fix

apache · Mar 25, 2024 · e7978cc · e7978cc
1 parent 5f145ac
commit e7978cc
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 6 deletions.
diff --git a/backends-velox/src/test/scala/io/glutenproject/expression/VeloxUdfSuite.scala b/backends-velox/src/test/scala/io/glutenproject/expression/VeloxUdfSuite.scala
@@ -47,6 +47,9 @@ abstract class VeloxUdfSuite extends GlutenQueryTest with SQLHelper {
             "/path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so")
     }
 
+  protected lazy val udfLibRelativePath: String =
+    udfLibPath.split(",").map(p => Paths.get(p).getFileName.toString).mkString(",")
+
   override protected def beforeAll(): Unit = {
     super.beforeAll()
     if (_spark == null) {
@@ -83,7 +86,7 @@ class VeloxUdfSuiteLocal extends VeloxUdfSuite {
   override protected def sparkConf: SparkConf = {
     super.sparkConf
       .set("spark.files", udfLibPath)
-      .set("spark.gluten.sql.columnar.backend.velox.udfLibraryPaths", "libmyudf.so")
+      .set("spark.gluten.sql.columnar.backend.velox.udfLibraryPaths", udfLibRelativePath)
   }
 }
 

diff --git a/docs/get-started/Velox.md b/docs/get-started/Velox.md
@@ -434,23 +434,23 @@ Gluten loads the UDF libraries at runtime. You can upload UDF libraries via `--f
 
 Note if running on Yarn client mode, the uploaded files are not reachable on driver side. Users should copy those files to somewhere reachable for driver and set `spark.gluten.sql.columnar.backend.velox.driver.udfLibraryPaths`. This configuration is also useful when the `udfLibraryPaths` is different between driver side and executor side.
 
-- Use `--files`
+- Use the `--files` option to upload a library and configure its relative path
 ```shell
 --files /path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so
 --conf spark.gluten.sql.columnar.backend.velox.udfLibraryPaths=libmyudf.so
 # Needed for Yarn client mode
---conf spark.gluten.sql.columnar.backend.velox.driver.udfLibraryPaths=file:///path/to/libmyudf.so
+--conf spark.gluten.sql.columnar.backend.velox.driver.udfLibraryPaths=file:///path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so
 ```
 
-- Use `--archives`
+- Use the `--archives` option to upload a archive and configure its relative path
 ```shell
 --archives /path/to/udf_archives.zip#udf_archives
 --conf spark.gluten.sql.columnar.backend.velox.udfLibraryPaths=udf_archives
 # Needed for Yarn client mode
 --conf spark.gluten.sql.columnar.backend.velox.driver.udfLibraryPaths=file:///path/to/udf_archives.zip
 ```
 
-- Specify URI
+- Only configure URI
 
 You can also specify the local or HDFS URIs to the UDF libraries or archives. Local URIs should exist on driver and every worker nodes.
 ```shell
@@ -462,10 +462,17 @@ You can also specify the local or HDFS URIs to the UDF libraries or archives. Lo
 We provided an Velox UDF example file [MyUDF.cpp](../../cpp/velox/udf/examples/MyUDF.cpp). After building gluten cpp, you can find the example library at /path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so
 
 Start spark-shell or spark-sql with below configuration 
-```
+```shell
+# Use the `--files` option to upload a library and configure its relative path
 --files /path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so
 --conf spark.gluten.sql.columnar.backend.velox.udfLibraryPaths=libmyudf.so
 ```
+or
+```shell
+# Only configure URI
+--conf spark.gluten.sql.columnar.backend.velox.udfLibraryPaths=file:///path/to/gluten/cpp/build/velox/udf/examples/libmyudf.so
+```
+
 Run query. The functions `myudf1` and `myudf2` increment the input value by a constant of 5
 ```
 select myudf1(1), myudf2(100L)