Big data describes the phenomenon of using data to
derive business value. Financial organizations create value
with big data through the collection and simulation of data
for risk analysis, research, and post-trade analytics. The
sheer volume and growth rate of data can strain storage
resources. Monte Carlo simulation, tick data analysis, and
portfolio optimization require high performance parallel
storage to satisfy the demand for fast, shared access to
large and small files alike. This data explosion is driving
the need for fast, extremely scalable, easy to manage, and
affordable high performance storage system
1. BIG DATA CREATES COMPETITIVE ADVANTAGES
Big data describes the phenomenon of using data to
derive business value. Financial organizations create value
with big data through the collection and simulation of data
for risk analysis, research, and post-trade analytics. The
sheer volume and growth rate of data can strain storage
resources. Monte Carlo simulation, tick data analysis, and
portfolio optimization require high performance parallel
storage to satisfy the demand for fast, shared access to
large and small files alike. This data explosion is driving
the need for fast, extremely scalable, easy to manage, and
affordable high performance storage systems.
Legacy storage systems were designed for highly
structured and centralized environments whereas the
big data world is highly unstructured and distributed.
Traditional NAS solutions, constrained by in-band filer
heads and hardware RAID controllers, frequently cannot
provide the required data throughput to keep ad-hoc and
real-time workflows running optimally. Legacy approaches
inevitably introduced bottlenecks which slowed research
and created costly islands of storage.
Panasas®
ActiveStor™ Parallel Storage
ActiveStor provides incredibly fast access to very large
data sets from many clients simultaneously. It removes
performance bottlenecks by allowing compute clients
to read and write data in parallel, to and from physical
storage devices. While market data is often generated in
A large international bank relies upon data-intensive,
business-critical applications for intra-day credit risk
analysis. Its large database which drives the Monte Carlo
scenarios contains financial simulation attributes of each
party. Multiple simulation scenarios involving up to 500,000
counter parties are required to predict the risk impact on
the bank. With its legacy SAN storage, risk figures that are
critical to traders were often unavailable even by the start of
the next trading day because of I/O bottlenecks. The bank
needed to provide traders with faster and more accurate risk
figures throughout the trading day.
The bank selected high performance, scalable, and reliable
Panasas storage to support its growing high performance
computing infrastructure. The migration from legacy SAN to
Panasas parallel storage increased bandwidth performance
by 6GB/s, enabling 100 times more scenarios per entity
in the same amount of processing time as the SAN, and
at a lower cost. Total cost/performance of the Panasas
solution provided even greater benefit by allowing the bank
to eliminate the need for an expensive ISV database solution.
The scalability and I/O issues with large databases were
resolved, enabling the bank to boost its competitiveness with
an increased number of simulations that minimized its risk in
credit markets.
single streams, analysis of that data can be done in parallel
among many clients. ActiveStor 14 uses Solid State Drive
(SSD) technology to accelerate access to metadata and
the small files that predominate within financial datasets.
Extreme performance for both large and small files supports
large numbers of users, intensive I/O, and enables financial
organizations to reduce their time-to-results.
Beyond satisfying performance demands, simplified
management makes ActiveStor a compelling solution for
financial applications. Linear scalability enables customers
to easily increase performance and capacity as demand
grows. ActiveStor delivers high availability and superior
reliability that financial organizations can depend on.
RISK ANALYSIS | MONTE CARLO SIMULATION | TICK DATA | MARKET ANALYTICS | PORTFOLIO OPTIMIZATION
A C C E L E R A T E F I N A N C I A L
S I M U L A T I O N & A N A L Y T I C S
W I T H H I G H P E R F O R M A N C E P A R A L L E L S T O R A G E