rocksdb/table/block_based/block_based_table_reader_test.cc

357 lines
13 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).
#include "table/block_based/block_based_table_reader.h"
#include "db/table_properties_collector.h"
#include "file/file_util.h"
#include "options/options_helper.h"
#include "port/port.h"
#include "port/stack_trace.h"
#include "rocksdb/file_system.h"
#include "table/block_based/block_based_table_builder.h"
#include "table/block_based/block_based_table_factory.h"
#include "table/block_based/partitioned_index_iterator.h"
#include "table/format.h"
#include "test_util/testharness.h"
#include "test_util/testutil.h"
#include "util/random.h"
namespace ROCKSDB_NAMESPACE {
class BlockBasedTableReaderTest
: public testing::Test,
public testing::WithParamInterface<std::tuple<
CompressionType, bool, BlockBasedTableOptions::IndexType, bool>> {
protected:
CompressionType compression_type_;
bool use_direct_reads_;
void SetUp() override {
BlockBasedTableOptions::IndexType index_type;
bool no_block_cache;
std::tie(compression_type_, use_direct_reads_, index_type, no_block_cache) =
GetParam();
SetupSyncPointsToMockDirectIO();
test_dir_ = test::PerThreadDBPath("block_based_table_reader_test");
env_ = Env::Default();
fs_ = FileSystem::Default();
ASSERT_OK(fs_->CreateDir(test_dir_, IOOptions(), nullptr));
BlockBasedTableOptions opts;
opts.index_type = index_type;
opts.no_block_cache = no_block_cache;
table_factory_.reset(
static_cast<BlockBasedTableFactory*>(NewBlockBasedTableFactory(opts)));
}
void TearDown() override { EXPECT_OK(DestroyDir(env_, test_dir_)); }
// Creates a table with the specificied key value pairs (kv).
void CreateTable(const std::string& table_name,
const CompressionType& compression_type,
const std::map<std::string, std::string>& kv) {
std::unique_ptr<WritableFileWriter> writer;
NewFileWriter(table_name, &writer);
// Create table builder.
Options options;
ImmutableOptions ioptions(options);
InternalKeyComparator comparator(options.comparator);
ColumnFamilyOptions cf_options;
MutableCFOptions moptions(cf_options);
IntTblPropCollectorFactories factories;
std::unique_ptr<TableBuilder> table_builder(table_factory_->NewTableBuilder(
TableBuilderOptions(ioptions, moptions, comparator, &factories,
compression_type, CompressionOptions(),
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
0 /* column_family_id */, kDefaultColumnFamilyName,
-1 /* level */),
writer.get()));
// Build table.
for (auto it = kv.begin(); it != kv.end(); it++) {
std::string k = ToInternalKey(it->first);
std::string v = it->second;
table_builder->Add(k, v);
}
ASSERT_OK(table_builder->Finish());
}
void NewBlockBasedTableReader(const FileOptions& foptions,
const ImmutableOptions& ioptions,
const InternalKeyComparator& comparator,
const std::string& table_name,
std::unique_ptr<BlockBasedTable>* table) {
std::unique_ptr<RandomAccessFileReader> file;
NewFileReader(table_name, foptions, &file);
uint64_t file_size = 0;
ASSERT_OK(env_->GetFileSize(Path(table_name), &file_size));
std::unique_ptr<TableReader> table_reader;
ReadOptions ro;
const auto* table_options =
table_factory_->GetOptions<BlockBasedTableOptions>();
ASSERT_NE(table_options, nullptr);
ASSERT_OK(BlockBasedTable::Open(ro, ioptions, EnvOptions(), *table_options,
comparator, std::move(file), file_size,
&table_reader));
table->reset(reinterpret_cast<BlockBasedTable*>(table_reader.release()));
}
std::string Path(const std::string& fname) { return test_dir_ + "/" + fname; }
const std::shared_ptr<FileSystem>& fs() const { return fs_; }
private:
std::string test_dir_;
Env* env_;
std::shared_ptr<FileSystem> fs_;
std::unique_ptr<BlockBasedTableFactory> table_factory_;
void WriteToFile(const std::string& content, const std::string& filename) {
std::unique_ptr<FSWritableFile> f;
ASSERT_OK(fs_->NewWritableFile(Path(filename), FileOptions(), &f, nullptr));
ASSERT_OK(f->Append(content, IOOptions(), nullptr));
ASSERT_OK(f->Close(IOOptions(), nullptr));
}
void NewFileWriter(const std::string& filename,
std::unique_ptr<WritableFileWriter>* writer) {
std::string path = Path(filename);
EnvOptions env_options;
FileOptions foptions;
std::unique_ptr<FSWritableFile> file;
ASSERT_OK(fs_->NewWritableFile(path, foptions, &file, nullptr));
writer->reset(new WritableFileWriter(std::move(file), path, env_options));
}
void NewFileReader(const std::string& filename, const FileOptions& opt,
std::unique_ptr<RandomAccessFileReader>* reader) {
std::string path = Path(filename);
std::unique_ptr<FSRandomAccessFile> f;
ASSERT_OK(fs_->NewRandomAccessFile(path, opt, &f, nullptr));
reader->reset(new RandomAccessFileReader(std::move(f), path,
env_->GetSystemClock().get()));
}
std::string ToInternalKey(const std::string& key) {
InternalKey internal_key(key, 0, ValueType::kTypeValue);
return internal_key.Encode().ToString();
}
};
// Tests MultiGet in both direct IO and non-direct IO mode.
// The keys should be in cache after MultiGet.
TEST_P(BlockBasedTableReaderTest, MultiGet) {
// Prepare key-value pairs to occupy multiple blocks.
// Each value is 256B, every 16 pairs constitute 1 block.
// Adjacent blocks contain values with different compression complexity:
// human readable strings are easier to compress than random strings.
std::map<std::string, std::string> kv;
{
Random rnd(101);
uint32_t key = 0;
for (int block = 0; block < 100; block++) {
for (int i = 0; i < 16; i++) {
char k[9] = {0};
// Internal key is constructed directly from this key,
// and internal key size is required to be >= 8 bytes,
// so use %08u as the format string.
sprintf(k, "%08u", key);
std::string v;
if (block % 2) {
v = rnd.HumanReadableString(256);
} else {
v = rnd.RandomString(256);
}
kv[std::string(k)] = v;
key++;
}
}
}
// Prepare keys, values, and statuses for MultiGet.
autovector<Slice, MultiGetContext::MAX_BATCH_SIZE> keys;
autovector<PinnableSlice, MultiGetContext::MAX_BATCH_SIZE> values;
autovector<Status, MultiGetContext::MAX_BATCH_SIZE> statuses;
{
const int step =
static_cast<int>(kv.size()) / MultiGetContext::MAX_BATCH_SIZE;
auto it = kv.begin();
for (int i = 0; i < MultiGetContext::MAX_BATCH_SIZE; i++) {
keys.emplace_back(it->first);
values.emplace_back();
statuses.emplace_back();
std::advance(it, step);
}
}
std::string table_name =
"BlockBasedTableReaderTest" + CompressionTypeToString(compression_type_);
CreateTable(table_name, compression_type_, kv);
std::unique_ptr<BlockBasedTable> table;
Options options;
ImmutableOptions ioptions(options);
FileOptions foptions;
foptions.use_direct_reads = use_direct_reads_;
InternalKeyComparator comparator(options.comparator);
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table);
// Ensure that keys are not in cache before MultiGet.
for (auto& key : keys) {
ASSERT_FALSE(table->TEST_KeyInCache(ReadOptions(), key));
}
// Prepare MultiGetContext.
autovector<GetContext, MultiGetContext::MAX_BATCH_SIZE> get_context;
autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
for (size_t i = 0; i < keys.size(); ++i) {
get_context.emplace_back(
BytewiseComparator(), nullptr, nullptr, nullptr, GetContext::kNotFound,
keys[i], &values[i], nullptr, nullptr, nullptr, true /* do_merge */,
nullptr, nullptr, nullptr, nullptr, nullptr, nullptr);
key_context.emplace_back(nullptr, keys[i], &values[i], nullptr,
&statuses.back());
key_context.back().get_context = &get_context.back();
}
for (auto& key_ctx : key_context) {
sorted_keys.emplace_back(&key_ctx);
}
MultiGetContext ctx(&sorted_keys, 0, sorted_keys.size(), 0, ReadOptions());
// Execute MultiGet.
MultiGetContext::Range range = ctx.GetMultiGetRange();
PerfContext* perf_ctx = get_perf_context();
perf_ctx->Reset();
table->MultiGet(ReadOptions(), &range, nullptr);
ASSERT_GE(perf_ctx->block_read_count - perf_ctx->index_block_read_count -
perf_ctx->filter_block_read_count -
perf_ctx->compression_dict_block_read_count,
1);
ASSERT_GE(perf_ctx->block_read_byte, 1);
for (const Status& status : statuses) {
ASSERT_OK(status);
}
// Check that keys are in cache after MultiGet.
for (size_t i = 0; i < keys.size(); i++) {
ASSERT_TRUE(table->TEST_KeyInCache(ReadOptions(), keys[i]));
ASSERT_EQ(values[i].ToString(), kv[keys[i].ToString()]);
}
}
class BlockBasedTableReaderTestVerifyChecksum
: public BlockBasedTableReaderTest {
public:
BlockBasedTableReaderTestVerifyChecksum() : BlockBasedTableReaderTest() {}
};
TEST_P(BlockBasedTableReaderTestVerifyChecksum, ChecksumMismatch) {
// Prepare key-value pairs to occupy multiple blocks.
// Each value is 256B, every 16 pairs constitute 1 block.
// Adjacent blocks contain values with different compression complexity:
// human readable strings are easier to compress than random strings.
Random rnd(101);
std::map<std::string, std::string> kv;
{
uint32_t key = 0;
for (int block = 0; block < 800; block++) {
for (int i = 0; i < 16; i++) {
char k[9] = {0};
// Internal key is constructed directly from this key,
// and internal key size is required to be >= 8 bytes,
// so use %08u as the format string.
sprintf(k, "%08u", key);
std::string v = rnd.RandomString(256);
kv[std::string(k)] = v;
key++;
}
}
}
std::string table_name =
"BlockBasedTableReaderTest" + CompressionTypeToString(compression_type_);
CreateTable(table_name, compression_type_, kv);
std::unique_ptr<BlockBasedTable> table;
Options options;
ImmutableOptions ioptions(options);
FileOptions foptions;
foptions.use_direct_reads = use_direct_reads_;
InternalKeyComparator comparator(options.comparator);
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table);
// Use the top level iterator to find the offset/size of the first
// 2nd level index block and corrupt the block
IndexBlockIter iiter_on_stack;
BlockCacheLookupContext context{TableReaderCaller::kUserVerifyChecksum};
InternalIteratorBase<IndexValue>* iiter = table->NewIndexIterator(
ReadOptions(), /*disable_prefix_seek=*/false, &iiter_on_stack,
/*get_context=*/nullptr, &context);
std::unique_ptr<InternalIteratorBase<IndexValue>> iiter_unique_ptr;
if (iiter != &iiter_on_stack) {
iiter_unique_ptr = std::unique_ptr<InternalIteratorBase<IndexValue>>(iiter);
}
ASSERT_OK(iiter->status());
iiter->SeekToFirst();
BlockHandle handle = static_cast<PartitionedIndexIterator*>(iiter)
->index_iter_->value()
.handle;
table.reset();
// Corrupt the block pointed to by handle
Fix many tests to run with MEM_ENV and ENCRYPTED_ENV; Introduce a MemoryFileSystem class (#7566) Summary: This PR does a few things: 1. The MockFileSystem class was split out from the MockEnv. This change would theoretically allow a MockFileSystem to be used by other Environments as well (if we created a means of constructing one). The MockFileSystem implements a FileSystem in its entirety and does not rely on any Wrapper implementation. 2. Make the RocksDB test suite work when MOCK_ENV=1 and ENCRYPTED_ENV=1 are set. To accomplish this, a few things were needed: - The tests that tried to use the "wrong" environment (Env::Default() instead of env_) were updated - The MockFileSystem was changed to support the features it was missing or mishandled (such as recursively deleting files in a directory or supporting renaming of a directory). 3. Updated the test framework to have a ROCKSDB_GTEST_SKIP macro. This can be used to flag tests that are skipped. Currently, this defaults to doing nothing (marks the test as SUCCESS) but will mark the tests as SKIPPED when RocksDB is upgraded to a version of gtest that supports this (gtest-1.10). I have run a full "make check" with MEM_ENV, ENCRYPTED_ENV, both, and neither under both MacOS and RedHat. A few tests were disabled/skipped for the MEM/ENCRYPTED cases. The error_handler_fs_test fails/hangs for MEM_ENV (presumably a timing problem) and I will introduce another PR/issue to track that problem. (I will also push a change to disable those tests soon). There is one more test in DBTest2 that also fails which I need to investigate or skip before this PR is merged. Theoretically, this PR should also allow the test suite to run against an Env loaded from the registry, though I do not have one to try it with currently. Finally, once this is accepted, it would be nice if there was a CircleCI job to run these tests on a checkin so this effort does not become stale. I do not know how to do that, so if someone could write that job, it would be appreciated :) Pull Request resolved: https://github.com/facebook/rocksdb/pull/7566 Reviewed By: zhichao-cao Differential Revision: D24408980 Pulled By: jay-zhuang fbshipit-source-id: 911b1554a4d0da06fd51feca0c090a4abdcb4a5f
2020-10-27 18:31:34 +01:00
ASSERT_OK(test::CorruptFile(options.env, Path(table_name),
static_cast<int>(handle.offset()), 128));
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table);
Status s = table->VerifyChecksum(ReadOptions(),
TableReaderCaller::kUserVerifyChecksum);
ASSERT_EQ(s.code(), Status::kCorruption);
}
// Param 1: compression type
// Param 2: whether to use direct reads
// Param 3: Block Based Table Index type
// Param 4: BBTO no_block_cache option
#ifdef ROCKSDB_LITE
// Skip direct I/O tests in lite mode since direct I/O is unsupported.
INSTANTIATE_TEST_CASE_P(
MultiGet, BlockBasedTableReaderTest,
::testing::Combine(
::testing::ValuesIn(GetSupportedCompressions()),
::testing::Values(false),
::testing::Values(BlockBasedTableOptions::IndexType::kBinarySearch),
::testing::Values(false)));
#else // ROCKSDB_LITE
INSTANTIATE_TEST_CASE_P(
MultiGet, BlockBasedTableReaderTest,
::testing::Combine(
::testing::ValuesIn(GetSupportedCompressions()), ::testing::Bool(),
::testing::Values(BlockBasedTableOptions::IndexType::kBinarySearch),
::testing::Values(false)));
#endif // ROCKSDB_LITE
INSTANTIATE_TEST_CASE_P(
VerifyChecksum, BlockBasedTableReaderTestVerifyChecksum,
::testing::Combine(
::testing::ValuesIn(GetSupportedCompressions()),
::testing::Values(false),
::testing::Values(
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch),
::testing::Values(true)));
} // namespace ROCKSDB_NAMESPACE
int main(int argc, char** argv) {
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}