Github user lvfangmin commented on a diff in the pull request:
https://github.com/apache/zookeeper/pull/684#discussion_r238786172
--- Diff:
zookeeper-server/src/main/java/org/apache/zookeeper/server/NIOServerCnxn.java
---
@@ -151,12 +148,17 @@ void sendBufferSync(ByteBuffer bb) {
* sendBuffer pushes a byte buffer onto the outgoing buffer queue for
* asynchronous writes.
*/
- public void sendBuffer(ByteBuffer bb) {
+ public void sendBuffer(ByteBuffer... buffers) {
if (LOG.isTraceEnabled()) {
LOG.trace("Add a buffer to outgoingBuffers, sk " + sk
+ " is valid: " + sk.isValid());
}
- outgoingBuffers.add(bb);
+ synchronized (outgoingBuffers) {
--- End diff --
We have E2E perf regression detect for different use cases with different
traffic, haven't seen any obvious perf impact there.
---
