/// <summary>Create a new checkpoint</summary>
/// <exception cref="System.IO.IOException"/>
internal virtual void DoCheckpoint()
{
BackupImage bnImage = GetFSImage();
NNStorage bnStorage = bnImage.GetStorage();
long startTime = Time.MonotonicNow();
bnImage.FreezeNamespaceAtNextRoll();
NamenodeCommand cmd = GetRemoteNamenodeProxy().StartCheckpoint(backupNode.GetRegistration
());
CheckpointCommand cpCmd = null;
switch (cmd.GetAction())
{
case NamenodeProtocol.ActShutdown:
{
Shutdown();
throw new IOException("Name-node " + backupNode.nnRpcAddress + " requested shutdown."
);
}
case NamenodeProtocol.ActCheckpoint:
{
cpCmd = (CheckpointCommand)cmd;
break;
}
default:
{
throw new IOException("Unsupported NamenodeCommand: " + cmd.GetAction());
}
}
bnImage.WaitUntilNamespaceFrozen();
CheckpointSignature sig = cpCmd.GetSignature();
// Make sure we're talking to the same NN!
sig.ValidateStorageInfo(bnImage);
long lastApplied = bnImage.GetLastAppliedTxId();
Log.Debug("Doing checkpoint. Last applied: " + lastApplied);
RemoteEditLogManifest manifest = GetRemoteNamenodeProxy().GetEditLogManifest(bnImage
.GetLastAppliedTxId() + 1);
bool needReloadImage = false;
if (!manifest.GetLogs().IsEmpty())
{
RemoteEditLog firstRemoteLog = manifest.GetLogs()[0];
// we don't have enough logs to roll forward using only logs. Need
// to download and load the image.
if (firstRemoteLog.GetStartTxId() > lastApplied + 1)
{
Log.Info("Unable to roll forward using only logs. Downloading " + "image with txid "
+ sig.mostRecentCheckpointTxId);
MD5Hash downloadedHash = TransferFsImage.DownloadImageToStorage(backupNode.nnHttpAddress
, sig.mostRecentCheckpointTxId, bnStorage, true);
bnImage.SaveDigestAndRenameCheckpointImage(NNStorage.NameNodeFile.Image, sig.mostRecentCheckpointTxId
, downloadedHash);
lastApplied = sig.mostRecentCheckpointTxId;
needReloadImage = true;
}
if (firstRemoteLog.GetStartTxId() > lastApplied + 1)
{
throw new IOException("No logs to roll forward from " + lastApplied);
}
// get edits files
foreach (RemoteEditLog log in manifest.GetLogs())
{
TransferFsImage.DownloadEditsToStorage(backupNode.nnHttpAddress, log, bnStorage);
}
if (needReloadImage)
{
Log.Info("Loading image with txid " + sig.mostRecentCheckpointTxId);
FilePath file = bnStorage.FindImageFile(NNStorage.NameNodeFile.Image, sig.mostRecentCheckpointTxId
);
bnImage.ReloadFromImageFile(file, backupNode.GetNamesystem());
}
RollForwardByApplyingLogs(manifest, bnImage, backupNode.GetNamesystem());
}
long txid = bnImage.GetLastAppliedTxId();
backupNode.namesystem.WriteLock();
try
{
backupNode.namesystem.SetImageLoaded();
if (backupNode.namesystem.GetBlocksTotal() > 0)
{
backupNode.namesystem.SetBlockTotal();
}
bnImage.SaveFSImageInAllDirs(backupNode.GetNamesystem(), txid);
bnStorage.WriteAll();
}
finally
{
backupNode.namesystem.WriteUnlock();
}
if (cpCmd.NeedToReturnImage())
{
TransferFsImage.UploadImageFromStorage(backupNode.nnHttpAddress, conf, bnStorage,
NNStorage.NameNodeFile.Image, txid);
}
GetRemoteNamenodeProxy().EndCheckpoint(backupNode.GetRegistration(), sig);
if (backupNode.GetRole() == HdfsServerConstants.NamenodeRole.Backup)
{
bnImage.ConvergeJournalSpool();
}
backupNode.SetRegistration();
// keep registration up to date
long imageSize = bnImage.GetStorage().GetFsImageName(txid).Length();
Log.Info("Checkpoint completed in " + (Time.MonotonicNow() - startTime) / 1000 +
" seconds." + " New Image Size: " + imageSize);
}
public virtual bool DoCheckpoint()
{
checkpointImage.EnsureCurrentDirExists();
NNStorage dstStorage = checkpointImage.GetStorage();
// Tell the namenode to start logging transactions in a new edit file
// Returns a token that would be used to upload the merged image.
CheckpointSignature sig = namenode.RollEditLog();
bool loadImage = false;
bool isFreshCheckpointer = (checkpointImage.GetNamespaceID() == 0);
bool isSameCluster = (dstStorage.VersionSupportsFederation(NameNodeLayoutVersion.
Features) && sig.IsSameCluster(checkpointImage)) || (!dstStorage.VersionSupportsFederation
(NameNodeLayoutVersion.Features) && sig.NamespaceIdMatches(checkpointImage));
if (isFreshCheckpointer || (isSameCluster && !sig.StorageVersionMatches(checkpointImage
.GetStorage())))
{
// if we're a fresh 2NN, or if we're on the same cluster and our storage
// needs an upgrade, just take the storage info from the server.
dstStorage.SetStorageInfo(sig);
dstStorage.SetClusterID(sig.GetClusterID());
dstStorage.SetBlockPoolID(sig.GetBlockpoolID());
loadImage = true;
}
sig.ValidateStorageInfo(checkpointImage);
// error simulation code for junit test
CheckpointFaultInjector.GetInstance().AfterSecondaryCallsRollEditLog();
RemoteEditLogManifest manifest = namenode.GetEditLogManifest(sig.mostRecentCheckpointTxId
+ 1);
// Fetch fsimage and edits. Reload the image if previous merge failed.
loadImage |= DownloadCheckpointFiles(fsName, checkpointImage, sig, manifest) | checkpointImage
.HasMergeError();
try
{
DoMerge(sig, manifest, loadImage, checkpointImage, namesystem);
}
catch (IOException ioe)
{
// A merge error occurred. The in-memory file system state may be
// inconsistent, so the image and edits need to be reloaded.
checkpointImage.SetMergeError();
throw;
}
// Clear any error since merge was successful.
checkpointImage.ClearMergeError();
//
// Upload the new image into the NameNode. Then tell the Namenode
// to make this new uploaded image as the most current image.
//
long txid = checkpointImage.GetLastAppliedTxId();
TransferFsImage.UploadImageFromStorage(fsName, conf, dstStorage, NNStorage.NameNodeFile
.Image, txid);
// error simulation code for junit test
CheckpointFaultInjector.GetInstance().AfterSecondaryUploadsNewImage();
Log.Warn("Checkpoint done. New Image Size: " + dstStorage.GetFsImageName(txid).Length
());
if (legacyOivImageDir != null && !legacyOivImageDir.IsEmpty())
{
try
{
checkpointImage.SaveLegacyOIVImage(namesystem, legacyOivImageDir, new Canceler());
}
catch (IOException e)
{
Log.Warn("Failed to write legacy OIV image: ", e);
}
}
return(loadImage);
}