X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=src%2Fceph%2Fqa%2Fworkunits%2Fhadoop%2Fwordcount.sh;fp=src%2Fceph%2Fqa%2Fworkunits%2Fhadoop%2Fwordcount.sh;h=1ff057a7f4a885969a35dd00555953ed8dd6a4d5;hb=812ff6ca9fcd3e629e49d4328905f33eee8ca3f5;hp=0000000000000000000000000000000000000000;hpb=15280273faafb77777eab341909a3f495cf248d9;p=stor4nfv.git

diff --git a/src/ceph/qa/workunits/hadoop/wordcount.sh b/src/ceph/qa/workunits/hadoop/wordcount.sh
new file mode 100755
index 0000000..1ff057a
--- /dev/null
+++ b/src/ceph/qa/workunits/hadoop/wordcount.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+
+set -e
+set -x
+
+WC_INPUT=/wc_input
+WC_OUTPUT=/wc_output
+DATA_INPUT=$(mktemp -d)
+
+echo "starting hadoop-wordcount test"
+
+# bail if $TESTDIR is not set as this test will fail in that scenario
+[ -z $TESTDIR ] && { echo "\$TESTDIR needs to be set, but is not. Exiting."; exit 1; }
+
+# if HADOOP_PREFIX is not set, use default
+[ -z $HADOOP_PREFIX ] && { HADOOP_PREFIX=$TESTDIR/hadoop; }
+
+# Nuke hadoop directories
+$HADOOP_PREFIX/bin/hadoop fs -rm -r $WC_INPUT $WC_OUTPUT || true
+
+# Fetch and import testing data set
+curl http://download.ceph.com/qa/hadoop_input_files.tar | tar xf - -C $DATA_INPUT
+$HADOOP_PREFIX/bin/hadoop fs -copyFromLocal $DATA_INPUT $WC_INPUT
+rm -rf $DATA_INPUT
+
+# Run the job
+$HADOOP_PREFIX/bin/hadoop jar \
+  $HADOOP_PREFIX/share/hadoop/mapreduce/hadoop-mapreduce-examples-*.jar \
+  wordcount $WC_INPUT $WC_OUTPUT
+
+# Cleanup
+$HADOOP_PREFIX/bin/hadoop fs -rm -r $WC_INPUT $WC_OUTPUT || true
+
+echo "completed hadoop-wordcount test"
+exit 0