Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Save allocating some zero length byte arrays (#13608) 

Something I found in a heap dump. For large numbers of `FieldReader`
where the minimum term is an empty string, we allocate MBs worth of
empty `byte[]` in ES. Worth adding the conditional here I think.
This commit is contained in:
Armin Braun 2024-07-24 21:53:30 +02:00 committed by GitHub
parent acbd714140
commit 4c1d50d8e8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/core/src/java/org/apache/lucene/codecs/lucene90/blocktree/Lucene90BlockTreeTermsReader.java
View File

@ -270,9 +270,8 @@ public final class Lucene90BlockTreeTermsReader extends FieldsProducer {
throw new CorruptIndexException("invalid bytes length: " + numBytes, in);
}
BytesRef bytes = new BytesRef();
BytesRef bytes = new BytesRef(numBytes);
bytes.length = numBytes;
bytes.bytes = new byte[numBytes];
in.readBytes(bytes.bytes, 0, numBytes);
return bytes;

4
lucene/core/src/java/org/apache/lucene/util/BytesRef.java
View File

@ -68,7 +68,7 @@ public final class BytesRef implements Comparable<BytesRef>, Cloneable {
* both be zero.
*/
public BytesRef(int capacity) {
this.bytes = new byte[capacity];
this.bytes = capacity == 0 ? EMPTY_BYTES : new byte[capacity];
}
/**
@ -77,7 +77,7 @@ public final class BytesRef implements Comparable<BytesRef>, Cloneable {
* @param text This must be well-formed unicode text, with no unpaired surrogates.
*/
public BytesRef(CharSequence text) {
this(new byte[UnicodeUtil.maxUTF8Length(text.length())]);
this(UnicodeUtil.maxUTF8Length(text.length()));
length = UnicodeUtil.UTF16toUTF8(text, 0, text.length(), bytes);
}