rocksdb/db/table_properties_collector_test.cc
sdong 953a885ebf A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.

Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties

Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.

Reviewers: yhchiang, igor.sugak, rven, igor

Reviewed By: rven, igor

Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 10:27:21 -07:00

520 lines
17 KiB
C++

// 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 <map>
#include <memory>
#include <string>
#include <vector>
#include "db/db_impl.h"
#include "db/dbformat.h"
#include "db/table_properties_collector.h"
#include "rocksdb/table.h"
#include "rocksdb/immutable_options.h"
#include "table/block_based_table_factory.h"
#include "table/meta_blocks.h"
#include "table/plain_table_factory.h"
#include "table/table_builder.h"
#include "util/coding.h"
#include "util/testharness.h"
#include "util/testutil.h"
namespace rocksdb {
class TablePropertiesTest : public testing::Test,
public testing::WithParamInterface<bool> {
public:
virtual void SetUp() override { backward_mode_ = GetParam(); }
bool backward_mode_;
};
// TODO(kailiu) the following classes should be moved to some more general
// places, so that other tests can also make use of them.
// `FakeWritableFile` and `FakeRandomeAccessFile` bypass the real file system
// and therefore enable us to quickly setup the tests.
class FakeWritableFile : public WritableFile {
public:
~FakeWritableFile() { }
const std::string& contents() const { return contents_; }
virtual Status Close() override { return Status::OK(); }
virtual Status Flush() override { return Status::OK(); }
virtual Status Sync() override { return Status::OK(); }
virtual Status Append(const Slice& data) override {
contents_.append(data.data(), data.size());
return Status::OK();
}
private:
std::string contents_;
};
class FakeRandomeAccessFile : public RandomAccessFile {
public:
explicit FakeRandomeAccessFile(const Slice& contents)
: contents_(contents.data(), contents.size()) {
}
virtual ~FakeRandomeAccessFile() { }
uint64_t Size() const { return contents_.size(); }
virtual Status Read(uint64_t offset, size_t n, Slice* result,
char* scratch) const override {
if (offset > contents_.size()) {
return Status::InvalidArgument("invalid Read offset");
}
if (offset + n > contents_.size()) {
n = contents_.size() - offset;
}
memcpy(scratch, &contents_[offset], n);
*result = Slice(scratch, n);
return Status::OK();
}
private:
std::string contents_;
};
class DumbLogger : public Logger {
public:
using Logger::Logv;
virtual void Logv(const char* format, va_list ap) override {}
virtual size_t GetLogFileSize() const override { return 0; }
};
// Utilities test functions
namespace {
void MakeBuilder(const Options& options, const ImmutableCFOptions& ioptions,
const InternalKeyComparator& internal_comparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
std::unique_ptr<FakeWritableFile>* writable,
std::unique_ptr<TableBuilder>* builder) {
writable->reset(new FakeWritableFile);
builder->reset(NewTableBuilder(
ioptions, internal_comparator, int_tbl_prop_collector_factories,
writable->get(), options.compression, options.compression_opts));
}
} // namespace
// Collects keys that starts with "A" in a table.
class RegularKeysStartWithA: public TablePropertiesCollector {
public:
const char* Name() const override { return "RegularKeysStartWithA"; }
Status Finish(UserCollectedProperties* properties) override {
std::string encoded;
std::string encoded_num_puts;
std::string encoded_num_deletes;
std::string encoded_num_size_changes;
PutVarint32(&encoded, count_);
PutVarint32(&encoded_num_puts, num_puts_);
PutVarint32(&encoded_num_deletes, num_deletes_);
PutVarint32(&encoded_num_size_changes, num_size_changes_);
*properties = UserCollectedProperties{
{"TablePropertiesTest", message_},
{"Count", encoded},
{"NumPuts", encoded_num_puts},
{"NumDeletes", encoded_num_deletes},
{"NumSizeChanges", encoded_num_size_changes},
};
return Status::OK();
}
Status AddUserKey(const Slice& user_key, const Slice& value, EntryType type,
SequenceNumber seq, uint64_t file_size) override {
// simply asssume all user keys are not empty.
if (user_key.data()[0] == 'A') {
++count_;
}
if (type == kEntryPut) {
num_puts_++;
} else if (type == kEntryDelete) {
num_deletes_++;
}
if (file_size < file_size_) {
message_ = "File size should not decrease.";
} else if (file_size != file_size_) {
num_size_changes_++;
}
return Status::OK();
}
virtual UserCollectedProperties GetReadableProperties() const override {
return UserCollectedProperties{};
}
private:
std::string message_ = "Rocksdb";
uint32_t count_ = 0;
uint32_t num_puts_ = 0;
uint32_t num_deletes_ = 0;
uint32_t num_size_changes_ = 0;
uint64_t file_size_ = 0;
};
// Collects keys that starts with "A" in a table. Backward compatible mode
// It is also used to test internal key table property collector
class RegularKeysStartWithABackwardCompatible
: public TablePropertiesCollector {
public:
const char* Name() const override { return "RegularKeysStartWithA"; }
Status Finish(UserCollectedProperties* properties) override {
std::string encoded;
PutVarint32(&encoded, count_);
*properties = UserCollectedProperties{{"TablePropertiesTest", "Rocksdb"},
{"Count", encoded}};
return Status::OK();
}
Status Add(const Slice& user_key, const Slice& value) override {
// simply asssume all user keys are not empty.
if (user_key.data()[0] == 'A') {
++count_;
}
return Status::OK();
}
virtual UserCollectedProperties GetReadableProperties() const override {
return UserCollectedProperties{};
}
private:
uint32_t count_ = 0;
};
class RegularKeysStartWithAInternal : public IntTblPropCollector {
public:
const char* Name() const override { return "RegularKeysStartWithA"; }
Status Finish(UserCollectedProperties* properties) override {
std::string encoded;
PutVarint32(&encoded, count_);
*properties = UserCollectedProperties{{"TablePropertiesTest", "Rocksdb"},
{"Count", encoded}};
return Status::OK();
}
Status InternalAdd(const Slice& user_key, const Slice& value,
uint64_t file_size) override {
// simply asssume all user keys are not empty.
if (user_key.data()[0] == 'A') {
++count_;
}
return Status::OK();
}
virtual UserCollectedProperties GetReadableProperties() const override {
return UserCollectedProperties{};
}
private:
uint32_t count_ = 0;
};
class RegularKeysStartWithAFactory : public IntTblPropCollectorFactory,
public TablePropertiesCollectorFactory {
public:
explicit RegularKeysStartWithAFactory(bool backward_mode)
: backward_mode_(backward_mode) {}
virtual TablePropertiesCollector* CreateTablePropertiesCollector() override {
if (!backward_mode_) {
return new RegularKeysStartWithA();
} else {
return new RegularKeysStartWithABackwardCompatible();
}
}
virtual IntTblPropCollector* CreateIntTblPropCollector() override {
return new RegularKeysStartWithAInternal();
}
const char* Name() const override { return "RegularKeysStartWithA"; }
bool backward_mode_;
};
class FlushBlockEveryThreePolicy : public FlushBlockPolicy {
public:
virtual bool Update(const Slice& key, const Slice& value) override {
return (++count_ % 3U == 0);
}
private:
uint64_t count_ = 0;
};
class FlushBlockEveryThreePolicyFactory : public FlushBlockPolicyFactory {
public:
explicit FlushBlockEveryThreePolicyFactory() {}
const char* Name() const override {
return "FlushBlockEveryThreePolicyFactory";
}
FlushBlockPolicy* NewFlushBlockPolicy(
const BlockBasedTableOptions& table_options,
const BlockBuilder& data_block_builder) const override {
return new FlushBlockEveryThreePolicy;
}
};
extern uint64_t kBlockBasedTableMagicNumber;
extern uint64_t kPlainTableMagicNumber;
namespace {
void TestCustomizedTablePropertiesCollector(
bool backward_mode, uint64_t magic_number, bool test_int_tbl_prop_collector,
const Options& options, const InternalKeyComparator& internal_comparator) {
const std::string kDeleteFlag = "D";
// make sure the entries will be inserted with order.
std::map<std::string, std::string> kvs = {
{"About ", "val5"}, // starts with 'A'
{"Abstract", "val2"}, // starts with 'A'
{"Around ", "val7"}, // starts with 'A'
{"Beyond ", "val3"},
{"Builder ", "val1"},
{"Love ", kDeleteFlag},
{"Cancel ", "val4"},
{"Find ", "val6"},
{"Rocks ", kDeleteFlag},
};
// -- Step 1: build table
std::unique_ptr<TableBuilder> builder;
std::unique_ptr<FakeWritableFile> writable;
const ImmutableCFOptions ioptions(options);
std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
int_tbl_prop_collector_factories;
if (test_int_tbl_prop_collector) {
int_tbl_prop_collector_factories.emplace_back(
new RegularKeysStartWithAFactory(backward_mode));
} else {
GetIntTblPropCollectorFactory(options, &int_tbl_prop_collector_factories);
}
MakeBuilder(options, ioptions, internal_comparator,
&int_tbl_prop_collector_factories, &writable, &builder);
SequenceNumber seqNum = 0U;
for (const auto& kv : kvs) {
InternalKey ikey(kv.first, seqNum++, (kv.second != kDeleteFlag)
? ValueType::kTypeValue
: ValueType::kTypeDeletion);
builder->Add(ikey.Encode(), kv.second);
}
ASSERT_OK(builder->Finish());
// -- Step 2: Read properties
FakeRandomeAccessFile readable(writable->contents());
TableProperties* props;
Status s = ReadTableProperties(
&readable,
writable->contents().size(),
magic_number,
Env::Default(),
nullptr,
&props
);
std::unique_ptr<TableProperties> props_guard(props);
ASSERT_OK(s);
auto user_collected = props->user_collected_properties;
ASSERT_TRUE(user_collected.find("TablePropertiesTest") !=
user_collected.end());
ASSERT_EQ("Rocksdb", user_collected.at("TablePropertiesTest"));
uint32_t starts_with_A = 0;
ASSERT_TRUE(user_collected.find("Count") != user_collected.end());
Slice key(user_collected.at("Count"));
ASSERT_TRUE(GetVarint32(&key, &starts_with_A));
ASSERT_EQ(3u, starts_with_A);
if (!backward_mode && !test_int_tbl_prop_collector) {
uint32_t num_deletes;
ASSERT_TRUE(user_collected.find("NumDeletes") != user_collected.end());
Slice key_deletes(user_collected.at("NumDeletes"));
ASSERT_TRUE(GetVarint32(&key_deletes, &num_deletes));
ASSERT_EQ(2u, num_deletes);
uint32_t num_puts;
ASSERT_TRUE(user_collected.find("NumPuts") != user_collected.end());
Slice key_puts(user_collected.at("NumPuts"));
ASSERT_TRUE(GetVarint32(&key_puts, &num_puts));
ASSERT_EQ(7u, num_puts);
uint32_t num_size_changes;
ASSERT_TRUE(user_collected.find("NumSizeChanges") != user_collected.end());
Slice key_size_changes(user_collected.at("NumSizeChanges"));
ASSERT_TRUE(GetVarint32(&key_size_changes, &num_size_changes));
ASSERT_GE(num_size_changes, 2u);
}
}
} // namespace
TEST_P(TablePropertiesTest, CustomizedTablePropertiesCollector) {
// Test properties collectors with internal keys or regular keys
// for block based table
for (bool encode_as_internal : { true, false }) {
if (!backward_mode_ && !encode_as_internal) {
continue;
}
Options options;
BlockBasedTableOptions table_options;
table_options.flush_block_policy_factory =
std::make_shared<FlushBlockEveryThreePolicyFactory>();
options.table_factory.reset(NewBlockBasedTableFactory(table_options));
test::PlainInternalKeyComparator ikc(options.comparator);
std::shared_ptr<TablePropertiesCollectorFactory> collector_factory(
new RegularKeysStartWithAFactory(backward_mode_));
options.table_properties_collector_factories.resize(1);
options.table_properties_collector_factories[0] = collector_factory;
TestCustomizedTablePropertiesCollector(backward_mode_,
kBlockBasedTableMagicNumber,
encode_as_internal, options, ikc);
// test plain table
PlainTableOptions plain_table_options;
plain_table_options.user_key_len = 8;
plain_table_options.bloom_bits_per_key = 8;
plain_table_options.hash_table_ratio = 0;
options.table_factory =
std::make_shared<PlainTableFactory>(plain_table_options);
TestCustomizedTablePropertiesCollector(backward_mode_,
kPlainTableMagicNumber,
encode_as_internal, options, ikc);
}
}
namespace {
void TestInternalKeyPropertiesCollector(
bool backward_mode, uint64_t magic_number, bool sanitized,
std::shared_ptr<TableFactory> table_factory) {
InternalKey keys[] = {
InternalKey("A ", 0, ValueType::kTypeValue),
InternalKey("B ", 1, ValueType::kTypeValue),
InternalKey("C ", 2, ValueType::kTypeValue),
InternalKey("W ", 3, ValueType::kTypeDeletion),
InternalKey("X ", 4, ValueType::kTypeDeletion),
InternalKey("Y ", 5, ValueType::kTypeDeletion),
InternalKey("Z ", 6, ValueType::kTypeDeletion),
};
std::unique_ptr<TableBuilder> builder;
std::unique_ptr<FakeWritableFile> writable;
Options options;
test::PlainInternalKeyComparator pikc(options.comparator);
std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
int_tbl_prop_collector_factories;
options.table_factory = table_factory;
if (sanitized) {
options.table_properties_collector_factories.emplace_back(
new RegularKeysStartWithAFactory(backward_mode));
// with sanitization, even regular properties collector will be able to
// handle internal keys.
auto comparator = options.comparator;
// HACK: Set options.info_log to avoid writing log in
// SanitizeOptions().
options.info_log = std::make_shared<DumbLogger>();
options = SanitizeOptions("db", // just a place holder
&pikc,
options);
GetIntTblPropCollectorFactory(options, &int_tbl_prop_collector_factories);
options.comparator = comparator;
} else {
int_tbl_prop_collector_factories.emplace_back(
new InternalKeyPropertiesCollectorFactory);
}
const ImmutableCFOptions ioptions(options);
for (int iter = 0; iter < 2; ++iter) {
MakeBuilder(options, ioptions, pikc, &int_tbl_prop_collector_factories,
&writable, &builder);
for (const auto& k : keys) {
builder->Add(k.Encode(), "val");
}
ASSERT_OK(builder->Finish());
FakeRandomeAccessFile readable(writable->contents());
TableProperties* props;
Status s =
ReadTableProperties(&readable, writable->contents().size(),
magic_number, Env::Default(), nullptr, &props);
ASSERT_OK(s);
std::unique_ptr<TableProperties> props_guard(props);
auto user_collected = props->user_collected_properties;
uint64_t deleted = GetDeletedKeys(user_collected);
ASSERT_EQ(4u, deleted);
if (sanitized) {
uint32_t starts_with_A = 0;
ASSERT_TRUE(user_collected.find("Count") != user_collected.end());
Slice key(user_collected.at("Count"));
ASSERT_TRUE(GetVarint32(&key, &starts_with_A));
ASSERT_EQ(1u, starts_with_A);
if (!backward_mode) {
uint32_t num_deletes;
ASSERT_TRUE(user_collected.find("NumDeletes") != user_collected.end());
Slice key_deletes(user_collected.at("NumDeletes"));
ASSERT_TRUE(GetVarint32(&key_deletes, &num_deletes));
ASSERT_EQ(4u, num_deletes);
uint32_t num_puts;
ASSERT_TRUE(user_collected.find("NumPuts") != user_collected.end());
Slice key_puts(user_collected.at("NumPuts"));
ASSERT_TRUE(GetVarint32(&key_puts, &num_puts));
ASSERT_EQ(3u, num_puts);
}
}
}
}
} // namespace
TEST_P(TablePropertiesTest, InternalKeyPropertiesCollector) {
TestInternalKeyPropertiesCollector(
backward_mode_, kBlockBasedTableMagicNumber, true /* sanitize */,
std::make_shared<BlockBasedTableFactory>());
if (backward_mode_) {
TestInternalKeyPropertiesCollector(
backward_mode_, kBlockBasedTableMagicNumber, false /* not sanitize */,
std::make_shared<BlockBasedTableFactory>());
}
PlainTableOptions plain_table_options;
plain_table_options.user_key_len = 8;
plain_table_options.bloom_bits_per_key = 8;
plain_table_options.hash_table_ratio = 0;
TestInternalKeyPropertiesCollector(
backward_mode_, kPlainTableMagicNumber, false /* not sanitize */,
std::make_shared<PlainTableFactory>(plain_table_options));
}
INSTANTIATE_TEST_CASE_P(InternalKeyPropertiesCollector, TablePropertiesTest,
::testing::Bool());
INSTANTIATE_TEST_CASE_P(CustomizedTablePropertiesCollector, TablePropertiesTest,
::testing::Bool());
} // namespace rocksdb
int main(int argc, char** argv) {
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}