问题导读
1.如何某一个row对应的region是在哪台Region server上?
2. -ROOT-、.META.表作用是什么?
HBase的table是该region切分的,client操作一个row的时候,如何知道这个row对应的region是在哪台Region server上呢?这里有个region location过程。主要涉及到2张系统表,-ROOT-,.META.。其结构见图
在zookeeper的/hbase/root-region-server节点中存着-ROOT-表所在的Region Server地址。
-ROOT-表的一个row代表着META的一个region信息,其key的结构是META表名,META表Region的startkey,RegionId。其value的主要保存regioninfo和server信息。ROOT表不能split
.META.表的一个row代表着用户表的一个region信息,其key的结构是其实就是用户表的regionName,用户表名,startKey,RegionId。其value同样保存着regioninfo和server信息。META表可以split,但是一个region默认有128M,可以存上亿个用户表的region信息,所以一般不会split。
其查找过程如下:
1.通过zk getData拿-ROOT-表的location
2.RPC -ROOT-表的rs,getClosestRowBefore,拿row对应的meta表的region location
3.RPC .META.表的某一个region,拿该row在真实table所在的region location
4.RPC对应region
region location需要3次网络IO,为了提升性能,client会cache数据。
LocationCache是一个2级Map,第一级的key是tableName的hash值,第二级的key是starRow,用SoftValueSortedMap包装了TreeMap实现,用软引用实现cache,内存不够时才会回收。Cache里存在META表和用户表的region location信息。
其代码实现如下,0.94版本:
HConnectionManager locateRegion入口
- private HRegionLocation locateRegion(final byte [] tableName,
- final byte [] row, boolean useCache)
- throws IOException {
- .......
- //检查下都应的zkTracker是否启动
- ensureZookeeperTrackers();
- //如果是-ROOT-表,则通过zk节点/hbase/root-region-server获取-ROOT-表所在的Location
- if (Bytes.equals(tableName, HConstants.ROOT_TABLE_NAME)) {
- try {
- //通过zk的getData接口拿节点数据,此处会等待节点数据就位或者超时
- ServerName servername = this.rootRegionTracker.waitRootRegionLocation(this.rpcTimeout);
- LOG.debug("Looked up root region location, connection=" + this +
- "; serverName=" + ((servername == null)? "": servername.toString()));
- if (servername == null) return null;
- //返回一个拼装的HRegionLocation,因为-ROOT-表只有一个region,而且不会split
- return new HRegionLocation(HRegionInfo.ROOT_REGIONINFO,
- servername.getHostname(), servername.getPort());
- } catch (InterruptedException e) {
- Thread.currentThread().interrupt();
- return null;
- }
- }
- //如果是.META.表,则请求.META.表,这里的row其实就是请求row拼装的regionName,类似test,key1,99999999999999
- //如果没命中cache,则继续请求-ROOT-表,拿到这个row对应的.META.表的region location
- else if (Bytes.equals(tableName, HConstants.META_TABLE_NAME)) {
- return locateRegionInMeta(HConstants.ROOT_TABLE_NAME, tableName, row,
- useCache, metaRegionLock);
- }
- //如果是用户表,则请求用户表,这里的row就是key1
- //如果没命中cache,则请求.META.表,获取该row对应的region location
- else {
- // Region not in the cache - have to go to the meta RS
- return locateRegionInMeta(HConstants.META_TABLE_NAME, tableName, row,
- useCache, userRegionLock);
- }
- }
复制代码
locateRegionInMeta方法
- private HRegionLocation locateRegionInMeta(final byte [] parentTable,
- final byte [] tableName, final byte [] row, boolean useCache,
- Object regionLockObject)
- throws IOException {
- HRegionLocation location;
- // If we are supposed to be using the cache, look in the cache to see if
- // we already have the region.
- //先读cache,cache没有再往上找
- //注意如果rowkey的region locatin变化了,RPC的时候会失败,客户端做重试的时候useCache是false
- if (useCache) {
- location = getCachedLocation(tableName, row);
- if (location != null) {
- return location;
- }
- }
-
- // build the key of the meta region we should be looking for.
- // the extra 9's on the end are necessary to allow "exact" matches
- // without knowing the precise region names.
- //先拼一个想查找的key,类似于test,key1,99999999999999
- byte [] metaKey = HRegionInfo.createRegionName(tableName, row,
- HConstants.NINES, false);
- //默认重试10次
- for (int tries = 0; true; tries++) {
- //找不到
- if (tries >= numRetries) {
- throw new NoServerForRegionException("Unable to find region for "
- + Bytes.toStringBinary(row) + " after " + numRetries + " tries.");
- }
-
- HRegionLocation metaLocation = null;
- try {
- // locate the root or meta region
- //递归查找parentTable
- metaLocation = locateRegion(parentTable, metaKey);
- // If null still, go around again.
- if (metaLocation == null) continue;
- //找到对应Region server地址之后,可以发起RPC请求了。
- //这里先生成一个RPC Proxy对象,具体RPC分析见后文
- HRegionInterface server =
- getHRegionConnection(metaLocation.getHostname(), metaLocation.getPort());
-
- Result regionInfoRow = null;
- // This block guards against two threads trying to load the meta
- // region at the same time. The first will load the meta region and
- // the second will use the value that the first one found.
- synchronized (regionLockObject) {
- // If the parent table is META, we may want to pre-fetch some
- // region info into the global region cache for this table.
- //如果parentTable是.META.表,则预先获取.META.的一些数据,默认10条
- if (Bytes.equals(parentTable, HConstants.META_TABLE_NAME) &&
- (getRegionCachePrefetch(tableName)) ) {
- prefetchRegionCache(tableName, row);
- }
-
- // Check the cache again for a hit in case some other thread made the
- // same query while we were waiting on the lock. If not supposed to
- // be using the cache, delete any existing cached location so it won't
- // interfere.
- if (useCache) {
- location = getCachedLocation(tableName, row);
- if (location != null) {
- return location;
- }
- }
- //如果不使用cache,则清除之,比如row对应的region发生了分裂,用老的location启动rpc时会抛异常,此时通过useCache=fasle重新
- //寻址,并把老的cache删掉
- else {
- deleteCachedLocation(tableName, row);
- }
-
- // Query the root or meta region for the location of the meta region
- //发起RPC请求,获取<=该key的行
- regionInfoRow = server.getClosestRowBefore(
- metaLocation.getRegionInfo().getRegionName(), metaKey,
- HConstants.CATALOG_FAMILY);
- }
- if (regionInfoRow == null) {
- throw new TableNotFoundException(Bytes.toString(tableName));
- }
- //region信息,做校验,region会处于不稳定状态
- byte [] value = regionInfoRow.getValue(HConstants.CATALOG_FAMILY,
- HConstants.REGIONINFO_QUALIFIER);
- if (value == null || value.length == 0) {
- throw new IOException("HRegionInfo was null or empty in " +
- Bytes.toString(parentTable) + ", row=" + regionInfoRow);
- }
- // convert the row result into the HRegionLocation we need!
- //反序列化
- HRegionInfo regionInfo = (HRegionInfo) Writables.getWritable(
- value, new HRegionInfo());
- // possible we got a region of a different table...
- //一些校验
- if (!Bytes.equals(regionInfo.getTableName(), tableName)) {
- throw new TableNotFoundException(
- "Table '" + Bytes.toString(tableName) + "' was not found, got: " +
- Bytes.toString(regionInfo.getTableName()) + ".");
- }
- if (regionInfo.isSplit()) {
- throw new RegionOfflineException("the only available region for" +
- " the required row is a split parent," +
- " the daughters should be online soon: " +
- regionInfo.getRegionNameAsString());
- }
- if (regionInfo.isOffline()) {
- throw new RegionOfflineException("the region is offline, could" +
- " be caused by a disable table call: " +
- regionInfo.getRegionNameAsString());
- }
- //该region的server location
- value = regionInfoRow.getValue(HConstants.CATALOG_FAMILY,
- HConstants.SERVER_QUALIFIER);
- String hostAndPort = "";
- if (value != null) {
- hostAndPort = Bytes.toString(value);
- }
- ......
-
- // Instantiate the location
- String hostname = Addressing.parseHostname(hostAndPort);
- int port = Addressing.parsePort(hostAndPort);
- location = new HRegionLocation(regionInfo, hostname, port);
- //cache之
- cacheLocation(tableName, location);
- return location;
- } catch (TableNotFoundException e) {
- // if we got this error, probably means the table just plain doesn't
- // exist. rethrow the error immediately. this should always be coming
- // from the HTable constructor.
- throw e;
- } catch (IOException e) {
- if (e instanceof RemoteException) {
- e = RemoteExceptionHandler.decodeRemoteException((RemoteException) e);
- }
- if (tries < numRetries - 1) {
- .......
- } else {
- throw e;
- }
- // Only relocate the parent region if necessary
- //网络有问题,则重新找
- if(!(e instanceof RegionOfflineException ||
- e instanceof NoServerForRegionException)) {
- relocateRegion(parentTable, metaKey);
- }
- }
- //重试次数越多,sleep越长,interrupt则退出重试
- try{
- Thread.sleep(ConnectionUtils.getPauseTime(this.pause, tries));
- } catch (InterruptedException e) {
- Thread.currentThread().interrupt();
- throw new IOException("Giving up trying to location region in " +
- "meta: thread is interrupted.");
- }
- }
- }
复制代码
|