We're working hard throughout Coronavirus to deliver as normal - 09/07/2020

Big Data Server & Storage Solutions

Broadberry Big Data server and storage solutions supercharge your Big Data applications through the latest hardware and software advances from PCI-E NF1 drives to Tesla GPU processing

More efficiency, more informed decision making and happier customers can all be a result of harnessing the power of Big Data.



Big Data Servers

Our HPC range of servers are perfect for Big Data applications due to their high RAM capacity and powerful processing capability.

Configure your Big Data server with a wide range of high-end Intel Xeon Scalable Family processors in conjunction with NVIDIA Tesla and GTX GPU cards for massive parallel processing power.

Read More

 
Broadberry GPU Server 1029GQ-TRT

Ultra High-Density GPU Computing 1U Supercomputer, 4x Tesla, Xeon Phi or GTX-Titan GPU Cards - 20,000 CUDA Cores! - Supermicro 1029GQ-TRT

Server Processor:
Xeon Scalable Processor - Dual Socket
Drive Bays:
Fixed Drives
Drive Interface:
SATA
HDD Size:
2.5" Drives
Form Factor:
1U
Features:
High RAM Capacity, Extra Expansion Slots, Full Height/Length Expansion, Redundant Power Supply Option
Max RAM Capacity:
1.5TB
from: £3,254
Configure
Broadberry ESC4000 G4 GPU Server

GPU Computing 2U Supercomputer, 4x Tesla, AMD or GTX-Titan GPU Cards - ASUS ESC4000 G4

Server Processor:
Xeon Scalable Processor - Dual Socket
Drive Bays:
Hot-Swap Drives
Drive Interface:
SATA , 12Gb/s SAS
HDD Size:
3.5" Drives
Form Factor:
2U
Features:
High RAM Capacity, Extra Expansion Slots, Full Height/Length Expansion, Redundant Power Supply Option
Max RAM Capacity:
2TB
from: £3,311
Configure
CyberServe Xeon SP G291-281 GPU Server

High Performance Computing Server - Dual Intel Xeon Scalable Processor Series, 2U Server, 8x GPU Cards - Gigabyte G291-281

Server Processor:
Xeon Scalable Processor - Dual Socket
Drive Bays:
Hot-Swap Drives
Drive Interface:
SATA , 12Gb/s SAS
HDD Size:
2.5" Drives
Form Factor:
2U
Features:
VMware Compatible, Best Value, Redundant Power Supply Option
Max RAM Capacity:
3.1TB
from: £3,991
Configure
 
Broadberry GPU Server ESC8000 G4

8x PCIE x16, Redundant 2400W Power, Dual Gigabit, ASUS ESC8000 G4

Server Processor:
Xeon Scalable Processor - Dual Socket
Drive Bays:
Hot-Swap Drives
Drive Interface:
SATA , 12Gb/s SAS
HDD Size:
2.5" Drives
Form Factor:
4U
Features:
High RAM Capacity, Extra Expansion Slots, Full Height/Length Expansion, Redundant Power Supply Option
Max RAM Capacity:
3.1TB
from: £5,531
Configure

Big Data Storage Servers

Our high-performance range of storage servers are perfect for Big Data applications due to their high storage capacity and I/O performance.

Configure your Broadberry storage server with a range of the latest storage technologies from SAS and PCI-E solid state drives to PCI-E NVM 1 drives for the ultimate performance.

Read More

  
CyberStore 208-4N 12Gb/s SAS with 4 x NVMe Drive Bays - Performance Storage

2U, (8 x SAS & 4 x NVME Bays) High-Performance Storage Server - SuperServer 6029UZ-TR4+

Form Factor:
2U
Drive Size:
3.5" Storage Servers
Drive Bays:
4 NVMe + 8 HDD/SSD Bays
Storage Capacity:
256TB
from: £3,548
Configure
   
CyberStore 110N 10x NVMe Drive All Flash Storage Array

1U, 10 Bay NVMe All Flash Storage Array

Form Factor:
1U
Drive Size:
2.5" Storage Servers
Drive Bays:
10 NVMe Drives
Storage Capacity:
160TB
from: £3,876
Configure
Windows Storage Spaces Direct S2D Node - 10x NVMe

1U, 10 Bay NVMe All Flash Storage Array

Form Factor:
1U
Drive Size:
3.5" Storage Servers
Drive Bays:
10 NVMe Drives
Storage Capacity:
160TB
from: £3,876
Configure
Windows Storage Spaces Direct S2D Node - 8x HDD, 4x NVMe

2U, (8 x SAS & 4 x NVME Bays) High-Performance Storage Server

Form Factor:
2U
Drive Size:
3.5" Storage Servers
Drive Bays:
4 NVMe + 8 HDD/SSD Bays
Storage Capacity:
192TB
from: £3,904
Configure
 
CyberStore 220-4N 12Gb/s SAS with 4 x NVMe Drive Bays - Performance Storage

2U, (20 x SAS & 4 x NVME Bays) High-Performance Storage Server

Form Factor:
2U
Drive Size:
2.5" Storage Servers
Drive Bays:
4 NVMe + 20 HDD/SSD Bays
Storage Capacity:
448TB
from: £4,214
Configure
   
Broadberry CyberStore R281-NO0 All-Flash server

High-Density 2U, 24x NVMe All Flash Storage Array, High IOPS

Form Factor:
2U
Drive Size:
2.5" Storage Servers
Drive Bays:
24 NVMe Bays
Storage Capacity:
384TB
from: £4,781
Configure
  
CyberStore 224N 24x NVMe All Flash Storage Array

High-Density 2U, 24x NVMe All Flash Storage Array, High IOPS

Form Factor:
2U
Drive Size:
2.5" Storage Servers
Drive Bays:
24 NVMe Bays
Storage Capacity:
384TB
from: £4,805
Configure
Windows Storage Spaces Direct S2D Node - 24x NVMe

High-Density 2U, 24x NVMe All Flash Storage Array, High IOPS

Form Factor:
2U
Drive Size:
2.5" Storage Servers
Drive Bays:
24 NVMe Bays
Storage Capacity:
384TB
from: £4,805
Configure
 
CyberStore 248N 48x NVMe All Flash Storage Array

2U, 24 Bay All Flash Storage Array - Supermicro SuperStorage Server 2028R-NR48N | SSG-2028R-NR48N

Form Factor:
2U
Drive Size:
2.5" Storage Servers
Drive Bays:
48 NVMe Bays
Storage Capacity:
768TB
from: £6,946
Configure
 
CyberStore 136NF1 - 36x NGSFF PCIe NVMe SSD All-Flash Storage Array

High-Density 1U, 36x Next Generation Small Form Factor Server - Great for Scale-out, Scale-up, Database, Real-time analytics, Deep Learning, Content Distribution Network, etc.

Form Factor:
1U
Drive Size:
2.5" Storage Servers
Drive Bays:
36x NGSFF PCIe NVME
Storage Capacity:
0
from: £7,011
Configure

Big Data JBODs

Our range of high-capacity, feature-rich JBOD's are the perfect fit for organisations looking to expand their current storage pool or create a new storage pool.

They are compatible with Broadberry Header Nodes, or any other vendor servers and offer enterprise-grade features at a fantastic price-point.

CyberStore 4U102 12GB SAS/SSD JBOD

The Next Generation Hybrid Platform for Software-Defined Storage

Form Factor:
4U
Drive Size:
3.5" Storage Servers
Drive Bays:
102 Drive Bays
Storage Capacity:
1.6PB
from: £7,726
Configure
Broadberry 4U 102 Bay Windows Storage Server 2016 JBOD

The Next Generation Hybrid Platform for Software-Defined Storage

Storage Type:
WSS JBODs
Form Factor:
4U
Drive Size:
3.5" Drives
JBOD Capacity:
1.6PB
from: £7,726
Configure


There are a number of high-quality programs out there capable of not only dealing with Big Data but maximising its usefulness. Our high-quality servers can be configured to very efficiently run these software.

Virtualisation and analytics are huge parts of utilising the power of Big Data.

Here are some of the best analytical software out there that can be configured with your new server to allow you harness the true power of Big Data.

MicroStrategy is an ideal software solution, delivering integrated analytics and allowing you to take advantage of integrated analytics to take your business to the next level. Featuring superior data and the capability of sophisticated analytics, MicroStrategy is also very easy to use and allows for user scalability.

Tableau is extremely effective at enabling businesses to visualise and understand their data. Providing a revolutionary new approach to business intelligence, Tableau allows you to very quickly connect and visualise data. Dashboards can be created and shared amongst a team without the need for programming skills. You can also share data seamlessly across devices.

Microsoft Power BI is a web-based platform ideal for business analytics and visualisation. It is suitable for businesses of any size. It closely monitors both data that is key to the organisation and that from each app used by the organisation. It provides tools you can use to transform and visualise data, to quickly analyse it and to share reports.

ZoomData very efficiently provides simple and intuitive ways to visually interact with data. Interactive visualisation is enabled at essentially every scale – from many billions of rows of data to real life streams in under a second. The complexities that often prevent users of traditional BI and analytics applications from utilising the full power of Big Data are avoided completely with ZoomData.

QlikView is a powerful BI data discovery software that enables the creation of tailor-made guided analytics applications. With this tool you can uncover data and information that you often wouldn’t be able to find with query-based tools. The tool can be used to create and deploy analytical applications without needing to have any serious development skills, enabling faster responses to the everchanging business landscape.

The amount of value you will be able to get out of Big Data relies a lot of the amount of processing and compute power you have at your disposal.

Here are some great choices of software to use to get the most out of your new server technology.

Hive offers three different dashboards that each provide users with team productivity. Dashboards provide summaries of both personal and workspace productivity, highlighting inefficient areas and allowing managers to find ways to rectify them. There are a variety of features such as workflow templates, group messaging, multiple task views and more than 100 third party apps.

Apache Drill is a quick, flexible solution that features a high level of usability. Its agility allows for you to gain quicker insights without the usual overhead (such as loading, schema creation, etc.) Analysis of the multi-structured and nested data in non-relational datastores can be done directly without the need to transform or restrict it. You can leverage your existing skills and tools including the likes of Tableau, QlikView, MicroStrategy, Excel and more, boosting the usability of Apache Drill.

Apache Flink is designed to run effectively in all common cluster environments. As a distributed processing engine, it is capable of stateful computations over unbounded and bounded data streams. It is able to perform computations at in-memory speed and at any scale.

Apache Kafka is a publish-subscribe messaging system that is suitable for both online and offline messaging. It protects from data loss through persisting messages on the disk and replicating them within the cluster. Kafka is a very reliable and durable system. It can also very efficiently handle failures as it is fault tolerant. When it comes to real-time streaming data analysis, Apache Kafka can integrate extremely well with Apache Storm and Apache Spark.

Cloudera is a powerful software solution that has been meticulously designed for data management and analytics. It has been branded by many as the world’s quickest, most easily usable and most secure Apache Hadoop platform. With Cloudera’s Enterprise Data Hub (EDG), the system delivers the first unified platform for big data. Providing reliable and unified place to store, process and analyse all your data.

Apache Storm is a distributed real-time computational system made to process data streams. This open source software is capable of processing more than a million jobs in a fraction of a second on a node. A quick and secure processing system, Apache Storm is built to handle high volume and high velocity data. It is fault tolerant and highly scalable.

One of the biggest advantages Apache Spark provides is speed. Its in-memory data engine means that in certain situations it has the ability to perform tasks up to a hundred times faster than MapReduce. This is particularly evident when you compare through multi-stage jobs which require the writing of state back out to the disk between stages. The Spark API is very user friendly, making it one of the easier solutions to get a grip on for inexperienced developers.

Software solutions dealing with big data storage feature compute-and-storage architecture that essentially collects and handles large data sets.

Big data storage also enables real-time analytics.

Hadoop is a scalable file system that is very effective in handling big data. It enables the distributed processing of large data sets across clusters of computers. It is able to scale up from a single server to thousands of machines with each offering local computation and storage.

Instead of relying on the hardware to provide high-availability, this software is designed to find and handle failures at the application layer. Essentially it delivers high-availability on top of a cluster of computers that could be prone to individual failures.

HBase is very useful when you need random, real-time read/write access to your Big Data. This software was created to host very large tables, reaching many millions of columns and billions of rows.

It features linear and modular scalability and maintains strictly consistent reads and writes. Failover support between RegionServers is automatic while sharding of tables can be both automatic and configurable.

HBase features an easy to use Java API for client access, giving you more control and improved usability. In addition, block cache and Bloom filters are supported, making real time query processing easy.

Splunk is an analytics software that takes the usually overwhelming task of analysis and makes it simple. The web-based interface is extremely easy to use and keeps all your data analysis in a single location. While you would usually have to use multiple tools to collect all the data you need, with Splunk all the work will be done by one piece of software.

Splunk has been designed for users without a lot of technical expertise. It also contains built-in failover and disaster recovery capabilities that ensure you will always have access to your data, even in the case of severe system disruption.

Elasticsearch is an open source and readily-scalable search engine for your database. You can use Elasticsearch to power extremely fast searches that support your Big Data discovery applications.

Apache Kudu is open source software that features streamlined architecture and allows for faster and more accurate analytics. Kudu’s success has been built on their vibrant community of users and developers from diverse backgrounds. Kudu utilises columnar storage to enable efficient encoding and compression. Techniques such as differential encoding, run-length encoding, vectorised bit-packing and more are used to increase the speed of data-writing and the space efficiency of storage.

Apache Cassandra is a wide column store NoSQL database management system that is designed to deal with large amounts of data. It provides high availability and has no single point of failure. It allows for the solving of complicated tasks with ease and has a relatively short learning curve, meaning you will be using it to its full capabilities in no time. It features rapid writing and scorching fast reading, extreme resilience and fault tolerance.

MongoDB is dynamic, simple, object-oriented and scalable NoSQL database based on the NoSQL document store model. Offering great scalability, MongoDB is very efficient at handling Big Data demands and has the flexibility to fit well with your business needs. With MongoDB, you are able to serve more data, more users and more insight with much greater ease.

Data warehouse is a system that is used for reporting and analysis. It is widely regarded as a core component of business intelligence.

DW’s are the central repositories of integrated data from either a single source or multiple disparate sources.

Greenplum is a massively parallel processing architecture that is capable of petabyte-scale loading. This solution allows for polymorphic data storage and execution. The settings for table or partition storage, compression and execution can all be configured to create a more efficient and effective accessing of data.

MapR features high availability and amazing performance. This solution is ideal for anyone looking for a low TCO, as it is very cost-effective. It offers complete protection and enterprise-grade security, making it one of the most secure options available for handling big data. Data integration is made easy with MapR.

Hortonworks provides you with the flexibility of deploying big data workloads in both hybrid and multi-cloud environments. Having this combination available provides optimal speed, cost-efficiency and security. This solution delivers data lineage, management, security, provenance tracking and governance extending across the platform for applications and workloads including machine learning, data science and analytics.


Our range of server and storage solutions built for Big Data applications feature high density and a high core count, making them powerful enough to sufficiently handle the demands of using systems dealing with big data.

Our Big Data servers are capable of amazing processing performance. High performance computing (HPC) holds a lot of importance in the current tech landscape. From finding new energy sources to predicting the weather and everything in between, there are a number of reasons HPC is needed.

If your organisation is looking to take advantage of the Big Data revolution, you are going to need processing servers with the performance, power and speed to handle the huge amounts of data that will require processing. Our processing servers are configurable with large amounts of RAM, as well as dual 26-core processors or up to 8 GPU processors.

Our range of high-performance servers can be configured with GPU based processors (such as GTX) or high-end Xeon Scalable family processors.

Broadberry deliver a variety of different servers with different configurations to ensure your storage server’s characteristics are perfectly aligned with your needs. In the case of Big Data, our line of GTX Servers and Tesla GPU based servers are ideal. This is due to their high core count and overall very strong performance.

The Tesla V100 in particular is engineered for the convergence of AI and HPC. As a platform it allows HPC systems dominate at computational science for scientific simulation. It is similarly effective at aiding data science and the finding of insights in data. Through the pairing of NVIDIA CUDA cores and Tensor cores in a unified architecture, just one Tesla V100 GPU can perform as well as hundreds of CPU-only commodity servers when you look at both traditional HPC and AI workloads. You can now enjoy a legitimate AI supercomputer for a very affordable price.


We configure our storage servers with the latest storage technology to ensure the very best performance when utilising Big Data. Our storage servers can be configured with a range of the latest technology drives, including NF1 drives and SAS/PCIe solid state drives.

PCI Express interface increases speed by enabling high bandwidth communication between the storage drive and motherboard. You can configure your server to come with a number of NF1 drives, greatly improving its I/O performance and capability to handle Big Data applications.


To properly handle Big Data, there are certain networking requirements that need to be met. One ideal type of computer-networking communications standard that is most often used in high-performance computing. It features super high throughput and very low latency. It is also scalable, offers failover and supports QoS (quality of service). Infiniband is one of the best options for a server connect in high-performance computing environments. Our storage servers can be configured with Infiniband, making them ideal for Big Data. They can also be configured with Mellanox Ethernet 100gb, another great networking option to use for increased Big Data compatibility.




Our Rigorous Testing

Before leaving our UK workshop, all Broadberry server and storage solutions undergo a rigorous 48 hour testing procedure. This, along with the high-quality industry leading components we use ensure all of our server and storage solutions meet the strictest quality guidelines demanded from us.


Un-Equaled Flexibility

Our main objective is to offer great value, high-quality server and storage solutions, we understand that every company has different requirements and as such are able to offer un-equaled flexibility in designing custom server and storage solutions to meet our clients' needs.

Trusted by the World's Biggest Brands

We have established ourselves as one of the biggest storage providers in the UK, and since 1989 supplied our server and storage solutions to the world's biggest brands. Our customers include: