mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
da86f150ab
This organizes all urls to be loaded in separate queues for each host. Each host separates the crawl depth into it's own queue. The primary rule for urls taken from any queue is, that the crawl depth is minimal. This produces a crawl depth which is identical to the clickdepth. Furthermorem the crawl is able to create a much better balancing over all hosts which is fair to all hosts that are in the queue. This process will create a very large number of files for wide crawls in the QUEUES folder: for each host a directory, for each crawl depth a file inside the directory. A crawl with maxdepth = 4 will be able to create 10.000s of files. To be able to use that many file readers, it was necessary to implement a new index data structure which opens the file only if an access is wanted (OnDemandOpenFileIndex). The usage of such on-demand file reader shall prevent that the number of file pointers is over the system limit, which is usually about 10.000 open files. Some parts of YaCy had to be adopted to handle the crawl depth number correctly. The logging and the IndexCreateQueues servlet had to be adopted to show the crawl queues differently, because the host name is attached to the port on the host to differentiate between http, https, and ftp services.
140 lines
5.7 KiB
Plaintext
140 lines
5.7 KiB
Plaintext
# Set the logging level for the root of the namespace.
|
|
# This becomes the default logging level for all Loggers.
|
|
.level=ALL
|
|
|
|
# setting logging levels vor individual classes
|
|
# possible values are:
|
|
# OFF no output at all
|
|
# SEVERE system-level error, internal cause, critical and not fixable (i.e. inconsistency)
|
|
# WARNING uncritical service failure, may require user activity (i.e. input required, wrong authorization)
|
|
# INFO regular action information (i.e. any httpd request URL)
|
|
# CONFIG regular system status information (i.e. start-up messages)
|
|
# FINE in-function status debug output
|
|
BASE64.level = OFF
|
|
PARSER.level = INFO
|
|
PROXY.level = INFO
|
|
YACY.level = INFO
|
|
HTCACHE.level = INFO
|
|
PLASMA.level = INFO
|
|
SERVER.level = INFO
|
|
FILEHANDLER.level = INFO
|
|
CRAWLER.level = INFO
|
|
STACKCRAWL.level = INFO
|
|
MEMORY.level = INFO
|
|
HTTPC.level = INFO
|
|
INDEX-TRANSFER-DISPATCHER.level = INFO
|
|
# UPnP related
|
|
UPNP.level = INFO
|
|
sun.net.www.protocol.http.HttpURLConnection.level = INFO
|
|
# Tray
|
|
sun.awt.level = OFF
|
|
java.awt.level = OFF
|
|
TABLE.level = INFO
|
|
|
|
# List of global handlers
|
|
handlers = java.util.logging.FileHandler,\
|
|
net.yacy.kelondro.logging.GuiHandler,\
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler,\
|
|
net.yacy.kelondro.logging.LogalizerHandler
|
|
|
|
# Properties for the FileHandler
|
|
java.util.logging.FileHandler.limit = 1048576
|
|
java.util.logging.FileHandler.count = 20
|
|
java.util.logging.FileHandler.pattern = DATA/LOG/yacy%u%g.log
|
|
java.util.logging.FileHandler.level = ALL
|
|
java.util.logging.FileHandler.formatter=net.yacy.kelondro.logging.SimpleLogFormatter
|
|
java.util.logging.FileHandler.encoding=UTF-8
|
|
|
|
# Properties for crawler
|
|
net.yacy.crawler.robots.RobotsTxt.level = SEVERE
|
|
|
|
# Properties for the GuiHandler
|
|
net.yacy.kelondro.logging.GuiHandler.level = ALL
|
|
net.yacy.kelondro.logging.GuiHandler.formatter=net.yacy.kelondro.logging.SimpleLogFormatter
|
|
net.yacy.kelondro.logging.GuiHandler.size = 1000
|
|
|
|
# Properties for the ConsoleOutErrHandler
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler.level = ALL
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler.levelStdOut = ALL
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler.levelSplit = WARNING
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler.levelStdErr = ALL
|
|
net.yacy.kelondro.logging.ConsoleOutErrHandler.formatter=net.yacy.kelondro.logging.SimpleLogFormatter
|
|
#net.yacy.kelondro.logging.ConsoleOutErrHandler.ignoreCtrlChr=true
|
|
|
|
# Properties for the proxy access logger
|
|
net.yacy.server.http.HTTPDProxyHandler.logging.enabled = TRUE
|
|
net.yacy.server.http.HTTPDProxyHandler.logging.FileHandler.limit = 1048576
|
|
net.yacy.server.http.HTTPDProxyHandler.logging.FileHandler.count = 20
|
|
net.yacy.server.http.HTTPDProxyHandler.logging.FileHandler.pattern = DATA/LOG/proxyAccess%u%g.log
|
|
|
|
# Properties for the LogalizerHandler
|
|
net.yacy.kelondro.logging.LogalizerHandler.enabled = false
|
|
net.yacy.kelondro.logging.LogalizerHandler.debug = false
|
|
net.yacy.kelondro.logging.LogalizerHandler.parserPackage = net.yacy.kelondro.logging
|
|
|
|
# Poperties for the HttpServer (Jetty)
|
|
org.eclipse.jetty.level = INFO
|
|
|
|
org.apache.http.level = OFF
|
|
org.apache.commons.httpclient.level = OFF
|
|
httpclient.wire.level = OFF
|
|
# above log setting can be replaced by separate levels for header and content
|
|
# e.g. to log content for attached Solr server
|
|
# httpclient.wire.header.level = OFF
|
|
# httpclient.wire.content.level = OFF
|
|
|
|
org.apache.pdfbox.level = INFO
|
|
|
|
# Properties for solr
|
|
org.apache.solr.client.solrj.impl.HttpClientUtil.level = SEVERE
|
|
org.apache.solr.core.Config.level = SEVERE
|
|
org.apache.solr.core.CoreContainer.level = SEVERE
|
|
org.apache.solr.core.JmxMonitoredMap.level = SEVERE
|
|
org.apache.solr.core.RequestHandlers.level = SEVERE
|
|
org.apache.solr.core.SolrConfig.level = SEVERE
|
|
org.apache.solr.core.SolrCore.level = SEVERE
|
|
org.apache.solr.core.SolrResourceLoader.level = SEVERE
|
|
org.apache.solr.core.CachingDirectoryFactory.level = OFF
|
|
org.apache.solr.util.plugin.AbstractPluginLoader.level = INFO
|
|
org.apache.solr.schema.IndexSchema.level = INFO
|
|
org.apache.solr.schema.FieldTypePluginLoader.level = INFO
|
|
org.apache.solr.handler.component.HttpShardHandlerFactory.level = SEVERE
|
|
org.apache.solr.handler.component.QueryElevationComponent.level = SEVERE
|
|
org.apache.solr.handler.component.SearchHandler.level = SEVERE
|
|
org.apache.solr.handler.component.SpellCheckComponent.level = SEVERE
|
|
org.apache.solr.handler.loader.XMLLoader.level = SEVERE
|
|
org.apache.solr.handler.ReplicationHandler.level = SEVERE
|
|
org.apache.solr.handler.UpdateRequestHandler.level = INFO
|
|
org.apache.solr.response.XSLTResponseWriter.level = SEVERE
|
|
org.apache.solr.schema.FileExchangeRateProvider.level = SEVERE
|
|
org.apache.solr.schema.IndexSchema.level = SEVERE
|
|
org.apache.solr.search.SolrIndexSearcher.level = SEVERE
|
|
org.apache.solr.spelling.DirectSolrSpellChecker.level = SEVERE
|
|
org.apache.solr.update.processor.LogUpdateProcessor.level = OFF
|
|
org.apache.solr.update.DefaultSolrCoreState.level = SEVERE
|
|
org.apache.solr.update.SolrCoreState.level = SEVERE
|
|
org.apache.solr.update.SolrIndexWriter.level = INFO
|
|
org.apache.solr.update.UpdateHandler.level = SEVERE
|
|
|
|
# Properties for jena
|
|
com.hp.hpl.jena.util.FileManager.level = SEVERE
|
|
com.hp.hpl.jena.util.LocationMapper.level = SEVERE
|
|
com.hp.hpl.jena.util.LocatorClassLoader.level = SEVERE
|
|
com.hp.hpl.jena.util.LocatorFile.level = SEVERE
|
|
com.hp.hpl.jena.util.SystemUtils.level = SEVERE
|
|
|
|
# Properties for the YaCy solr interface
|
|
net.yacy.cora.federate.solr.connector.SolrServerConnector.level = INFO
|
|
net.yacy.cora.federate.solr.instance.RemoteInstance$1.level = INFO
|
|
|
|
# Some more cora loggers
|
|
net.yacy.cora.lod.JenaTripleStore.level = SEVERE
|
|
net.yacy.cora.protocol.Domains.level = SEVERE
|
|
|
|
# java properties
|
|
javax.management.misc.level = INFO
|
|
javax.management.mbeanserver.level = INFO
|
|
|
|
# Properties for Collection
|
|
CollectionConfiguration.CRHost.level = SEVERE
|