Merge branch 'master' into fix_parameter

Author: dwdwqfwe

.github/workflows/build-thirdparty.yml

@@ -132,6 +132,8 @@ jobs:
           export PATH="$(find /usr/lib/jvm/java-8-openjdk* -maxdepth 1 -type d -name 'bin'):${PATH}"
           export JAVA_HOME="$(find /usr/lib/jvm/java-8-openjdk* -maxdepth 0)"
           export DORIS_TOOLCHAIN=gcc
+          export CMAKE_POLICY_VERSION_MINIMUM=3.10
+          export CUSTOM_CMAKE="/usr/local/bin/cmake"
 
           cd thirdparty
           ./build-thirdparty.sh -j "$(nproc)"
@@ -190,6 +192,8 @@ jobs:
       - name: Build
         run: |
           export MACOSX_DEPLOYMENT_TARGET=12.0
+          export CMAKE_POLICY_VERSION_MINIMUM=3.10
+          export CUSTOM_CMAKE="/usr/local/bin/cmake"
 
           cd thirdparty
           ./build-thirdparty.sh -j "$(nproc)"
@@ -248,6 +252,8 @@ jobs:
       - name: Build
         run: |
           export MACOSX_DEPLOYMENT_TARGET=12.0
+          export CMAKE_POLICY_VERSION_MINIMUM=3.10
+          export CUSTOM_CMAKE="/usr/local/bin/cmake"
 
           cd thirdparty
           ./build-thirdparty.sh -j "$(nproc)"

be/benchmark/benchmark_bit_pack.hpp

@@ -50,7 +50,7 @@ void bit_pack(const T* input, uint8_t in_num, int bit_width, uint8_t* output) {
 }
 
 static void BM_BitPack(benchmark::State& state) {
-    int w = state.range(0);
+    int w = (int)state.range(0);
     int n = 255;
 
     std::default_random_engine e;
@@ -67,15 +67,15 @@ static void BM_BitPack(benchmark::State& state) {
     for (auto _ : state) {
         benchmark::DoNotOptimize(test_data.data());
         benchmark::DoNotOptimize(output.data());
-        bit_pack(test_data.data(), n, w, output.data());
+        bit_pack(test_data.data(), (uint8_t)n, w, output.data());
         benchmark::ClobberMemory();
     }
 
     state.SetBytesProcessed(int64_t(state.iterations()) * size);
 }
 
 static void BM_BitPackOptimized(benchmark::State& state) {
-    int w = state.range(0);
+    int w = (int)state.range(0);
     int n = 255;
 
     std::default_random_engine e;
@@ -94,7 +94,7 @@ static void BM_BitPackOptimized(benchmark::State& state) {
     for (auto _ : state) {
         benchmark::DoNotOptimize(test_data.data());
         benchmark::DoNotOptimize(output.data());
-        forEncoder.bit_pack(test_data.data(), n, w, output.data());
+        forEncoder.bit_pack(test_data.data(), (uint8_t)n, w, output.data());
         benchmark::ClobberMemory();
     }
 

be/benchmark/benchmark_block_bloom_filter.hpp

@@ -0,0 +1,97 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+#include <benchmark/benchmark.h>
+
+#include "common/status.h"
+#include "exprs/block_bloom_filter.hpp"
+
+namespace doris {
+    static std::unique_ptr<BlockBloomFilter> create_bloom_filter(int batch, int log_space_bytes = 20) {
+        auto bloom_filter = std::make_unique<BlockBloomFilter>();
+        [[maybe_unused]] Status status = bloom_filter->init(log_space_bytes, 0);
+
+        for (int i = 0; i < batch; i++) {
+            bloom_filter->insert(i);
+        }
+
+        return bloom_filter;
+    }
+} // namespace doris
+
+static void BM_BBF_BucketInsert(benchmark::State& state) {
+    const int batch = static_cast<int>(state.range(0));
+    auto bf = doris::create_bloom_filter(batch);
+
+    for (auto _ : state) {
+        for (int i = 0; i < batch; i++) {
+            bf->insert(i);
+        }
+    }
+
+    state.SetItemsProcessed(state.iterations() * static_cast<int64_t>(batch));
+}
+
+static void BM_BBF_BucketFind_Hit(benchmark::State& state) {
+    const int batch = static_cast<int>(state.range(0));
+    auto bf = doris::create_bloom_filter(batch);
+
+    for (auto _ : state) {
+        bool acc = false;
+        for (int i = 0; i < batch; i++) {
+            acc ^= bf->find(i);
+        }
+        benchmark::DoNotOptimize(acc);
+    }
+    state.SetItemsProcessed(state.iterations() * static_cast<int64_t>(batch));
+}
+
+static void BM_BBF_BucketFind_Miss(benchmark::State& state) {
+    const int batch = static_cast<int>(state.range(0));
+    auto bf = doris::create_bloom_filter(batch);
+
+    for (auto _ : state) {
+        bool acc = false;
+        for (int i = 0; i < batch; i++) {
+            acc ^= bf->find(i + batch);
+        }
+        benchmark::DoNotOptimize(acc);
+    }
+    state.SetItemsProcessed(state.iterations() * static_cast<int64_t>(batch));
+}
+
+BENCHMARK(BM_BBF_BucketInsert)
+    ->Unit(benchmark::kNanosecond)
+    ->Arg(1 << 12)
+    ->Arg(1 << 15)
+    ->Arg(1 << 18)
+    ->Repetitions(5)
+    ->DisplayAggregatesOnly();
+BENCHMARK(BM_BBF_BucketFind_Hit)
+    ->Unit(benchmark::kNanosecond)
+    ->Arg(1 << 12)
+    ->Arg(1 << 15)
+    ->Arg(1 << 18)
+    ->Repetitions(5)
+    ->DisplayAggregatesOnly();
+BENCHMARK(BM_BBF_BucketFind_Miss)
+    ->Unit(benchmark::kNanosecond)
+    ->Arg(1 << 12)
+    ->Arg(1 << 15)
+    ->Arg(1 << 18)
+    ->Repetitions(5)
+    ->DisplayAggregatesOnly();

be/benchmark/benchmark_main.cpp

@@ -18,8 +18,10 @@
 #include <benchmark/benchmark.h>
 
 #include "benchmark_bit_pack.hpp"
+#include "benchmark_block_bloom_filter.hpp"
 #include "benchmark_fastunion.hpp"
 #include "benchmark_hll_merge.hpp"
+#include "benchmark_string.hpp"
 #include "binary_cast_benchmark.hpp"
 #include "vec/columns/column_string.h"
 #include "vec/core/block.h"