technical direction for HPE 3PAR and its portfolio of software and hardware. He worked on HPE 3PAR technology from 2000 to 2018, responsible for designing and implementing distributed memory management and the high availability features of the system.

Prior to joining 3PAR, Siamak was the technical lead for distributed highly available Proxy Filesystem (pxfs) of Sun Cluster 3.0.

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).

0102 GreyBeards talk big memory data with Charles Fan, CEO & Co-founder, MemVerge

It’s been a couple of months since we last talked with a startup, so the GreyBeards thought it was time. We reached out to Charles Fan (@CharlesFan14), CEO and Co-Founder of MemVerge to find out about their big memory solution or as Charles likes to call it, “software defined (big) memory”. Although neither Matt or I had ever talked with Charles before, he’s been just about everywhere in the storage industry throughout his career.

If you have been following my RayOnStorage blog you will have seen a post (Need memory, Intel’s Optane DC PM to the rescue) last year on Intel’s new Persistent Memory solutions using 3D XPoint, called Optane DC PM (data center, persistent memory) . At the announcement Intel made available a couple of ways customers could use Optane DC PM (PMem).

Optane DC PM primer

Native Optane DC PM access modes include:

  • A Memory Mode, which has Pmem emulating a large volatile memory space and uses a defined ratio of DRAM to PMem as a cache to access the Optane DC PM memory behind it.
  • An Application Direct (AppDirect) Mode which supports two sub-modes: a storage device mode that uses Pmem to emulate a persistent, 4KB block storage device; and a byte addressable, persistent memory address space mode that uses Pmem to emulate a large, non-volatile memory space . AppDirect memory content persists across boots, power failures and other system crashes.

Native PMem modes are selectected in the BIOS and are deployed at Boot time. Optane DC PM on a server can be split up into any of the three modes. And currently with Optane DC PM (Gen 1), a single server can have up to 6TB of DC PM which will go up to 8TB with Optane DC PM Gen 2 coming out later this year.

MemVerge Memory Machine

MemVerge has written a “software defined memory” service called the Memory Machine, that sits above the Intel Optane DC PM in server(s) and provides application access AND data services for PMem. .

Charles likens their Memory Machine to what VMware did for CPU cores, ie. they provide memory virtualization. This, Charles believes will bring on the age of Big Memory applications. He feels that PMem, with Memory Machine on top of it, will eliminate the need for high performance, tier 0 storage. Tier 0 storage is ~$10B market today, which he sees shifting from networked storage to PMem solutions. 

Memory Machine Data Services

One of the data services that the Memory Machine offers is a Pmem snapshot service. PMem thick or thin snapshots can be taken any (infinite) number of times (for thick snapshots storage space availability may limit their number) and can be taken up to once per minute. PMem thin snapshots take little time to accomplish and are very PMem space efficient but thick snapshots are a PMem to PMem copy of data, which will take longer to accomplish and will take double the memory of the original PMem being snapshot.

One significant use case for Pmem snapshots is for checkpoint crash recovery. Charles mentioned many securities and financial analysis firms use KDB as streaming data base service to monitor/analyze market activity and provide automated trading and other market services. These firms are always trying to gain an advantage through speed and reduced latency and as a result have moved their time sensitive processing to use in memory data structures/databases.

However, because checkpointing for crash recovery takes time, they usually checkpoint in memory databases only once a day (after market close) and maintain a log of database transactions on SSD. If there’s a system crash, they reload the last checkpoint and re-play all the transaction logs since that checkpoint to bring their in memory database back to the point of crash. Due to the number of transactions these firms do, this sort of crash recoverys can take hours.

With Memory Machine, these customers can take in memory checkpoints every minute and in the event of a crash, only have to re-play a minutes worth of transaction logs which could be done in no time to get back up

Other environments do similar checkpoint crash recoveries all of which could also take advantage of PMem snapshots to take more frequent checkpoints. Charles mentioned Rendering farms on the podcast but long scientific simulations (HPC) and others use checkpoints for crash recovery.

Another data (or application) service offered by Memory Machine is application cloning. Most in memory applications are single threaded. meaning they can only take advantage of a single CPU core (thread). In order to speed up processing, customers must shard (split up) or copy their database and application onto other servers/CPU/cores to provide more processing power. Memory Machine can use its thick or thin snapshots to clone applications in seconds.

Charles also mentioned that Memory Machine offers PMem dynamic reconfiguration. That is instead of having to make BIOS changes and re-boot server(s) to re-allocate PMem across different applications, Memory Machine is allocated 100% of the PMem at boot time but then, on demand, anytime its operating, operators using MemVerge’s GUI/CLI can carve Pmem up into any number of application memory spaces. That is as application demand for in memory data changes, operations can use the Memory Machine to re-allocate PMem to keep up.

Memory Machine also supports PMem clustering or scaling across servers. With the current 6TB (and soon 8TB) per server PMem limit, some customer applications still run out of memory. Memory Machine is able to cluster or aggregate PMem across up to 32 servers to support a single larger, PMem address space of 192TB (Gen 1) or 256TB (Gen 2) DC PM. The Memory Machine uses an RDMA (RoCE Ethernet or InfiniBand) cluster interconnect which adds ~1 microsecond of overhead to access PMem in another server. This comes with PMem automatic data tiering using DRAM, local (on the server) PMem and remote (across cluster interconnect) PMem.

Charles mentioned another data service provided by Memory Machine is (Synch or Asynch) replication. One use case for replication is to create a Pub-Sub service for market data.

Charles believes that in memory databases and data processing workloads are just starting to become popular these days. Besides KDB and rendering, other data processing such as AI training/inferencing, Reddis applications, and other database systems are able to take advantage of in memory, large data structures to speed up their data processing

MemVerge’s EAP (early access program) opened up recently (5/19/2020). Charles suggested anyone using large, in memory data processing, take a look at what the Memory Machine can do and contact them to sign up.

The podcast runs ~45 minutes. Charles was very articulate as well as knowledgeable about the technology and its applications. He was great to talk tech with. Matt and I had a fun time talking Optane DC PM and Memory Machine functionality/applications with him. Listen to the podcast to learn more.

Charles Fan, CEO & Co-founder, MemVerge

Charles Fan is co-founder and CEO of MemVerge. Prior to MemVerge, Charles was a SVP/GM at VMware, founding the storage business unit that developed the Virtual SAN product.

Charles also worked at EMC and was the founder of the EMC China R&D Center. Charles joined EMC via the acquisition of Rainfinity, where he was a co-founder and CTO.

Charles received his Ph.D. and M.S. in Electrical Engineering from the California Institute of Technology, and his B.E. in Electrical Engineering from the Cooper Union.