[ https://issues.apache.org/jira/browse/SOLR-16838?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17729551#comment-17729551 ]
Rahul Goswami commented on SOLR-16838: -------------------------------------- I ran the test to index 5 million docs (batches of 1000 docs in 15 parallel threads). To eliminate the network overhead and get as accurate a benchmark as possible, I used an AtomicLong to measure the time around the RTG call in DistibutedUpdateProcessor across all calls ([https://github.com/apache/lucene-solr/blob/releases/lucene-solr/7.7.2/solr/core/src/java/org/apache/solr/update/processor/DistributedUpdateProcessor.java#L1416]). Did this for both Solr 7.7.2 and Solr 8.11.1 and built the solr-core.jar to replace it in the solr webapp lib. RTG in Solr 8.x is ~10x slower. Here are the numbers (times are in milliseconds): *+Solr 7.7.2+* : 2023-06-01 15:39:48.272 WARN (qtp1034094674-24) [ x:techproducts] o.a.s.u.p.LogUpdateProcessorFactory *+Total rtg time:7293486+* *{+}Solr 8.11.1{+}:* 2023-06-01 04:46:24.758 WARN (qtp391506011-71) [ x:techproducts] o.a.s.u.p.LogUpdateProcessorFactory *+Total rtg time:72029877+* > Atomic updates too slow in Solr 8 vs Solr 7 > ------------------------------------------- > > Key: SOLR-16838 > URL: https://issues.apache.org/jira/browse/SOLR-16838 > Project: Solr > Issue Type: Bug > Security Level: Public(Default Security Level. Issues are Public) > Components: SearchComponents - other > Affects Versions: 8.11.1 > Reporter: Rahul Goswami > Priority: Major > > Started experiencing slowness with updates in production after upgrading from > Solr 7.7.2 to 8.11.1. Upon comparing the performance it turns out that > indexing 20 million docs via atomic updates through the same client program > (running 15 parallel threads indexing in batches of 1000) takes below time: > > Solr 7 : 78 mins > Solr 8: 370 mins > > Environment details: > - Java 11 on Windows server > - Xms1536m Xmx3072m > - Indexing client code running 15 parallel threads indexing in batches of 1000 > - using SimpleFSDirectoryFactory (since Mmap doesn't quite work well on > Windows for our index sizes which commonly run north of 1 TB) > > Looking at the thread dump, the bottleneck seems to be RealTimeGet and I can > see that Solr 7 takes a different code path than Solr 8. Note that the > performance of regular updates (non-atomic) is still pretty good on Solr 8 > completing in < 1 hour for the same 20 million data set. > > Sharing the indexing code, solrconfig, schema and thread dumps in the link > below: > [https://drive.google.com/drive/folders/1q2DPNTYQEU6fi3NeXIKJhaoq3KPnms0h?usp=sharing] -- This message was sent by Atlassian Jira (v8.20.10#820010) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@solr.apache.org For additional commands, e-mail: issues-h...@solr.apache.org