Skip to content
GitLab
Menu
Projects
Groups
Snippets
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
cld
workloads
tpcds
Commits
1136dc70
Commit
1136dc70
authored
Apr 11, 2017
by
Jonathan Mace
Browse files
Resolve merge conflicts
parents
34a240f6
a4d09780
Changes
2
Hide whitespace changes
Inline
Side-by-side
src/main/resources/reference.conf
View file @
1136dc70
tpcds
{
scaleFactor
=
1
dataLocation
=
"hdfs://
127.0.0.1
:9000/tpcds"
scaleFactor
=
1
00
dataLocation
=
"hdfs://
namenode
:9000/tpcds
100
"
dataFormat
=
"parquet"
overwrite
=
false
partitionTables
=
fals
e
partitionTables
=
tru
e
useDoubleForDecimal
=
false
clusterByPartitionColumns
=
false
filterOutNullPartitionValues
=
false
}
\ No newline at end of file
}
src/main/scala/com/databricks/spark/sql/perf/tpcds/Tables.scala
View file @
1136dc70
...
...
@@ -113,7 +113,7 @@ class Tables(sqlContext: SQLContext, scaleFactor: Int) extends Serializable {
overwrite
:
Boolean
,
clusterByPartitionColumns
:
Boolean
,
filterOutNullPartitionValues
:
Boolean
)
:
Unit
=
{
println
(
s
"Begin genData for table $name in database to $location
with save mode $mode
"
)
println
(
s
"Begin genData for table $name in database to $location"
)
val
mode
=
if
(
overwrite
)
SaveMode
.
Overwrite
else
SaveMode
.
Ignore
val
data
=
df
(
format
!=
"text"
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment