Hi, I’ve seen similar jump in thread number when DBQ was used. Do you delete documents while indexing?
Emir -- Monitoring - Log Management - Alerting - Anomaly Detection Solr & Elasticsearch Consulting Support Training - http://sematext.com/ > On 5 Apr 2018, at 07:56, Doss <itsmed...@gmail.com> wrote: > > @wunder > > Are you sending updates in batches? Are you doing a commit after every > update? > >>> We want the system to be near real time, so we are not doing updates in >>> batches and also we are not doing commit after every update. >>> autoSoftCommit once in every minute, and autoCommit once in every 10 >>> minutes. > > This thread increase is not happening in all the time, on our peak hours > where used we to get more user interactions the system works absolutely > fine, suddenly this problem creeps up and system gets into trouble. > > nproc value increased 18000. > > Did jetty related linux fine tuning as described in the below link > > http://www.eclipse.org/jetty/documentation/current/high-load.html > > Thanks. > > > > -- > Sent from: http://lucene.472066.n3.nabble.com/Solr-User-f472068.html