From d41cf6ac9f791b431762892b4ce8e85419e44eba Mon Sep 17 00:00:00 2001
From: Nhat Nguyen <nhat.nguyen@elastic.co>
Date: Sat, 8 Dec 2018 21:24:36 -0500
Subject: [PATCH] Use delCount of SegmentInfos to calculate numDocs (#36323)

Today, we iterate the bitset of hardLiveDocs to calculate the number of
live docs. This calculation might be expensive if we enable soft-deletes
(by default) for old indices whose soft-deletes was disabled previously
and had hard-deletes.

Once soft-deletes is enabled, we no longer hard-update or hard-delete
documents directly. We have hard-deletes in two scenarios: (1) from old
segments where soft-deletes was disabled, (2) when IndexWriter hits
non-aborted exceptions. These two cases, IW flushes SegmentInfos before
exposing the hard-deletes; thus we can use the hard-delete count of
SegmentInfos.
---
 .../elasticsearch/common/lucene/Lucene.java   | 28 +++++++++++++------
 .../index/engine/InternalEngine.java          |  5 ++++
 2 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/server/src/main/java/org/elasticsearch/common/lucene/Lucene.java b/server/src/main/java/org/elasticsearch/common/lucene/Lucene.java
index f515db43ab9..fd9d63ea225 100644
--- a/server/src/main/java/org/elasticsearch/common/lucene/Lucene.java
+++ b/server/src/main/java/org/elasticsearch/common/lucene/Lucene.java
@@ -956,18 +956,17 @@ public class Lucene {
             super(in, new SubReaderWrapper() {
                 @Override
                 public LeafReader wrap(LeafReader leaf) {
-                    SegmentReader segmentReader = segmentReader(leaf);
-                    Bits hardLiveDocs = segmentReader.getHardLiveDocs();
+                    final SegmentReader segmentReader = segmentReader(leaf);
+                    final Bits hardLiveDocs = segmentReader.getHardLiveDocs();
                     if (hardLiveDocs == null) {
                         return new LeafReaderWithLiveDocs(leaf, null, leaf.maxDoc());
                     }
-                    // TODO: Can we avoid calculate numDocs by using SegmentReader#getSegmentInfo with LUCENE-8458?
-                    int numDocs = 0;
-                    for (int i = 0; i < hardLiveDocs.length(); i++) {
-                        if (hardLiveDocs.get(i)) {
-                            numDocs++;
-                        }
-                    }
+                    // Once soft-deletes is enabled, we no longer hard-update or hard-delete documents directly.
+                    // Two scenarios that we have hard-deletes: (1) from old segments where soft-deletes was disabled,
+                    // (2) when IndexWriter hits non-aborted exceptions. These two cases, IW flushes SegmentInfos
+                    // before exposing the hard-deletes, thus we can use the hard-delete count of SegmentInfos.
+                    final int numDocs = segmentReader.maxDoc() - segmentReader.getSegmentInfo().getDelCount();
+                    assert numDocs == popCount(hardLiveDocs) : numDocs + " != " + popCount(hardLiveDocs);
                     return new LeafReaderWithLiveDocs(segmentReader, hardLiveDocs, numDocs);
                 }
             });
@@ -984,6 +983,17 @@ public class Lucene {
         }
     }
 
+    private static int popCount(Bits bits) {
+        assert bits != null;
+        int onBits = 0;
+        for (int i = 0; i < bits.length(); i++) {
+            if (bits.get(i)) {
+                onBits++;
+            }
+        }
+        return onBits;
+    }
+
     /**
      * Returns a numeric docvalues which can be used to soft-delete documents.
      */
diff --git a/server/src/main/java/org/elasticsearch/index/engine/InternalEngine.java b/server/src/main/java/org/elasticsearch/index/engine/InternalEngine.java
index e29b6ca362d..4ac63dacca2 100644
--- a/server/src/main/java/org/elasticsearch/index/engine/InternalEngine.java
+++ b/server/src/main/java/org/elasticsearch/index/engine/InternalEngine.java
@@ -2585,6 +2585,11 @@ public class InternalEngine extends Engine {
             assert softDeleteEnabled : "Call #softUpdateDocuments but soft-deletes is disabled";
             return super.softUpdateDocuments(term, docs, softDeletes);
         }
+        @Override
+        public long tryDeleteDocument(IndexReader readerIn, int docID) {
+            assert false : "#tryDeleteDocument is not supported. See Lucene#DirectoryReaderWithAllLiveDocs";
+            throw new UnsupportedOperationException();
+        }
     }
 
     /**