diff --git a/core/src/main/scala/org/apache/spark/deploy/RRunner.scala b/core/src/main/scala/org/apache/spark/deploy/RRunner.scala index 58cc1f9d963df9759c577bc9f92b601a0384545e..ed183cf16a9cbdd803cb17a7acda59416642e59d 100644 --- a/core/src/main/scala/org/apache/spark/deploy/RRunner.scala +++ b/core/src/main/scala/org/apache/spark/deploy/RRunner.scala @@ -40,7 +40,16 @@ object RRunner { // Time to wait for SparkR backend to initialize in seconds val backendTimeout = sys.env.getOrElse("SPARKR_BACKEND_TIMEOUT", "120").toInt - val rCommand = "Rscript" + val rCommand = { + // "spark.sparkr.r.command" is deprecated and replaced by "spark.r.command", + // but kept here for backward compatibility. + var cmd = sys.props.getOrElse("spark.sparkr.r.command", "Rscript") + cmd = sys.props.getOrElse("spark.r.command", cmd) + if (sys.props.getOrElse("spark.submit.deployMode", "client") == "client") { + cmd = sys.props.getOrElse("spark.r.driver.command", cmd) + } + cmd + } // Check if the file path exists. // If not, change directory to current working directory for YARN cluster mode diff --git a/docs/configuration.md b/docs/configuration.md index be9c36bdfe3de258c7cf8f9a5cfd0b49a5e7fb71..682384d4249e029fbb005bf5caed16932cbbc22f 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -1589,6 +1589,20 @@ Apart from these, the following properties are also available, and may be useful Number of threads used by RBackend to handle RPC calls from SparkR package. </td> </tr> +<tr> + <td><code>spark.r.command</code></td> + <td>Rscript</td> + <td> + Executable for executing R scripts in cluster modes for both driver and workers. + </td> +</tr> +<tr> + <td><code>spark.r.driver.command</code></td> + <td>spark.r.command</td> + <td> + Executable for executing R scripts in client modes for driver. Ignored in cluster modes. + </td> +</tr> </table> #### Cluster Managers @@ -1628,6 +1642,10 @@ The following variables can be set in `spark-env.sh`: <td><code>PYSPARK_DRIVER_PYTHON</code></td> <td>Python binary executable to use for PySpark in driver only (default is <code>PYSPARK_PYTHON</code>).</td> </tr> + <tr> + <td><code>SPARKR_DRIVER_R</code></td> + <td>R binary executable to use for SparkR shell (default is <code>R</code>).</td> + </tr> <tr> <td><code>SPARK_LOCAL_IP</code></td> <td>IP address of the machine to bind to.</td>