/// <summary>
/// Verify a DN remains in DECOMMISSION_INPROGRESS state if it is marked
/// as dead before decommission has completed.
/// </summary>
/// <remarks>
/// Verify a DN remains in DECOMMISSION_INPROGRESS state if it is marked
/// as dead before decommission has completed. That will allow DN to resume
/// the replication process after it rejoins the cluster.
/// </remarks>
/// <exception cref="System.Exception"/>
public virtual void TestDecommissionStatusAfterDNRestart()
{
DistributedFileSystem fileSys = (DistributedFileSystem)cluster.GetFileSystem();
// Create a file with one block. That block has one replica.
Path f = new Path("decommission.dat");
DFSTestUtil.CreateFile(fileSys, f, fileSize, fileSize, fileSize, (short)1, seed);
// Find the DN that owns the only replica.
RemoteIterator <LocatedFileStatus> fileList = fileSys.ListLocatedStatus(f);
BlockLocation[] blockLocations = fileList.Next().GetBlockLocations();
string dnName = blockLocations[0].GetNames()[0];
// Decommission the DN.
FSNamesystem fsn = cluster.GetNamesystem();
DatanodeManager dm = fsn.GetBlockManager().GetDatanodeManager();
DecommissionNode(fsn, localFileSys, dnName);
dm.RefreshNodes(conf);
// Stop the DN when decommission is in progress.
// Given DFS_DATANODE_BALANCE_BANDWIDTHPERSEC_KEY is to 1 and the size of
// the block, it will take much longer time that test timeout value for
// the decommission to complete. So when stopDataNode is called,
// decommission should be in progress.
MiniDFSCluster.DataNodeProperties dataNodeProperties = cluster.StopDataNode(dnName
);
IList <DatanodeDescriptor> dead = new AList <DatanodeDescriptor>();
while (true)
{
dm.FetchDatanodes(null, dead, false);
if (dead.Count == 1)
{
break;
}
Sharpen.Thread.Sleep(1000);
}
// Force removal of the dead node's blocks.
BlockManagerTestUtil.CheckHeartbeat(fsn.GetBlockManager());
// Force DatanodeManager to check decommission state.
BlockManagerTestUtil.RecheckDecommissionState(dm);
// Verify that the DN remains in DECOMMISSION_INPROGRESS state.
NUnit.Framework.Assert.IsTrue("the node should be DECOMMISSION_IN_PROGRESSS", dead
[0].IsDecommissionInProgress());
// Check DatanodeManager#getDecommissionNodes, make sure it returns
// the node as decommissioning, even if it's dead
IList <DatanodeDescriptor> decomlist = dm.GetDecommissioningNodes();
NUnit.Framework.Assert.IsTrue("The node should be be decommissioning", decomlist.
Count == 1);
// Delete the under-replicated file, which should let the
// DECOMMISSION_IN_PROGRESS node become DECOMMISSIONED
CleanupFile(fileSys, f);
BlockManagerTestUtil.RecheckDecommissionState(dm);
NUnit.Framework.Assert.IsTrue("the node should be decommissioned", dead[0].IsDecommissioned
());
// Add the node back
cluster.RestartDataNode(dataNodeProperties, true);
cluster.WaitActive();
// Call refreshNodes on FSNamesystem with empty exclude file.
// This will remove the datanodes from decommissioning list and
// make them available again.
WriteConfigFile(localFileSys, excludeFile, null);
dm.RefreshNodes(conf);
}