This is an automated email from the ASF dual-hosted git repository.
ethanfeng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-celeborn.git
The following commit(s) were added to refs/heads/main by this push:
new 1dcfdb0c [CELEBORN-281] Add metrics about buffer stream read buffer.
(#1216)
1dcfdb0c is described below
commit 1dcfdb0c8fed1db443efe174088f8cd1d1618ec8
Author: Ethan Feng <[email protected]>
AuthorDate: Fri Feb 17 11:20:07 2023 +0800
[CELEBORN-281] Add metrics about buffer stream read buffer. (#1216)
---
.../apache/celeborn/common/network/server/memory/MemoryManager.java | 6 +++++-
.../scala/org/apache/celeborn/service/deploy/worker/Worker.scala | 3 +++
.../org/apache/celeborn/service/deploy/worker/WorkerSource.scala | 1 +
3 files changed, 9 insertions(+), 1 deletion(-)
diff --git
a/common/src/main/java/org/apache/celeborn/common/network/server/memory/MemoryManager.java
b/common/src/main/java/org/apache/celeborn/common/network/server/memory/MemoryManager.java
index 2dd8c04c..dd0273dc 100644
---
a/common/src/main/java/org/apache/celeborn/common/network/server/memory/MemoryManager.java
+++
b/common/src/main/java/org/apache/celeborn/common/network/server/memory/MemoryManager.java
@@ -67,7 +67,7 @@ public class MemoryManager {
private boolean underPressure;
private final AtomicBoolean trimInProcess = new AtomicBoolean(false);
- // For read buffer
+ // For buffer stream
private final AtomicLong readBufferCounter = new AtomicLong(0);
private long readBufferThreshold = 0;
private final ReadBufferDispatcher readBufferDispatcher;
@@ -342,6 +342,10 @@ public class MemoryManager {
return diskBufferCounter;
}
+ public AtomicLong getReadBufferCounter() {
+ return readBufferCounter;
+ }
+
public long getPausePushDataCounter() {
return pausePushDataCounter.sum();
}
diff --git
a/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Worker.scala
b/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Worker.scala
index 800cec31..7617d1c6 100644
---
a/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Worker.scala
+++
b/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Worker.scala
@@ -239,6 +239,9 @@ private[celeborn] class Worker(
workerSource.addGauge(
WorkerSource.PausePushDataAndReplicateCount,
_ => memoryTracker.getPausePushDataAndReplicateCounter)
+ workerSource.addGauge(
+ WorkerSource.BufferStreamReadBuffer,
+ _ => memoryTracker.getReadBufferCounter.get())
private def heartBeatToMaster(): Unit = {
val activeShuffleKeys = new JHashSet[String]()
diff --git
a/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/WorkerSource.scala
b/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/WorkerSource.scala
index df662542..ea9b293d 100644
---
a/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/WorkerSource.scala
+++
b/worker/src/main/scala/org/apache/celeborn/service/deploy/worker/WorkerSource.scala
@@ -91,6 +91,7 @@ object WorkerSource {
val DiskBuffer = "DiskBuffer"
val PausePushDataCount = "PausePushData"
val PausePushDataAndReplicateCount = "PausePushDataAndReplicate"
+ val BufferStreamReadBuffer = "BufferStreamReadBuffer"
// local device
val DeviceOSFreeCapacity = "DeviceOSFreeCapacity(B)"