/// <exception cref="System.IO.IOException"/>
internal static void DoMerge(CheckpointSignature sig, RemoteEditLogManifest manifest
, bool loadImage, FSImage dstImage, FSNamesystem dstNamesystem)
{
NNStorage dstStorage = dstImage.GetStorage();
dstStorage.SetStorageInfo(sig);
if (loadImage)
{
FilePath file = dstStorage.FindImageFile(NNStorage.NameNodeFile.Image, sig.mostRecentCheckpointTxId
);
if (file == null)
{
throw new IOException("Couldn't find image file at txid " + sig.mostRecentCheckpointTxId
+ " even though it should have " + "just been downloaded");
}
dstNamesystem.WriteLock();
try
{
dstImage.ReloadFromImageFile(file, dstNamesystem);
}
finally
{
dstNamesystem.WriteUnlock();
}
dstNamesystem.ImageLoadComplete();
}
// error simulation code for junit test
CheckpointFaultInjector.GetInstance().DuringMerge();
Checkpointer.RollForwardByApplyingLogs(manifest, dstImage, dstNamesystem);
// The following has the side effect of purging old fsimages/edit logs.
dstImage.SaveFSImageInAllDirs(dstNamesystem, dstImage.GetLastAppliedTxId());
dstStorage.WriteAll();
}
/// <exception cref="System.IO.IOException"/>
internal static void DownloadEditsToStorage(Uri fsName, RemoteEditLog log, NNStorage
dstStorage)
{
System.Diagnostics.Debug.Assert(log.GetStartTxId() > 0 && log.GetEndTxId() > 0, "bad log: "
+ log);
string fileid = ImageServlet.GetParamStringForLog(log, dstStorage);
string finalFileName = NNStorage.GetFinalizedEditsFileName(log.GetStartTxId(), log
.GetEndTxId());
IList <FilePath> finalFiles = dstStorage.GetFiles(NNStorage.NameNodeDirType.Edits,
finalFileName);
System.Diagnostics.Debug.Assert(!finalFiles.IsEmpty(), "No checkpoint targets.");
foreach (FilePath f in finalFiles)
{
if (f.Exists() && FileUtil.CanRead(f))
{
Log.Info("Skipping download of remote edit log " + log + " since it already is stored locally at "
+ f);
return;
}
else
{
if (Log.IsDebugEnabled())
{
Log.Debug("Dest file: " + f);
}
}
}
long milliTime = Time.MonotonicNow();
string tmpFileName = NNStorage.GetTemporaryEditsFileName(log.GetStartTxId(), log.
GetEndTxId(), milliTime);
IList <FilePath> tmpFiles = dstStorage.GetFiles(NNStorage.NameNodeDirType.Edits, tmpFileName
);
GetFileClient(fsName, fileid, tmpFiles, dstStorage, false);
Log.Info("Downloaded file " + tmpFiles[0].GetName() + " size " + finalFiles[0].Length
() + " bytes.");
CheckpointFaultInjector.GetInstance().BeforeEditsRename();
foreach (Storage.StorageDirectory sd in dstStorage.DirIterable(NNStorage.NameNodeDirType
.Edits))
{
FilePath tmpFile = NNStorage.GetTemporaryEditsFile(sd, log.GetStartTxId(), log.GetEndTxId
(), milliTime);
FilePath finalizedFile = NNStorage.GetFinalizedEditsFile(sd, log.GetStartTxId(),
log.GetEndTxId());
if (Log.IsDebugEnabled())
{
Log.Debug("Renaming " + tmpFile + " to " + finalizedFile);
}
bool success = tmpFile.RenameTo(finalizedFile);
if (!success)
{
Log.Warn("Unable to rename edits file from " + tmpFile + " to " + finalizedFile);
}
}
}
/// <exception cref="System.IO.IOException"/>
private static void CopyFileToStream(OutputStream @out, FilePath localfile, FileInputStream
infile, DataTransferThrottler throttler, Canceler canceler)
{
byte[] buf = new byte[HdfsConstants.IoFileBufferSize];
try
{
CheckpointFaultInjector.GetInstance().AboutToSendFile(localfile);
if (CheckpointFaultInjector.GetInstance().ShouldSendShortFile(localfile))
{
// Test sending image shorter than localfile
long len = localfile.Length();
buf = new byte[(int)Math.Min(len / 2, HdfsConstants.IoFileBufferSize)];
// This will read at most half of the image
// and the rest of the image will be sent over the wire
infile.Read(buf);
}
int num = 1;
while (num > 0)
{
if (canceler != null && canceler.IsCancelled())
{
throw new SaveNamespaceCancelledException(canceler.GetCancellationReason());
}
num = infile.Read(buf);
if (num <= 0)
{
break;
}
if (CheckpointFaultInjector.GetInstance().ShouldCorruptAByte(localfile))
{
// Simulate a corrupted byte on the wire
Log.Warn("SIMULATING A CORRUPT BYTE IN IMAGE TRANSFER!");
buf[0]++;
}
@out.Write(buf, 0, num);
if (throttler != null)
{
throttler.Throttle(num, canceler);
}
}
}
catch (EofException)
{
Log.Info("Connection closed by client");
@out = null;
}
finally
{
// so we don't close in the finally
if (@out != null)
{
@out.Close();
}
}
}
/// <exception cref="System.Exception"/>
public Void Run()
{
if (parsedParams.IsGetImage())
{
long txid = parsedParams.GetTxId();
FilePath imageFile = null;
string errorMessage = "Could not find image";
if (parsedParams.ShouldFetchLatest())
{
imageFile = nnImage.GetStorage().GetHighestFsImageName();
}
else
{
errorMessage += " with txid " + txid;
imageFile = nnImage.GetStorage().GetFsImage(txid, EnumSet.Of(NNStorage.NameNodeFile
.Image, NNStorage.NameNodeFile.ImageRollback));
}
if (imageFile == null)
{
throw new IOException(errorMessage);
}
CheckpointFaultInjector.GetInstance().BeforeGetImageSetsHeaders();
long start = Time.MonotonicNow();
this.ServeFile(imageFile);
if (metrics != null)
{
long elapsed = Time.MonotonicNow() - start;
metrics.AddGetImage(elapsed);
}
}
else
{
if (parsedParams.IsGetEdit())
{
long startTxId = parsedParams.GetStartTxId();
long endTxId = parsedParams.GetEndTxId();
FilePath editFile = nnImage.GetStorage().FindFinalizedEditsFile(startTxId, endTxId
);
long start = Time.MonotonicNow();
this.ServeFile(editFile);
if (metrics != null)
{
long elapsed = Time.MonotonicNow() - start;
metrics.AddGetEdit(elapsed);
}
}
}
return(null);
}
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);
}
