- 300 ppm is default now (but this is switched off by default; if you switch it on you may want more traffic?)
- better timing for busy queue
- better amount of remote url retrieval
- better time-out values
- better tracking of availability of remote crawl urls
- more logging for result of receipt sending
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7159 6c8d7289-2bf4-0310-a012-ef5d649a1542
if(this.log.isFine())log.logFine("remoteCrawlLoaderJob: too many processes in loader queue, dismissed ("+"cacheLoader="+this.workers.size()+"), httpClients = "+ConnectionInfo.getCount());
returnfalse;
}
@ -363,12 +363,12 @@ public class CrawlQueues {
returnfalse;
}
if(remoteTriggeredCrawlJobSize()>100){
if(remoteTriggeredCrawlJobSize()>200){
if(this.log.isFine())log.logFine("remoteCrawlLoaderJob: the remote-triggered crawl job queue is filled, omitting processing");
deployThread(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL,"Local Crawl","thread that performes a single crawl step from the local crawl queue","/IndexCreateWWWLocalQueue_p.html",
newInstantBusyThread(
crawlQueues,
@ -661,6 +656,11 @@ public final class Switchboard extends serverSwitch {
log.logInfo("Sending crawl receipt for '"+reference.metadata().url().toNormalform(false,true)+"' to "+initiatorPeer.getName()+" FAILED, send time = "+(System.currentTimeMillis()-t));
return;
}
Stringdelay=response.get("delay");
log.logInfo("Sending crawl receipt for '"+reference.metadata().url().toNormalform(false,true)+"' to "+initiatorPeer.getName()+" success, delay = "+delay+", send time = "+(System.currentTimeMillis()-t));