[
https://issues.apache.org/jira/browse/SOLR-15715?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17448993#comment-17448993
]
Atri Sharma commented on SOLR-15715:
------------------------------------
A well known issue with this model is that the aggregation nodes can a. become
bottlenecks to the overall throughput and b. cause outages if they are not
scaled correctly.
In an aggregation heavy system, these nodes will become the target of maximum
load, thus potentially causing a skew in the cluster where the data nodes are
relatively lower loaded vs the aggregation nodes bearing most of the load. To
sustain that, a separate scalability model will be required for the aggregation
nodes, thus leading to more complexity and state.
Compared to status quo, in a state of high load, the chances of the cluster
running into a cascading failure mode are higher for this solution.
What are the steps taken to avoid the situation described above, and what kind
of testing/simulation has been performed for the same?
> Dedicated query aggregator nodes in the solr cluster.
> ------------------------------------------------------
>
> Key: SOLR-15715
> URL: https://issues.apache.org/jira/browse/SOLR-15715
> Project: Solr
> Issue Type: New Feature
> Components: SearchComponents - other
> Affects Versions: 8.10.1
> Reporter: Hitesh Khamesra
> Priority: Major
> Attachments: coordinator-poc.jpg, coordinator-poc.pdf,
> regular-node.jpg, regular-node.pdf
>
>
> We have a large collection with 1000s of shards in the solr cluster. We have
> observed that distributed solr query takes many resources(thread, memory,
> etc.) on the solr data node(node which contains indexes). Thus we need
> dedicated query nodes to execute distributed queries on large solr
> collection. That would reduce the memory/cpu pressure from solr data nodes.
> Elastis search has similar functionality
> [here|https://www.elastic.co/guide/en/elasticsearch/reference/current/modules-node.html#coordinating-node]
>
> [~noble.paul] [~ichattopadhyaya]
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@solr.apache.org
For additional commands, e-mail: issues-h...@solr.apache.org
