One collection has 2 replicas, no sharding, the collections are not that big.

No, they are unfortunately not independent. There are collections with customer 
documents (some thousand customers) and product collections. One customer has 
at least on customer collection and 1 to some hundred products.
The combination of these collections is used to drive the search of a Liferay 
portal. Each customer has its own Liferay portal.

We could split up the cluster in several clusters by customers, but then we had 
for duplicate the product collections in each SolrCluster.

Will Solr go in the direction of "large number of collections"? And the 
question is, what is a "large number"?

Best
Christoph

-----Ursprüngliche Nachricht-----
Von: Jack Krupansky [mailto:j...@basetechnology.com] 
Gesendet: Sonntag, 31. August 2014 14:09
An: solr-user@lucene.apache.org
Betreff: Re: Scaling to large Number of Collections

How are the 5 servers arranged in terms of shards and replicas? 5 shards with 1 
replica each, 1 shard with 5 replicas, 2 shards with 2 and 3 replicas, or... 
what?

How big is each collection? The key strength of SolrCloud is scaling large 
collections via shards, NOT scaling large numbers of collections. If you have 
large numbers of collections, maybe they should be divided into separate 
clusters, especially if they are independent.

Is this a multi-tenancy situation or a single humongous app?

In any case, "large numbers of collections in a single SolrCloud cluster" is 
not a supported scenario at this time. Certainly suggestions for future 
enhancement can be made though.

-- Jack Krupansky

-----Original Message-----
From: Christoph Schmidt
Sent: Sunday, August 31, 2014 4:04 AM
To: solr-user@lucene.apache.org
Subject: Scaling to large Number of Collections

we see at least two problems when scaling to large number of collections. I 
would like to ask the community, if they are known and maybe already addressed 
in development:
We have a SolrCloud running with the following numbers:
-          5 Servers (each 24 CPUs, 128 RAM)
-          13.000 Collection with 25.000 SolrCores in the Cloud
The Cloud is working fine, but we see two problems, if we like to scale further
1.       Resource consumption of native system threads
We see that each collection opens at least two threads: one for the zookeeper 
(coreZkRegister-1-thread-5154) and one for the searcher
(searcherExecutor-28357-thread-1)
We will run in "OutOfMemoryError: unable to create new native thread". Maybe 
the architecture could be changed here to use thread pools?
2.       The shutdown and the startup of one server in the SolrCloud takes 2 
hours. So a rolling start is about 10h. For me the problem seems to be that 
leader election is "linear". The Overseer does core per core. The organisation 
of the cloud is not done parallel or distributed. Is this already addressed by 
https://issues.apache.org/jira/browse/SOLR-5473 or is there more needed?

Thanks for discussion and help
Christoph
_______________________________________________

Dr. Christoph Schmidt | Geschäftsführer

P +49-89-523041-72
M +49-171-1419367
Skype: cs_moresophy
christoph.schm...@moresophy.de<mailto:heiko.be...@moresophy.de>
www.moresophy.com<http://www.moresophy.com/>
moresophy GmbH | Fraunhoferstrasse 15 | 82152 München-Martinsried

Reply via email to