Parallel I/O Technology Drives More than 1.5M SPC-1 IOPS
Response Time While Simultaneously Running Enterprise-class Database Workloads; Delivers
SPC-1 Price-Performance™ of
9 Cents per SPC-1 IOPS™
FORT LAUDERDALE, Fla., March 29, 2016 –
, the leader in Parallel-Powered Software,Application-Adaptive Data Infrastructure and Hyper-converged Virtual SAN solutions, today announced that its second
SPC-1 result has catapulted the company into third place among the SPC’s Top 10 of absolute performers while achieving the best price-performance and
fastest response times among those Top 10. DataCore again leapfrogged the field and now holds the top two positions in the SPC-1 Price-Performance™
category. The DataCore™ Parallel Server software at the heart of the hyper-converged configuration delivered 1,510,090.52 SPC-1 IOPS™. Notably, the number one and two systems  in the category are very large footprint multimillion dollar systems that are 14 times more costly than the compact 4U-sized DataCore based solution.
“There is no magic in what we are doing,” states Ziya Aral, Chairman of DataCore Software. “Yes, we use a standard 2U server but it is a server with 36
cores and 72 logical CPUs. At 2.5 GHz clock speed that multiplies out to the equivalent of 180 GHz, provided only that we use those CPUs concurrently. Even
if the CPUs don’t scale perfectly, we have an ‘embarrassment of riches’ in compute power. If they scaled at only 60% – and they do much better than that –
we effectively have access to over 100 GHz of CPU power. Frankly, we would have been disappointed if we hadn’t been able to put up these kinds of I/O
numbers with a 100 GHz CPU.”
DataCore’s initial results showcasing the power of parallel I/O were first published in late 2015. The new results, which tripled the previous performance
achievements, were attained on the same server platform hardware to demonstrate the potential and the pace of advancement possible from the company’s new
software and parallel I/O architecture. And, there is more to come.
To illustrate the system’s I/O power in demanding database environments, DataCore chose the Storage Performance Council’s SPC-1 benchmark – the Gold
Standard used by all major storage manufacturers to measure top end I/O performance, price-performance and response time. For the benchmark, DataCore used
an off-the-shelf Intel-based Lenovo System x3650 M5 server.
The 1,510,090.52 SPC-1 IOPS™ were attained with the total cost for hardware, software and three years of support totaling $136,758.88. This yielded the
SPC-1 Price-Performance™ result of $0.09 per SPC-1 IOPS™, which is more than eight times lower than all of the top performing high-end systems that have
achieved over one million SPC-1 IOPS™.
The DataCore Parallel Server configuration placed third overall in SPC-1 IOPS™ behind two systems costing over $2 million. Only the Huawei OceanStor
18800V3 at a total price of $2,370,760 and the Hitachi VSP G1000 system at $2,003,803 had higher SPC-1 IOPS™ numbers than the $136,759 solution from
DataCore. Unlike those two storage systems which only provide external SAN functions, the DataCore Parallel Server also ran the computational
enterprise-class database and OLTP workloads inside the same compact package.
Most remarkably, the DataCore configuration delivered the fastest SPC-1 response time ever recorded (100 Microseconds at 100% load), besting all systems,
including multi-million dollar systems and all-flash arrays, by seven times or more. From a real estate standpoint, the entire system takes up only 4U
(seven vertical inches for a 2U server and 2U for disks) of standard 19” rack space. In stark contrast, other systems reaching the million SPC-1 IOPS™ mark
occupy multiple 42U cabinets consuming considerably more data center space, power, and cooling.
DataCore now holds the two top positions in the SPC-1 Price-Performance™ category  (the previous DataCore™ SANsymphony™ system running on a hyper-converged configuration using a similar Lenovo System x server attained an SPC-1
Price-Performance™ record of $0.08/SPC-1 IOPS™). “Essentially the only major difference between our first and second SPC-1 results was our software,” notes Ziya Aral who continued by answering the
obvious question – how is that possible? “The truth is that the hardware platform matters, multiprocessing matters, and I/O craft matters, but what matters
most of all is software architecture. DataCore was designed from the outset for parallel architectures…but the definition of ‘parallel’ at the time was
4, 8, maybe 12 CPUs. Today, we are running in standard platforms with 72, 144 or even 288 logical CPU cores, and that will double with the next few ticks
of the clock – because Moore’s law now advances in multiples.”
Aral explains further, “Parallel Server is designed to take advantage of that evolution in computer architectures – not just for the present but into the
future. This software inverts our previous understanding: what was once a precious commodity now exists in surplus and the software must take advantage of
Tested Product: DataCore™ Parallel Server for Hyper-Converged and Server Systems
DataCore certified its results using DataCore Parallel Server software on a compact 2U Lenovo System x3650 M5 multi-core server featuring Intel® Xeon®
E5-2600 v3 series processors with a mix of flash SSD and disk storage.
DataCore Parallel Server is a software product that transforms standard servers into parallel servers targeted for applications where extremely high IOPS
and low latency are the primary requirements. DataCore’s parallel I/O technology executes many independent I/O streams simultaneously across multiple CPU
cores, significantly reducing the latency to service and process I/Os. This technology removes the serialized I/O limitations and bottlenecks that restrict
the number of virtual machines (VMs), virtual desktops (VDI) and application workloads that can be consolidated on a server or a hyper-converged platform –
and instead enables them to process far more work per server and significantly accelerate I/O-intensive applications.
DataCore Parallel Server software is now available to DataCore OEM partners and is currently being evaluated by server and system vendors. General
availability is planned for Q2 2016.
Hyper-Consolidation and Next Generation Productivity with DataCore Parallel I/O Technology
The practical significance and business advantages of DataCore Parallel Server’s record-breaking results can be appreciated from several perspectives:
Servers are the new storage:
I/O-intensive workloads which had previously required enormous investments in exotic SAN hardware or enterprise-class external arrays can now be
addressed with relatively inexpensive, compact, off-the-shelf hardware equipped with DataCore Parallel Server software.
One machine is simpler than many:
Organizations no longer need to split I/O-intensive problems across hundreds of servers to reduce their dependency on exotic equipment. They can run
these programs unaltered inside a few low-cost servers without undue complexity, delay and expense.
Hyper-consolidation versus server sprawl:
Several years into virtualization initiatives, serial I/O processing inside servers remains singularly responsible for poor virtual machine densities.
By putting multiple CPU cores to work on I/O, DataCore helps customers do the work of 10 servers on one or two.
DataCore’s Parallel Server software enables industry-standard x86 servers to fully harness their untapped parallel computation power and gain the essential
I/O functionality needed to drive today’s demanding tier-1 business application requirements. In this way, companies benefit from dramatically higher
productivity and huge server consolidation savings. To learn more visit: http://ift.tt/1WCaekw.
About the Storage Performance Council
The Storage Performance Council (SPC) is a vendor-neutral standards body focused on the storage industry. The SPC created the first industry-standard
performance benchmark targeted at the needs and concerns of the storage industry. From component level evaluation to the measurement of complete
distributed storage systems, the SPC benchmark portfolio provides independently audited, rigorous and reliable measures of performance, price-performance
and power consumption. For more information about the SPC and its benchmarks, please visit: http://ift.tt/1wxUDHw.
DataCore, the Data Infrastructure Software company, is the leading provider of Software-Defined Storage and
Adaptive Parallel I/O Software
– harnessing today’s powerful and cost-efficient server platforms with Parallel I/O to overcome the IT industry’s biggest problem, the I/O bottleneck, in
order to deliver unsurpassed performance, hyper-consolidation efficiencies and cost savings. The company’s comprehensive and flexible storage virtualization and hyper-converged virtual SAN solutions free users from the pain of
labor-intensive storage management and provide true independence from solutions that cannot offer a hardware agnostic architecture. DataCore’s
Software-Defined and Parallel I/O powered platforms revolutionize data infrastructure and serve as the cornerstone of the next-generation, software-defined
data center – delivering greater value, industry-best performance, availability and simplicity. Visit http://www.datacore.com or call (877) 780-5111 for more information.
Storage Performance Council, SPC-1, SPC-1 IOPS, SPC-1 Price-Performance and SPC-1 Result are trademarks or registered trademarks of the Storage
DataCore, the DataCore logo, Parallel Server and SANsymphony are trademarks or registered trademarks of DataCore Software Corporation. Other DataCore
product or service names or logos referenced herein are trademarks of DataCore Software Corporation. All other products, services and company names
mentioned herein may be trademarks of their respective owners.
For media & PR inquiries:
SVM on behalf of DataCore
Jill Colna or Sarah Anderson
SPC Benchmark 1 Full Disclosure Report DataCore Software Corporation DataCore Parallel Server
(Current as of 2/26/2016)
SPC Benchmark 1 Full Disclosure Report DataCore Software Corporation DataCore SANsymphony-V 10.0
(Current as of 11/30/2015)