rocksdb/db/flush_job_test.cc

213 lines
7.5 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.
#include <algorithm>
#include <map>
#include <string>
#include "db/flush_job.h"
#include "db/column_family.h"
#include "db/version_set.h"
#include "db/writebuffer.h"
#include "rocksdb/cache.h"
#include "util/file_reader_writer.h"
#include "util/string_util.h"
#include "util/testharness.h"
#include "util/testutil.h"
#include "table/mock_table.h"
namespace rocksdb {
// TODO(icanadi) Mock out everything else:
// 1. VersionSet
// 2. Memtable
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' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
class FlushJobTest : public testing::Test {
public:
FlushJobTest()
: env_(Env::Default()),
dbname_(test::TmpDir() + "/flush_job_test"),
table_cache_(NewLRUCache(50000, 16)),
write_buffer_(db_options_.db_write_buffer_size),
versions_(new VersionSet(dbname_, &db_options_, env_options_,
table_cache_.get(), &write_buffer_,
&write_controller_)),
shutting_down_(false),
mock_table_factory_(new mock::MockTableFactory()) {
rocksdb: Replace ASSERT* with EXPECT* in functions that does not return void value Summary: gtest does not use exceptions to fail a unit test by design, and `ASSERT*`s are implemented using `return`. As a consequence we cannot use `ASSERT*` in a function that does not return `void` value ([[ https://code.google.com/p/googletest/wiki/AdvancedGuide#Assertion_Placement | 1]]), and have to fix our existing code. This diff does this in a generic way, with no manual changes. In order to detect all existing `ASSERT*` that are used in functions that doesn't return void value, I change the code to generate compile errors for such cases. In `util/testharness.h` I defined `EXPECT*` assertions, the same way as `ASSERT*`, and redefined `ASSERT*` to return `void`. Then executed: ```lang=bash % USE_CLANG=1 make all -j55 -k 2> build.log % perl -naF: -e 'print "-- -number=".$F[1]." ".$F[0]."\n" if /: error:/' \ build.log | xargs -L 1 perl -spi -e 's/ASSERT/EXPECT/g if $. == $number' % make format ``` After that I reverted back change to `ASSERT*` in `util/testharness.h`. But preserved introduced `EXPECT*`, which is the same as `ASSERT*`. This will be deleted once switched to gtest. This diff is independent and contains manual changes only in `util/testharness.h`. Test Plan: Make sure all tests are passing. ```lang=bash % USE_CLANG=1 make check ``` Reviewers: igor, lgalanis, sdong, yufei.zhu, rven, meyering Reviewed By: meyering Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33333
2015-03-17 03:52:32 +00:00
EXPECT_OK(env_->CreateDirIfMissing(dbname_));
db_options_.db_paths.emplace_back(dbname_,
std::numeric_limits<uint64_t>::max());
// TODO(icanadi) Remove this once we mock out VersionSet
NewDB();
std::vector<ColumnFamilyDescriptor> column_families;
cf_options_.table_factory = mock_table_factory_;
column_families.emplace_back(kDefaultColumnFamilyName, cf_options_);
rocksdb: Replace ASSERT* with EXPECT* in functions that does not return void value Summary: gtest does not use exceptions to fail a unit test by design, and `ASSERT*`s are implemented using `return`. As a consequence we cannot use `ASSERT*` in a function that does not return `void` value ([[ https://code.google.com/p/googletest/wiki/AdvancedGuide#Assertion_Placement | 1]]), and have to fix our existing code. This diff does this in a generic way, with no manual changes. In order to detect all existing `ASSERT*` that are used in functions that doesn't return void value, I change the code to generate compile errors for such cases. In `util/testharness.h` I defined `EXPECT*` assertions, the same way as `ASSERT*`, and redefined `ASSERT*` to return `void`. Then executed: ```lang=bash % USE_CLANG=1 make all -j55 -k 2> build.log % perl -naF: -e 'print "-- -number=".$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 03:52:32 +00:00
EXPECT_OK(versions_->Recover(column_families, false));
}
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), EnvOptions()));
{
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);
}
Env* env_;
std::string dbname_;
EnvOptions env_options_;
std::shared_ptr<Cache> table_cache_;
WriteController write_controller_;
DBOptions db_options_;
WriteBuffer write_buffer_;
ColumnFamilyOptions cf_options_;
std::unique_ptr<VersionSet> versions_;
InstrumentedMutex mutex_;
std::atomic<bool> shutting_down_;
std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
};
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' $file fi done % sh ~/transform % make format ``` Second iteration of this diff contains only scripted changes. Third iteration contains manual changes to fix last errors and make it compilable. Test Plan: Build and notice no errors. ```lang=bash % USE_CLANG=1 make check -j55 ``` Tests are still testing. Reviewers: meyering, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 21:08:00 +00:00
TEST_F(FlushJobTest, Empty) {
JobContext job_context(0);
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
EventLogger event_logger(db_options_.info_log.get());
FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
db_options_, *cfd->GetLatestMutableCFOptions(),
env_options_, versions_.get(), &mutex_, &shutting_down_,
{}, &job_context, nullptr, nullptr, nullptr,
kNoCompression, nullptr, &event_logger);
ASSERT_OK(flush_job.Run());
2014-11-15 00:57:17 +00:00
job_context.Clean();
}
rocksdb: switch to gtest Summary: Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different. In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest. There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides. ```lang=bash % cat ~/transform #!/bin/sh files=$(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(FlushJobTest, NonEmpty) {
JobContext job_context(0);
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
kMaxSequenceNumber);
new_mem->Ref();
auto inserted_keys = mock::MakeMockFile();
// Test data:
// seqno [ 1, 2 ... 8998, 8999, 9000, 9001, 9002 ... 9999 ]
// key [ 1001, 1002 ... 9998, 9999, 0, 1, 2 ... 999 ]
// Expected:
// smallest_key = "0"
// largest_key = "9999"
// smallest_seqno = 1
// smallest_seqno = 9999
for (int i = 1; i < 10000; ++i) {
std::string key(ToString((i + 1000) % 10000));
std::string value("value" + key);
new_mem->Add(SequenceNumber(i), kTypeValue, key, value);
InternalKey internal_key(key, SequenceNumber(i), kTypeValue);
inserted_keys.insert({internal_key.Encode().ToString(), value});
}
Support saving history in memtable_list Summary: For transactions, we are using the memtables to validate that there are no write conflicts. But after flushing, we don't have any memtables, and transactions could fail to commit. So we want to someone keep around some extra history to use for conflict checking. In addition, we want to provide a way to increase the size of this history if too many transactions fail to commit. After chatting with people, it seems like everyone prefers just using Memtables to store this history (instead of a separate history structure). It seems like the best place for this is abstracted inside the memtable_list. I decide to create a separate list in MemtableListVersion as using the same list complicated the flush/installalflushresults logic too much. This diff adds a new parameter to control how much memtable history to keep around after flushing. However, it sounds like people aren't too fond of adding new parameters. So I am making the default size of flushed+not-flushed memtables be set to max_write_buffers. This should not change the maximum amount of memory used, but make it more likely we're using closer the the limit. (We are now postponing deleting flushed memtables until the max_write_buffer limit is reached). So while we might use more memory on average, we are still obeying the limit set (and you could argue it's better to go ahead and use up memory now instead of waiting for a write stall to happen to test this limit). However, if people are opposed to this default behavior, we can easily set it to 0 and require this parameter be set in order to use transactions. Test Plan: Added a xfunc test to play around with setting different values of this parameter in all tests. Added testing in memtablelist_test and planning on adding more testing here. Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37443
2015-05-28 23:34:24 +00:00
autovector<MemTable*> to_delete;
cfd->imm()->Add(new_mem, &to_delete);
for (auto& m : to_delete) {
delete m;
}
EventLogger event_logger(db_options_.info_log.get());
FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
db_options_, *cfd->GetLatestMutableCFOptions(),
env_options_, versions_.get(), &mutex_, &shutting_down_,
{}, &job_context, nullptr, nullptr, nullptr,
kNoCompression, nullptr, &event_logger);
FileMetaData fd;
mutex_.Lock();
ASSERT_OK(flush_job.Run(&fd));
mutex_.Unlock();
ASSERT_EQ(ToString(0), fd.smallest.user_key().ToString());
ASSERT_EQ(ToString(9999), fd.largest.user_key().ToString());
ASSERT_EQ(1, fd.smallest_seqno);
ASSERT_EQ(9999, fd.largest_seqno);
mock_table_factory_->AssertSingleFile(inserted_keys);
job_context.Clean();
}
TEST_F(FlushJobTest, Snapshots) {
JobContext job_context(0);
auto cfd = versions_->GetColumnFamilySet()->GetDefault();
auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
kMaxSequenceNumber);
std::vector<SequenceNumber> snapshots;
std::set<SequenceNumber> snapshots_set;
int keys = 10000;
int max_inserts_per_keys = 8;
Random rnd(301);
for (int i = 0; i < keys / 2; ++i) {
snapshots.push_back(rnd.Uniform(keys * (max_inserts_per_keys / 2)) + 1);
snapshots_set.insert(snapshots.back());
}
std::sort(snapshots.begin(), snapshots.end());
new_mem->Ref();
SequenceNumber current_seqno = 0;
auto inserted_keys = mock::MakeMockFile();
for (int i = 1; i < keys; ++i) {
std::string key(ToString(i));
int insertions = rnd.Uniform(max_inserts_per_keys);
for (int j = 0; j < insertions; ++j) {
std::string value(test::RandomHumanReadableString(&rnd, 10));
auto seqno = ++current_seqno;
new_mem->Add(SequenceNumber(seqno), kTypeValue, key, value);
// a key is visible only if:
// 1. it's the last one written (j == insertions - 1)
// 2. there's a snapshot pointing at it
bool visible = (j == insertions - 1) ||
(snapshots_set.find(seqno) != snapshots_set.end());
if (visible) {
InternalKey internal_key(key, seqno, kTypeValue);
inserted_keys.insert({internal_key.Encode().ToString(), value});
}
}
}
autovector<MemTable*> to_delete;
cfd->imm()->Add(new_mem, &to_delete);
for (auto& m : to_delete) {
delete m;
}
EventLogger event_logger(db_options_.info_log.get());
FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
db_options_, *cfd->GetLatestMutableCFOptions(),
env_options_, versions_.get(), &mutex_, &shutting_down_,
snapshots, &job_context, nullptr, nullptr, nullptr,
kNoCompression, nullptr, &event_logger);
mutex_.Lock();
ASSERT_OK(flush_job.Run());
mutex_.Unlock();
mock_table_factory_->AssertSingleFile(inserted_keys);
2014-11-15 00:57:17 +00:00
job_context.Clean();
}
} // 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();
}