Hi there: I'm running a little test on a hadoop 2.2.0 installation with Giraph 1.1.0-snapshot. Here is the command I'm running:
hadoop jar giraph-examples-1.1.0-SNAPSHOT-for-hadoop-2.2.0-jar-with-dependencies.jar org.apache.giraph.benchmark.PageRankBenchmark -Dgiraph.zkList=127.0.0.1:2181 -e 3 -s 10 -v -V 1000000 -w 8 This is my mapred-site.xml: <property> <name>mapreduce.framework.name</name> <value>yarn</value> </property> <property> <name>mapreduce.jobtracker.address</name> <value>localhost:54311</value> </property> <property> <name>mapreduce.tasktracker.map.tasks.maximum</name> <value>10</value> </property> <property> <name>mapreduce.tasktracker.map.tasks.minimum</name> <value>10</value> </property> <property> <name>mapreduce.job.maps</name> <value>10</value> </property> and I'm getting this at the application log: org.apache.giraph.master.BspServiceMaster: checkWorkers: Only found 5 responses of 8 needed to start superstep -1. Reporting every 30000 msecs, 535020 more msecs left before giving up And finally the job finishes with an error (after a long wait). Did anybody have this problem? This doesn't happen if I run the benchmark with 5 workers. I couldn't find any hint why it works with 5 and not with 6 or more. Thanks for any help. Gustavo