THE explosion of Big Data has prompted much research
to develop systems to support ultra-low latency service
and real-time data analytics. Existing disk-based systems
can no longer offer timely response due to the high access
latency to hard disks. The unacceptable performance was
initially encountered by Internet companies such as Amazon,
Google, Facebook and Twitter, but is now also becoming
an obstacle for other companies/organizations which
desire to provide a meaningful real-time service (e.g., realtime
bidding, advertising, social gaming). For instance,
trading companies need to detect a sudden change in the
trading prices and react instantly (in several milliseconds),
which is impossible to achieve using traditional disk-based
processing/storage systems. To meet the strict real-time
requirements for analyzing mass amounts of data and servicing
requests within milliseconds, an in-memory system/
database that keeps the data in the random access memory
(RAM) all the time is necessary.