From f0444014b8b2dd75284d317149addd8b288c91ff Mon Sep 17 00:00:00 2001
From: Doug Meil <dmeil@apache.org>
Date: Wed, 2 Nov 2011 20:40:14 +0000
Subject: [PATCH] HBASE-4730 book.xml, ops_mgt.xml, performance.xml - handful
 of changes

git-svn-id: https://svn.apache.org/repos/asf/hbase/trunk@1196792 13f79535-47bb-0310-9956-ffa450edef68
---
 src/docbkx/book.xml        | 18 +++++++++++++++++-
 src/docbkx/ops_mgt.xml     |  5 +++++
 src/docbkx/performance.xml |  5 +++++
 3 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/src/docbkx/book.xml b/src/docbkx/book.xml
index 669aff03f8a..371a88e3cf1 100644
--- a/src/docbkx/book.xml
+++ b/src/docbkx/book.xml
@@ -565,6 +565,12 @@ admin.enableTable(table);
         second and third column family in the case where data access is usually column scoped;
         i.e. you query one column family or the other but usually not both at the one time.
     </para>
+    <section xml:id="number.of.cfs.card"><title>Cardinality of ColumnFamilies</title>
+      <para>Where multiple ColumnFamilies exist in a single table, be aware of the cardinality (i.e., number of rows).  
+      If ColumnFamily-A has 1000,000 rows and ColumnFamily-B has 1 billion rows, ColumnFamily-A's data will likely be spread 
+      across many, many regions (and RegionServers).  This makes mass scans for ColumnFamily-A less efficient.  
+      </para>
+    </section>
   </section>
   <section xml:id="rowkey.design"><title>Rowkey Design</title>
     <section xml:id="timeseries">
@@ -972,6 +978,11 @@ public static class MyMapper extends TableMapper&lt;ImmutableBytesWritable, Put&
     </para>
     </para>
     </section>
+    <section xml:id="mapreduce.example.readwrite.multi">
+      <title>HBase MapReduce Read/Write Example With Multi-Table Output</title>
+      <para>TODO:  example for <classname>MultiTableOutputFormat</classname>.
+    </para>
+    </section>
     <section xml:id="mapreduce.example.summary">
     <title>HBase MapReduce Summary Example</title>
     <para>The following example uses HBase as a MapReduce source and sink with a summarization step.  This example will 
@@ -1575,7 +1586,6 @@ scan.setFilter(filter);
           <para>For more information, see the <link xlink:href="http://hbase.apache.org/xref/org/apache/hadoop/hbase/io/hfile/HFile.html">HFile source code</link>.
           </para>
       </section>
-
       <section xml:id="hfile_tool">
         <title>HFile Tool</title>
 
@@ -1589,7 +1599,13 @@ scan.setFilter(filter);
         usage for other things to do with the <classname>HFile</classname>
         tool.</para>
       </section>
+      <section xml:id="store.file.dir">
+       <title>StoreFile Directory Structure on HDFS</title>
+        <para>For more information of what StoreFiles look like on HDFS with respect to the directory structure, see <xref linkend="trouble.namenode.hbase.objects" />.
+        </para>
       </section>
+      </section> <!--  hfile -->
+      
       <section xml:id="hfile.blocks">
         <title>Blocks</title>
         <para>StoreFiles are composed of blocks.  The blocksize is configured on a per-ColumnFamily basis.
diff --git a/src/docbkx/ops_mgt.xml b/src/docbkx/ops_mgt.xml
index 8601427734f..fa534842564 100644
--- a/src/docbkx/ops_mgt.xml
+++ b/src/docbkx/ops_mgt.xml
@@ -417,6 +417,11 @@ false
         </para>
       </section>
     </section>
+    <section xml:id="ops.capacity.regions"><title>Regions</title>
+      <para>Another common question for HBase administrators is determining the right number of regions per
+      RegionServer.  This affects both storage and hardware planning. See <xref linkend="perf.number.of.regions" />.
+      </para>
+    </section>
   </section>
 
 </chapter>
diff --git a/src/docbkx/performance.xml b/src/docbkx/performance.xml
index c2fffbb6716..12b1d19d006 100644
--- a/src/docbkx/performance.xml
+++ b/src/docbkx/performance.xml
@@ -140,6 +140,11 @@
       <para>The number of regions for an HBase table is driven by the <xref
               linkend="bigger.regions" />. Also, see the architecture
           section on <xref linkend="arch.regions.size" /></para>
+       <para>A lower number of regions is preferred, generally in the range of 20 to 200
+       per RegionServer.  Adjust the regionsize as appropriate to achieve this number.  There
+       are some clusters that set the regionsize to 20Gb, for example, so you may need to 
+       experiment with this setting based on your hardware configuration and application needs.
+       </para>
     </section>
 
     <section xml:id="perf.compactions.and.splits">