pan3793 commented on code in PR #2061:
URL:
https://github.com/apache/incubator-celeborn/pull/2061#discussion_r1407337218
##########
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 " +
+ "to determine whether to take action.")
+ .doubleConf
+ .createWithDefault(5)
+
+ val WORKER_JVM_QUAKE_DUMP_THRESHOLD: ConfigEntry[Long] =
+ buildConf("celeborn.worker.jvm.quake.dump.threshold")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("The threshold of heap dump for the maximum GC \"deficit\" which
can be accumulated before jvmquake takes action.")
+ .timeConf(TimeUnit.MILLISECONDS)
+ .createWithDefaultString("30s")
+
+ val WORKER_JVM_QUAKE_KILL_THRESHOLD: ConfigEntry[Long] =
+ buildConf("celeborn.worker.jvm.quake.kill.threshold")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("The threshold of system kill for the maximum GC \"deficit\" which
can be accumulated before jvmquake takes action.")
+ .timeConf(TimeUnit.MILLISECONDS)
+ .createWithDefaultString("60s")
+
+ val WORKER_JVM_QUAKE_DUMP_ENABLED: ConfigEntry[Boolean] =
+ buildConf("celeborn.worker.jvm.quake.dump.enabled")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("Whether to heap dump for the maximum GC \"deficit\" during worker
jvm quake.")
+ .booleanConf
+ .createWithDefault(true)
+
+ val WORKER_JVM_QUAKE_DUMP_PATH: OptionalConfigEntry[String] =
+ buildConf("celeborn.worker.jvm.quake.dump.path")
+ .categories("worker")
+ .version("0.3.2")
+ .doc("The path of heap dump for the maximum GC \"deficit\" during worker
jvm quake, " +
+ "which default value is
[java.io.tmpdir]/celeborn/jvm-quake/dump/[pid].")
+ .stringConf
+ .createOptional
+
+ val WORKER_JVM_QUAKE_EXIT_CODE: ConfigEntry[Int] =
+ buildConf("celeborn.worker.jvm.quake.exit.code")
Review Comment:
Avoid using `.` to introduce unnecessary new namespace
```suggestion
buildConf("celeborn.worker.jvmQuake.exitCode")
```
--
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]
