Skip to content

Commit

Permalink
Use getDocIdUpTo to determine lead impacts
Browse files Browse the repository at this point in the history 
            TaskQPS baseline      StdDevQPS my_modified_version      StdDev                Pct diff p-value
     CFQHighHigh        3.68      (6.5%)        2.66      (7.3%)  -27.8% ( -39% -  -14%) 0.000
      CFQHighLow       14.19      (7.9%)       11.31      (8.0%)  -20.3% ( -33% -   -4%) 0.000
      CFQHighMed       12.92      (9.5%)       10.41      (9.9%)  -19.4% ( -35% -    0%) 0.000
        PKLookup      104.92      (6.7%)      104.49      (9.0%)   -0.4% ( -15% -   16%) 0.869

= Candidate CPU JFR
PROFILE SUMMARY from 87201 events (total: 87201)
  tests.profile.mode=cpu
  tests.profile.count=30
  tests.profile.stacksize=1
  tests.profile.linenumbers=false
PERCENT       CPU SAMPLES   STACK
15.13%        13191         org.apache.lucene.sandbox.search.MultiNormsLeafSimScorer$MultiFieldNormValues#advanceExact()
7.42%         6466          org.apache.lucene.search.similarities.BM25Similarity$BM25Scorer#score()
7.29%         6354          org.apache.lucene.search.DisjunctionDISIApproximation#advance()
6.79%         5921          org.apache.lucene.search.DisiPriorityQueue#downHeap()
4.34%         3785          org.apache.lucene.search.DisiPriorityQueue#topList()
3.97%         3465          org.apache.lucene.search.TopScoreDocCollector$SimpleTopScoreDocCollector$1#collect()
3.85%         3360          org.apache.lucene.sandbox.search.CombinedFieldQuery$WeightedDisiWrapper#freq()
3.18%         2777          java.lang.Math#round()
3.01%         2624          org.apache.lucene.sandbox.search.CombinedFieldQuery$CombinedFieldScorer#freq()
3.01%         2624          org.apache.lucene.search.DisiPriorityQueue#top()
2.33%         2036          org.apache.lucene.sandbox.search.CombinedFieldQuery$CombinedFieldScorer#score()
2.20%         1917          org.apache.lucene.sandbox.search.MultiNormsLeafSimScorer#getNormValue()
2.07%         1809          org.apache.lucene.util.SmallFloat#longToInt4()
1.81%         1580          org.apache.lucene.codecs.lucene90.Lucene90NormsProducer$3#longValue()
1.78%         1555          org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockImpactsDocsEnum#advance()
1.77%         1545          org.apache.lucene.store.ByteBufferGuard#ensureValid()
1.51%         1316          org.apache.lucene.codecs.lucene90.Lucene90PostingsReader#findFirstGreater()
1.39%         1210          org.apache.lucene.search.DisiPriorityQueue#updateTop()
1.29%         1124          org.apache.lucene.search.ImpactsDISI#docID()
1.22%         1063          jdk.internal.misc.Unsafe#getByte()
1.19%         1037          org.apache.lucene.store.ByteBufferGuard#getByte()
1.08%         938           org.apache.lucene.search.DisiPriorityQueue#prepend()
0.97%         849           org.apache.lucene.search.Weight$DefaultBulkScorer#scoreAll()
0.86%         750           org.apache.lucene.codecs.MultiLevelSkipListReader#skipTo()
0.82%         717           org.apache.lucene.util.SmallFloat#intToByte4()
0.78%         683           java.lang.Math#toIntExact()
0.62%         540           org.apache.lucene.codecs.lucene90.PForUtil#decode()
0.61%         529           org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockImpactsDocsEnum#freq()
0.51%         441           org.apache.lucene.search.ImpactsDISI#nextDoc()
0.50%         435           org.apache.lucene.search.ImpactsDISI#advanceTarget()

= Baseline CPU JFR
PROFILE SUMMARY from 81578 events (total: 81578)
  tests.profile.mode=cpu
  tests.profile.count=30
  tests.profile.stacksize=1
  tests.profile.linenumbers=false
PERCENT       CPU SAMPLES   STACK
16.38%        13363         org.apache.lucene.sandbox.search.MultiNormsLeafSimScorer$MultiFieldNormValues#advanceExact()
8.67%         7073          org.apache.lucene.search.similarities.BM25Similarity$BM25Scorer#score()
8.05%         6569          org.apache.lucene.search.DisjunctionDISIApproximation#nextDoc()
6.50%         5305          org.apache.lucene.search.DisiPriorityQueue#downHeap()
5.17%         4220          org.apache.lucene.sandbox.search.CombinedFieldQuery$CombinedFieldScorer#freq()
4.40%         3587          org.apache.lucene.search.TopScoreDocCollector$SimpleTopScoreDocCollector$1#collect()
4.30%         3505          org.apache.lucene.search.DisiPriorityQueue#topList()
3.37%         2751          java.lang.Math#round()
2.77%         2263          org.apache.lucene.search.DisiPriorityQueue#top()
2.64%         2156          org.apache.lucene.sandbox.search.CombinedFieldQuery$WeightedDisiWrapper#freq()
2.62%         2135          org.apache.lucene.sandbox.search.CombinedFieldQuery$CombinedFieldScorer#score()
2.12%         1729          org.apache.lucene.sandbox.search.MultiNormsLeafSimScorer#getNormValue()
2.11%         1723          org.apache.lucene.util.SmallFloat#longToInt4()
2.06%         1678          org.apache.lucene.search.Weight$DefaultBulkScorer#scoreAll()
2.01%         1640          org.apache.lucene.store.ByteBufferGuard#ensureValid()
1.77%         1442          org.apache.lucene.codecs.lucene90.Lucene90NormsProducer$3#longValue()
1.62%         1325          org.apache.lucene.search.DisiPriorityQueue#updateTop()
1.26%         1028          org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockDocsEnum#nextDoc()
1.10%         899           java.lang.Math#toIntExact()
1.10%         898           org.apache.lucene.util.SmallFloat#intToByte4()
1.09%         888           org.apache.lucene.codecs.lucene90.Lucene90PostingsReader$BlockDocsEnum#freq()
1.06%         864           org.apache.lucene.store.ByteBufferGuard#getByte()
0.80%         652           jdk.internal.misc.Unsafe#getByte()
0.74%         605           org.apache.lucene.codecs.lucene90.PForUtil#decode()
0.68%         552           org.apache.lucene.search.DisiPriorityQueue#prepend()
0.60%         492           org.apache.lucene.codecs.lucene90.PForUtil#decodeAndPrefixSum()
0.55%         451           java.io.RandomAccessFile#readBytes()
0.38%         314           org.apache.lucene.codecs.lucene90.PForUtil#innerPrefixSum32()
0.38%         307           org.apache.lucene.codecs.lucene90.ForUtil#expand8()
0.32%         260           org.apache.lucene.codecs.lucene90.PForUtil#expand32()
  • Loading branch information
@zacharymorn
zacharymorn committed Dec 2, 2021
1 parent 808fec2 commit 75c5b04
Showing 1 changed file with 8 additions and 8 deletions.
16 changes: 8 additions & 8 deletions lucene/sandbox/src/java/org/apache/lucene/sandbox/search/CombinedFieldQuery.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -520,7 +520,7 @@ public Impacts getImpacts() throws IOException {
fieldImpacts.put(field, impacts);

if (field.equals(maxWeightField)) {
long minCost = Long.MAX_VALUE;
// long minCost = Long.MAX_VALUE;
for (int i = 0; i < impactsEnums.length; ++i) {
ImpactsEnum impactsEnum = impactsEnums[i];
impacts[i] = impactsEnum.getImpacts();
Expand All @@ -530,15 +530,15 @@ public Impacts getImpacts() throws IOException {
// this may have the result of getting larger upTo bound, as low doc freq (cost)
// term may
// also have large gap in doc ids
if (tmpLead == null || impactsEnum.cost() < minCost) {
minCost = impactsEnum.cost();
// if (tmpLead == null || impactsEnum.cost() < minCost) {
// minCost = impactsEnum.cost();
// tmpLead = impacts[i];
// }

if (tmpLead == null || impacts[i].getDocIdUpTo(0) <
tmpLead.getDocIdUpTo(0)) {
tmpLead = impacts[i];
}

// if (tmpLead == null || impacts.getDocIdUpTo(0) <
// tmpLead.getDocIdUpTo(0)) {
// tmpLead = impacts[i];
// }
}
} else {
// find the impact that has the lowest next boundary for this field
Expand Down

0 comments on commit 75c5b04

Please sign in to comment.