rocksdb/db/compaction_job_test.cc

711 lines
25 KiB
C++
Raw Normal View History

// Copyright (c) 2013, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
#ifndef ROCKSDB_LITE
#include <algorithm>
#include <map>
#include <string>
#include <tuple>
#include "db/compaction_job.h"
#include "db/column_family.h"
#include "db/version_set.h"
#include "db/writebuffer.h"
#include "rocksdb/cache.h"
#include "rocksdb/db.h"
#include "rocksdb/options.h"
#include "table/mock_table.h"
#include "util/file_reader_writer.h"
#include "util/string_util.h"
#include "util/testharness.h"
#include "util/testutil.h"
#include "utilities/merge_operators.h"
namespace rocksdb {
namespace {
void VerifyInitializationOfCompactionJobStats(
const CompactionJobStats& compaction_job_stats) {
#if !defined(IOS_CROSS_COMPILE)
ASSERT_EQ(compaction_job_stats.elapsed_micros, 0U);
ASSERT_EQ(compaction_job_stats.num_input_records, 0U);
ASSERT_EQ(compaction_job_stats.num_input_files, 0U);
ASSERT_EQ(compaction_job_stats.num_input_files_at_output_level, 0U);
ASSERT_EQ(compaction_job_stats.num_output_records, 0U);
ASSERT_EQ(compaction_job_stats.num_output_files, 0U);
ASSERT_EQ(compaction_job_stats.is_manual_compaction, true);
ASSERT_EQ(compaction_job_stats.total_input_bytes, 0U);
ASSERT_EQ(compaction_job_stats.total_output_bytes, 0U);
ASSERT_EQ(compaction_job_stats.total_input_raw_key_bytes, 0U);
ASSERT_EQ(compaction_job_stats.total_input_raw_value_bytes, 0U);
ASSERT_EQ(compaction_job_stats.smallest_output_key_prefix[0], 0);
ASSERT_EQ(compaction_job_stats.largest_output_key_prefix[0], 0);
ASSERT_EQ(compaction_job_stats.num_records_replaced, 0U);
ASSERT_EQ(compaction_job_stats.num_input_deletion_records, 0U);
ASSERT_EQ(compaction_job_stats.num_expired_deletion_records, 0U);
ASSERT_EQ(compaction_job_stats.num_corrupt_keys, 0U);
#endif // !defined(IOS_CROSS_COMPILE)
}
} // namespace
// TODO(icanadi) Make it simpler once we mock out VersionSet
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' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 22:08:00 +01:00
class CompactionJobTest : public testing::Test {
public:
CompactionJobTest()
: env_(Env::Default()),
dbname_(test::TmpDir() + "/compaction_job_test"),
2014-11-14 22:42:13 +01:00
mutable_cf_options_(Options(), ImmutableCFOptions(Options())),
table_cache_(NewLRUCache(50000, 16)),
write_buffer_(db_options_.db_write_buffer_size),
versions_(new VersionSet(dbname_, &db_options_, env_options_,
table_cache_.get(), &write_buffer_,
&write_controller_)),
shutting_down_(false),
mock_table_factory_(new mock::MockTableFactory()) {
rocksdb: Replace ASSERT* with EXPECT* in functions that does not return void value Summary: gtest does not use exceptions to fail a unit test by design, and `ASSERT*`s are implemented using `return`. As a consequence we cannot use `ASSERT*` in a function that does not return `void` value ([[ https://code.google.com/p/googletest/wiki/AdvancedGuide#Assertion_Placement | 1]]), and have to fix our existing code. This diff does this in a generic way, with no manual changes. In order to detect all existing `ASSERT*` that are used in functions that doesn't return void value, I change the code to generate compile errors for such cases. In `util/testharness.h` I defined `EXPECT*` assertions, the same way as `ASSERT*`, and redefined `ASSERT*` to return `void`. Then executed: ```lang=bash % USE_CLANG=1 make all -j55 -k 2> build.log % perl -naF: -e 'print "-- -number=".$F[1]." ".$F[0]."\n" if /: error:/' \ build.log | xargs -L 1 perl -spi -e 's/ASSERT/EXPECT/g if $. == $number' % make format ``` After that I reverted back change to `ASSERT*` in `util/testharness.h`. But preserved introduced `EXPECT*`, which is the same as `ASSERT*`. This will be deleted once switched to gtest. This diff is independent and contains manual changes only in `util/testharness.h`. Test Plan: Make sure all tests are passing. ```lang=bash % USE_CLANG=1 make check ``` Reviewers: igor, lgalanis, sdong, yufei.zhu, rven, meyering Reviewed By: meyering Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33333
2015-03-17 04:52:32 +01:00
EXPECT_OK(env_->CreateDirIfMissing(dbname_));
db_options_.db_paths.emplace_back(dbname_,
std::numeric_limits<uint64_t>::max());
}
std::string GenerateFileName(uint64_t file_number) {
FileMetaData meta;
std::vector<DbPath> db_paths;
db_paths.emplace_back(dbname_, std::numeric_limits<uint64_t>::max());
meta.fd = FileDescriptor(file_number, 0, 0);
return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
}
std::string KeyStr(const std::string& user_key, const SequenceNumber seq_num,
const ValueType t) {
return InternalKey(user_key, seq_num, t).Encode().ToString();
}
void AddMockFile(const stl_wrappers::KVMap& contents, int level = 0) {
assert(contents.size() > 0);
bool first_key = true;
std::string smallest, largest;
InternalKey smallest_key, largest_key;
SequenceNumber smallest_seqno = kMaxSequenceNumber;
SequenceNumber largest_seqno = 0;
for (auto kv : contents) {
ParsedInternalKey key;
std::string skey;
std::string value;
std::tie(skey, value) = kv;
ParseInternalKey(skey, &key);
smallest_seqno = std::min(smallest_seqno, key.sequence);
largest_seqno = std::max(largest_seqno, key.sequence);
if (first_key ||
cfd_->user_comparator()->Compare(key.user_key, smallest) < 0) {
smallest.assign(key.user_key.data(), key.user_key.size());
smallest_key.DecodeFrom(skey);
}
if (first_key ||
cfd_->user_comparator()->Compare(key.user_key, largest) > 0) {
largest.assign(key.user_key.data(), key.user_key.size());
largest_key.DecodeFrom(skey);
}
first_key = false;
}
uint64_t file_number = versions_->NewFileNumber();
EXPECT_OK(mock_table_factory_->CreateMockTable(
env_, GenerateFileName(file_number), std::move(contents)));
VersionEdit edit;
edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
smallest_seqno, largest_seqno, false);
mutex_.Lock();
versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
mutable_cf_options_, &edit, &mutex_);
mutex_.Unlock();
}
void SetLastSequence(const SequenceNumber sequence_number) {
versions_->SetLastSequence(sequence_number + 1);
}
// returns expected result after compaction
stl_wrappers::KVMap CreateTwoFiles(bool gen_corrupted_keys) {
auto expected_results = mock::MakeMockFile();
const int kKeysPerFile = 10000;
const int kCorruptKeysPerFile = 200;
const int kMatchingKeys = kKeysPerFile / 2;
SequenceNumber sequence_number = 0;
auto corrupt_id = [&](int id) {
return gen_corrupted_keys && id > 0 && id <= kCorruptKeysPerFile;
};
for (int i = 0; i < 2; ++i) {
auto contents = mock::MakeMockFile();
for (int k = 0; k < kKeysPerFile; ++k) {
auto key = ToString(i * kMatchingKeys + k);
auto value = ToString(i * kKeysPerFile + k);
InternalKey internal_key(key, ++sequence_number, kTypeValue);
Make Compaction class easier to use Summary: The goal of this diff is to make Compaction class easier to use. This should also make new compaction algorithms easier to write (like CompactFiles from @yhchiang and dynamic leveled and multi-leveled universal from @sdong). Here are couple of things demonstrating that Compaction class is hard to use: 1. we have two constructors of Compaction class 2. there's this thing called grandparents_, but it appears to only be setup for leveled compaction and not compactfiles 3. it's easy to introduce a subtle and dangerous bug like this: D36225 4. SetupBottomMostLevel() is hard to understand and it shouldn't be. See this comment: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction.cc#L236-L241. It also made it harder for @yhchiang to write CompactFiles, as evidenced by this: https://github.com/facebook/rocksdb/blob/afbafeaeaebfd27a0f3e992fee8e0c57d07658fa/db/compaction_picker.cc#L204-L210 The problem is that we create Compaction object, which holds a lot of state, and then pass it around to some functions. After those functions are done mutating, then we call couple of functions on Compaction object, like SetupBottommostLevel() and MarkFilesBeingCompacted(). It is very hard to see what's happening with all that Compaction's state while it's travelling across different functions. If you're writing a new PickCompaction() function you need to try really hard to understand what are all the functions you need to run on Compaction object and what state you need to setup. My proposed solution is to make important parts of Compaction immutable after construction. PickCompaction() should calculate compaction inputs and then pass them onto Compaction object once they are finalized. That makes it easy to create a new compaction -- just provide all the parameters to the constructor and you're done. No need to call confusing functions after you created your object. This diff doesn't fully achieve that goal, but it comes pretty close. Here are some of the changes: * have one Compaction constructor instead of two. * inputs_ is constant after construction * MarkFilesBeingCompacted() is now private to Compaction class and automatically called on construction/destruction. * SetupBottommostLevel() is gone. Compaction figures it out on its own based on the input. * CompactionPicker's functions are not passing around Compaction object anymore. They are only passing around the state that they need. Test Plan: make check make asan_check make valgrind_check Reviewers: rven, anthony, sdong, yhchiang Reviewed By: yhchiang Subscribers: sdong, yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36687
2015-04-11 00:01:54 +02:00
// This is how the key will look like once it's written in bottommost
// file
InternalKey bottommost_internal_key(key, 0, kTypeValue);
if (corrupt_id(k)) {
test::CorruptKeyType(&internal_key);
test::CorruptKeyType(&bottommost_internal_key);
}
contents.insert({ internal_key.Encode().ToString(), value });
if (i == 1 || k < kMatchingKeys || corrupt_id(k - kMatchingKeys)) {
expected_results.insert(
{ bottommost_internal_key.Encode().ToString(), value });
}
}
AddMockFile(contents);
}
SetLastSequence(sequence_number);
return expected_results;
}
void NewDB() {
VersionEdit new_db;
new_db.SetLogNumber(0);
new_db.SetNextFile(2);
new_db.SetLastSequence(0);
const std::string manifest = DescriptorFileName(dbname_, 1);
unique_ptr<WritableFile> file;
Status s = env_->NewWritableFile(
manifest, &file, env_->OptimizeForManifestWrite(env_options_));
ASSERT_OK(s);
unique_ptr<WritableFileWriter> file_writer(
new WritableFileWriter(std::move(file), env_options_));
{
log::Writer log(std::move(file_writer), 0, false);
std::string record;
new_db.EncodeTo(&record);
s = log.AddRecord(record);
}
ASSERT_OK(s);
// Make "CURRENT" file that points to the new manifest file.
s = SetCurrentFile(env_, dbname_, 1, nullptr);
std::vector<ColumnFamilyDescriptor> column_families;
cf_options_.table_factory = mock_table_factory_;
cf_options_.merge_operator = merge_op_;
cf_options_.compaction_filter = compaction_filter_.get();
column_families.emplace_back(kDefaultColumnFamilyName, cf_options_);
EXPECT_OK(versions_->Recover(column_families, false));
cfd_ = versions_->GetColumnFamilySet()->GetDefault();
}
void RunCompaction(const std::vector<std::vector<FileMetaData*>>& input_files,
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
const stl_wrappers::KVMap& expected_results,
const std::vector<SequenceNumber>& snapshots = {}) {
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
size_t num_input_files = 0;
std::vector<CompactionInputFiles> compaction_input_files;
for (size_t level = 0; level < input_files.size(); level++) {
auto level_files = input_files[level];
CompactionInputFiles compaction_level;
compaction_level.level = static_cast<int>(level);
compaction_level.files.insert(compaction_level.files.end(),
level_files.begin(), level_files.end());
compaction_input_files.push_back(compaction_level);
num_input_files += level_files.size();
}
Compaction compaction(cfd->current()->storage_info(),
*cfd->GetLatestMutableCFOptions(),
compaction_input_files, 1, 1024 * 1024, 10, 0,
kNoCompression, {}, true);
compaction.SetInputVersion(cfd->current());
LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
mutex_.Lock();
EventLogger event_logger(db_options_.info_log.get());
CompactionJob compaction_job(
0, &compaction, db_options_, env_options_, versions_.get(),
&shutting_down_, &log_buffer, nullptr, nullptr, nullptr, snapshots,
kMaxSequenceNumber, table_cache_, &event_logger, false, false, dbname_,
&compaction_job_stats_);
VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
compaction_job.Prepare();
mutex_.Unlock();
Status s;
s = compaction_job.Run();
ASSERT_OK(s);
mutex_.Lock();
ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions(),
&mutex_));
mutex_.Unlock();
if (expected_results.size() == 0) {
ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
} else {
ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
mock_table_factory_->AssertLatestFile(expected_results);
}
}
Env* env_;
std::string dbname_;
EnvOptions env_options_;
MutableCFOptions mutable_cf_options_;
std::shared_ptr<Cache> table_cache_;
WriteController write_controller_;
DBOptions db_options_;
ColumnFamilyOptions cf_options_;
WriteBuffer write_buffer_;
std::unique_ptr<VersionSet> versions_;
InstrumentedMutex mutex_;
std::atomic<bool> shutting_down_;
std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
CompactionJobStats compaction_job_stats_;
ColumnFamilyData* cfd_;
std::unique_ptr<CompactionFilter> compaction_filter_;
std::shared_ptr<MergeOperator> merge_op_;
};
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 22:08:00 +01:00
TEST_F(CompactionJobTest, Simple) {
NewDB();
auto expected_results = CreateTwoFiles(false);
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
auto files = cfd->current()->storage_info()->LevelFiles(0);
ASSERT_EQ(2U, files.size());
RunCompaction({ files }, expected_results);
}
TEST_F(CompactionJobTest, SimpleCorrupted) {
NewDB();
auto expected_results = CreateTwoFiles(true);
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
auto files = cfd->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
ASSERT_EQ(compaction_job_stats_.num_corrupt_keys, 400U);
}
TEST_F(CompactionJobTest, SimpleDeletion) {
NewDB();
auto file1 = mock::MakeMockFile({{KeyStr("c", 4U, kTypeDeletion), ""},
{KeyStr("c", 3U, kTypeValue), "val"}});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("b", 2U, kTypeValue), "val"},
{KeyStr("b", 1U, kTypeValue), "val"}});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{KeyStr("b", 0U, kTypeValue), "val"}});
SetLastSequence(4U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, SimpleOverwrite) {
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("a", 3U, kTypeValue), "val2"},
{KeyStr("b", 4U, kTypeValue), "val3"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"},
{KeyStr("b", 2U, kTypeValue), "val"}});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "val2"},
{KeyStr("b", 0U, kTypeValue), "val3"}});
SetLastSequence(4U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, SimpleNonLastLevel) {
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("a", 5U, kTypeValue), "val2"},
{KeyStr("b", 6U, kTypeValue), "val3"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("a", 3U, kTypeValue), "val"},
{KeyStr("b", 4U, kTypeValue), "val"}});
AddMockFile(file2, 1);
auto file3 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"},
{KeyStr("b", 2U, kTypeValue), "val"}});
AddMockFile(file3, 2);
// Because level 1 is not the last level, the sequence numbers of a and b
// cannot be set to 0
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 5U, kTypeValue), "val2"},
{KeyStr("b", 6U, kTypeValue), "val3"}});
SetLastSequence(6U);
auto lvl0_files = cfd_->current()->storage_info()->LevelFiles(0);
auto lvl1_files = cfd_->current()->storage_info()->LevelFiles(1);
RunCompaction({lvl0_files, lvl1_files}, expected_results);
}
TEST_F(CompactionJobTest, SimpleMerge) {
merge_op_ = MergeOperators::CreateStringAppendOperator();
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("a", 5U, kTypeMerge), "5"},
{KeyStr("a", 4U, kTypeMerge), "4"},
{KeyStr("a", 3U, kTypeValue), "3"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile(
{{KeyStr("b", 2U, kTypeMerge), "2"}, {KeyStr("b", 1U, kTypeValue), "1"}});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
{KeyStr("b", 0U, kTypeValue), "1,2"}});
SetLastSequence(5U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, NonAssocMerge) {
merge_op_ = MergeOperators::CreateStringAppendTESTOperator();
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("a", 5U, kTypeMerge), "5"},
{KeyStr("a", 4U, kTypeMerge), "4"},
{KeyStr("a", 3U, kTypeMerge), "3"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile(
{{KeyStr("b", 2U, kTypeMerge), "2"}, {KeyStr("b", 1U, kTypeMerge), "1"}});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
{KeyStr("b", 2U, kTypeMerge), "2"},
{KeyStr("b", 1U, kTypeMerge), "1"}});
SetLastSequence(5U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
// Filters merge operands with value 10.
TEST_F(CompactionJobTest, MergeOperandFilter) {
merge_op_ = MergeOperators::CreateUInt64AddOperator();
compaction_filter_.reset(new test::FilterNumber(10U));
NewDB();
auto file1 = mock::MakeMockFile(
{{KeyStr("a", 5U, kTypeMerge), test::EncodeInt(5U)},
{KeyStr("a", 4U, kTypeMerge), test::EncodeInt(10U)}, // Filtered
{KeyStr("a", 3U, kTypeMerge), test::EncodeInt(3U)}});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({
{KeyStr("b", 2U, kTypeMerge), test::EncodeInt(2U)},
{KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)} // Filtered
});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), test::EncodeInt(8U)},
{KeyStr("b", 2U, kTypeMerge), test::EncodeInt(2U)}});
SetLastSequence(5U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, FilterSomeMergeOperands) {
merge_op_ = MergeOperators::CreateUInt64AddOperator();
compaction_filter_.reset(new test::FilterNumber(10U));
NewDB();
auto file1 = mock::MakeMockFile(
{{KeyStr("a", 5U, kTypeMerge), test::EncodeInt(5U)},
{KeyStr("a", 4U, kTypeMerge), test::EncodeInt(10U)}, // Filtered
{KeyStr("a", 3U, kTypeValue), test::EncodeInt(5U)},
{KeyStr("d", 8U, kTypeMerge), test::EncodeInt(10U)}});
AddMockFile(file1);
auto file2 =
mock::MakeMockFile({{KeyStr("b", 2U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("c", 2U, kTypeMerge), test::EncodeInt(3U)},
{KeyStr("c", 1U, kTypeValue), test::EncodeInt(7U)},
{KeyStr("d", 1U, kTypeValue), test::EncodeInt(6U)}});
AddMockFile(file2);
auto file3 =
mock::MakeMockFile({{KeyStr("a", 1U, kTypeMerge), test::EncodeInt(3U)}});
AddMockFile(file3, 2);
auto expected_results = mock::MakeMockFile({
{KeyStr("a", 5U, kTypeValue), test::EncodeInt(10U)},
{KeyStr("c", 2U, kTypeValue), test::EncodeInt(10U)},
{KeyStr("d", 1U, kTypeValue), test::EncodeInt(6U)}
// b does not appear because the operands are filtered
});
SetLastSequence(5U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
// Test where all operands/merge results are filtered out.
TEST_F(CompactionJobTest, FilterAllMergeOperands) {
merge_op_ = MergeOperators::CreateUInt64AddOperator();
compaction_filter_.reset(new test::FilterNumber(10U));
NewDB();
auto file1 =
mock::MakeMockFile({{KeyStr("a", 11U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("a", 10U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("a", 9U, kTypeMerge), test::EncodeInt(10U)}});
AddMockFile(file1);
auto file2 =
mock::MakeMockFile({{KeyStr("b", 8U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 7U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 6U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 5U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 4U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 3U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 2U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("c", 2U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("c", 1U, kTypeMerge), test::EncodeInt(10U)}});
AddMockFile(file2);
auto file3 =
mock::MakeMockFile({{KeyStr("a", 2U, kTypeMerge), test::EncodeInt(10U)},
{KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)}});
AddMockFile(file3, 2);
SetLastSequence(11U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
stl_wrappers::KVMap empty_map;
RunCompaction({files}, empty_map);
}
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
TEST_F(CompactionJobTest, SimpleSingleDelete) {
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("a", 5U, kTypeDeletion), ""},
{KeyStr("b", 6U, kTypeSingleDeletion), ""},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("a", 3U, kTypeValue), "val"},
{KeyStr("b", 4U, kTypeValue), "val"}});
AddMockFile(file2);
auto file3 = mock::MakeMockFile({
{KeyStr("a", 1U, kTypeValue), "val"},
});
AddMockFile(file3, 2);
auto expected_results =
mock::MakeMockFile({{KeyStr("a", 5U, kTypeDeletion), ""}});
SetLastSequence(6U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
TEST_F(CompactionJobTest, SingleDeleteSnapshots) {
NewDB();
auto file1 = mock::MakeMockFile({{KeyStr("A", 12U, kTypeSingleDeletion), ""},
{KeyStr("a", 12U, kTypeSingleDeletion), ""},
{KeyStr("b", 21U, kTypeSingleDeletion), ""},
{KeyStr("c", 22U, kTypeSingleDeletion), ""},
{KeyStr("d", 9U, kTypeSingleDeletion), ""}});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({{KeyStr("0", 2U, kTypeSingleDeletion), ""},
{KeyStr("a", 11U, kTypeValue), "val1"},
{KeyStr("b", 11U, kTypeValue), "val2"},
{KeyStr("c", 21U, kTypeValue), "val3"},
{KeyStr("d", 8U, kTypeValue), "val4"},
{KeyStr("e", 2U, kTypeSingleDeletion), ""}});
AddMockFile(file2);
auto file3 = mock::MakeMockFile({{KeyStr("A", 1U, kTypeValue), "val"},
{KeyStr("e", 1U, kTypeValue), "val"}});
AddMockFile(file3, 2);
auto expected_results =
mock::MakeMockFile({{KeyStr("A", 12U, kTypeSingleDeletion), ""},
{KeyStr("b", 21U, kTypeSingleDeletion), ""},
{KeyStr("b", 11U, kTypeValue), "val2"},
{KeyStr("e", 2U, kTypeSingleDeletion), ""}});
SetLastSequence(22U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results, {10U, 20U});
}
TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("A", 10U, kTypeSingleDeletion), ""},
{KeyStr("dummy", 5U, kTypeValue), "val2"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({
{KeyStr("A", 0U, kTypeValue), "val"},
});
AddMockFile(file2);
auto expected_results = mock::MakeMockFile({
{KeyStr("dummy", 0U, kTypeValue), "val2"},
});
SetLastSequence(22U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results, {});
}
TEST_F(CompactionJobTest, MultiSingleDelete) {
// Tests three scenarios involving multiple single delete/put pairs:
//
// A: Put Snapshot SDel Put SDel -> Put Snapshot SDel
// B: Put SDel Put SDel -> (Removed)
// C: SDel Put SDel Snapshot Put -> Snapshot Put
// D: (Put) SDel Snapshot Put SDel -> (Put) SDel Snapshot
NewDB();
auto file1 = mock::MakeMockFile({
{KeyStr("A", 14U, kTypeSingleDeletion), ""},
{KeyStr("A", 13U, kTypeValue), "val5"},
{KeyStr("A", 12U, kTypeSingleDeletion), ""},
{KeyStr("B", 14U, kTypeSingleDeletion), ""},
{KeyStr("B", 13U, kTypeValue), "val2"},
{KeyStr("C", 14U, kTypeValue), "val3"},
{KeyStr("D", 12U, kTypeSingleDeletion), ""},
{KeyStr("D", 11U, kTypeValue), "val4"},
});
AddMockFile(file1);
auto file2 = mock::MakeMockFile({
{KeyStr("A", 10U, kTypeValue), "val"},
{KeyStr("B", 12U, kTypeSingleDeletion), ""},
{KeyStr("B", 11U, kTypeValue), "val2"},
{KeyStr("C", 10U, kTypeSingleDeletion), ""},
{KeyStr("C", 9U, kTypeValue), "val6"},
{KeyStr("C", 8U, kTypeSingleDeletion), ""},
{KeyStr("D", 10U, kTypeSingleDeletion), ""},
});
AddMockFile(file2);
auto file3 = mock::MakeMockFile({
{KeyStr("D", 11U, kTypeValue), "val"},
});
AddMockFile(file3, 2);
auto expected_results = mock::MakeMockFile({
{KeyStr("A", 12U, kTypeSingleDeletion), ""},
{KeyStr("A", 10U, kTypeValue), "val"},
{KeyStr("C", 14U, kTypeValue), "val3"},
{KeyStr("D", 10U, kTypeSingleDeletion), ""},
});
SetLastSequence(22U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results, {10U});
}
// This test documents the behavior where a corrupt key follows a deletion or a
// single deletion and the (single) deletion gets removed while the corrupt key
// gets written out. TODO(noetzli): We probably want a better way to treat
// corrupt keys.
TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
NewDB();
auto file1 =
mock::MakeMockFile({{test::KeyStr("A", 6U, kTypeValue), "val3"},
{test::KeyStr("a", 5U, kTypeDeletion), ""},
{test::KeyStr("a", 4U, kTypeValue, true), "val"}});
AddMockFile(file1);
auto file2 =
mock::MakeMockFile({{test::KeyStr("b", 3U, kTypeSingleDeletion), ""},
{test::KeyStr("b", 2U, kTypeValue, true), "val"},
{test::KeyStr("c", 1U, kTypeValue), "val2"}});
AddMockFile(file2);
auto expected_results =
mock::MakeMockFile({{test::KeyStr("A", 0U, kTypeValue), "val3"},
{test::KeyStr("a", 0U, kTypeValue, true), "val"},
{test::KeyStr("b", 0U, kTypeValue, true), "val"},
{test::KeyStr("c", 0U, kTypeValue), "val2"}});
SetLastSequence(6U);
auto files = cfd_->current()->storage_info()->LevelFiles(0);
RunCompaction({files}, expected_results);
}
} // 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 22:08:00 +01:00
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 CompactionJobStats is not supported in ROCKSDB_LITE\n");
return 0;
}
#endif // ROCKSDB_LITE