Author: dogacan
Date: Tue Aug 25 05:45:53 2009
New Revision: 807485
URL: http://svn.apache.org/viewvc?rev=807485&view=rev
Log:
Fetcher2 slow. Patch contributed by Julien Nioche.
Modified:
lucene/nutch/trunk/CHANGES.txt
lucene/nutch/trunk/conf/nutch-default.xml
lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java
Modified: lucene/nutch/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/CHANGES.txt?rev=807485&r1=807484&r2=807485&view=diff
==============================================================================
--- lucene/nutch/trunk/CHANGES.txt (original)
+++ lucene/nutch/trunk/CHANGES.txt Tue Aug 25 05:45:53 2009
@@ -5,6 +5,8 @@
1. NUTCH-735 - crawl-tool.xml must be read before nutch-site.xml when
invoked using crawl command (Susam Pal via dogacan)
+ 2. NUTCH-721 - Fetcher2 Slow (Julien Nioche via dogacan)
+
Release 1.0 - 2009-03-23
1. NUTCH-474 - Fetcher2 crawlDelay and blocking fix (Dogacan Guney via ab)
Modified: lucene/nutch/trunk/conf/nutch-default.xml
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/conf/nutch-default.xml?rev=807485&r1=807484&r2=807485&view=diff
==============================================================================
--- lucene/nutch/trunk/conf/nutch-default.xml (original)
+++ lucene/nutch/trunk/conf/nutch-default.xml Tue Aug 25 05:45:53 2009
@@ -575,7 +575,7 @@
<property>
<name>fetcher.threads.per.host.by.ip</name>
- <value>true</value>
+ <value>false</value>
<description>If true, then fetcher will count threads by IP address,
to which the URL's host name resolves. If false, only host name will be
used. NOTE: this should be set to the same value as
Modified: lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java?rev=807485&r1=807484&r2=807485&view=diff
==============================================================================
--- lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java (original)
+++ lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java Tue Aug
25 05:45:53 2009
@@ -460,8 +460,7 @@
this.protocolFactory = new ProtocolFactory(conf);
this.normalizers = new URLNormalizers(conf,
URLNormalizers.SCOPE_FETCHER);
this.maxCrawlDelay = conf.getInt("fetcher.max.crawl.delay", 30) * 1000;
- // backward-compatible default setting
- this.byIP = conf.getBoolean("fetcher.threads.per.host.by.ip", true);
+ this.byIP = conf.getBoolean("fetcher.threads.per.host.by.ip", false);
this.maxRedirect = conf.getInt("http.redirect.max", 3);
this.ignoreExternalLinks =
conf.getBoolean("db.ignore.external.links", false);