This option can be set either to "internal" or "external" When set to "external" H2O Context is created by connecting to existing H2O cluster, otherwise it creates H2O cluster living in Spark - that means that each Spark executor will have one h2o instance running in it.
This option can be set either to "internal" or "external" When set to "external" H2O Context is created by connecting to existing H2O cluster, otherwise it creates H2O cluster living in Spark - that means that each Spark executor will have one h2o instance running in it. The internal is not recommended for big clusters and clusters where Spark executors are not stable.
Location of iced directory for the driver instance.
IP of H2O client node
Location of log directory for the driver instance.
H2O log level for client running in Spark driver
Subnet selector for H2O client - if the mask is specified then Spark network setup is not discussed.
Port on which H2O client publishes its API.
Port on which H2O client publishes its API. If already occupied, the next odd port is tried and so on
Print detailed messages to client stdout
Exact client port to access web UI.
Exact client port to access web UI.
The value -1
means automatic search for free port starting at spark.ext.h2o.port.base
.
Configuration property - name of H2O cloud
Enable/Disable listener which kills H2O when there is a change in underlying cluster's topology*
Disable GA tracking
Enable/Disable exit on unsupported Spark parameters.
Enable hash login.
Path to Java KeyStore file.
Password for Java KeyStore file.
Enable Kerberos login.
Enable LDAP login.
Login configuration file.
Location of log directory for remote nodes.
H2O internal log level for launched remote nodes.
Limit for number of threads used by H2O, default -1 means unlimited
Enable/Disable Sparkling-Water REPL *
Number of executors started at the start of h2o services, by default 1
Enable/Disable check for Spark version.
Path to Java KeyStore file.
Interval for updates of Spark UI in milliseconds
Override user name for cluster.