attilapiros commented on a change in pull request #23278: [SPARK-24920][Core]
Allow sharing Netty's memory pool allocators
URL: https://github.com/apache/spark/pull/23278#discussion_r242627612
##########
File path:
common/network-common/src/main/java/org/apache/spark/network/util/NettyUtils.java
##########
@@ -36,6 +36,22 @@
* Utilities for creating various Netty constructs based on whether we're
using EPOLL or NIO.
*/
public class NettyUtils {
+
+ /**
+ * Specifies an upper bound on the number of Netty threads that Spark
requires by default.
+ * In practice, only 2-4 cores should be required to transfer roughly 10
Gb/s, and each core
+ * that we use will have an initial overhead of roughly 32 MB of off-heap
memory, which comes
+ * at a premium.
+ *
+ * Thus, this value should still retain maximum throughput and reduce wasted
off-heap memory
+ * allocation. It can be overridden by setting the number of serverThreads
and clientThreads
+ * manually in Spark's configuration.
+ */
+ private static int MAX_DEFAULT_NETTY_THREADS = 8;
+
+ private static PooledByteBufAllocator[] _sharedPooledByteBufAllocator =
Review comment:
It is a bit simple to use and array as based on the index I can set the
right element.
Does not matter which one (0 or 1) as long as it is consistent (and that one
line of code calculating the index is consistent).
Otherwise an extra if should be introduced to set the right field. Whit the
checking of is it initialised it would be a scoped if. And I just prefer to
avoid scoped if-s, like:
```scala
public static synchronized PooledByteBufAllocator
getSharedPooledByteBufAllocator(
boolean allowDirectBufs,
boolean allowCache) {
if (allowCache) {
if (_sharedPooledByteBufAllocatorWithAllowCache == null) {
_sharedPooledByteBufAllocatorWithAllowCache =
createPooledByteBufAllocator(
allowDirectBufs,
allowCache,
defaultNumThreads(0));
}
return _sharedPooledByteBufAllocatorWithAllowCache;
} else {
if (_sharedPooledByteBufAllocatorWithoutAllowCache == null) {
_sharedPooledByteBufAllocatorWithoutAllowCache =
createPooledByteBufAllocator(
allowDirectBufs,
allowCache,
defaultNumThreads(0));
}
return _sharedPooledByteBufAllocatorWithoutAllowCache;
}
}
```
Or am I miss something?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
