lucene-solr-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jack Krupansky" <j...@basetechnology.com>
Subject Re: Scaling to large Number of Collections
Date Sun, 31 Aug 2014 12:08:42 GMT
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.schmidt@moresophy.de<mailto:heiko.beier@moresophy.de>
www.moresophy.com<http://www.moresophy.com/>
moresophy GmbH | Fraunhoferstrasse 15 | 82152 München-Martinsried


Mime
View raw message