[
https://issues.apache.org/jira/browse/SOLR-13013?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16702034#comment-16702034
]
Joel Bernstein commented on SOLR-13013:
---------------------------------------
You're exactly right that improving performance of export helps the MapReduce
use cases as well. It's just that in a sharded, replicated environment with a
tier of worker nodes performing a reduce operation, you can get massive
throughput already just because you can have dozens of servers pushing out an
export and reducing in parallel.
But you could easily argue that your usecase is the more common use case and we
should really try to make it as fast as possible.
I wouldn't worry too much about testing this is in sharded scenarios. We can
extrapolate the single shard findings to multiple shards, realizing that the
aggregator node will quickly become the bottleneck and the /export will spend
much of it's time blocked while writing data. Having a tier of worker nodes
unlocks this bottleneck in the case where worker nodes are performing some form
of reduce operation.
> Change export to extract DocValues in docID order
> -------------------------------------------------
>
> Key: SOLR-13013
> URL: https://issues.apache.org/jira/browse/SOLR-13013
> Project: Solr
> Issue Type: Improvement
> Security Level: Public(Default Security Level. Issues are Public)
> Components: Export Writer
> Affects Versions: 7.5, master (8.0)
> Reporter: Toke Eskildsen
> Priority: Major
> Fix For: master (8.0)
>
> Attachments: SOLR-13013_proof_of_concept.patch,
> SOLR-13013_proof_of_concept.patch
>
>
> The streaming export writer uses a sliding window of 30,000 documents for
> paging through the result set in a given sort order. Each time a window has
> been calculated, the values for the export fields are retrieved from the
> underlying DocValues structures in document sort order and delivered.
> The iterative DocValues API introduced in Lucene/Solr 7 does not support
> random access. The current export implementation bypasses this by creating a
> new DocValues-iterator for each individual value to retrieve. This slows down
> export as the iterator has to seek to the given docID from start for each
> value. The slowdown scales with shard size (see LUCENE-8374 for details). An
> alternative is to extract the DocValues in docID-order, with re-use of
> DocValues-iterators. The idea is as follows:
> # Change the FieldWriters for export to re-use the DocValues-iterators if
> subsequent requests are for docIDs higher than the previous ones
> # Calculate the sliding window of SortDocs as usual
> # Take a note of the order of the SortDocs in the sliding window
> # Re-sort the SortDocs in docID-order
> # Extract the DocValues to a temporary on-heap structure
> # Re-sort the extracted values to the original sliding window order
> Deliver the values
> One big difference from the current export code is of course the need to hold
> the whole sliding window scaled result set in memory. This might well be a
> showstopper as there is no real limit to how large this partial result set
> can be. Maybe such an optimization could be requested explicitly if the user
> knows that there is enough memory?
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
