Hi Otis; I've read at somewhere says that if you have one replica and 1000 query per second search rate and if you switch to 5 replica you may get 200 qps search rate. What do you think about that and how Solr parallelize searching within replicas? By the way when you say replica do you mean both replica and leader (because of leader is a replica too) or nodes of shard except for leader?
2013/4/17 Otis Gospodnetic <otis.gospodne...@gmail.com> > No. > > Otis > -- > Solr & ElasticSearch Support > http://sematext.com/ > > > > > > On Tue, Apr 16, 2013 at 6:23 PM, Furkan KAMACI <furkankam...@gmail.com> > wrote: > > All in all will replica ask to its leader about where is remaining of > data > > or it directly asks to Zookeper? > > > > 2013/4/17 Otis Gospodnetic <otis.gospodne...@gmail.com> > > > >> Hi, > >> > >> No, I believe "redirect" from replica to leader would happen only at > >> index time, so a doc first gets indexed to leader and from there it's > >> replicated to non-leader shards. At query time there is no redirect > >> to leader, I imagine, as that would quickly turn leaders into > >> hotspots. > >> > >> Otis > >> -- > >> Solr & ElasticSearch Support > >> http://sematext.com/ > >> > >> > >> > >> > >> > >> On Tue, Apr 16, 2013 at 6:01 PM, Furkan KAMACI <furkankam...@gmail.com> > >> wrote: > >> > I want to make it clear in my mind: > >> > > >> > When a search query comes to a replica what happens? > >> > > >> > -Does it forwards the search query to leader and leader collects all > the > >> > data and prepares response (this will cause a performance issue > because > >> > leader is responsible for indexing at same time) > >> > or > >> > - replica communicates with leader and learns where is remaining > >> > data(leaders asks to Zookeper and tells it to replica) and replica > >> collects > >> > all data and response it? > >> >
