fe元数据ckp时发生oom

版本:2.5.3
问题:fe元数据ckp时发生oom,导致dbd文件一直增加,总大小达到50G且还会不断变大,无法生成新的image
影响:fe重启时bdb文件过多导致回放时间过长,需要好几个小时


2025-03-28 15:50:57,686 ERROR (leaderCheckpointer|193) [Daemon.run():117] daemon thread got exception. name: leaderCheckpointer
java.lang.OutOfMemoryError: null
at java.lang.AbstractStringBuilder.hugeCapacity(AbstractStringBuilder.java:161) ~[?:1.8.0_351]
at java.lang.AbstractStringBuilder.newCapacity(AbstractStringBuilder.java:155) ~[?:1.8.0_351]
at java.lang.AbstractStringBuilder.ensureCapacityInternal(AbstractStringBuilder.java:125) ~[?:1.8.0_351]
at java.lang.AbstractStringBuilder.append(AbstractStringBuilder.java:448) ~[?:1.8.0_351]
at java.lang.StringBuffer.append(StringBuffer.java:276) ~[?:1.8.0_351]
at java.io.StringWriter.write(StringWriter.java:112) ~[?:1.8.0_351]
at com.google.gson.stream.JsonWriter.string(JsonWriter.java:584) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.stream.JsonWriter.value(JsonWriter.java:418) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.TypeAdapters$15.write(TypeAdapters.java:384) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.TypeAdapters$15.write(TypeAdapters.java:368) ~[spark-dpp-1.0.0.jar:?]
at com.starrocks.persist.gson.GsonUtils$ProcessHookTypeAdapterFactory$1.write(GsonUtils.java:503) ~[starrocks-fe.jar:?]
at com.google.gson.internal.bind.TypeAdapterRuntimeTypeWrapper.write(TypeAdapterRuntimeTypeWrapper.java:69) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.ReflectiveTypeAdapterFactory$1.write(ReflectiveTypeAdapterFactory.java:127) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.ReflectiveTypeAdapterFactory$Adapter.write(ReflectiveTypeAdapterFactory.java:245) ~[spark-dpp-1.0.0.jar:?]
at com.starrocks.persist.gson.GsonUtils$ProcessHookTypeAdapterFactory$1.write(GsonUtils.java:503) ~[starrocks-fe.jar:?]
at com.google.gson.internal.bind.TypeAdapterRuntimeTypeWrapper.write(TypeAdapterRuntimeTypeWrapper.java:69) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.CollectionTypeAdapterFactory$Adapter.write(CollectionTypeAdapterFactory.java:97) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.CollectionTypeAdapterFactory$Adapter.write(CollectionTypeAdapterFactory.java:61) ~[spark-dpp-1.0.0.jar:?]
at com.starrocks.persist.gson.GsonUtils$ProcessHookTypeAdapterFactory$1.write(GsonUtils.java:503) ~[starrocks-fe.jar:?]
at com.google.gson.internal.bind.TypeAdapterRuntimeTypeWrapper.write(TypeAdapterRuntimeTypeWrapper.java:69) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.ReflectiveTypeAdapterFactory$1.write(ReflectiveTypeAdapterFactory.java:127) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.internal.bind.ReflectiveTypeAdapterFactory$Adapter.write(ReflectiveTypeAdapterFactory.java:245) ~[spark-dpp-1.0.0.jar:?]
at com.starrocks.persist.gson.GsonUtils$ProcessHookTypeAdapterFactory$1.write(GsonUtils.java:503) ~[starrocks-fe.jar:?]
at com.google.gson.Gson.toJson(Gson.java:735) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.Gson.toJson(Gson.java:714) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.Gson.toJson(Gson.java:669) ~[spark-dpp-1.0.0.jar:?]
at com.google.gson.Gson.toJson(Gson.java:649) ~[spark-dpp-1.0.0.jar:?]
at com.starrocks.scheduler.TaskManager.saveTasks(TaskManager.java:453) ~[starrocks-fe.jar:?]
at com.starrocks.server.GlobalStateMgr.saveImage(GlobalStateMgr.java:1616) ~[starrocks-fe.jar:?]
at com.starrocks.server.GlobalStateMgr.saveImage(GlobalStateMgr.java:1567) ~[starrocks-fe.jar:?]
at com.starrocks.leader.Checkpoint.replayAndGenerateGlobalStateMgrImage(Checkpoint.java:204) ~[starrocks-fe.jar:?]
at com.starrocks.leader.Checkpoint.runAfterCatalogReady(Checkpoint.java:93) ~[starrocks-fe.jar:?]
at com.starrocks.common.util.LeaderDaemon.runOneCycle(LeaderDaemon.java:60) ~[starrocks-fe.jar:?]
at com.starrocks.common.util.Daemon.run(Daemon.java:115) [starrocks-fe.jar:?]