Hi, I ran Spark application in local mode with command: $SPARK_HOME/bin/spark-submit --driver-memory 1g <class> <jar> with set master=local.
After around 10 minutes of computing it started to slow down significantly that next stage took around 50 minutes and next after 5 hours in 80% done and CPU usage decreased from 160% to almost 0% (according to system monitor) where 200% is max for one core. (This stage that took more than 5h was saveAsTextFile on 50MB RDD). During that computing my system was significantly slower and less responsible. Moreover when I wanted to interrupt this application I tried ctrl-c and current stage was interrupted but program didn't exit. When I shut down my computer system didn't want to shutdown because killing Spark app failed. (It shut down after ctrl-alt-del). After reboot system didn't want to start and finally I had to reinstall it. The same thing was when I killed next app using kill -9, system was corrupted and I had to reinstall it. When I ran this app on a bit smaller data everything was ok. I have Linux Mint 17, 8GB RAM, Intel Core i7-3630QM (4x2,4GHz). Do you have any idea why Spark slow down or how to properly kill spark app run through spark-submit? Thanks, Grzegorz