Guanghao Zhang created HBASE-23895:
--------------------------------------
Summary: STUCK Region-In-Transition because failed to insert
procedure to procedure store
Key: HBASE-23895
URL: https://issues.apache.org/jira/browse/HBASE-23895
Project: HBase
Issue Type: Bug
Reporter: Guanghao Zhang
When move an region, it will generate a TRSP first and set the procedure to the
region state node. But if the submit TRSP failed, the procedure cannot be unset
now and the region will stuck in RIT.
hbase-server/src/main/java/org/apache/hadoop/hbase/master/assignment/AssignmentManager.java
{code:java}
public Future<byte[]> moveAsync(RegionPlan regionPlan) throws HBaseIOException {
TransitRegionStateProcedure proc =
createMoveRegionProcedure(regionPlan.getRegionInfo(),
regionPlan.getDestination());
return
ProcedureSyncWait.submitProcedure(master.getMasterProcedureExecutor(), proc);
}
public TransitRegionStateProcedure createMoveRegionProcedure(RegionInfo
regionInfo,
ServerName targetServer) throws HBaseIOException {
RegionStateNode regionNode =
this.regionStates.getRegionStateNode(regionInfo);
if (regionNode == null) {
throw new UnknownRegionException("No RegionStateNode found for " +
regionInfo.getEncodedName() + "(Closed/Deleted?)");
}
TransitRegionStateProcedure proc;
regionNode.lock();
try {
preTransitCheck(regionNode, STATES_EXPECTED_ON_UNASSIGN_OR_MOVE);
regionNode.checkOnline();
proc = TransitRegionStateProcedure.move(getProcedureEnvironment(),
regionInfo, targetServer);
regionNode.setProcedure(proc);
} finally {
regionNode.unlock();
}
return proc;
}
{code}
hbase-server/src/main/java/org/apache/hadoop/hbase/master/assignment/RegionStateNode.java
{code:java}
public void setProcedure(TransitRegionStateProcedure proc) {
assert this.procedure == null;
this.procedure = proc;
ritMap.put(regionInfo, this);
}
public void unsetProcedure(TransitRegionStateProcedure proc) {
assert this.procedure == proc;
this.procedure = null;
ritMap.remove(regionInfo, this);
}
{code}
{code:java}
2020-02-26,13:45:21,344 ERROR
[RpcServer.default.RWQ.Fifo.read.handler=437,queue=5,port=21500]
org.apache.hadoop.hbase.ipc.RpcServer: Unexpected throwable object
java.io.UncheckedIOException:
org.apache.hadoop.hbase.exceptions.TimeoutIOException: Timed out waiting for
lock for row: \x00\x00\x00\x00\x00\x0B\xAB\xD2 in region
9731aea823e7f83264b14713ae486fb7
at
org.apache.hadoop.hbase.procedure2.store.region.RegionProcedureStore.update(RegionProcedureStore.java:588)
at
org.apache.hadoop.hbase.procedure2.store.region.RegionProcedureStore.insert(RegionProcedureStore.java:545)
at
org.apache.hadoop.hbase.procedure2.ProcedureExecutor.submitProcedure(ProcedureExecutor.java:1042)
at
org.apache.hadoop.hbase.procedure2.ProcedureExecutor.submitProcedure(ProcedureExecutor.java:860)
at
org.apache.hadoop.hbase.master.procedure.ProcedureSyncWait.submitProcedure(ProcedureSyncWait.java:123)
at
org.apache.hadoop.hbase.master.assignment.AssignmentManager.moveAsync(AssignmentManager.java:657)
at
org.apache.hadoop.hbase.master.HMaster.executeRegionPlansWithThrottling(HMaster.java:1793)
at org.apache.hadoop.hbase.master.HMaster.balance(HMaster.java:1761)
at
org.apache.hadoop.hbase.master.MasterRpcServices.balance(MasterRpcServices.java:654)
at
org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java)
at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:374)
at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:135)
at
org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:352)
at
org.apache.hadoop.hbase.ipc.RpcExecutor$Handler.run(RpcExecutor.java:332)
Caused by: org.apache.hadoop.hbase.exceptions.TimeoutIOException: Timed out
waiting for lock for row: \x00\x00\x00\x00\x00\x0B\xAB\xD2 in region
9731aea823e7f83264b14713ae486fb7
at
org.apache.hadoop.hbase.regionserver.HRegion.getRowLockInternal(HRegion.java:6158)
at
org.apache.hadoop.hbase.regionserver.HRegion$BatchOperation.lockRowsAndBuildMiniBatch(HRegion.java:3488)
at
org.apache.hadoop.hbase.regionserver.HRegion.doMiniBatchMutate(HRegion.java:4235)
at
org.apache.hadoop.hbase.regionserver.HRegion.batchMutate(HRegion.java:4208)
at
org.apache.hadoop.hbase.regionserver.HRegion.batchMutate(HRegion.java:4134)
at
org.apache.hadoop.hbase.regionserver.HRegion.batchMutate(HRegion.java:4125)
at
org.apache.hadoop.hbase.regionserver.HRegion.batchMutate(HRegion.java:4139)
at
org.apache.hadoop.hbase.regionserver.HRegion.doBatchMutate(HRegion.java:4511)
at org.apache.hadoop.hbase.regionserver.HRegion.put(HRegion.java:3209)
at
org.apache.hadoop.hbase.procedure2.store.region.RegionProcedureStore.update(RegionProcedureStore.java:584)
... 13 more
{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)