Feng Guo created LUCENE-10350:
---------------------------------
Summary: Avoid some null checking for
FastTaxonomyFacetCounts#countAll()
Key: LUCENE-10350
URL: https://issues.apache.org/jira/browse/LUCENE-10350
Project: Lucene - Core
Issue Type: Improvement
Reporter: Feng Guo
I find that {{org.apache.lucene.facet.taxonomy.IntTaxonomyFacets#increment()}}
is using about 2% cpu of luceneutil, this could probably be replaced with
{{values[doc]++}} since {{#countAll}} will never use hashTable.
Two changes:
# No need to check liveDocs null again and again.
# Call {{values[doc]++}} instead of {{#increment}} since {{#countAll}} will
never use hashTable.
*Benchmark* (baseline is the newest main, including LUCENE-10346)
{code:java}
TaskQPS baseline StdDevQPS my_modified_version
StdDev Pct diff p-value
IntNRQ 128.51 (27.8%) 120.13
(27.4%) -6.5% ( -48% - 67%) 0.455
PKLookup 232.55 (5.0%) 226.26
(4.2%) -2.7% ( -11% - 6%) 0.065
Wildcard 178.54 (5.5%) 175.13
(5.7%) -1.9% ( -12% - 9%) 0.283
BrowseMonthSSDVFacets 16.37 (6.9%) 16.13
(4.6%) -1.5% ( -12% - 10%) 0.422
HighPhrase 211.52 (3.7%) 209.59
(3.3%) -0.9% ( -7% - 6%) 0.414
MedPhrase 239.31 (3.2%) 237.14
(2.5%) -0.9% ( -6% - 4%) 0.311
HighSloppyPhrase 33.08 (3.3%) 32.79
(3.5%) -0.9% ( -7% - 6%) 0.407
Prefix3 171.63 (7.5%) 170.33
(8.3%) -0.8% ( -15% - 16%) 0.762
Respell 80.21 (3.3%) 79.74
(2.7%) -0.6% ( -6% - 5%) 0.530
LowPhrase 26.21 (3.6%) 26.05
(2.5%) -0.6% ( -6% - 5%) 0.549
LowSloppyPhrase 165.34 (2.4%) 164.47
(2.7%) -0.5% ( -5% - 4%) 0.516
OrHighNotLow 1984.04 (3.9%) 1974.07
(5.2%) -0.5% ( -9% - 8%) 0.730
OrHighMed 93.69 (4.2%) 93.23
(4.1%) -0.5% ( -8% - 8%) 0.711
MedSpanNear 12.19 (3.6%) 12.14
(4.0%) -0.3% ( -7% - 7%) 0.777
Fuzzy2 98.86 (3.0%) 98.56
(2.6%) -0.3% ( -5% - 5%) 0.735
HighTerm 2284.28 (4.3%) 2277.92
(3.4%) -0.3% ( -7% - 7%) 0.819
BrowseDayOfYearSSDVFacets 14.65 (4.8%) 14.61
(4.0%) -0.3% ( -8% - 8%) 0.844
LowSpanNear 101.85 (1.7%) 101.58
(2.0%) -0.3% ( -3% - 3%) 0.662
BrowseRandomLabelSSDVFacets 11.04 (5.4%) 11.02
(7.2%) -0.2% ( -12% - 13%) 0.902
OrHighHigh 39.59 (4.2%) 39.49
(4.1%) -0.2% ( -8% - 8%) 0.859
Fuzzy1 84.27 (3.1%) 84.11
(2.3%) -0.2% ( -5% - 5%) 0.826
AndHighMed 94.85 (5.1%) 94.77
(6.9%) -0.1% ( -11% - 12%) 0.969
HighTermDayOfYearSort 179.66 (17.0%) 179.56
(12.8%) -0.1% ( -25% - 35%) 0.991
LowTerm 2016.63 (3.5%) 2015.71
(3.9%) -0.0% ( -7% - 7%) 0.969
AndHighLow 1011.34 (4.1%) 1011.05
(5.3%) -0.0% ( -9% - 9%) 0.985
HighTermTitleBDVSort 121.48 (14.4%) 121.49
(15.9%) 0.0% ( -26% - 35%) 0.998
MedTerm 2239.73 (4.6%) 2245.65
(3.1%) 0.3% ( -7% - 8%) 0.830
AndHighHigh 102.09 (3.1%) 102.48
(5.3%) 0.4% ( -7% - 9%) 0.778
OrNotHighLow 1113.23 (2.3%) 1117.98
(2.4%) 0.4% ( -4% - 5%) 0.568
HighSpanNear 1.92 (4.7%) 1.93
(5.4%) 0.5% ( -9% - 11%) 0.738
OrHighNotMed 1322.20 (4.3%) 1330.58
(3.1%) 0.6% ( -6% - 8%) 0.592
AndHighMedDayTaxoFacets 65.82 (1.8%) 66.30
(2.5%) 0.7% ( -3% - 5%) 0.295
OrNotHighMed 1262.49 (3.0%) 1272.12
(3.8%) 0.8% ( -5% - 7%) 0.480
MedTermDayTaxoFacets 52.07 (4.7%) 52.54
(6.9%) 0.9% ( -10% - 13%) 0.628
OrNotHighHigh 944.56 (3.7%) 953.87
(3.0%) 1.0% ( -5% - 7%) 0.352
MedSloppyPhrase 64.28 (5.4%) 64.92
(4.7%) 1.0% ( -8% - 11%) 0.531
OrHighLow 921.30 (2.8%) 930.66
(2.6%) 1.0% ( -4% - 6%) 0.232
AndHighHighDayTaxoFacets 23.67 (3.4%) 23.93
(4.2%) 1.1% ( -6% - 9%) 0.380
OrHighNotHigh 1186.72 (3.3%) 1202.71
(3.6%) 1.3% ( -5% - 8%) 0.222
HighTermMonthSort 160.65 (14.7%) 164.05
(14.0%) 2.1% ( -23% - 36%) 0.641
OrHighMedDayTaxoFacets 15.46 (8.0%) 15.82
(9.0%) 2.3% ( -13% - 21%) 0.393
LowIntervalsOrdered 67.72 (6.2%) 69.70
(7.8%) 2.9% ( -10% - 17%) 0.188
TermDTSort 140.38 (14.3%) 144.53
(15.1%) 3.0% ( -23% - 37%) 0.525
MedIntervalsOrdered 30.74 (7.2%) 31.79
(8.9%) 3.4% ( -11% - 21%) 0.186
HighIntervalsOrdered 23.08 (9.6%) 24.19
(11.4%) 4.8% ( -14% - 28%) 0.151
BrowseRandomLabelTaxoFacets 12.83 (10.3%) 15.91
(56.9%) 24.0% ( -39% - 101%) 0.064
BrowseDateTaxoFacets 14.28 (13.0%) 18.66
(68.0%) 30.7% ( -44% - 128%) 0.047
BrowseDayOfYearTaxoFacets 14.37 (13.1%) 18.92
(70.0%) 31.7% ( -45% - 132%) 0.047
BrowseMonthTaxoFacets 16.23 (12.6%) 24.57
(66.4%) 51.4% ( -24% - 149%) 0.001
{code}
baseline
{code:java}
5.48% 23030
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#nextPosition()
4.31% 18110
org.apache.lucene.queries.spans.NearSpansOrdered#stretchToOrder()
3.68% 15450
org.apache.lucene.util.packed.DirectReader$DirectPackedReader20#get()
3.65% 15362
org.apache.lucene.queries.spans.TermSpans#nextStartPosition()
3.23% 13569
org.apache.lucene.facet.sortedset.SortedSetDocValuesFacetCounts#countOneSegment()
2.66% 11187
org.apache.lucene.queries.spans.SpanScorer#setFreqCurrentDoc()
2.62% 11023
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#skipPositions()
2.15% 9056
org.apache.lucene.queries.spans.NearSpansOrdered#nextStartPosition()
2.13% 8934
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$DenseNumericDocValues#nextDoc()
1.86% 7818
org.apache.lucene.facet.taxonomy.IntTaxonomyFacets#increment()
1.80% 7552
org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts#countAll()
1.67% 7024 jdk.internal.misc.Unsafe#convEndian()
1.63% 6860
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$20#ordValue()
1.56% 6576
org.apache.lucene.util.packed.DirectReader$DirectPackedReader4#get()
1.54% 6461 java.nio.Buffer#checkIndex()
1.45% 6113 org.apache.lucene.search.ConjunctionDISI#doNext()
1.41% 5947
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$4#longValue()
1.33% 5590
org.apache.lucene.store.ByteBufferGuard#ensureValid()
1.28% 5377
org.apache.lucene.queries.intervals.OrderedIntervalsSource$OrderedIntervalIterator#nextInterval()
1.25% 5273
org.apache.lucene.queries.spans.NearSpansOrdered#twoPhaseCurrentDocMatches()
1.16% 4877
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#advance()
1.16% 4868
org.apache.lucene.util.packed.DirectReader$DirectPackedReader12#get()
1.15% 4855
org.apache.lucene.queries.spans.TermSpans#endPosition()
1.15% 4852 java.nio.Buffer#scope()
1.15% 4838
org.apache.lucene.search.similarities.BM25Similarity$BM25Scorer#score()
1.14% 4775 java.nio.DirectByteBuffer#ix()
1.13% 4735
org.apache.lucene.queries.spans.NearSpansOrdered#advancePosition()
1.01% 4229 org.apache.lucene.store.ByteBufferGuard#getByte()
1.00% 4223
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockImpactsPostingsEnum#advance()
0.97% 4065
jdk.internal.misc.ScopedMemoryAccess#getByteInternal()
{code}
candidate
{code:java}
5.15% 21244
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#nextPosition()
4.85% 19998
org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts#countAll()
3.78% 15561
org.apache.lucene.util.packed.DirectReader$DirectPackedReader20#get()
3.74% 15406
org.apache.lucene.queries.spans.NearSpansOrdered#stretchToOrder()
3.41% 14066
org.apache.lucene.queries.spans.TermSpans#nextStartPosition()
3.27% 13463
org.apache.lucene.facet.sortedset.SortedSetDocValuesFacetCounts#countOneSegment()
2.88% 11859
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#skipPositions()
2.75% 11352
org.apache.lucene.queries.spans.SpanScorer#setFreqCurrentDoc()
2.04% 8424
org.apache.lucene.queries.spans.NearSpansOrdered#nextStartPosition()
1.72% 7102
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$20#ordValue()
1.69% 6967 jdk.internal.misc.Unsafe#convEndian()
1.57% 6485
org.apache.lucene.util.packed.DirectReader$DirectPackedReader4#get()
1.43% 5878 java.nio.Buffer#checkIndex()
1.41% 5813 org.apache.lucene.search.ConjunctionDISI#doNext()
1.34% 5535
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$EverythingEnum#advance()
1.28% 5269
org.apache.lucene.store.ByteBufferGuard#ensureValid()
1.24% 5122
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$4#longValue()
1.21% 4992
jdk.internal.misc.ScopedMemoryAccess#getByteInternal()
1.21% 4981
org.apache.lucene.queries.intervals.OrderedIntervalsSource$OrderedIntervalIterator#nextInterval()
1.17% 4809 java.nio.DirectByteBuffer#ix()
1.12% 4628
org.apache.lucene.queries.spans.NearSpansOrdered#advancePosition()
1.12% 4601
org.apache.lucene.search.similarities.BM25Similarity$BM25Scorer#score()
1.11% 4585 org.apache.lucene.store.ByteBufferGuard#getByte()
1.11% 4575
org.apache.lucene.util.packed.DirectReader$DirectPackedReader12#get()
1.07% 4417 org.apache.lucene.codecs.lucene90.ForUtil#expand8()
1.05% 4332 java.nio.Buffer#scope()
1.02% 4195
org.apache.lucene.queries.spans.NearSpansOrdered#twoPhaseCurrentDocMatches()
1.01% 4150
org.apache.lucene.codecs.lucene90.Lucene90DocValuesProducer$20#nextDoc()
0.99% 4101
org.apache.lucene.queries.spans.TermSpans#endPosition()
0.99% 4065
org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockImpactsPostingsEnum#advance()
{code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
