Patch attached. I haven't added any properties from plugins or test classes.
best regards,
Dominik
Stefan Groschupf schrieb:
to my nutch-site.xml. I saw in this file and other files also
properties that are not in nutch-default.xml and some are not even
read from NutchConf but set directly in the source code, e.g. in
mapred/MRConstants.java. I could go through the current code and
create an updated nutch-site.xml with all properties some day next week.
That would be great! !!
Thanks!
Index: nutch-default.xml
===================================================================
--- nutch-default.xml (revision 369731)
+++ nutch-default.xml (working copy)
@@ -379,6 +379,14 @@
exception.</description>
</property>
+<property>
+ <name>io.map.index.skip</name>
+ <value>0</value>
+ <description>Number of index entries to skip between each entry. Zero by
default.
+ Setting this to values larger than zero can facilitate opening large map
+ files using less memory.</description>
+</property>
+
<!-- file system properties -->
<property>
@@ -412,6 +420,39 @@
directories, typically on different devices.</description>
</property>
+<property>
+ <name>ndfs.replication</name>
+ <value>3</value>
+ <description>How many copies we try to have at all times. The actual number
of
+ replications is at max the number of datanodes in the cluster.</description>
+</property>
+
+<property>
+ <name>ndfs.max-repl-streams</name>
+ <value>2</value>
+ <description>How many outgoing replication streams a given node should
+ have at one time.</description>
+</property>
+
+<property>
+ <name>ndfs.availability.allocation</name>
+ <value>false</value>
+ <description>Whether we should use disk-availability info when
+ determining target.</description>
+</property>
+
+<property>
+ <name>ndfs.namenode.handler.count</name>
+ <value>10</value>
+ <description>Number of handler threads.</description>
+</property>
+
+<property>
+ <name>test.ndfs.same.host.targets.allowed</name>
+ <value>false</value>
+ <description>??? You better don't change it unless you know what you
do.</description>
+</property>
+
<!-- map/reduce properties -->
<property>
@@ -511,6 +552,13 @@
child processes.</description>
</property>
+<property>
+ <name>mapred.combine.buffer.size</name>
+ <value>100000</value>
+ <description>The number of entries the combining collector caches befor
+ combining them and writing to disk.</description>
+</property>
+
<!-- indexer properties -->
<property>
@@ -926,4 +974,13 @@
</description>
</property>
+<!-- PruneIndexTool -->
+
+<property>
+ <name>prune.index.tool.queries</name>
+ <value></value>
+ <description>With no -queries Parameter calling PruneIndexTool this file
+ is used.</description>
+</property>
+
</nutch-conf>
