def generateData(scale, base, namenode, tableName=""):
loggerInfo = buildReportLogger("gen")
reportName = loggerInfo[0]
report = loggerInfo[1]
trueScale = scaleConverter(scale)
uniInfoLog("Creating Dataset for " + str(trueScale), report)
print str(trueScale)
if (Hadoop.ls(base))[0] == -1:
result = Hadoop.mkdir(base)
if result[0] < 0:
print result[1]
exit()
else:
print "Base Directory already exists. Please change and rerun"
exit()
buildGen()
os.chdir(workingDir + "/tpcds-gen")
for file in glob.glob("target/*.jar"):
jarFile = file
uniInfoLog("Data Generation MapRed Job Starting", report)
# TABLE GEN DOESN"T WORK, SO COMMENTING THIS OUT TO KEEP FROM RUNNING IT
# if tableName:
# result = Hadoop.runTable(jarFile, scale, base, tableName)
# else:
# result = Hadoop.run(jarFile, scale, base)
result = Hadoop.run(jarFile, str(trueScale), base)
uniInfoLog("Data Generation MapRed Job Complete", report)
uniInfoLog("Changing Replication Factor of RawData to 2")
result = Hadoop.setrep(2, base)
def capacityReport(namenode, hdfsDir):
results = Hadoop.size(hdfsDir)
print results[1]
