Open asfimport opened 2 years ago
ASF subversion and git services (migrated from JIRA)
Commit 26713b3f572cc6e316cf4b3ba36dee0faed3a4af in lucene's branch refs/heads/main from gf2121 https://gitbox.apache.org/repos/asf?p=lucene.git;h=26713b3
LUCENE-10346: Specially treat SingletonSortedNumericDocValues in FastTaxonomyFacetCounts#countAll() (#574)
ASF subversion and git services (migrated from JIRA)
Commit 835e821287e03a455751727576a400d68ab7124a in lucene's branch refs/heads/main from Adrien Grand https://gitbox.apache.org/repos/asf?p=lucene.git;h=835e821
LUCENE-10346: Move CHANGES entry to 9.1.
ASF subversion and git services (migrated from JIRA)
Commit 01f5e7bb7b4f5efb5330ab97896008c83daef657 in lucene's branch refs/heads/branch_9x from gf2121 https://gitbox.apache.org/repos/asf?p=lucene.git;h=01f5e7b
LUCENE-10346: Specially treat SingletonSortedNumericDocValues in FastTaxonomyFacetCounts#countAll() (#574)
CPU profile often tells
SingletonSortedNumericDocValues#nextDoc()
is using a high percentage of CPU when running luceneutil, but thenextDoc()
of dense cases should be rather simple. So I suspect that it is too many layers of abstraction (and wrap) that cause the stress of JVM. Unwraping it toNumericDocvalues
shows around 30% speed up.Baseline
Candidate
Migrated from LUCENE-10346 by Feng Guo (@gf2121), updated Jan 04 2022 Pull requests: https://github.com/apache/lucene/pull/574