I did the test on Spark 2.2.0 and problem still exists. Any ideas how to fix it ?
Regards, Maciek 2017-07-11 11:52 GMT+02:00 Maciej Bryński <mac...@brynski.pl>: > Hi, > I have following issue. > I'm trying to use Spark as a proxy to Cassandra. > The problem is the thrift server overhead. > > I'm using following query: > select * from table where primay_key = 123 > > Job time (from jobs tab) is around 50ms. (and it's similar to query time > from SQL tab) > Unfortunately query time from JDBC/ODBC Server is 650 ms. > Any ideas why ? What could cause such an overhead ? > > Regards, > -- > Maciek Bryński > -- Maciek Bryński