Nutanix has built a cloud-native Nutanix Enterprise AI (NAI) software stack that can support the deployment of generative AI (GenAI) apps “in minutes, not days or weeks” by helping customers deploy, run, and scale inference endpoints for large language models.
NAI can run on-premises, at the edge, or in datacenters, and in the three main public clouds’ Kubernetes offerings – AWS EKS, Azure AKS, and Google GKE – as well as other Kubernetes run-time environments. This multi-cloud operating software can run LLMs with Nvidia NIM-optimized inference microservices as well as open source foundation models from Hugging Face. The LLMs operate atop the NAI platform and can access NAI-stored data.
Thomas Cornely
Thomas Cornely, SVP for Product Management at Nutanix, stated: “With Nutanix Enterprise AI, we’re helping our customers simply and securely run GenAI applications on-premises or in public clouds. Nutanix Enterprise AI can run on any Kubernetes platform and allows their AI applications to run in their secure location, with a predictable cost model.”
NAI is a component of Nutanix GPT-in-a-Box 2.0, which also includes Nutanix Cloud Infrastructure, Nutanix Kubernetes Platform, and Nutanix Unified Storage, plus services to support customer configuration and sizing needs for on-premises training and inferencing.
Nutanix sees AI training – particularly large-scale generalized LLM training – taking place in specialized mass GPU server facilities. New GenAI apps are often built in the public cloud, with fine-tuning of models using private data occurring on-premises. Inferencing is deployed closest to the business logic, which could be at the edge, in datacenters, or in the public cloud. NAI supports these inferencing workloads and app locations.
Nutanix says NAI has a transparent and predictable pricing model based on infrastructure resources. This is in contrast to most cloud services that come with complex metering and unpredictable usage-based pricing.
NAI deployment scenarios
The usability and security angles have roles here. NAI offers an intuitive dashboard for troubleshooting, observability, and utilization of resources used for LLMs, as well as role-based access controls (RBAC) to ensure LLM accessibility is controllable and understood. Organizations requiring hardened security will also be able to deploy in air-gapped or dark-site environments.
Nutanix diagram
Nutanix suggests NAI can be used for enhancing customer experience with GenAI through improved analysis of customer feedback and documents. It can accelerate code and content creation by leveraging copilots and intelligent document processing as well as fine-tuning models on domain-specific data. It can also strengthen security – including leveraging AI models for fraud detection, threat detection, alert enrichment, and automatic policy creation.
We see NAI presented as an LLM fine-tuning and inference alternative to offerings from Microsoft, Red Hat, and VMware that should appeal to Nutanix’s 25,000-plus customers. Coincidentally, Red Hat has just announced updates to its enterprise offerings including OpenShift AI, OpenShift, and Developer Hub:
Developer Hub – Includes tools for leveraging AI to build smarter applications, including new software templates and expanded catalog options.
OpenShift AI 2.15 – Offers enhanced flexibility, optimization, and tracking, empowering businesses to accelerate AI/ML innovation and maintain secure operations at scale across cloud and edge environments.
OpenShift 4.17 – Streamlines application development and integrate new security features, helping businesses to tackle complex challenges.
On top of that, Red Hat has signed a definitive agreement to acquire Neural Magic – a pioneer in software and algorithms that accelerate GenAI inference workloads.
SUSE also presented its SUSE AI, described as “a secure, trusted platform to deploy and run GenAI applications” at KubeCon North America.
NAI and GPT-in-a-Box 2.0 are currently available to customers. More information here.
Hitachi Vantara has added a low-cost all flash array and object storage to its Virtual Storage One (VSP One) portfolio.
The VSP One portfolio is described as unified hybrid cloud product suite, which includes the on-premises VSP One SDS Block, VSP One Block appliance and VSP One File offerings for on-premises use, and VSP One SDS Cloud (cloud-native SVOS) for the AWS cloud. Hitachi V has now extended VSP One with this new block product and a new object storage appliance.
Octavian Tanese.
The company’s chief product officer, Octavian Tanase, stated: “Enterprises today are navigating an incredibly complex data landscape, with hybrid and multi-cloud environments and the growing influence of GenAI transforming how they operate.”
The QLC flash array provides “high-density, cost-effective storage ideal for large-capacity needs.” It “features public cloud replication providing disaster recovery and higher data availability. It uses dual-ported Samsung 30TB QLC SSDs “offering the best combination of performance and availability.” Hitachi V blogger Michael Hay – – says that the VSP One Block Array has operating software “SVOS improvements ensuring longer media life” for these drives but there are no details.
There is also “additional telemetry, covering performance and wear data, that can be used to analyze individual arrays and our fleet with QLC, learning with our customers over time.” The wear rate telemetry is monitored by Hitachi Remote Ops and visible in the Clear Sight management facility.
We’re not given array details such as the number of drives per chassis, raw capacity, network connectivity, etc. But we are told there is a 4:1 data reduction guarantee plus a 100 percent data availability one as well.
A VSP One Block datasheet says customers can choose either TLC or QLC drives, meaning VSP One Block QLC is basically just a SKU variation and not a separate product. The basic chassis takes up 2RU and can hold up to 3.6 PB of effective storage, implying 900TB raw at a 4:1 data reduction ratio, and 30 x 30TB SSDs, which seems high for a 2RU chassis with controllers inside it. A system can scale out to 65 appliances in total and individual appliances can have up to two NVMe drive expansion shelves. That would explain the 30 drive number, by having them spread across a base and pair of expansion chassis.
VSP One Block Appliance chassis.
There is 256 GBps of available Fibre bandwidth. A VSP One Block model can have Compression Accelerator Modules (CAMs) to offload data reduction processing workloads from controller processors. And patented Dynamic Carbon Reduction (DCR) technology optimizes power consumption by switching controller CPUs into low-power ECO mode during periods of low activity.
There is even less information available about VSP One Object than VSP One Block. We’re told the multi-node S3-compliant object storage product has been “engineered for scalability and provides a robust solution for managing massive volumes of unstructured data driven by AI workloads,” particularly in the media, healthcare, and finance markets.
As we understand things, it’s basically updated Hitachi Content Platform (HCP) software – as a Learn more link on its web page takes you to an HCP webpage. We have no idea what storage media is used and have asked Hitachi V questions about this and the VSP One Block QLC appliance.
There’s a little more information about the Virtual Storage Platform One suite of products here but it’s mostly marketing.
AI infosec startup DeepTempo finds evidence of cyber security incidents by using deep learning to check log data and has launched its Tempo app to do this by running natively in Snowflake.
It has just emerged from stealth and its founding CEO is Evan Powell. Tempo uses a large language model, LogLM, that can identify incidents and work with admin staff on fixing them.
DeepTempo Snowflake diagram
The Tempo app’s agentless LogLM detects anomalies in network traffic and provides additional context such as similar attack patterns from the MITRE ATT&CK matrix, potentially impacted entities, and other information needed by security operations teams for triage and response. DeepTempo claims customers get faster detection of attack indicators – including new and evolving threats – and can optimize security spend by running the DeepTempo software on their existing security data lakes.
Powell stated: “Attackers are using AI and collaboration to surpass defenders in innovation. Our mission at DeepTempo is to return the initiative to the defenders. By making available our AI-driven security solution as a Snowflake Native App, we are able to leverage Snowflake’s high availability and disaster recovery along with their security reviews and controls. Our Tempo software is available with immediate availability to the thousands of Snowflake customers.”
A Tempo blog explains: “Built and pre-trained with the assistance of a major global financial institution, Tempo has demonstrated a unique blend of accuracy and practicality, with false positive and false negative rates lower than one percent after adaptation to a new user’s domain. Tempo has been initially optimized to work with Netflow data and DeepTempo is recruiting users with similar logs such as VPC Flow logs as design partners.
“Tempo can identify subtle deviations from normal behavior, including longer-duration attacks that might slip past traditional signature-based systems. This capability is particularly valuable in the face of innovative attackers, as Tempo doesn’t need to keep track of specific attack patterns. Instead, it simply recognizes when activities deviate from the norm, triggering detection for any threat that emerges.”
Tempo is claimed to save money “by enabling organizations to keep more of their logs within Snowflake and use their SIEMs primarily for incident response rather than log storage … In one case study involving a large financial institution, projected savings reached several million dollars, representing up to 45 percent of their existing SIEM spending. These savings stem from the ability to use Snowflake as the system of record instead of pushing NetFlow and VPC flow logs into a separate SIEM.”
DeepTempo actually uses software technology from another startup, Skidaway, co-founded by CEO Evan Powell and CTO Brennan Lodge. Lodge has a cyber security, data management, and financial services background, gained from working at JP Morgan Chase, the Federal Reserve Bank of New York, Bloomberg, and Goldman Sachs.
Powell has been the founding CEO for several acquired startups: Clarus Systems, DDN-acquired Nexenta, Brocade-bought StackStorm, and Kubernetes-focused and DataCore-acquired MayaData.
Skidaway has developed the deep learning Log Language Model (LogLM) software to detect cyber security incidents by analyzing and filtering raw log data that is used by DeepTempo in its Tempo app. The LogLM software can run on-premises in any Kubernetes-based workload management system, or in a data lake, like the Tempo Snowflake native app, for example, and can scale to handle petabytes of log data.
DeepTempo graphic
This incident detection is done without sending the raw data to SIEM (Security Information and Event Management) systems.
LogLM is a generalized log analysis tool to detect anomalies and support troubleshooting. Skidaway claims existing log analysis tools are task-specific and need task-specific data sets with specialized log label pairs for each task. LogLM has an instruction-based framework that can interpret and respond to user instructions by generalizing across multiple log analysis tasks.
Eric Zietlow, the DevRel leader and platform lead at Skidaway, spent time at Powell’s MayaData startup.
DeepTempo’s Tempo is available in preview mode and is the first native app for cyber security in the Snowflake Marketplace. Find out more about using Tempo inside Snowflake here.
Bootnote
A Cornell University software engineering paper on LogLM: From Task-based to Instruction-based Automated Log Analysis, discusses automatic log analysis and how to transform log label pairs from multiple tasks and domains into a unified format of instruction response pairs. The abstract reads: “Experimentally, LogLM outperforms existing approaches across five log analysis capabilities, and exhibits strong generalization abilities on complex instructions and unseen tasks.”
VDURA has upgraded its VDURA Data Platform (VDP) storage operating system to provide more performance, scalability, and simpler management – with a twin focus on AI and HPC users.
Ken Claffey
VDURA was previously known as Panasas, and its flagship product was PanFS (parallel file system software). It claims VDP is a significant modernization on previous releases, with a move to a fully parallel, microservices-based architecture, a new flash-optimized metadata engine, and an enhanced object storage layer.
CEO Ken Claffey stated: “Our latest release simplifies data management while delivering exceptional performance and reliability. By enabling enterprises to scale seamlessly, VDURA accelerates AI initiatives and helps businesses tackle complexity to achieve transformative results.”
The VDP software introduces VeLO (Velocity Layered Operations) and a VPOD (Virtualized Protected Object Device) concept. VDP is deployed as discrete microservices, simplifying deployment across thousands of nodes and helping ensure linear performance scalability with an infinitely expandable global namespace.
VDP layers
It has intelligent data orchestration capabilities that enable optimal data placement across discrete tiers of storage, all sharing a unified data and control plane within a single namespace.
VeLO is a key-value store used within VDP’s Director layer for handling small files and metadata operations, often found in AI workloads. VDP supports an infinitely scalable number of VeLO instances in the same Global Namespace. VeLO is optimized for flash and delivers up to two million IOPS per instance.
VPODs are discrete, virtualized, protected storage units, which provide the foundation of data storage in hybrid nodes. VPOD instances are infinitely scalable, operate within a unified global namespace, and provide high performance and flexible scalability. Data is safeguarded through erasure coding across multiple VPODs in a VDP cluster, with an optional, additional layer of erasure coding within each VPOD for enhanced protection. This multi-layered approach achieves up to 11 nines of durability with minimal overhead. Data reduction services further optimize efficiency, reducing costs and total ownership expenses.
VDURA has also introduced a V5000 Certified Platform – a hardware architecture combining modular storage nodes that can be configured for maximum throughput, capacity, or IOPS, depending on the user’s requirements.
VDURA V5000 diagram
It includes:
1RU Director Nodes powered by the latest AMD EPYC 9005 processors, Nvidia ConnectX-7, Broadcom 200Gbit/sec Ethernet, SAS 4 adapters, and Phison PCIe NVMe SSDs, optimized for high IOPS and metadata operations through VeLO.
Hybrid Storage Nodes incorporating the same 1RU server used with the Director Node and 4RU JBODs running VPODs for cost-effective bulk storage with high performance and reliability.
VDURA tells us that VDP supports a flexible ratio of HDD to flash content, meaning customers can balance capacity and throughput, while maintaining a consistent global namespace, and optimizing VDP configurations for cost, performance, and durability needs. We asked VDURA a few questions about this VDP release to find out more.
Will The VDURA Data Platform (VDP) support GPU Direct?
Yes, VDURA is planning to support GPUDirect Storage (GDS), as well as RDMA and RoCE (v2), summer of 2025. Ultra Ethernet Transport support will follow afterwards.
Do the V5000 Director Nodes support SAS?
The V5000 Director Nodes are all NVMe-based and do not use SAS. The Storage Nodes do support SAS 4 adapters to manage high-density, high-performance JBODs within the platform, enabling scalable and cost-effective bulk storage with optimized performance.
How do V5000 Director nodes communicate with VPODs in hybrid nodes?
V5000 Director Nodes communicate with VPODs over a high-speed network. This can be either Ethernet 100/200/400 or InfiniBand NDR. SAS is not used as a network between Director and Hybrid Nodes.
How does a parallel file system “talk” to a VPOD object storage backend? Do the Director Nodes do file-to-object mapping?
The VDURA Data Platform utilizes a unified namespace where Director Nodes handle metadata and small files via VeLO and larger data through VPODs. The Director Nodes manage file-to-object mapping, allowing seamless integration between the parallel file system and object storage.
What Phison SSDs are used in the V5000 Director Nodes?
The V5000 Director Nodes are equipped with Phison Pascari X200 PCIe NVMe SSDs with various capacity options.
Is VDP with VeLO and VPODs a disaggregated architecture?
Yes, VDP with VeLO and VPODs instances operates as part of a disaggregated, composable architecture.
The software instances are disaggregated from the physical hardware via the distributed microservices architecture.
The metadata and data are disaggregated to different logical and physical domains within the same global namespace.
The hardware platforms are themselves disaggregated and composable with compute-intensive Director Nodes that house the VeLO instances and then the Storage Nodes that house the VPOD instances, with a number of Director Nodes and Storage Nodes supported per cluster/namespace, all connected via a high-speed network.
Will VDP run in the public clouds, considering it is microservices-based and supports storage classes?
Yes, we’re providing early access to the cloud edition of VDP to some of our customers now. General availability is set for the first half of 2025, enabling VDURA to seamlessly support both on-prem and public cloud instances of VDP.
VDURA’s platform combines the high-performance parallel file system capabilities with object storage in a single namespace.
IBM Storage Scale (aka GPFS) has a similar design point origin to Lustre as a “scratch” file system. IBM has developed its data protection capability over time bolting on additional layers into the ever-deeper, more complex stack. However, it does not offer the same level of protection as VDP and the biggest difference we hear from customers that have experience of both is that VDP offers far greater ease of use and reliability.
DDN’s Lustre is a “scratch” file system. It is not designed to protect your data. Nor is it designed for the reliability or the ease of use required by enterprise customers. At the most basic level, it requires a third-party/additional software stack to provide data protection and handle hardware failures. In DDN’s case, they rely on their old RAID stack to provide this data protection. This discrete RAID layer is itself based on the legacy HA pair controller architecture. There are lots of problems with this approach at scale and that is why the availability and durability of these types of systems degrade as the number of storage nodes grows.
This is in stark contrast to VDP, which has advanced data protection built into the file system itself. Indeed, we protect data at multiple layers in the stack, which means that as the number of nodes in the cluster grows, our availability and durability only increases. This single integrated stack approach – and its self-healing capabilities – all help culminate in the superior ease of use and reliability that our customers enjoy.
Compared to WEKA, VDURA offers better scalability and integration for hybrid storage, leveraging both flash and HDD, which allows more flexible tiering with significant cost benefits and ease of use. If we compare V5000 with the latest WekaPOD announcement, we can deliver the same or even better performance for a much lower price.
Micron’s 6550 ION SSD matches the 61.44 TB capacity of Samsung, Solidigm, and WD’s competing drives, but promises higher performance as it uses the PCIe gen 5 bus instead of PCIe gen 4.
The 6550 ION is to be used in networked AI data lakes, and for ingest, data preparation and checkpointing, file and object storage, public cloud storage, analytic databases, as well as content delivery.
Micron says the drive is the industry’s first E3.S and PCIe 5 60 TB SSD. It has OCP 2.5 support with active state power management (ASPM). This allows the drive to idle at 4 watts in the L1 state versus 5 watts in the L0 state, improving energy efficiency by up to 20 percent when idling.
Alvaro Toledo
Alvaro Toledo, Micron’s Data Center Storage Group VP and GM, said in a statement: “Featuring a first-to-market 60 TB capacity in an E3.S form factor and up to 20 percent better energy efficiency than competitive drives, the Micron 6550 ION is a game-changer for high-capacity storage solutions to address the insatiable capacity and power demands of AI workloads.”
He said it “achieves a remarkable 12 GBps while using just 20 watts of power, setting a new standard in datacenter performance and energy efficiency.”
The 6550 ION comes in E3.S, E1.L, and U.2 form factors. It is an all-Micron drive using in-house DRAM, NAND, controller, and firmware. From the security point of view, it supports SPDM 1.2 for attestation, SHA-512 for secure signature generation, and is TAA-compliant and FIPS 140-3 L2 certifiable.
The drive’s endurance is one full drive write a day for the five-year warranty period. It’s built with what Micron calls its G8 NAND, with 232-layers. In June this year, Micron announced 276-layer 3D NAND, saying it was G9 NAND.
Micron 6550 ION SSDs
The 6550 ION follows on from the existing 6500 ION, which is a 30.72 TB PCIe gen 4 SSD with an NVMe link. It was announced in May 2023, built with 232-layer TLC NAND, and marketed as having TLC performance with QLC pricing. The drive was produced in U.3 and E1.L form factors, and the 6550 comes in these plus the E3.S form factor. The 6550 is built with Micron’s G8 3D NAND in TLC format, and claimed to be “one to three NAND generations ahead of competing 60 TB SSDs,” meaning drives from Samsung, Solidigm, and Western Digital, which all use the PCIe gen 4 bus.
We think Micron has renumbered its 3D NAND generations and missed out a generation as well. B&F asked to clarify its 3D NAND generation numbering and layer counts.
Micron-supplied 3D NAND generation table.
For reference, Samsung’s QLC BM1743 uses its seventh generation 176-layer 3D NAND. Solidigm’s QLC D5-P5336 has 196-layer NAND, and Western Digital’s TLC DC SN655 drive uses 112-layer NAND with a PCIe gen 4 interface.
The actual 6550 performance numbers are 12.5 GBps for sequential read/write bandwidth, 1.6 million random read IOPS, and 70,000 random write IOPS. This is faster than the competing drives named above:
Samsung BM1743 – 7.2/2 GBps sequential read/write and 1.6 million/110K random read/write IOPS
Solidigm D5-P5336 – 7/3.3 GBps sequential read/write and 1.005 million/43K random read/write IOPS
WD DC SN655 – 6.8/3.7 GBps sequential read/write and 1.1 million/125K random read/write IOPS
As the 6550 uses the faster PCIe gen 5 bus, the sequential speed advantage is hardly surprising. It is slower in terms of random read and write IOPS than Samsung’s BM1743.
Micron claimed that “as the world’s first E3.S 60TB SSD, the 6550 offers best-in-class density, reducing rack storage needs by up to 67 percent.” It can “store over 1.2 petabytes per rack unit” and by “using a 1U high-density server, such as the HPE ProLiant DL360 Gen11 that can accommodate 20 E3.S drives per rack unit, operators can load servers in a single rack with 44.2 petabytes.”
The 6550 ION can be fully written in 3.4 hours, while competing drives take up to 150 percent longer to fill. Micron says the 6550 ION delivers:
179 percent faster sequential reads and 179 percent higher read bandwidth per watt
150 percent faster sequential writes and 213 percent higher write bandwidth per watt
80 percent faster random reads and 99 percent higher read IOPS per watt
Specifically with AI workloads, it has:
147 percent higher performance for Nvidia Magnum IO GPUDirect Storage (GDS) and 104 percent better energy efficiency
30 percent higher 4KB transfer performance for deep learning IO Unet3D testing and 20 percent better energy efficiency
151 percent improvement in completion times for AI model checkpointing while competitors consume 209 percent more energy
With large AI training jobs involving models with billions of parameters, checkpointing is sometimes run as often as hourly, causing GPUs to be idle for minutes or even tens of minutes while the checkpoint is written to SSD storage. Faster checkpoints pay off with faster training job times and fewer idle GPU hours.
Open source storage systems supplier 45Drives has developed SnapShield ransomware protection and CephArmor encryption for Ceph.
Ceph, developed by RedHat, is an open source object, block, and file storage with three copies of data kept for reliability. 45Drives is a Protocase subsidiary with offices in North Carolina and Nova Scotia. It supplies the Storinator storage server, Stornado all-flash server, Proxinator virtualization server, Destroyinator drive wiping, enterprise drives, plus other products.
SnapShield uses real-time behavioral analysis and functions as a “ransomware-activated fuse,” snapshotting files every five minutes. When it detects ransomware, it disconnects the compromised client from the server and snapshots existing files. The theory is that the attack is stopped quickly after it starts and damage is limited.
45Drives president Doug Milburn claimed: “It catches the attack within a few tens of files.”
SnapShield maintains detailed logs of the malicious activity, produces a list of damaged files, and offers a restore function to “quickly repair” any affected files.
45Drives diagram
There is no requirement for client-side agents and it has minimal impact on system performance. It’s compatible with 45Drives storage systems running ZFS or Ceph with Windows file sharing.
45Drives says Ceph lacks native block and file encryption and it has partnered with the University of New Brunswick (UNB), Faculty of Computer Science, to develop CephArmor object-level encryption to fill the gap. This is an enhancement to Ceph’s Reliable Autonomic Distributed Object Store (RADOS) layer and encrypts data, at object-level, before it is stored. Evaluations on the Storinator hardware have shown that the added CephArmor security layer maintains Ceph’s performance levels.
We’ll have to wait, though, as the CephArmor project is expected to be ready for implementation by the end of 2025.
Apache Cassandra is an established open source, NoSQL database designed for handling workloads across commodity servers. So what applications is it now supporting?
The annual Cassandra Community survey has landed, revealing Cassandra’s evolving usage. Among respondents, 41 percent said Cassandra was their organization’s primary database, with more than 50 percent of enterprise data going through it. Over a third (34 percent) said 10 to 50 percent of their enterprise data was handled by Cassandra.
“Scalability” was cited by 78 percent of respondents as a reason for using the database, while 73 percent claimed it was down to “performance.”
Cassandra Community Survey November 2024 chart
Among multiple use cases at organizations, 47 percent use the database for time series data, and 34 percent use it for event logging. In addition, 31 percent use the platform for data aggregation.
Other significant uses include online retail/e-commerce, user activity tracking, user profile management, fraud detection, and backup and archiving.
In the future, 43 percent vowed to use Cassandra for AI workloads, and 38.5 percent planned to use it for machine learning workloads. Currently, 36 percent of users said they were already “experimenting” with the database to run at least one generative AI app.
In terms of data volumes, 30 percent currently run over 100 TB on Cassandra, and 27 percent handle 10 to 100 TB on it. Just under a quarter (23 percent) put 1 to 10 TB through it.
The survey found that 35 percent of Cassandra workloads were already in the cloud, and 25 percent of organizations pledged to put 10 to 50 percent of their workloads into the cloud over the next 12 months. Eight percent said they would be moving at least half of their workloads into the cloud in the next year.
Some 37 percent of Cassandra users had been using the platform for five to ten years, and nearly a fifth (18 percent) had used the database for upwards of ten years.
NetApp has refreshed the low end of its all-flash A-Series AFF arrays following the May midrange and high-end upgrade. It has also updated the capacity-optimized C-Series hardware and added functionality to StorageGRID object storage software.
Customers can now access its storage “at more accessible entry points, making it easier to scale up from a smaller starting point or expand their capabilities to remote and branch locations,” Net App said in a statement.
Sandeep Singh
Sandeep Singh, Enterprise Storage SVP and GM at NetApp, described the updated A-Series as “more powerful, intelligent, and secure”, and said the C-Series is more “scalable, efficient, and secure.”
A-Series
Until May, NetApp’s ONTAP-powered A-Series comprised the A150, A250, A400, A800, and A900. The bigger the number, the more powerful the system, with generally faster controllers and higher capacity as we move up the range. That naming was discontinued for certain systems in May when the company added three new models: A70, A90, and A1K (not A1000), which refreshed the A400, A800, and A900 – the midrange and high-end A-Series. No end of availability was announced for the A400, A800, and A900.
A major hardware change included the move to Intel’s Sapphire Rapids gen 4 Xeon SP processors.
NetApp AFF A20, A30 and A50.
Now NetApp has attended to the low end (A20, A30, and A50 systems), saying they have “sub-millisecond latency with up to 2.5x better performance over their predecessors.” That implies they get Sapphire Rapids CPUs as well. No end of availability has been announced for the existing low-end A150 and A250 arrays either.
The AFF A20 starts at 15.35 TB. The AFF A30 can scale to more than 1 PB of raw storage. The AFF A50, we’re told, delivers twice the performance of its predecessor in a third of the rack space.
Logic would suggest the A20 is the new low-end model, with the A30 positioned to replace the A150, and the A250 giving way to the A50. The implied new A-Series range, once the prior models are declared end-of-life, will be the A20, A30, A50, A70, A90, and A1K. NetApp has provided tech specs for the new systems;
Competitor Dell upgraded its PowerStore unified file and block storage arrays to gen 4 Xeon processors in May, with the range starting at the 500T and extending through the 1200T, 3200T, and 3200Q systems to the high-end 5200T and 9200T.
C-Series
NetApp AFF C-Series C30, C60 and C80.
Compared to the A-Series, NetApp’s C-Series are higher-capacity and lower cost all-flash ONTAP arrays using QLC (4bits/cell) SSDs. In February last year, the range consisted of three products – the C250, C400, and C800 – which all scaled out to 24-node clusters. They use NVMe drives, and the smallest, the C250 in a 2RU chassis, had 1.5 PB of effective capacity.
NetApp says there are new AFF C30, C60, and C80 systems with “an industry-leading 1.5 PB of storage capacity in two-rack [unit] deployments.” No change there, then. We’re told by Singh they are ”scalable, efficient, and secure.”
StorageGRID is an on-premises scale-out, S3-compatible object storage system. The existing high-end SGF6112 product now supports 60 TB SSDs, “doubling the density of object deployments,” NetApp said in a statement. The previous maximum raw SSD capacity was 368.4 TB using 12 x 30.7 TB drives in the 1RU chassis. These drives were introduced last May. Doubling that would imply 736.8 TB from 12 x 61.4 TB drives. Both Samsung and Solidigm supply 61.44 TB QLC SSDs.
The StorageGRID object storage software has been upgraded to v11.9 “with increased bucket counts.” It can now have “metadata-only and data-only nodes for increased performance with small object workloads and mixed-media grids.”
50 percent will move to cloud – this is split evenly across different cloud deployment options
24 percent will go to hybrid cloud, 24 percent will use multi-cloud, and 24 percent will use a Cassandra-as-a-Service
37 percent will run their environments in private datacenter environments
Cassandra users are predominantly running their own environments
94 percent run their own self-managed deployments
14 percent use service providers to manage Cassandra for them
Self-managed deployments include more complex deployments, both multi-cloud (20 percent) and hybrid cloud (16 percent)
84 percent of community members are planning a migration
23 percent will move in the next 6 months
48 percent will move in 6-12 months
13 percent will move, but in more than a year
16 percent do not plan to migrate to new versions
The Cassandra community is shifting from experimentation to production around AI
More than 50 percent of respondents have one or more GenAI use cases in production
28 percent of users have two use cases in production
17 percent of users have three or more use cases in production
…
Q3 2024 revenues for cloud storage provider Backblaze were up 29 percent to $32.6 million with a GAAP loss of $12.8 million, better than the year-ago $16.1 million loss. The B2 Cloud storage segment grew 39 percent to $16.2 million while the original computer backup business grew 20 percent to $16.4 million.
It looks set to be overtaken by B2 Cloud storage revenues next quarter, but analyst Jason Ader reports: “The 17 percent growth rate expected in the fourth quarter is a sharp deceleration from the 29 percent rate reported in the third quarter, and primarily reflects a slowdown in the B2 Cloud business where growth is expected to drop below 25 percent due mainly to higher churn and a go-to-market reset.”
CEO Gleb Budman said: “I’m excited that we have kicked off a go-to-market transformation and continue to build our upmarket momentum with two multi-year deals, each totaling approximately $1 million. We are also aggressively executing cost efficiencies throughout the organization to accelerate being adjusted free cash flow positive by Q4 2025.”
Ader said about the sales reset: ”Under new CRO Jason Wakeam, Backblaze is in the process of overhauling its go-to-market strategy, which is focused on three major areas: 1) upskilling, … 2) prioritizing partners in the channel … and 3) aligning the sales and marketing teams on a core set of sales plays.
“Backblaze is increasingly focused on driving cost efficiencies and improving its operating leverage. To this end, the company announced a 12 percent reduction in workforce, effective immediately, largely targeted at headcount reduction within marketing. In addition, Backblaze kicked off a zero-based budgeting approach, which now sees the company putting its existing vendors out to bid and negotiating all contracts. These initiatives should lead to an $8 million year-over-year decrease in run-rate operating expenses, helping the company achieve its target of 20 percent adjusted EBITDA margin in the fourth quarter of 2025.”
…
Cerabyte, developing ceramic-based data storage systems, announced its participation at SuperComputing 2024 (SC24), taking place at the Georgia World Congress Center from November 17-22. It will present in sessins at the Arcitecta booth. Arcitecta and Cerabyte are both members of the Active Archive Alliance. Arcitecta’s booth is designed in a way where they invited Cerabyte and other vendors to present in the Arcitecta booth as part of the Arcitecta Co-LAB at SC2024. Arcitrectya says the Co-LAB “is an exciting joint endeavor with the company’s customers, partners and friends. The lab offers a unique opportunity to engage with HPC thought leaders, including Cerabyte, Princeton University, the University of Melbourne and many others, who will ‘take over’ the Arcitecta booth. They will delve into forward-thinking ideas, share insights and experiences, present groundbreaking research, and discuss topics ranging from the future of big data to strategies for resilience against loss.”
…
Analyst house DCIG announced availability of the 2025-26 DCIG TOP 5 Modern SDS Block Storage Solutions Report. The top 5 are;
Data archiver FalconStor reported Q3 2024 revenues of $2.9 million, down 12 percent year-over-year, with a GAAP loss of $680,000, better than the year-ago $840,000 loss. CEO Todd Brooks said: “Our Q3 results highlight the ongoing strength of our Hybrid Cloud ARR run-rate growth across Cloud, On-Premises, and MSP segments, reflecting the effectiveness of our strategy and solutions.” If you say so.
…
SaaS data protector HYCU says Box users can use the latest HYCU R-Cloud integration, in addition to existing Box data protection capabilities, to safeguard data and recover from any data loss scenario. Valiantys, an Atlassian global consulting and services provider and Box partner, helped develop the R-Cloud integration for Box to provide these additional backup and recovery capabilities. HYCU is showcasing the R-Cloud data protection for Box capabilities at BoxWorks (Booth #1), Nov 12 – 13, Pier 27 in San Francisco.
…
Reuters reports Kioxia expects NAND demand to rise 2.7x between now and 2028. It’s readying a major capacity expansion at its new fab at Kitakami in Iwate prefecture, north of Tokyo. The Japanese government is providing up to $1.64 billion to Kioxia and Western Digital to expand capacity at Yokkaichi and Kitakami.
…
Kioxia is getting involved in CXL. It says it has been adopted by Japan’s national research and development agency, New Energy and Industrial Technology Development Organization (NEDO), for its proposal regarding CXL memory on the Development of Manufacturing Technology for Innovative Memory to enhance the post-5G information and communication system infrastructure. The objective is to develop memory that offers lower power consumption and higher bit density than DRAM, and faster read speed than flash memory. Kioxia does not make DRAM. A Kioxia diagram illustrates its view (right).
…
Kioxia, Reuters reports, has made a fresh filing for an IPO, partly to finance the ramp for its Kitakami 2 fab and its BiCS8 technology, as well as return cash to its private equity owners. The latest IPO intention is to go for a listing between December 2024 and June 2025. Kioxia anticipates receiving approval from the Tokyo Stock Exchange in late November, with the indicative price of the IPO disclosed at that time.
…
Micron said its low-power double data rate 5X (LPDDR5X) memory and universal flash storage 4.0 (UFS 4.0) are validated for use with, and featured in the reference designs of, the latest mobile platform from Qualcomm Technologies for flagship smartphones, the Snapdragon 8 Elite Mobile Platform.
…
MSP backup storage supplier N-able reported Q3 2024 revenues up 8.3 percent year-over-year to $116.4 million, but down from last quarter’s $119.4 million. There was a $10.8 million GAAP profit, up 80 percent year-over-year, and subscription revenue rose 9.3 percent year-over-year to $115 million, again down sequentially from the prior quarter’s $117.4 million.
…
Cloud file services supplier Nasuni is working with major brands in the consumer and retail market (such as Mattel, Crate & Barrel, Williams Sonoma, BJ’s Wholesale Club, Barnes & Noble, and Patagonia) to optimize their cloud infrastructure, streamline collaboration, and reduce costs ahead of the holiday season. Other Nasuni customers include Pernod Ricard, Peter Millar, Dyson, SharkNinja, and Tommy Bahama.
Kelly Wells
…
Object First, which supplies a Veeam backup target appliance, promoted Kelly Wells to COO. She had been overseeing the Global Operations organization since joining last year, coming from being VP Customer Success & Enablement at Axcient.
…
OWC (Other World Computing) announced that 100 percent of its Thunderbolt docks and hubs, USB-C docks, storage, and Thunderbolt (USB-C) cables are fully compatible with Apple’s latest iMac with M4 release. Its USB-C Dual HDMI 4K Display Adapter offers seamless compatibility with this model.
…
PNY today announced specs and availability of two new high-performance DDR5 desktop memory products engineered for PC gamers and enthusiasts. XLR8 Gaming DDR5 and XLR8 Gaming EPICheat spreader design offer dual support for both Intel XMP 3.0 and AMD EXPO, and will be available as a 32 GB kit (2 x 16 GB) with speeds ranging from 5,600 MHz to 6,400 MHz with a CAS latency of 36.
…
Solix Technologies unveiled its SOLIXCloud Enterprise Data Lake that enables organizations to develop applications within their AI infrastructure, integrating governance elements like metadata and cataloging for robust data management. It provides a comprehensive framework for high-performance data fabric for streaming transactions, and ensures compliance with complex data regulations. Solix Enterprise Data Lake supports structured, unstructured, and semi-structured data across a wide range of open table and open file formats including Apache Hudi, as well as Parquet, CSV, Postgres, and Oracle. It also incorporates cloud-native object storage tiers and enables auto-scaling of compute engines including Apache Spark. More information here.
…
TrendForce reports that HBM vendors are considering whether to adopt hybrid bonding – which does not require microbumps between HBM DRAM layers – for HBM4 16hi stack products and have confirmed plans to implement this technology in the HBM5 20hi stack generation.
…
Veeamannounced the addition of the Recon Scanner to Veeam Data Platform for free; a new lightweight software agent designed to proactively scan Veeam backup servers. From now on, it’s available to all Veeam Data Platform Premium customers. The Recon Scanner recognizes suspicious activity in the backup servers and maps it to adversary tactics, techniques, and procedures (TTPs) so that organizations can take defensive and mitigative actions.
…
UK-based Predatar’s Cyber Recovery Orchestration has achieved Veeam Ready Security status in the Security category, and is the only Veeam Ready solution that alerts Veeam users of confirmed malware that has been ingested into their backups using Veeam’s Incident API. Predatar uses AI-powered threat detection to identify signs of hidden malware that has been ingested into its customers’ storage environments. It then automates recovery tests and malware verification on suspect workloads. Predatar will also run a search to check if viruses have spread.
…
Virtuozzo Hybrid Infrastructure 6.3 has been released with new features to enhance disaster recovery, streamline backup management, improve storage capabilities, and optimize Kubernetes networking.
Seamless backup with Commvault integration
Integration with Storware and Cloudbase Coriolis disaster recovery solutions
Broadcom announced that VMware Live Recovery will support Google Cloud VMware Engine (GCVE) as a target Isolated Recovery Environment (IRE) for VCF workloads, in addition to VMware Cloud on AWS and on-premises IRE, for both cyber and disaster recovery. This builds on VMware Live Recovery’s existing protection of GCVE sites as a source, and enables a consistent, secure, and simplified experience for those looking to protect VMware workloads running on-premises or in the cloud to GCVE. VMware vDefend Advanced Service for VCF now offers GenAI-based intelligent assistance to help IT security teams proactively triage sophisticated threat campaigns and recommend remediation options. For more details, read these blogs.
NetApp is pushing out its storage solutions through the cybersecurity channel after signing a distribution deal with global cyber player Exclusive Networks. The partners reckon that combining security with storage is a canny offer in the market as ransomware tries to take hold, and protection for mushrooming AI data becomes increasingly important.
Rob Tomlin
Initially, the pair said they will provide “highly secure, data-centric solutions” to channel partners in the UK and Ireland as data-centric approaches are “no longer an option but a requirement” for ransomware protection and data breach prevention.
As a result of the deal, NetApp will become Exclusive’s primary data infrastructure vendor in the UK and Ireland. There are currently no confirmed plans to extend the deal to other territories.
“We see data security and resilience as significant growth sectors and a key part of our cybersecurity strategy,” said Rob Tomlin, managing director of Exclusive Networks UK & Ireland. “NetApp became the obvious partner due to their best-in-class technology, channel-first approach, and strong technical integrations with many of our core cybersecurity vendors. NetApp’s intelligent data infrastructure solutions are a strategic addition to our cybersecurity portfolio.”
Sonya Mathieu
Sonya Mathieu, partner lead for NetApp UK & Ireland, added: “This leverages Exclusive Networks’ specialist cyber expertise and partner ecosystems, and will introduce NetApp’s intelligent data infrastructure to new customers, empowering businesses to navigate today’s complex security landscape with unmatched data protection and recovery capabilities.”
For the half-year, Exclusive reported revenues of €723 million ($779 million), which was an annual drop of 7 percent, largely due to lower hardware sales. By bringing NetApp into the fold, Exclusive will be generating extra hardware sales.
Earlier this week, Exclusive posted a 10 percent increase in third-quarter sales. The Euronext-listed company is currently in talks with equity investment firms to take it private in a deal valued at €2.2 billion ($2.4 billion) this July.
Huawei’s in-house development of Magneto-Electric Disk (MED) archive storage technology combines an SSD with a Huawei-developed tape drive to provide warm (nearline) and cold data storage.
MED technology was first revealed back in March. We were told that, facing potential disk supply disruption due to US technology export restrictions, Huawei was working on its own warm and cold data storage device by combining an SSD, tape cartridge, and drive in a single enclosure. Its storage portfolio could then run from fast (SSD) for hot data and MED for warm and cold data, skipping disk drives entirely.
Presentation images of the MED now show a seven-inch device:
The MED is a sealed unit presenting a disk-like, block storage interface to the outside world, not a streaming tape interface. Inside the enclosure there are two separate storage media devices: a solid-state drive with NAND, and a tape system, including a tape motor for moving the tape ribbon, a read-write head, and tape spools.
This is unlike current tape cartridges, which contain a single reel of tape, approximately 1,000 meters long, and have to be loaded into a separate drive for the tape to be read and have data written to it. A tape autoloader contains the motor and spare reel with tape cartridges loaded into it and moved to the drive by a robotic mover. Much bigger tape libraries also have robotics to select cartridges from the hundreds or thousands stored inside them, and transport them to and from the tape drives.
The MED contains an internal motor to move the tape and an empty reel on which to rewind the tape from the full reel after it is pulled out and moved through the read and write heads. A conceptual diagram of the device illustrates its design:
The MED contains a full reel of tape, about half the length of an LTO tape, motor, read-write heads and an empty reel to hold the used tape. Huawei engineers could choose to have the tape ribbon positioned by default with half on one reel and half on the other so that the read-write heads are at the midpoint of the ribbon, shortening the time to get to either end of the tape.
The system is designed to be a combined archive for cold data and nearline store for warm data. Data flows into the MED through the SSD at NAND speed, from where it is written to the tape in sequentially streamed blocks. Warm data can be read from the SSD at NAND speed. Cold data is read from the MED more slowly as it has to be located on the tape and the tape ribbon moved to the right position before reading can begin. This can take up to two minutes.
The MED has a disk-like, block interface, with the SSD logically having a flash translation layer (FTL) in its controller that takes in incoming data and stores it in NAND cell blocks. From there, a logical second tape translation layer assembles them into a sequential stream and writes them to the tape.
When the MED receives a data read request, the controller system locates the requisite blocks using a metadata map, stored and maintained in the NAND, and then fetches the data either from the NAND, or from the tape, streaming it out through the MED’s IO ports.
Huawei and its Chinese suppliers have developed their tape media and the read-write technology, not using IBM LTO tape drive technology or LTO tape media, which is made by Fujifilm and Sony. The tape media ribbon is about half the length of an LTO tape and has a much higher areal density. The MED NAND is produced in China as well. Huawei is open to using NAND from other suppliers should US technology export restrictions allow it.
The MED system and its components are protected by patents. The first-generation MED should arrive sometime in 2025. A second-generation MED, with a 3.5-inch disk bay slot size, with a shorter and much higher density tape ribbon, has a 2026/2027 position on the MED roadmap:
A gen 1 MED will store 72 TB, and draw just 10 percent of the electricity needed by a disk drive.
It should have a 20 percent lower total cost of ownership than an equivalent capacity tape system.
A gen 1 MED rack will deliver 8 GBps, hold more than 10 PB, and need less than 2 kW of electricity
We don’t know if the 72 TB capacity is based on raw or compressed data.
The MEDs won’t run hot as they store mostly archive data. A MED chassis has no need of robots and can be filled with MEDs like a dense JBOD. It will function like a better-than-tape archive system, providing much faster data access, both for reads and writes, draw less electricity, and occupy less datacenter rack space.
It is simple to envisage MED variants with more or less NAND storage, pitched at applications needing more or warm storage compared to cold, archival data storage in the future, squeezing the disk market somewhat. In effect, Huawei is compressing the storage hierarchy from three elements to two. From “SSD-to-HDD-to-Tape” to “SSD-to-MED.”
Such two-element hierarchies could be easier to manage, more power efficient and enable faster cold data access. They could become popular in regions with constrained disk supply through US restrictions, and elsewhere as well, because they will make on-premises datacenter and tier 1, 2, and 3 public cloud archival storage more practicable. Chinese public cloud suppliers are having conversations with Huawei about using the technology, we’re told.
It is possible that MEDs could have a profound effect on the robotics-using tape autoloader and library systems markets, prompting suppliers of such systems to look at developing their own MED-like technology. MEDs might also add to the pressure on disk drives from NAND by moving some nearline data to MEDs, squeezing the disk drive market from two sides.
It’s notable that Huawei has only developed its MED technology because of US disk tech export restrictions, and that MED technology could end up threatening Western Digital and Seagate because of Huawei’s inventive response to those restrictions.
Bootnote
Huawei is said to be developing its own 60 TB capacity SSD, using QLC NAND with an SLC cache.
DDN enterprise storage subsidiary Tintri is releasing data management features for Kubernetes environments, with its new VMstore Container Storage Interface (CSI) driver.
The VMstore platform provides visibility into performance, data protection, and management for virtual machine workloads. The new CSI driver provides VMstore customers with that same insight within Kubernetes, using a single interface.
With cloud-native application support, VMstore can efficiently manage data for microservices-based deployments.
The driver allows admins to manage all data using familiar Tintri interfaces and tools to reduce complexity in hybrid VM/container environments, said the provider. The driver enables dynamic provisioning and automatic attachment and detachment of volumes to containers.
Brock Mowry
“This IO-aware CSI driver is the most adaptable data management platform for Kubernetes, transforming how IT administrators handle Kubernetes environments in both cloud and on-prem,” said Brock Mowry, CTO at Tintri. “The driver empowers administrators, regardless of their Kubernetes expertise, with the essential tools to efficiently manage and optimize data across physical and virtual clusters.”
The driver also enables the easy management of workload transitions between cloud environments, enhancing operational efficiency through automated performance tuning. In addition, ETPH analytics provide insight to optimize cloud storage costs.
The driver leans on Tintri’s TxOS performance, analysis, and optimization capabilities, allowing admins to dynamically manage container performance and autonomously prioritize application workloads in real time, we are told. With Tintri Global Center (TGC), admins can manage multiple VMstores serving as Kubernetes clusters, either globally or locally, through a single pane of glass.
Through the VMstore TxOS integration, Tintri also brings data protection and disaster recovery to Kubernetes environments, including snapshots and cloning of persistent volumes or large data sets, ensuring consistent storage, secure data management, and efficient recoverability, according to the company.
Tim Averill, US CTO at IT infrastructure and managed security service provider at Silicon Sky, said: “We are leveraging the Tintri CSI driver within our datacenters, both in the cloud and on-premises. By providing primary storage, disaster recovery and data protection in one solution, we are simplifying and enhancing our IT operations.”
In August, Tintri said it was developing a disaster recovery feature with autonomous detection and alerting to combat ransomware attacks.
