otterc commented on a change in pull request #30312:
URL: https://github.com/apache/spark/pull/30312#discussion_r536266305



##########
File path: core/src/main/scala/org/apache/spark/internal/config/package.scala
##########
@@ -1992,4 +1992,32 @@ package object config {
       .version("3.1.0")
       .doubleConf
       .createWithDefault(5)
+
+  private[spark] val SHUFFLE_NUM_PUSH_THREADS =
+    ConfigBuilder("spark.shuffle.push.numPushThreads")
+      .doc("Specify the number of threads in the block pusher pool. These 
threads assist " +
+        "in creating connections and pushing blocks to remote shuffle 
services. By default, the " +
+        "threadpool size is equal to the number of spark executor cores.")
+      .version("3.1.0")
+      .intConf
+      .createOptional
+
+  private[spark] val SHUFFLE_MAX_BLOCK_SIZE_TO_PUSH =
+    ConfigBuilder("spark.shuffle.push.maxBlockSizeToPush")
+      .doc("The max size of an individual block to push to the remote shuffle 
services. Blocks " +
+       "larger than this threshold are not pushed to be merged remotely. These 
shuffle blocks " +
+       "will be fetched by the executors in the original manner.")
+      .version("3.1.0")
+      .bytesConf(ByteUnit.KiB)
+      .createWithDefaultString("800k")
+
+  private[spark] val SHUFFLE_MAX_BLOCK_BATCH_SIZE_FOR_PUSH =
+    ConfigBuilder("spark.shuffle.push.maxBlockBatchSize")
+      .doc("The max size of a batch of shuffle blocks to be grouped into a 
single push request.")
+      .version("3.1.0")
+      .bytesConf(ByteUnit.MiB)
+      // 2m is also the default value for TransportConf#memoryMapBytes.
+      // Having this default to 2m will very likely make each batch of block 
loaded in memory with
+      // memory mapping, which has higher overhead with small MB sized chunk 
of data.
+      .createWithDefaultString("3m")

Review comment:
       done




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to