This is an automated email from the ASF dual-hosted git repository.
zhouky 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 e2c42faed [CELEBORN-934] Make the log description in
switchServingState more precise
e2c42faed is described below
commit e2c42faed9b268de38420ed94fe64a3b09a940d4
Author: jiaoqingbo <[email protected]>
AuthorDate: Wed Aug 30 14:27:20 2023 +0800
[CELEBORN-934] Make the log description in switchServingState more precise
### What changes were proposed in this pull request?
Modify log content and location to accurately describe state changes
### Why are the changes needed?
In the previous implementation, when servingState was PUSH_PAUSED and
lastState was PUSH_AND_REPLICATE_PAUSED, the code only triggered the Resume of
REPLICATE_MODULE, but the log showed "Trigger action: PAUSE PUSH, RESUME
REPLICATE"
The above log content is not accurate
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
PASS GA
Closes #1864 from jiaoqingbo/934.
Authored-by: jiaoqingbo <[email protected]>
Signed-off-by: zky.zhoukeyong <[email protected]>
---
.../celeborn/service/deploy/worker/memory/MemoryManager.java | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git
a/worker/src/main/java/org/apache/celeborn/service/deploy/worker/memory/MemoryManager.java
b/worker/src/main/java/org/apache/celeborn/service/deploy/worker/memory/MemoryManager.java
index cb248dd9b..ac87db327 100644
---
a/worker/src/main/java/org/apache/celeborn/service/deploy/worker/memory/MemoryManager.java
+++
b/worker/src/main/java/org/apache/celeborn/service/deploy/worker/memory/MemoryManager.java
@@ -255,12 +255,13 @@ public class MemoryManager {
switch (servingState) {
case PUSH_PAUSED:
pausePushDataCounter.increment();
- logger.info("Trigger action: PAUSE PUSH, RESUME REPLICATE");
if (lastState == ServingState.PUSH_AND_REPLICATE_PAUSED) {
+ logger.info("Trigger action: RESUME REPLICATE");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onResume(TransportModuleConstants.REPLICATE_MODULE));
} else if (lastState == ServingState.NONE_PAUSED) {
+ logger.info("Trigger action: PAUSE PUSH");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onPause(TransportModuleConstants.PUSH_MODULE));
@@ -269,24 +270,26 @@ public class MemoryManager {
break;
case PUSH_AND_REPLICATE_PAUSED:
pausePushDataAndReplicateCounter.increment();
- logger.info("Trigger action: PAUSE PUSH and REPLICATE");
if (lastState == ServingState.NONE_PAUSED) {
+ logger.info("Trigger action: PAUSE PUSH");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onPause(TransportModuleConstants.PUSH_MODULE));
}
+ logger.info("Trigger action: PAUSE REPLICATE");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onPause(TransportModuleConstants.REPLICATE_MODULE));
trimAllListeners();
break;
case NONE_PAUSED:
- logger.info("Trigger action: RESUME PUSH and REPLICATE");
if (lastState == ServingState.PUSH_AND_REPLICATE_PAUSED) {
+ logger.info("Trigger action: RESUME REPLICATE");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onResume(TransportModuleConstants.REPLICATE_MODULE));
}
+ logger.info("Trigger action: RESUME PUSH");
memoryPressureListeners.forEach(
memoryPressureListener ->
memoryPressureListener.onResume(TransportModuleConstants.PUSH_MODULE));