spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Pa Rö <paul.roewer1...@googlemail.com>
Subject k-means iteration not terminate
Date Mon, 20 Jul 2015 14:51:00 GMT
hi community,

i have write a spark k-means app. now i run it on a cluster.
my job start and at iteration nine or ten the process stop.
in the spark dashbord all time shown "is running", but nothing
happend, no exceptions.

my setting is the following:
1000 input points
k=10
maxIteration=30
a tree node cluster (one node have 16GB RAM und 8cores i7)
i use cloudera live 5.4.4 with spark 1.3

maybe spark need more memory or i have a wrong setting?

best regards,
paul

Mime
View raw message