pan3793 commented on code in PR #2061:
URL:
https://github.com/apache/incubator-celeborn/pull/2061#discussion_r1407337819
##########
common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala:
##########
@@ -2896,6 +2911,75 @@ object CelebornConf extends Logging {
.longConf
.createOptional
+ val WORKER_JVM_QUAKE_ENABLED: ConfigEntry[Boolean] =
+ buildConf("celeborn.worker.jvm.quake.enabled")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("When true, Celeborn worker will start the jvm quake to monitor of
gc behavior, " +
+ "which enables early detection of memory management issues and
facilitates fast failure.")
+ .booleanConf
+ .createWithDefault(false)
+
+ val WORKER_JVM_QUAKE_CHECK_INTERVAL: ConfigEntry[Long] =
+ buildConf("celeborn.worker.jvm.quake.check.interval")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("Interval of gc behavior checking for worker jvm quake.")
+ .timeConf(TimeUnit.MILLISECONDS)
+ .createWithDefaultString("1s")
+
+ val WORKER_JVM_QUAKE_RUNTIME_WEIGHT: ConfigEntry[Double] =
+ buildConf("celeborn.worker.jvm.quake.runtime.weight")
+ .categories("worker")
+ .version("0.3.2")
+ .doc(
+ "The factor by which to multiply running JVM time, when weighing it
against GCing time. " +
+ "\"Deficit\" is accumulated as gc_time - runtime * runtime_weight,
and is compared against threshold " +
Review Comment:
```suggestion
"'Deficit' is accumulated as `gc_time - runtime * runtime_weight`,
and is compared against threshold " +
```
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
