Skip to content

[core] Update writer/reader benchmark for bloom filter #4350

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JingsongLi merged 1 commit into from
Oct 21, 2024
Merged

[core] Update writer/reader benchmark for bloom filter #4350

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ...-benchmarks/src/test/java/org/apache/paimon/benchmark/lookup/AbstractLookupBenchmark.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,6 @@ private BloomFilter.Builder createBloomFiler(boolean enabled) {
if (!enabled) {
return null;
}
return BloomFilter.builder(100, 0.01);
return BloomFilter.builder(5000000, 0.01);
}
}
31 changes: 26 additions & 5 deletions ...ro-benchmarks/src/test/java/org/apache/paimon/benchmark/lookup/LookupReaderBenchmark.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,14 +62,25 @@ public static List<List<Object>> getVarSeg() {
return getCountBloomList();
}

/** Query data based on some keys that are definitely stored. */
@TestTemplate
void testLookupReader() throws IOException {
readLookupDataBenchmark(
generateSequenceInputs(0, recordCount),
generateRandomInputs(0, recordCount, QUERY_KEY_COUNT));
generateRandomInputs(0, recordCount, QUERY_KEY_COUNT),
false);
}

private void readLookupDataBenchmark(byte[][] inputs, byte[][] randomInputs)
/** Query data based on some keys that are definitely not stored. */
@TestTemplate
void testLookupReaderMiss() throws IOException {
readLookupDataBenchmark(
generateSequenceInputs(0, recordCount),
generateRandomInputs(recordCount + 1, recordCount * 2, QUERY_KEY_COUNT),
true);
}

private void readLookupDataBenchmark(byte[][] inputs, byte[][] randomInputs, boolean nullResult)
throws IOException {
Benchmark benchmark =
new Benchmark("reader-" + randomInputs.length, randomInputs.length)
Expand All @@ -91,7 +102,12 @@ private void readLookupDataBenchmark(byte[][] inputs, byte[][] randomInputs)
5,
() -> {
try {
readData(options, randomInputs, pair.getLeft(), pair.getRight());
readData(
options,
randomInputs,
pair.getLeft(),
pair.getRight(),
nullResult);
} catch (IOException e) {
throw new RuntimeException(e);
}
Expand All @@ -106,7 +122,8 @@ private void readData(
CoreOptions options,
byte[][] randomInputs,
String filePath,
LookupStoreFactory.Context context)
LookupStoreFactory.Context context,
boolean nullResult)
throws IOException {
LookupStoreFactory factory =
LookupStoreFactory.create(
Expand All @@ -118,7 +135,11 @@ private void readData(
File file = new File(filePath);
LookupStoreReader reader = factory.createReader(file, context);
for (byte[] input : randomInputs) {
assertThat(reader.lookup(input)).isNotNull();
if (nullResult) {
assertThat(reader.lookup(input)).isNull();
} else {
assertThat(reader.lookup(input)).isNotNull();
}
}
reader.close();
}
Expand Down