Real time Query on Hadoop - Cloudera Impala

Agenda
a) How do we improve latency to query data on Hadoop? Use case and the need for Impala
b) How is Impala different from competition? (Dremel, Drill, others)? Key differences in approaches
c) How does Impala provide an MPP style execution on Hadoop? Technical overview of Impala architecture
d) What happens to MR jobs? Does impala reduce the need for MR programming?
e) Performance statistics of Impala on large sets of data
f) Demo of Impala and future road map