rocksdb/table/cuckoo_table_builder_test.cc

634 lines
26 KiB
C++
Raw Normal View History

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#ifndef ROCKSDB_LITE
#include <vector>
#include <string>
#include <map>
#include <utility>
#include "table/meta_blocks.h"
#include "table/cuckoo_table_builder.h"
#include "util/file_reader_writer.h"
#include "util/testharness.h"
#include "util/testutil.h"
namespace rocksdb {
extern const uint64_t kCuckooTableMagicNumber;
namespace {
std::unordered_map<std::string, std::vector<uint64_t>> hash_map;
uint64_t GetSliceHash(const Slice& s, uint32_t index,
uint64_t /*max_num_buckets*/) {
return hash_map[s.ToString()][index];
}
} // namespace
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
class CuckooBuilderTest : public testing::Test {
public:
CuckooBuilderTest() {
env_ = Env::Default();
Options options;
options.allow_mmap_reads = true;
env_options_ = EnvOptions(options);
}
void CheckFileContents(const std::vector<std::string>& keys,
const std::vector<std::string>& values,
const std::vector<uint64_t>& expected_locations,
std::string expected_unused_bucket, uint64_t expected_table_size,
uint32_t expected_num_hash_func, bool expected_is_last_level,
uint32_t expected_cuckoo_block_size = 1) {
// Read file
unique_ptr<RandomAccessFile> read_file;
ASSERT_OK(env_->NewRandomAccessFile(fname, &read_file, env_options_));
uint64_t read_file_size;
ASSERT_OK(env_->GetFileSize(fname, &read_file_size));
// @lint-ignore TXT2 T25377293 Grandfathered in
Options options;
options.allow_mmap_reads = true;
ImmutableCFOptions ioptions(options);
// Assert Table Properties.
TableProperties* props = nullptr;
unique_ptr<RandomAccessFileReader> file_reader(
new RandomAccessFileReader(std::move(read_file), fname));
ASSERT_OK(ReadTableProperties(file_reader.get(), read_file_size,
kCuckooTableMagicNumber, ioptions,
&props, true /* compression_type_missing */));
// Check unused bucket.
std::string unused_key = props->user_collected_properties[
CuckooTablePropertyNames::kEmptyKey];
ASSERT_EQ(expected_unused_bucket.substr(0,
props->fixed_key_len), unused_key);
uint64_t value_len_found =
*reinterpret_cast<const uint64_t*>(props->user_collected_properties[
CuckooTablePropertyNames::kValueLength].data());
ASSERT_EQ(values.empty() ? 0 : values[0].size(), value_len_found);
ASSERT_EQ(props->raw_value_size, values.size()*value_len_found);
const uint64_t table_size =
*reinterpret_cast<const uint64_t*>(props->user_collected_properties[
CuckooTablePropertyNames::kHashTableSize].data());
ASSERT_EQ(expected_table_size, table_size);
const uint32_t num_hash_func_found =
*reinterpret_cast<const uint32_t*>(props->user_collected_properties[
CuckooTablePropertyNames::kNumHashFunc].data());
ASSERT_EQ(expected_num_hash_func, num_hash_func_found);
const uint32_t cuckoo_block_size =
*reinterpret_cast<const uint32_t*>(props->user_collected_properties[
CuckooTablePropertyNames::kCuckooBlockSize].data());
ASSERT_EQ(expected_cuckoo_block_size, cuckoo_block_size);
const bool is_last_level_found =
*reinterpret_cast<const bool*>(props->user_collected_properties[
CuckooTablePropertyNames::kIsLastLevel].data());
ASSERT_EQ(expected_is_last_level, is_last_level_found);
ASSERT_EQ(props->num_entries, keys.size());
ASSERT_EQ(props->fixed_key_len, keys.empty() ? 0 : keys[0].size());
ASSERT_EQ(props->data_size, expected_unused_bucket.size() *
(expected_table_size + expected_cuckoo_block_size - 1));
ASSERT_EQ(props->raw_key_size, keys.size()*props->fixed_key_len);
ASSERT_EQ(props->column_family_id, 0);
ASSERT_EQ(props->column_family_name, kDefaultColumnFamilyName);
delete props;
// Check contents of the bucket.
std::vector<bool> keys_found(keys.size(), false);
size_t bucket_size = expected_unused_bucket.size();
for (uint32_t i = 0; i < table_size + cuckoo_block_size - 1; ++i) {
Slice read_slice;
ASSERT_OK(file_reader->Read(i * bucket_size, bucket_size, &read_slice,
nullptr));
size_t key_idx =
std::find(expected_locations.begin(), expected_locations.end(), i) -
expected_locations.begin();
if (key_idx == keys.size()) {
// i is not one of the expected locations. Empty bucket.
if (read_slice.data() == nullptr) {
ASSERT_EQ(0, expected_unused_bucket.size());
} else {
ASSERT_EQ(read_slice.compare(expected_unused_bucket), 0);
}
} else {
keys_found[key_idx] = true;
ASSERT_EQ(read_slice.compare(keys[key_idx] + values[key_idx]), 0);
}
}
for (auto key_found : keys_found) {
// Check that all keys wereReader found.
ASSERT_TRUE(key_found);
}
}
std::string GetInternalKey(Slice user_key, bool zero_seqno) {
IterKey ikey;
ikey.SetInternalKey(user_key, zero_seqno ? 0 : 1000, kTypeValue);
return ikey.GetInternalKey().ToString();
}
Improve Cuckoo Table Reader performance. Inlined hash function and number of buckets a power of two. Summary: Use inlined hash functions instead of function pointer. Make number of buckets a power of two and use bitwise and instead of mod. After these changes, we get almost 50% improvement in performance. Results: With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.231us (4.3 Mqps) with batch size of 0 Time taken per op is 0.229us (4.4 Mqps) with batch size of 0 Time taken per op is 0.185us (5.4 Mqps) with batch size of 0 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.108us (9.3 Mqps) with batch size of 10 Time taken per op is 0.100us (10.0 Mqps) with batch size of 10 Time taken per op is 0.103us (9.7 Mqps) with batch size of 10 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.101us (9.9 Mqps) with batch size of 25 Time taken per op is 0.098us (10.2 Mqps) with batch size of 25 Time taken per op is 0.097us (10.3 Mqps) with batch size of 25 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.100us (10.0 Mqps) with batch size of 50 Time taken per op is 0.097us (10.3 Mqps) with batch size of 50 Time taken per op is 0.097us (10.3 Mqps) with batch size of 50 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.102us (9.8 Mqps) with batch size of 100 Time taken per op is 0.098us (10.2 Mqps) with batch size of 100 Time taken per op is 0.115us (8.7 Mqps) with batch size of 100 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.201us (5.0 Mqps) with batch size of 0 Time taken per op is 0.155us (6.5 Mqps) with batch size of 0 Time taken per op is 0.152us (6.6 Mqps) with batch size of 0 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.089us (11.3 Mqps) with batch size of 10 Time taken per op is 0.084us (11.9 Mqps) with batch size of 10 Time taken per op is 0.086us (11.6 Mqps) with batch size of 10 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.087us (11.5 Mqps) with batch size of 25 Time taken per op is 0.085us (11.7 Mqps) with batch size of 25 Time taken per op is 0.093us (10.8 Mqps) with batch size of 25 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.094us (10.6 Mqps) with batch size of 50 Time taken per op is 0.094us (10.7 Mqps) with batch size of 50 Time taken per op is 0.093us (10.8 Mqps) with batch size of 50 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.092us (10.9 Mqps) with batch size of 100 Time taken per op is 0.089us (11.2 Mqps) with batch size of 100 Time taken per op is 0.088us (11.3 Mqps) with batch size of 100 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.154us (6.5 Mqps) with batch size of 0 Time taken per op is 0.168us (6.0 Mqps) with batch size of 0 Time taken per op is 0.190us (5.3 Mqps) with batch size of 0 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.081us (12.4 Mqps) with batch size of 10 Time taken per op is 0.077us (13.0 Mqps) with batch size of 10 Time taken per op is 0.083us (12.1 Mqps) with batch size of 10 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.077us (13.0 Mqps) with batch size of 25 Time taken per op is 0.073us (13.7 Mqps) with batch size of 25 Time taken per op is 0.073us (13.7 Mqps) with batch size of 25 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.076us (13.1 Mqps) with batch size of 50 Time taken per op is 0.072us (13.8 Mqps) with batch size of 50 Time taken per op is 0.072us (13.8 Mqps) with batch size of 50 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.077us (13.0 Mqps) with batch size of 100 Time taken per op is 0.074us (13.6 Mqps) with batch size of 100 Time taken per op is 0.073us (13.6 Mqps) with batch size of 100 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.190us (5.3 Mqps) with batch size of 0 Time taken per op is 0.186us (5.4 Mqps) with batch size of 0 Time taken per op is 0.184us (5.4 Mqps) with batch size of 0 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.079us (12.7 Mqps) with batch size of 10 Time taken per op is 0.070us (14.2 Mqps) with batch size of 10 Time taken per op is 0.072us (14.0 Mqps) with batch size of 10 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.080us (12.5 Mqps) with batch size of 25 Time taken per op is 0.072us (14.0 Mqps) with batch size of 25 Time taken per op is 0.071us (14.1 Mqps) with batch size of 25 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.082us (12.1 Mqps) with batch size of 50 Time taken per op is 0.071us (14.1 Mqps) with batch size of 50 Time taken per op is 0.073us (13.6 Mqps) with batch size of 50 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.080us (12.5 Mqps) with batch size of 100 Time taken per op is 0.077us (13.0 Mqps) with batch size of 100 Time taken per op is 0.078us (12.8 Mqps) with batch size of 100 Test Plan: make check all make valgrind_check make asan_check Reviewers: sdong, ljin Reviewed By: ljin Subscribers: leveldb Differential Revision: https://reviews.facebook.net/D22539
2014-08-30 02:06:15 +00:00
uint64_t NextPowOf2(uint64_t num) {
uint64_t n = 2;
while (n <= num) {
n *= 2;
}
return n;
}
uint64_t GetExpectedTableSize(uint64_t num) {
return NextPowOf2(static_cast<uint64_t>(num / kHashTableRatio));
}
Env* env_;
EnvOptions env_options_;
std::string fname;
const double kHashTableRatio = 0.9;
};
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, SuccessWithEmptyFile) {
unique_ptr<WritableFile> writable_file;
Improve Cuckoo Table Reader performance. Inlined hash function and number of buckets a power of two. Summary: Use inlined hash functions instead of function pointer. Make number of buckets a power of two and use bitwise and instead of mod. After these changes, we get almost 50% improvement in performance. Results: With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.231us (4.3 Mqps) with batch size of 0 Time taken per op is 0.229us (4.4 Mqps) with batch size of 0 Time taken per op is 0.185us (5.4 Mqps) with batch size of 0 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.108us (9.3 Mqps) with batch size of 10 Time taken per op is 0.100us (10.0 Mqps) with batch size of 10 Time taken per op is 0.103us (9.7 Mqps) with batch size of 10 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.101us (9.9 Mqps) with batch size of 25 Time taken per op is 0.098us (10.2 Mqps) with batch size of 25 Time taken per op is 0.097us (10.3 Mqps) with batch size of 25 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.100us (10.0 Mqps) with batch size of 50 Time taken per op is 0.097us (10.3 Mqps) with batch size of 50 Time taken per op is 0.097us (10.3 Mqps) with batch size of 50 With 120000000 items, utilization is 89.41%, number of hash functions: 2. Time taken per op is 0.102us (9.8 Mqps) with batch size of 100 Time taken per op is 0.098us (10.2 Mqps) with batch size of 100 Time taken per op is 0.115us (8.7 Mqps) with batch size of 100 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.201us (5.0 Mqps) with batch size of 0 Time taken per op is 0.155us (6.5 Mqps) with batch size of 0 Time taken per op is 0.152us (6.6 Mqps) with batch size of 0 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.089us (11.3 Mqps) with batch size of 10 Time taken per op is 0.084us (11.9 Mqps) with batch size of 10 Time taken per op is 0.086us (11.6 Mqps) with batch size of 10 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.087us (11.5 Mqps) with batch size of 25 Time taken per op is 0.085us (11.7 Mqps) with batch size of 25 Time taken per op is 0.093us (10.8 Mqps) with batch size of 25 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.094us (10.6 Mqps) with batch size of 50 Time taken per op is 0.094us (10.7 Mqps) with batch size of 50 Time taken per op is 0.093us (10.8 Mqps) with batch size of 50 With 100000000 items, utilization is 74.51%, number of hash functions: 2. Time taken per op is 0.092us (10.9 Mqps) with batch size of 100 Time taken per op is 0.089us (11.2 Mqps) with batch size of 100 Time taken per op is 0.088us (11.3 Mqps) with batch size of 100 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.154us (6.5 Mqps) with batch size of 0 Time taken per op is 0.168us (6.0 Mqps) with batch size of 0 Time taken per op is 0.190us (5.3 Mqps) with batch size of 0 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.081us (12.4 Mqps) with batch size of 10 Time taken per op is 0.077us (13.0 Mqps) with batch size of 10 Time taken per op is 0.083us (12.1 Mqps) with batch size of 10 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.077us (13.0 Mqps) with batch size of 25 Time taken per op is 0.073us (13.7 Mqps) with batch size of 25 Time taken per op is 0.073us (13.7 Mqps) with batch size of 25 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.076us (13.1 Mqps) with batch size of 50 Time taken per op is 0.072us (13.8 Mqps) with batch size of 50 Time taken per op is 0.072us (13.8 Mqps) with batch size of 50 With 80000000 items, utilization is 59.60%, number of hash functions: 2. Time taken per op is 0.077us (13.0 Mqps) with batch size of 100 Time taken per op is 0.074us (13.6 Mqps) with batch size of 100 Time taken per op is 0.073us (13.6 Mqps) with batch size of 100 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.190us (5.3 Mqps) with batch size of 0 Time taken per op is 0.186us (5.4 Mqps) with batch size of 0 Time taken per op is 0.184us (5.4 Mqps) with batch size of 0 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.079us (12.7 Mqps) with batch size of 10 Time taken per op is 0.070us (14.2 Mqps) with batch size of 10 Time taken per op is 0.072us (14.0 Mqps) with batch size of 10 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.080us (12.5 Mqps) with batch size of 25 Time taken per op is 0.072us (14.0 Mqps) with batch size of 25 Time taken per op is 0.071us (14.1 Mqps) with batch size of 25 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.082us (12.1 Mqps) with batch size of 50 Time taken per op is 0.071us (14.1 Mqps) with batch size of 50 Time taken per op is 0.073us (13.6 Mqps) with batch size of 50 With 70000000 items, utilization is 52.15%, number of hash functions: 2. Time taken per op is 0.080us (12.5 Mqps) with batch size of 100 Time taken per op is 0.077us (13.0 Mqps) with batch size of 100 Time taken per op is 0.078us (12.8 Mqps) with batch size of 100 Test Plan: make check all make valgrind_check make asan_check Reviewers: sdong, ljin Reviewed By: ljin Subscribers: leveldb Differential Revision: https://reviews.facebook.net/D22539
2014-08-30 02:06:15 +00:00
fname = test::TmpDir() + "/EmptyFile";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, 4, 100,
BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
ASSERT_EQ(0UL, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
CheckFileContents({}, {}, {}, "", 2, 2, false);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WriteSuccessNoCollisionFullKey) {
uint32_t num_hash_fun = 4;
std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1, 2, 3}},
{user_keys[1], {1, 2, 3, 4}},
{user_keys[2], {2, 3, 4, 5}},
{user_keys[3], {3, 4, 5, 6}}};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
std::vector<std::string> keys;
for (auto& user_key : user_keys) {
keys.push_back(GetInternalKey(user_key, false));
}
uint64_t expected_table_size = GetExpectedTableSize(keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/NoCollisionFullKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(keys[i]), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = GetInternalKey("key00", true);
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 2, false);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionFullKey) {
uint32_t num_hash_fun = 4;
std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1, 2, 3}},
{user_keys[1], {0, 1, 2, 3}},
{user_keys[2], {0, 1, 2, 3}},
{user_keys[3], {0, 1, 2, 3}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
std::vector<std::string> keys;
for (auto& user_key : user_keys) {
keys.push_back(GetInternalKey(user_key, false));
}
uint64_t expected_table_size = GetExpectedTableSize(keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionFullKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(keys[i]), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = GetInternalKey("key00", true);
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 4, false);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionAndCuckooBlock) {
uint32_t num_hash_fun = 4;
std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1, 2, 3}},
{user_keys[1], {0, 1, 2, 3}},
{user_keys[2], {0, 1, 2, 3}},
{user_keys[3], {0, 1, 2, 3}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
std::vector<std::string> keys;
for (auto& user_key : user_keys) {
keys.push_back(GetInternalKey(user_key, false));
}
uint64_t expected_table_size = GetExpectedTableSize(keys.size());
unique_ptr<WritableFile> writable_file;
uint32_t cuckoo_block_size = 2;
fname = test::TmpDir() + "/WithCollisionFullKey2";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(
file_writer.get(), kHashTableRatio, num_hash_fun, 100,
BytewiseComparator(), cuckoo_block_size, false, false, GetSliceHash,
0 /* column_family_id */, kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(keys[i]), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = GetInternalKey("key00", true);
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 3, false, cuckoo_block_size);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WithCollisionPathFullKey) {
// Have two hash functions. Insert elements with overlapping hashes.
// Finally insert an element with hash value somewhere in the middle
// so that it displaces all the elements after that.
uint32_t num_hash_fun = 2;
std::vector<std::string> user_keys = {"key01", "key02", "key03",
"key04", "key05"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04", "v05"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1}},
{user_keys[1], {1, 2}},
{user_keys[2], {2, 3}},
{user_keys[3], {3, 4}},
{user_keys[4], {0, 2}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 3, 4, 2};
std::vector<std::string> keys;
for (auto& user_key : user_keys) {
keys.push_back(GetInternalKey(user_key, false));
}
uint64_t expected_table_size = GetExpectedTableSize(keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionPathFullKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(keys[i]), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = GetInternalKey("key00", true);
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 2, false);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WithCollisionPathFullKeyAndCuckooBlock) {
uint32_t num_hash_fun = 2;
std::vector<std::string> user_keys = {"key01", "key02", "key03",
"key04", "key05"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04", "v05"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1}},
{user_keys[1], {1, 2}},
{user_keys[2], {3, 4}},
{user_keys[3], {4, 5}},
{user_keys[4], {0, 3}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {2, 1, 3, 4, 0};
std::vector<std::string> keys;
for (auto& user_key : user_keys) {
keys.push_back(GetInternalKey(user_key, false));
}
uint64_t expected_table_size = GetExpectedTableSize(keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionPathFullKeyAndCuckooBlock";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 2, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(keys[i]), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = GetInternalKey("key00", true);
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 2, false, 2);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WriteSuccessNoCollisionUserKey) {
uint32_t num_hash_fun = 4;
std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1, 2, 3}},
{user_keys[1], {1, 2, 3, 4}},
{user_keys[2], {2, 3, 4, 5}},
{user_keys[3], {3, 4, 5, 6}}};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/NoCollisionUserKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(GetInternalKey(user_keys[i], true)), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = user_keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = "key00";
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(user_keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 2, true);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionUserKey) {
uint32_t num_hash_fun = 4;
std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1, 2, 3}},
{user_keys[1], {0, 1, 2, 3}},
{user_keys[2], {0, 1, 2, 3}},
{user_keys[3], {0, 1, 2, 3}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionUserKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(GetInternalKey(user_keys[i], true)), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = user_keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = "key00";
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(user_keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 4, true);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, WithCollisionPathUserKey) {
uint32_t num_hash_fun = 2;
std::vector<std::string> user_keys = {"key01", "key02", "key03",
"key04", "key05"};
std::vector<std::string> values = {"v01", "v02", "v03", "v04", "v05"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1}},
{user_keys[1], {1, 2}},
{user_keys[2], {2, 3}},
{user_keys[3], {3, 4}},
{user_keys[4], {0, 2}},
};
hash_map = std::move(hm);
std::vector<uint64_t> expected_locations = {0, 1, 3, 4, 2};
uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionPathUserKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
2, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(GetInternalKey(user_keys[i], true)), Slice(values[i]));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
size_t bucket_size = user_keys[0].size() + values[0].size();
ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
ASSERT_OK(builder.Finish());
ASSERT_OK(file_writer->Close());
ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
std::string expected_unused_bucket = "key00";
expected_unused_bucket += std::string(values[0].size(), 'a');
CheckFileContents(user_keys, values, expected_locations,
expected_unused_bucket, expected_table_size, 2, true);
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, FailWhenCollisionPathTooLong) {
// Have two hash functions. Insert elements with overlapping hashes.
// Finally try inserting an element with hash value somewhere in the middle
// and it should fail because the no. of elements to displace is too high.
uint32_t num_hash_fun = 2;
std::vector<std::string> user_keys = {"key01", "key02", "key03",
"key04", "key05"};
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{user_keys[0], {0, 1}},
{user_keys[1], {1, 2}},
{user_keys[2], {2, 3}},
{user_keys[3], {3, 4}},
{user_keys[4], {0, 1}},
};
hash_map = std::move(hm);
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/WithCollisionPathUserKey";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
2, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
for (uint32_t i = 0; i < user_keys.size(); i++) {
builder.Add(Slice(GetInternalKey(user_keys[i], false)), Slice("value"));
ASSERT_EQ(builder.NumEntries(), i + 1);
ASSERT_OK(builder.status());
}
ASSERT_TRUE(builder.Finish().IsNotSupported());
ASSERT_OK(file_writer->Close());
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(CuckooBuilderTest, FailWhenSameKeyInserted) {
// Need to have a temporary variable here as VS compiler does not currently
// support operator= with initializer_list as a parameter
std::unordered_map<std::string, std::vector<uint64_t>> hm = {
{"repeatedkey", {0, 1, 2, 3}}};
hash_map = std::move(hm);
uint32_t num_hash_fun = 4;
std::string user_key = "repeatedkey";
unique_ptr<WritableFile> writable_file;
fname = test::TmpDir() + "/FailWhenSameKeyInserted";
ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(writable_file), EnvOptions()));
CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
100, BytewiseComparator(), 1, false, false,
GetSliceHash, 0 /* column_family_id */,
kDefaultColumnFamilyName);
ASSERT_OK(builder.status());
builder.Add(Slice(GetInternalKey(user_key, false)), Slice("value1"));
ASSERT_EQ(builder.NumEntries(), 1u);
ASSERT_OK(builder.status());
builder.Add(Slice(GetInternalKey(user_key, true)), Slice("value2"));
ASSERT_EQ(builder.NumEntries(), 2u);
ASSERT_OK(builder.status());
ASSERT_TRUE(builder.Finish().IsNotSupported());
ASSERT_OK(file_writer->Close());
}
} // namespace rocksdb
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(git ls-files '*test\.cc') for file in $files do if grep -q "rocksdb::test::RunAllTests()" $file then if grep -Eq '^class \w+Test {' $file then perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file perl -pi -e 's/^(TEST)/${1}_F/g' $file fi perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
int main(int argc, char** argv) {
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}
#else
#include <stdio.h>
int main(int /*argc*/, char** /*argv*/) {
fprintf(stderr, "SKIPPED as Cuckoo table is not supported in ROCKSDB_LITE\n");
return 0;
}
#endif // ROCKSDB_LITE