Keep It Green with Supermicro and Tego Data
A global leader in high performance, high efficiency server technology and innovator of premier end-to-end green computing solutions for HPC, Data Center, Cloud Computing, Enterprise IT, Hadoop/Big Data and Embedded Systems worldwide.
The widest selection of enterprise-ready servers featuring the most advanced technology, the Supermicro SuperServer line of servers provide the highest levels of performance, efficiency, scalability, and flexibility. They are available in a wide variety of application targeted designs and form factors.
Tego Data partners with Supermicro to offer a turn-key storage integration of Red Hat Ceph Storage on fully optimized SuperStorage hardware. The Total Solution for Ceph includes datacenter proven on-site service and support provided by Supermicro and is available for deployments in the US and Canada.
The storage landscape is evolving from premium priced proprietary hardware and software solutions to software defined storage based on open industry standard hardware and the benefits are significant: reduced vendor lock-in, significantly lower storage costs and rapid open innovation with new technologies like all NVMe solutions.
- Uncompromising Quality Control
- The most Comprehensive Line of Servers, Storage Systems, and Subsystems
- Widest Variety of Application Optimized Solutions, from High End Clusters to MicroServers
- Best Performance per-Watt, per-Square-Foot, and per-Dollar
- Superior Product Design Based in Silicon Valley
- Consistently First-to-Market
- Best Total Cost of Ownership (TCO)
- Highest Quality Components and Materials
- 3-Year Limited Warranty
- 24-Hour Support and Global Services
- Redfish API support
These benefits combined with an excellent track record have earned Supermicro a reputation as a true leader in the high-end server/storage industry. Supermicro provides the most outstanding product line in the industry, ranging from single Atom™ and dual Xeon® to quad Xeon® MP systems. Their proven high level of quality and performance has made SuperServers the platform of choice for HPC, enterprise, cloud, data center, hyperscale, embedded, and business-critical, front-end server applications.
- Flexible Connectivity Options
- Dual socket R3 (LGA 2011) supports Intel® Xeon® processor E5-2600 v4†/ v3 family; QPI up to 9.6GT/s
- Up to 3TB† ECC 3DS LRDIMM , up to DDR4- 2400†MHz ; 24x DIMM slots
- 1x PCI-E 3.0 x16 slot (FH, 10.5″ L), 6x PCI-E 3.0 x8 slots (4x FH, 10.5″ L, 1x LP, 1x Internal LP)
- 4x 10GBase-T ports
- 24x Hot-swap 2.5″ Drive Bays; 10x SATA3 ports by default; Optional drive support: 24x SAS3
- 4x heavy duty fans w/ optimal fan speed control
- 1000W High efficiency (96%) Redundant PSU; Titanium Level
Best TCO with Highest Performance-per-Watt/per-Dollar
FatTwin™ Server Solution
The Supermicro FatTwin™ is a high-density 8/4/2 hot-plug node SuperServer® system available with a variety of memory capacities, HDD technologies, PCI alternatives, networking capabilities, and GPU support options. The FatTwin™ supports up to: 2TB ECC 3DS LRDIMM or RDIMM DDR4-2400MHz in 16 DIMM slots, 1 PCI-E 3.0 x16 and 1 PCI-E 3.0 x8 Micro LP card , 8 ports of LSI® 3008 SAS 3.0 (12Gbps) with Software RAID, 10 ports of SATA 3.0 (6Gbps) with Intel® C612 controller, dual 10GBase-T or dual Gigabit Ethernet ports, redundant Titanium Level (96%) Digital power supplies, integrated IPMI 2.0 with KVM over dedicated LAN, and dual Intel® Xeon® processor E5-2600 v4 product families up to 22 cores and 145W TDP.
The Supermicro FatTwin™ represents a revolution in Green Computing designed to support customers’ critical applications and also reduce Data Center TCO to help preserve the environment. The FatTwin™ extends the compute and storage capabilities of Supermicro’s existing Twin SuperServer® systems to achieve increased performance and power efficiency. Due to its shared components the FatTwin™ improves cost-effectiveness and reliability, while its modular architecture makes it flexible to configure and easy to maintain.
Versatile configurations allow the FatTwin™ to be optimized for many different environments including Enterprise, Data Center, Cloud Computing, HPC, Financial, Science and Engineering, File and Storage Servers.
Supermicro’s patented Twin Architecture with up to 24 DIMMs per node for Highest Performance is the foundation of the most advanced server platforms in HPC/Data Center, Cloud Computing and Enterprise IT applications. These high performance, high density systems feature optimum airflow for energy efficient cooling, easy maintenance and high availability with hot-swappable nodes and redundant power supply modules. These systems also feature the latest CPU and interconnect technologies for maximum processing performance and data throughput.
Broadest Spectrum of Twin Products with up to:
- 24 DIMMs of Up to 3TB of up to 2400MHz memory per node
- Redundant (96%) Efficiency Titantium Level Power Supplies
- Dual Intel® Xeon® Processor E5-2600 v4/v3 product families
- Up to 6x 3.5″ or 12x 2.5″ SAS3 / SATA3 HDDs / SSDs per node
- NVMe Support
- PCI-E 3.0 x16 slots for 56Gb/s ConnectX-3 FDR IB or 10GbE SFP+
- SATA DOM Support
- Server Management with Onboard IPMI 2.0 + KVM with dedicated LAN
Total Solution for Ceph
Designed for Reliable Large Scale Storage Deployments
With the advancement of large scale cloud computing platforms like OpenStack, the business of data storage has been forever changed. Scale out software defined storage solutions are rapidly becoming pervasive as the implementation model of choice for large scale deployments. Agile business models require equally agile platforms to build upon. By replacing the proprietary data silos of the past with flexible server hardware, cloud providers have more control of their environments resulting in better value for their customers. Supermicro has embraced this change, offering the widest selection of server hardware in the industry.
Ready to Deploy Configurations
- Role specific cluster configurations – turn-key cluster configurations offer performance, capacity, and density to fit popular application workloads. Memory and networking options are easily customized to meet specific requirements
- Optimized network configurations – cluster and rack level integration offers streamlined deployment of Red Hat Ceph Storage and infrastructure with consistency not attainable using improvised methods
- Storage/Media Ratios to fit user applications – deployment of flash and rotating magnetic media allows the solution to meet workload tuned performance and density targets
Object-based Storage with Block and Object Interfaces
Organizations prefer object-based storage when deploying large-scale storage systems because it stores data more efficiently. Object-based storage systems separate the object namespace from the underlying storage hardware – This simplifies data migration.
The Ceph Storage Difference
Ceph’s CRUSH algorithm liberates client access limitations imposed by centralizing the data table mapping typically used in scale-out storage. Ceph continuously re-balances data across the cluster-delivering consistent performance and massive scaling. The self-healing capabilities of Ceph provide aggressive levels of resiliency. Data redundancy is achieved by replication or erasure coding allowing for extremely efficient capacity utilization.
Supermicro Total Solution for Ceph Specifications
Supermicro’s Total Solution for Ceph offers turn-key storage integration of Red Hat Ceph Storage on fully optimized SuperStorage hardware. The Total Solution for Ceph includes datacenter proven on-site service and support provided by Supermicro and is available for deployments in the US and Canada.
|Workload / Application||MySQL / Database||Digital Media Serving – Small||Digital Media Serving – Large||Capacity-Archive|
|I/O profile / Protocol||IOP / Block||Throughput/Block & Object||Capacity/Object||Capacity/Object|
|Data Protection||2x Replication||3x Replication||3x Replication and Erasure code||Erasure code|
|Form factor||3U||23U (with switches and 3x Monitor nodes)||41U (with switches and 3x Monitor nodes)||41U (with switches and 3x Monitor nodes)|
|Usable Capacity||3.2TB||240TB||1.5 PB using 7+2 Erasure Code||2.5 PB using 7+2 Erasure Code|
|Node count||8x OSD nodes||3x Mon, 10x OSD nodes||3x Mon, 9x OSD nodes||3x Mon, 9x OSD nodes|
|Network / Switches||10G SFP+ / NA||10G SFP+ / 1x SSE-X3348SR, 48 port SFP+ – Reverse Air Flow, 1x SSE-G24-TG4, 24x port switch||10G SFP+ / 2x SSE-X3348SR, 48 port SFP+ – Reverse Air Flow, 1x SSE-G24-TG4, 24x port switch||10G SFP+ / 2x SSE-X3348SR, 48 port SFP+ – Reverse Air Flow, 1x SSE-G24-TG4, 24x port switch|
|Rack dimensions & PDU||NA / NA||42U (82.4″Hx 23.5″Wx 48″D) / 2x Metered Rack PDU,NEMA L6-30P,IEC 320 C13,C19||42U (82.4″Hx 23.5″Wx 48″D) / 2x Metered Rack PDU,NEMA L6- 30P,IEC 320 C13,C19||42U (82.4″Hx 23.5″Wx 48″D) / 2x Rack PDU 208V 50A 3-Phase|
|Subscription||Capacity based subscription for Red Hat Ceph Storage 1.3 (includes Red Hat Enterprise Linux 7.1)|
Supermicro’s SuperStorage® solutions include everything needed for a rock solid storage foundation. Standard features, including unmatched computing power with the latest Intel® Xeon® processor E5-2600 v4/v3 product families of dual socket processors. Individual models are designed to meet the demands of the toughest storage environments, from low-latency SSD applications to the massive capacity needed for large files used in media and entertainment and Big Data applications. SuperStorage supports both scale-up and scaleout deployment strategies allowing CPU and storage resources scale to meet diverse application requirements.
- Complete Portfolio of open industry standard storage offerings optimized for Microsoft, VMWare, RedHat and Software Defined Storage solutions
- Maximum Performance – Full NVMe support, in hybrid expander and direct attach storage backplane with up to 20 GB/s throughput
- Maximum Efficiency – High capacity 2U, 3U and 4U form factors with industry leading density. Highest efficiency platinum rated power supplies (95% power efficient)
- Mission Critical Reliability – fully redundant, fault-tolerant architecture with hot swappable drive bays, power supplies and cooling fans. The active-active capable JBOD hardware is perfect for mission critical applications
- SuperStorage Systems can be expanded using JBOD for improving economy as you scale.
- Enterprise customers in need of highest performance appreciate Supermicro SAS 3.0 (12Gbps) support which provides low-latency and maximum data bandwidth delivering >7x Lower Latency than SAS 3.0 (12Gbps) SSDs
- SuperStorage offers a no compromise storage platform with flexible market entry points from 2U, 3U and 4U form factors using 2.5” and 3.5” HDDs.
- SuperStorage Systems can be expanded using JBOD for improving economy as you scale
- Highest Performance and Storage Density – Supports up to: • 44 Cores per Server • 145W TDP CPUs • 3TB DDR4-2400MHz in 24 DIMMs
- Hot-swap NVMe
- Maximum Acceleration for Highest-Performance Workloads with Pascal/GPU Coprocessor (4/6/8 GPU/Intel® Xeon Phi™ coprocessor in 1U/2U/4U)
Large Bandwidth and Latency Improvements with True Hot-Swap Capability
The primary benefits of Supermicro SuperServer® solutions with NVMe support include improved performance (throughput and latency), hot-swap capability, ability to support many true hot-swap NVMe drives per server, cost-effectiveness compared to add-on card based solutions, and availability of many cost-optimized models from which to choose.
Supermicro is the first to market with true hot-swap support for NVMe SSD drives. This feature allows easy addition of storage capacity through the addition of SSDs, the replacement of existing SSDs with higher capacity units, or replacement of failed drives, while the server system is in operation. Additionally, the hot-swap feature protects against surprise removals, random device failures, or operator errors. Software hardening from Supermicro on its NVMe server product line provides an excellent protection against these all too-common data center issues.
- Higher Performance Up to 12x higher IOPS and 7x lower latency than SAS3 SSDs
- Lower Power Up to 15x less wattage per IOPS than SAS3 SSDs
- Reduced Cost No SAS HBA/AOC required, less CAPEX and power consumption
- Efficient & Scalable Streamlined protocol & command set, fewer clock cycles per I/O
- Optimized for Next Generation NVM New storage stack with lower latency and less overhead