diff --git a/src/main/java/org/apache/hadoop/hbase/HConstants.java b/src/main/java/org/apache/hadoop/hbase/HConstants.java index 485006b..e85d4ee 100644 --- a/src/main/java/org/apache/hadoop/hbase/HConstants.java +++ b/src/main/java/org/apache/hadoop/hbase/HConstants.java @@ -66,6 +66,11 @@ public final class HConstants { // Configuration parameters + /** + * Default block size for an HFile. + */ + public final static int DEFAULT_BLOCKSIZE = 64 * 1024; + //TODO: Is having HBase homed on port 60k OK? /** Cluster is in distributed mode or not */ diff --git a/src/main/java/org/apache/hadoop/hbase/master/HMaster.java b/src/main/java/org/apache/hadoop/hbase/master/HMaster.java index 52dedc2..9cbdab7 100644 --- a/src/main/java/org/apache/hadoop/hbase/master/HMaster.java +++ b/src/main/java/org/apache/hadoop/hbase/master/HMaster.java @@ -107,6 +107,7 @@ import org.apache.hadoop.hbase.snapshot.SnapshotDescriptionUtils; import org.apache.hadoop.hbase.security.User; import org.apache.hadoop.hbase.util.Bytes; import org.apache.hadoop.hbase.util.FSTableDescriptors; +import org.apache.hadoop.hbase.util.FSUtils; import org.apache.hadoop.hbase.util.HFileArchiveUtil; import org.apache.hadoop.hbase.util.HasThread; import org.apache.hadoop.hbase.util.InfoServer; @@ -268,6 +269,7 @@ Server { this.conf = new Configuration(conf); // Disable the block cache on the master this.conf.setFloat(HConstants.HFILE_BLOCK_CACHE_SIZE_KEY, 0.0f); + FSUtils.setupShortCircuitRead(conf); // Set how many times to retry talking to another server over HConnection. HConnectionManager.setServerSideHConnectionRetries(this.conf, LOG); // Server to handle client requests. diff --git a/src/main/java/org/apache/hadoop/hbase/regionserver/HRegionServer.java b/src/main/java/org/apache/hadoop/hbase/regionserver/HRegionServer.java index 003b351..10a550f 100644 --- a/src/main/java/org/apache/hadoop/hbase/regionserver/HRegionServer.java +++ b/src/main/java/org/apache/hadoop/hbase/regionserver/HRegionServer.java @@ -208,7 +208,6 @@ public class HRegionServer implements HRegionInterface, HBaseRPCErrorHandler, protected final AtomicBoolean haveRootRegion = new AtomicBoolean(false); private HFileSystem fs; - private boolean useHBaseChecksum; // verify hbase checksums? private Path rootDir; private final Random rand = new Random(); @@ -395,10 +394,7 @@ public class HRegionServer implements HRegionInterface, HBaseRPCErrorHandler, this.isOnline = false; checkCodecs(this.conf); - // do we use checksum verfication in the hbase? If hbase checksum verification - // is enabled, then we automatically switch off hdfs checksum verification. - this.useHBaseChecksum = conf.getBoolean( - HConstants.HBASE_CHECKSUM_VERIFICATION, false); + FSUtils.setupShortCircuitRead(this.conf); // Config'ed params this.numRetries = conf.getInt("hbase.client.retries.number", 10); @@ -1061,8 +1057,10 @@ public class HRegionServer implements HRegionInterface, HBaseRPCErrorHandler, // accessors will be going against wrong filesystem (unless all is set // to defaults). this.conf.set("fs.defaultFS", this.conf.get("hbase.rootdir")); - // Get fs instance used by this RS - this.fs = new HFileSystem(this.conf, this.useHBaseChecksum); + // Get fs instance used by this RS. Do we use checksum verification in the hbase? If hbase + // checksum verification enabled, then automatically switch off hdfs checksum verification. + boolean useHBaseChecksum = conf.getBoolean(HConstants.HBASE_CHECKSUM_VERIFICATION, true); + this.fs = new HFileSystem(this.conf, useHBaseChecksum); this.rootDir = new Path(this.conf.get(HConstants.HBASE_DIR)); this.tableDescriptors = new FSTableDescriptors(this.fs, this.rootDir, true); this.hlog = setupWALAndReplication(); diff --git a/src/main/java/org/apache/hadoop/hbase/util/FSUtils.java b/src/main/java/org/apache/hadoop/hbase/util/FSUtils.java index 6ab6a1a..2c7ac6b 100644 --- a/src/main/java/org/apache/hadoop/hbase/util/FSUtils.java +++ b/src/main/java/org/apache/hadoop/hbase/util/FSUtils.java @@ -1385,4 +1385,40 @@ public abstract class FSUtils { } } } -} + + /** + * Do our short circuit read setup. + * Checks buffer size to use and whether to do checksumming in hbase or hdfs. + * @param conf + */ + public static void setupShortCircuitRead(final Configuration conf) { + // Check that the user has not set the "dfs.client.read.shortcircuit.skip.checksum" property. + boolean shortCircuitSkipChecksum = + conf.getBoolean("dfs.client.read.shortcircuit.skip.checksum", false); + boolean useHBaseChecksum = conf.getBoolean(HConstants.HBASE_CHECKSUM_VERIFICATION, true); + if (shortCircuitSkipChecksum) { + LOG.warn("Configuration \"dfs.client.read.shortcircuit.skip.checksum\" should not " + + "be set to true." + (useHBaseChecksum ? " HBase checksum doesn't require " + + "it, see https://issues.apache.org/jira/browse/HBASE-6868." : "")); + assert !shortCircuitSkipChecksum; //this will fail if assertions are on + } + checkShortCircuitReadBufferSize(conf); + } + + /** + * Check if short circuit read buffer size is set and if not, set it to hbase value. + * @param conf + */ + public static void checkShortCircuitReadBufferSize(final Configuration conf) { + final int defaultSize = HConstants.DEFAULT_BLOCKSIZE * 2; + final int notSet = -1; + // DFSConfigKeys.DFS_CLIENT_READ_SHORTCIRCUIT_BUFFER_SIZE_KEY is only defined in h2 + final String dfsKey = "dfs.client.read.shortcircuit.buffer.size"; + int size = conf.getInt(dfsKey, notSet); + // If a size is set, return -- we will use it. + if (size != notSet) return; + // But short circuit buffer size is normally not set. Put in place the hbase wanted size. + int hbaseSize = conf.getInt("hbase." + dfsKey, defaultSize); + conf.setIfUnset(dfsKey, Integer.toString(hbaseSize)); + } +} \ No newline at end of file diff --git a/src/main/resources/hbase-default.xml b/src/main/resources/hbase-default.xml index b375ecf..856c46e 100644 --- a/src/main/resources/hbase-default.xml +++ b/src/main/resources/hbase-default.xml @@ -157,6 +157,20 @@ + hbase.dfs.client.read.shortcircuit.buffer.size + 131072 + If the DFSClient configuration + dfs.client.read.shortcircuit.buffer.size is unset, we will + use what is configured here as the short circuit read default + direct byte buffer size. DFSClient native default is 1MB; HBase + keeps its HDFS files open so number of file blocks * 1MB soon + starts to add up and threaten OOME because of a shortage of + direct memory. So, we set it down from the default. Make + it > the default hbase block size set in the HColumnDescriptor + which is usually 64k. + + + hbase.client.keyvalue.maxsize 10485760 Specifies the combined maximum allowed size of a KeyValue