/** Initialize SecondaryNameNode. */
private void initialize(Configuration conf) throws IOException {
// initiate Java VM metrics
JvmMetrics.init("SecondaryNameNode", conf.get("session.id"));
// Create connection to the namenode.
shouldRun = true;
nameNodeAddr = NameNode.getAddress(conf);
this.conf = conf;
this.namenode =
(NamenodeProtocol)
RPC.waitForProxy(
NamenodeProtocol.class, NamenodeProtocol.versionID, nameNodeAddr, conf);
// initialize checkpoint directories
fsName = getInfoServer();
checkpointDirs = FSImage.getCheckpointDirs(conf, "/tmp/hadoop/dfs/namesecondary");
checkpointEditsDirs = FSImage.getCheckpointEditsDirs(conf, "/tmp/hadoop/dfs/namesecondary");
checkpointImage = new CheckpointStorage(conf);
checkpointImage.recoverCreate(checkpointDirs, checkpointEditsDirs);
// Initialize other scheduling parameters from the configuration
checkpointPeriod = conf.getLong("fs.checkpoint.period", 3600);
checkpointSize = conf.getLong("fs.checkpoint.size", 4194304);
// initialize the webserver for uploading files.
String infoAddr =
NetUtils.getServerAddress(
conf,
"dfs.secondary.info.bindAddress",
"dfs.secondary.info.port",
"dfs.secondary.http.address");
InetSocketAddress infoSocAddr = NetUtils.createSocketAddr(infoAddr);
infoBindAddress = infoSocAddr.getHostName();
int tmpInfoPort = infoSocAddr.getPort();
infoServer = new HttpServer("secondary", infoBindAddress, tmpInfoPort, tmpInfoPort == 0, conf);
infoServer.setAttribute("name.system.image", checkpointImage);
this.infoServer.setAttribute("name.conf", conf);
infoServer.addInternalServlet("getimage", "/getimage", GetImageServlet.class);
infoServer.start();
// The web-server port can be ephemeral... ensure we have the correct info
infoPort = infoServer.getPort();
conf.set("dfs.secondary.http.address", infoBindAddress + ":" + infoPort);
LOG.info("Secondary Web-server up at: " + infoBindAddress + ":" + infoPort);
LOG.warn(
"Checkpoint Period :"
+ checkpointPeriod
+ " secs "
+ "("
+ checkpointPeriod / 60
+ " min)");
LOG.warn(
"Log Size Trigger :"
+ checkpointSize
+ " bytes "
+ "("
+ checkpointSize / 1024
+ " KB)");
}
/**
* Add an file path to the current set of classpath entries It adds the file to cache as well.
*
* @param file Path of the file to be added
* @param conf Configuration that contains the classpath setting
*/
public static void addFileToClassPath(Path file, Configuration conf) throws IOException {
String classpath = conf.get("mapred.job.classpath.files");
conf.set(
"mapred.job.classpath.files",
classpath == null
? file.toString()
: classpath + System.getProperty("path.separator") + file.toString());
URI uri = file.makeQualified(file.getFileSystem(conf)).toUri();
addCacheFile(uri, conf);
}
private static URI addArchiveToClassPathHelper(Path archive, Configuration conf)
throws IOException {
String classpath = conf.get("mapred.job.classpath.archives");
// the scheme/authority use ':' as separator. put the unqualified path in classpath
String archivePath = archive.toUri().getPath();
conf.set(
"mapred.job.classpath.archives",
classpath == null
? archivePath
: classpath + System.getProperty("path.separator") + archivePath);
return archive.makeQualified(archive.getFileSystem(conf)).toUri();
}
/**
* This method checks to see if symlinks are to be create for the localized cache files in the
* current working directory
*
* @param conf the jobconf
* @return true if symlinks are to be created- else return false
*/
public static boolean getSymlink(Configuration conf) {
String result = conf.get("mapred.create.symlink");
if ("yes".equals(result)) {
return true;
}
return false;
}
public String[] getCleanSql() {
if (cleanSql == null) {
// loop over all foreign key constraints
List dropForeignKeysSql = new ArrayList();
List createForeignKeysSql = new ArrayList();
Iterator iter = configuration.getTableMappings();
while (iter.hasNext()) {
Table table = (Table) iter.next();
if (table.isPhysicalTable()) {
Iterator subIter = table.getForeignKeyIterator();
while (subIter.hasNext()) {
ForeignKey fk = (ForeignKey) subIter.next();
if (fk.isPhysicalConstraint()) {
// collect the drop key constraint
dropForeignKeysSql.add(
fk.sqlDropString(
dialect,
properties.getProperty(Environment.DEFAULT_CATALOG),
properties.getProperty(Environment.DEFAULT_SCHEMA)));
createForeignKeysSql.add(
fk.sqlCreateString(
dialect,
mapping,
properties.getProperty(Environment.DEFAULT_CATALOG),
properties.getProperty(Environment.DEFAULT_SCHEMA)));
}
}
}
}
List deleteSql = new ArrayList();
iter = configuration.getTableMappings();
while (iter.hasNext()) {
Table table = (Table) iter.next();
deleteSql.add("delete from " + table.getName());
}
List cleanSqlList = new ArrayList();
cleanSqlList.addAll(dropForeignKeysSql);
cleanSqlList.addAll(deleteSql);
cleanSqlList.addAll(createForeignKeysSql);
cleanSql = (String[]) cleanSqlList.toArray(new String[cleanSqlList.size()]);
}
return cleanSql;
}
// return the RpcEngine configured to handle a protocol
static synchronized RpcEngine getProtocolEngine(Class<?> protocol, Configuration conf) {
RpcEngine engine = PROTOCOL_ENGINES.get(protocol);
if (engine == null) {
Class<?> impl =
conf.getClass(ENGINE_PROP + "." + protocol.getName(), WritableRpcEngine.class);
engine = (RpcEngine) ReflectionUtils.newInstance(impl, conf);
PROTOCOL_ENGINES.put(protocol, engine);
}
return engine;
}
/**
* Get the archive entries in classpath as an array of Path
*
* @param conf Configuration that contains the classpath setting
*/
public static Path[] getArchiveClassPaths(Configuration conf) {
String classpath = conf.get("mapred.job.classpath.archives");
if (classpath == null) return null;
ArrayList list =
Collections.list(new StringTokenizer(classpath, System.getProperty("path.separator")));
Path[] paths = new Path[list.size()];
for (int i = 0; i < list.size(); i++) {
paths[i] = new Path((String) list.get(i));
}
return paths;
}
public IdentitySchema(Configuration configuration) {
this.configuration = configuration;
this.properties = configuration.getProperties();
this.dialect = Dialect.getDialect(properties);
try {
// get the mapping field via reflection :-(
Field mappingField = Configuration.class.getDeclaredField("mapping");
mappingField.setAccessible(true);
this.mapping = (Mapping) mappingField.get(configuration);
} catch (Exception e) {
throw new RuntimeException("couldn't get the hibernate mapping", e);
}
}
/**
* Construct an RPC server.
*
* @param instance the instance whose methods will be called
* @param conf the configuration to use
* @param bindAddress the address to bind on to listen for connection
* @param port the port to listen for connections on
* @param numHandlers the number of method handler threads to run
* @param verbose whether each call should be logged
* @param supportOldJobConf supports server to deserialize old job conf
*/
public Server(
Object instance,
Configuration conf,
String bindAddress,
int port,
int numHandlers,
boolean verbose,
boolean supportOldJobConf)
throws IOException {
super(
bindAddress,
port,
Invocation.class,
numHandlers,
conf,
classNameBase(instance.getClass().getName()),
supportOldJobConf);
this.instance = instance;
this.verbose = verbose;
this.authorize =
conf.getBoolean(ServiceAuthorizationManager.SERVICE_AUTHORIZATION_CONFIG, false);
}
/**
* Add a archives to be localized to the conf
*
* @param uri The uri of the cache to be localized
* @param conf Configuration to add the cache to
*/
public static void addSharedCacheArchive(URI uri, Configuration conf) {
String archives = conf.get("mapred.cache.shared.archives");
conf.set(
"mapred.cache.shared.archives",
archives == null ? uri.toString() : archives + "," + uri.toString());
}
/**
* Add a file to be localized to the conf
*
* @param uri The uri of the cache to be localized
* @param conf Configuration to add the cache to
*/
public static void addCacheFile(URI uri, Configuration conf) {
String files = conf.get("mapred.cache.files");
conf.set("mapred.cache.files", files == null ? uri.toString() : files + "," + uri.toString());
}
/**
* Set the conf to contain the location for localized archives
*
* @param conf The conf to modify to contain the localized caches
* @param str a comma separated list of local archives
*/
public static void setLocalArchives(Configuration conf, String str) {
conf.set("mapred.cache.localArchives", str);
}
/**
* Set the conf to contain the location for localized files
*
* @param conf The conf to modify to contain the localized caches
* @param str a comma separated list of local files
*/
public static void setLocalSharedFiles(Configuration conf, String str) {
conf.set("mapred.cache.shared.localFiles", str);
}
/**
* Get the locally cached file or archive; it could either be previously cached (and valid) or
* copy it from the {@link FileSystem} now.
*
* @param cache the cache to be localized, this should be specified as new
* URI(hdfs://hostname:port/absolute_path_to_file#LINKNAME). If no schema or hostname:port is
* provided the file is assumed to be in the filesystem being used in the Configuration
* @param conf The Confguration file which contains the filesystem
* @param subDir The sub cache Dir where you want to localize the files/archives
* @param fileStatus The file status on the dfs.
* @param isArchive if the cache is an archive or a file. In case it is an archive with a .zip or
* .jar or .tar or .tgz or .tar.gz extension it will be unzipped/unjarred/untarred
* automatically and the directory where the archive is unzipped/unjarred/untarred is returned
* as the Path. In case of a file, the path to the file is returned
* @param confFileStamp this is the hdfs file modification timestamp to verify that the file to be
* cached hasn't changed since the job started
* @param fileLength this is the length of the cache file
* @param currentWorkDir this is the directory where you would want to create symlinks for the
* locally cached files/archives
* @param honorSymLinkConf if this is false, then the symlinks are not created even if conf says
* so (this is required for an optimization in task launches
* @param lDirAllocator LocalDirAllocator of the tracker
* @return the path to directory where the archives are unjarred in case of archives, the path to
* the file where the file is copied locally
* @throws IOException
*/
private static Path getLocalCache(
URI cache,
Configuration conf,
Path subDir,
FileStatus fileStatus,
boolean isArchive,
long confFileStamp,
long fileLength,
Path currentWorkDir,
boolean honorSymLinkConf,
MRAsyncDiskService asyncDiskService,
LocalDirAllocator lDirAllocator)
throws IOException {
String key = getKey(cache, conf, confFileStamp);
CacheStatus lcacheStatus;
Path localizedPath;
synchronized (cachedArchives) {
lcacheStatus = cachedArchives.get(key);
if (lcacheStatus == null) {
// was never localized
Path uniqueParentDir = new Path(subDir, String.valueOf(random.nextLong()));
String cachePath = new Path(uniqueParentDir, makeRelative(cache, conf)).toString();
Path localPath = lDirAllocator.getLocalPathForWrite(cachePath, fileLength, conf);
lcacheStatus =
new CacheStatus(
new Path(localPath.toString().replace(cachePath, "")), localPath, uniqueParentDir);
cachedArchives.put(key, lcacheStatus);
}
lcacheStatus.refcount++;
}
boolean initSuccessful = false;
try {
synchronized (lcacheStatus) {
if (!lcacheStatus.isInited()) {
localizedPath = localizeCache(conf, cache, confFileStamp, lcacheStatus, isArchive);
lcacheStatus.initComplete();
} else {
if (fileStatus != null) {
localizedPath =
checkCacheStatusValidity(
conf, cache, confFileStamp, lcacheStatus, fileStatus, isArchive);
} else {
// if fileStatus is null, then the md5 must be correct
// so there is no need to check for cache validity
localizedPath = lcacheStatus.localizedLoadPath;
}
}
createSymlink(conf, cache, lcacheStatus, isArchive, currentWorkDir, honorSymLinkConf);
}
// try deleting stuff if you can
long size = 0;
int numberSubDir = 0;
synchronized (lcacheStatus) {
synchronized (baseDirSize) {
Long get = baseDirSize.get(lcacheStatus.getBaseDir());
if (get != null) {
size = get.longValue();
} else {
LOG.warn("Cannot find size of baseDir: " + lcacheStatus.getBaseDir());
}
}
synchronized (baseDirNumberSubDir) {
Integer get = baseDirNumberSubDir.get(lcacheStatus.getBaseDir());
if (get != null) {
numberSubDir = get.intValue();
} else {
LOG.warn("Cannot find subdirectories limit of baseDir: " + lcacheStatus.getBaseDir());
}
}
}
// setting the cache size to a default of 10GB
long allowedSize = conf.getLong("local.cache.size", DEFAULT_CACHE_SIZE);
long allowedNumberSubDir =
conf.getLong("local.cache.numbersubdir", DEFAULT_CACHE_SUBDIR_LIMIT);
if (allowedSize < size || allowedNumberSubDir < numberSubDir) {
// try some cache deletions
LOG.debug(
"Start deleting released cache because"
+ " [size, allowedSize, numberSubDir, allowedNumberSubDir] ="
+ " ["
+ size
+ ", "
+ allowedSize
+ ", "
+ numberSubDir
+ ", "
+ allowedNumberSubDir
+ "]");
deleteCache(conf, asyncDiskService);
}
initSuccessful = true;
return localizedPath;
} finally {
if (!initSuccessful) {
synchronized (cachedArchives) {
lcacheStatus.refcount--;
}
}
}
}
public static void setSharedFileLength(Configuration conf, String length) {
conf.set("mapred.cache.shared.files.length", length);
}
public String[] getDropSql() {
if (dropSql == null) {
dropSql = configuration.generateDropSchemaScript(dialect);
}
return dropSql;
}
/**
* Set a protocol to use a non-default RpcEngine.
*
* @param conf configuration to use
* @param protocol the protocol interface
* @param engine the RpcEngine impl
*/
public static void setProtocolEngine(Configuration conf, Class<?> protocol, Class<?> engine) {
conf.setClass(ENGINE_PROP + "." + protocol.getName(), engine, RpcEngine.class);
}
/**
* Get the timestamps of the archives
*
* @param conf The configuration which stored the timestamps
* @return a string array of timestamps
* @throws IOException
*/
public static String[] getArchiveTimestamps(Configuration conf) {
return conf.getStrings("mapred.cache.archives.timestamps");
}
/**
* Set the configuration with the given set of archives
*
* @param archives The list of archives that need to be localized
* @param conf Configuration which will be changed
*/
public static void setCacheArchives(URI[] archives, Configuration conf) {
String sarchives = StringUtils.uriToString(archives);
conf.set("mapred.cache.archives", sarchives);
}
/**
* Return the path array of the localized files
*
* @param conf Configuration that contains the localized files
* @return A path array of localized files
* @throws IOException
*/
public static Path[] getLocalSharedCacheFiles(Configuration conf) throws IOException {
return StringUtils.stringToPath(conf.getStrings("mapred.cache.shared.localFiles"));
}
/**
* Return the path array of the localized caches
*
* @param conf Configuration that contains the localized archives
* @return A path array of localized caches
* @throws IOException
*/
public static Path[] getLocalCacheArchives(Configuration conf) throws IOException {
return StringUtils.stringToPath(conf.getStrings("mapred.cache.localArchives"));
}
/**
* Get cache files set in the Configuration
*
* @param conf The configuration which contains the files
* @return A URI array of the files set in the Configuration
* @throws IOException
*/
public static URI[] getSharedCacheFiles(Configuration conf) throws IOException {
return StringUtils.stringToURI(conf.getStrings("mapred.cache.shared.files"));
}
/**
* Get cache archives set in the Configuration
*
* @param conf The configuration which contains the archives
* @return A URI array of the caches set in the Configuration
* @throws IOException
*/
public static URI[] getCacheArchives(Configuration conf) throws IOException {
return StringUtils.stringToURI(conf.getStrings("mapred.cache.archives"));
}
/**
* Set the configuration with the given set of files
*
* @param files The list of files that need to be localized
* @param conf Configuration which will be changed
*/
public static void setCacheFiles(URI[] files, Configuration conf) {
String sfiles = StringUtils.uriToString(files);
conf.set("mapred.cache.files", sfiles);
}
public String[] getCreateSql() {
if (createSql == null) {
createSql = configuration.generateSchemaCreationScript(dialect);
}
return createSql;
}
public static String[] getSharedFileLength(Configuration conf) {
return conf.getStrings("mapred.cache.shared.files.length");
}
/**
* This is to check the timestamp of the archives to be localized
*
* @param conf Configuration which stores the timestamp's
* @param timestamps comma separated list of timestamps of archives. The order should be the same
* as the order in which the archives are added.
*/
public static void setArchiveTimestamps(Configuration conf, String timestamps) {
conf.set("mapred.cache.archives.timestamps", timestamps);
}
/**
* This is to check the timestamp of the files to be localized
*
* @param conf Configuration which stores the timestamp's
* @param timestamps comma separated list of timestamps of files. The order should be the same as
* the order in which the files are added.
*/
public static void setFileTimestamps(Configuration conf, String timestamps) {
conf.set("mapred.cache.files.timestamps", timestamps);
}
/**
* Get the timestamps of the files
*
* @param conf The configuration which stored the timestamps
* @return a string array of timestamps
* @throws IOException
*/
public static String[] getFileTimestamps(Configuration conf) {
return conf.getStrings("mapred.cache.files.timestamps");
}
/**
* This method allows you to create symlinks in the current working directory of the task to all
* the cache files/archives
*
* @param conf the jobconf
*/
public static void createSymlink(Configuration conf) {
conf.set("mapred.create.symlink", "yes");
}
