Hi Franke,
Let me clarify our situation more detailed. We want to store all our
data in memory and all the job will never access the backend data. However,
we still need backend storage such as HDFS to persist in memory data
asynchronously in case of data lose which is caused by node failure.
Of course, we will use a cluster to get thinks work. In order to avoid
the network I/O effecting my experiment, I use a single node to test and
check whether ignite can be treated as a memory cache acceleration layer for
map-reduce job or spark job.
--
View this message in context:
http://apache-ignite-users.70518.x6.nabble.com/Apache-Ignite-vs-alluxio-tp9140p9145.html
Sent from the Apache Ignite Users mailing list archive at Nabble.com.
