mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +00:00
ed46981bea
Summary: FilePrefetchBuffer makes an unchecked assumption about the behavior of RandomAccessFileReader::Read: that it will write to the provided buffer rather than returning the data in an alternate buffer. FilePrefetchBuffer has been quietly incompatible with mmap reads (e.g. allow_mmap_reads / use_mmap_reads) because in that case an alternate buffer is returned (mmapped memory). This incompatibility currently leads to quiet data corruption, as seen in amplified crash test failure in https://github.com/facebook/rocksdb/issues/12200. In this change, * Check whether RandomAccessFileReader::Read has the expected behavior, and fail if not. (Assertion failure in debug build, return Corruption in release build.) This will detect future regressions synchronously and precisely, rather than relying on debugging downstream data corruption. * Why not recover? My understanding is that FilePrefetchBuffer is not intended for use when RandomAccessFileReader::Read uses an alternate buffer, so quietly recovering could lead to undesirable (inefficient) behavior. * Mention incompatibility with mmap-based readers in the internal API comments for FilePrefetchBuffer * Fix two cases where FilePrefetchBuffer could be used with mmap, both stemming from SstFileDumper, though one fix is in BlockBasedTableReader. There is currently no way to ask a RandomAccessFileReader whether it's using mmap, so we currently have to rely on other options as clues. Keeping separate from https://github.com/facebook/rocksdb/issues/12200 in part because this change is more appropriate for backport than that one. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12206 Test Plan: * Manually verified that the new check aids in debugging. * Unit test added, that fails if either fix is missed. * Ran blackbox_crash_test for hours, with and without https://github.com/facebook/rocksdb/issues/12200 Reviewed By: akankshamahajan15 Differential Revision: D52551701 Pulled By: pdillinger fbshipit-source-id: dea87c5782b7c484a6c6e424585c8832dfc580dc
849 lines
35 KiB
C++
849 lines
35 KiB
C++
// 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 <cmath>
|
|
#include <memory>
|
|
#include <string>
|
|
|
|
#include "cache/cache_reservation_manager.h"
|
|
#include "db/db_test_util.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/compression_type.h"
|
|
#include "rocksdb/db.h"
|
|
#include "rocksdb/file_system.h"
|
|
#include "rocksdb/options.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 BlockBasedTableReaderBaseTest : public testing::Test {
|
|
public:
|
|
static constexpr int kBytesPerEntry = 256;
|
|
// 16 = (default block size) 4 * 1024 / kBytesPerEntry
|
|
static constexpr int kEntriesPerBlock = 16;
|
|
|
|
protected:
|
|
// Prepare key-value pairs to occupy multiple blocks.
|
|
// Each (key, value) pair is `kBytesPerEntry` byte, every kEntriesPerBlock
|
|
// pairs constitute 1 block.
|
|
// If mixed_with_human_readable_string_value == true,
|
|
// then adjacent blocks contain values with different compression
|
|
// complexity: human readable strings are easier to compress than random
|
|
// strings. key is an internal key.
|
|
// When ts_sz > 0 and `same_key_diff_ts` is true, this
|
|
// function generate keys with the same user provided key, with different
|
|
// user defined timestamps and different sequence number to differentiate them
|
|
static std::vector<std::pair<std::string, std::string>> GenerateKVMap(
|
|
int num_block = 2, bool mixed_with_human_readable_string_value = false,
|
|
size_t ts_sz = 0, bool same_key_diff_ts = false) {
|
|
std::vector<std::pair<std::string, std::string>> kv;
|
|
|
|
SequenceNumber seq_no = 0;
|
|
uint64_t current_udt = 0;
|
|
if (same_key_diff_ts) {
|
|
// These numbers are based on the number of keys to create + an arbitrary
|
|
// buffer number (100) to avoid overflow.
|
|
current_udt = kEntriesPerBlock * num_block + 100;
|
|
seq_no = kEntriesPerBlock * num_block + 100;
|
|
}
|
|
Random rnd(101);
|
|
uint32_t key = 0;
|
|
// To make each (key, value) pair occupy exactly kBytesPerEntry bytes.
|
|
int value_size = kBytesPerEntry - (8 + static_cast<int>(ts_sz) +
|
|
static_cast<int>(kNumInternalBytes));
|
|
for (int block = 0; block < num_block; block++) {
|
|
for (int i = 0; i < kEntriesPerBlock; 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.
|
|
snprintf(k, sizeof(k), "%08u", key);
|
|
std::string v;
|
|
if (mixed_with_human_readable_string_value) {
|
|
v = (block % 2) ? rnd.HumanReadableString(value_size)
|
|
: rnd.RandomString(value_size);
|
|
} else {
|
|
v = rnd.RandomString(value_size);
|
|
}
|
|
std::string user_key = std::string(k);
|
|
if (ts_sz > 0) {
|
|
if (same_key_diff_ts) {
|
|
PutFixed64(&user_key, current_udt);
|
|
current_udt -= 1;
|
|
} else {
|
|
PutFixed64(&user_key, 0);
|
|
}
|
|
}
|
|
InternalKey internal_key(user_key, seq_no, ValueType::kTypeValue);
|
|
kv.emplace_back(internal_key.Encode().ToString(), v);
|
|
if (same_key_diff_ts) {
|
|
seq_no -= 1;
|
|
} else {
|
|
key++;
|
|
}
|
|
}
|
|
}
|
|
return kv;
|
|
}
|
|
|
|
void SetUp() override {
|
|
SetupSyncPointsToMockDirectIO();
|
|
test_dir_ = test::PerThreadDBPath("block_based_table_reader_test");
|
|
env_ = Env::Default();
|
|
fs_ = FileSystem::Default();
|
|
ASSERT_OK(fs_->CreateDir(test_dir_, IOOptions(), nullptr));
|
|
ConfigureTableFactory();
|
|
}
|
|
|
|
virtual void ConfigureTableFactory() = 0;
|
|
|
|
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 ImmutableOptions& ioptions,
|
|
const CompressionType& compression_type,
|
|
const std::vector<std::pair<std::string, std::string>>& kv,
|
|
uint32_t compression_parallel_threads = 1,
|
|
uint32_t compression_dict_bytes = 0) {
|
|
std::unique_ptr<WritableFileWriter> writer;
|
|
NewFileWriter(table_name, &writer);
|
|
|
|
InternalKeyComparator comparator(ioptions.user_comparator);
|
|
ColumnFamilyOptions cf_options;
|
|
cf_options.prefix_extractor = options_.prefix_extractor;
|
|
MutableCFOptions moptions(cf_options);
|
|
CompressionOptions compression_opts;
|
|
compression_opts.parallel_threads = compression_parallel_threads;
|
|
// Enable compression dictionary and set a buffering limit that is the same
|
|
// as each block's size.
|
|
compression_opts.max_dict_bytes = compression_dict_bytes;
|
|
compression_opts.max_dict_buffer_bytes = compression_dict_bytes;
|
|
IntTblPropCollectorFactories factories;
|
|
const ReadOptions read_options;
|
|
const WriteOptions write_options;
|
|
std::unique_ptr<TableBuilder> table_builder(
|
|
options_.table_factory->NewTableBuilder(
|
|
TableBuilderOptions(ioptions, moptions, read_options, write_options,
|
|
comparator, &factories, compression_type,
|
|
compression_opts, 0 /* column_family_id */,
|
|
kDefaultColumnFamilyName, -1 /* level */),
|
|
writer.get()));
|
|
|
|
// Build table.
|
|
for (auto it = kv.begin(); it != kv.end(); it++) {
|
|
std::string v = it->second;
|
|
table_builder->Add(it->first, 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,
|
|
bool prefetch_index_and_filter_in_cache = true,
|
|
Status* status = nullptr,
|
|
bool user_defined_timestamps_persisted = true) {
|
|
const MutableCFOptions moptions(options_);
|
|
TableReaderOptions table_reader_options = TableReaderOptions(
|
|
ioptions, moptions.prefix_extractor, foptions, comparator,
|
|
0 /* block_protection_bytes_per_key */, false /* _skip_filters */,
|
|
false /* _immortal */, false /* _force_direct_prefetch */,
|
|
-1 /* _level */, nullptr /* _block_cache_tracer */,
|
|
0 /* _max_file_size_for_l0_meta_pin */, "" /* _cur_db_session_id */,
|
|
0 /* _cur_file_num */, {} /* _unique_id */, 0 /* _largest_seqno */,
|
|
0 /* _tail_size */, user_defined_timestamps_persisted);
|
|
|
|
std::unique_ptr<RandomAccessFileReader> file;
|
|
NewFileReader(table_name, foptions, &file);
|
|
|
|
uint64_t file_size = 0;
|
|
ASSERT_OK(env_->GetFileSize(Path(table_name), &file_size));
|
|
|
|
ReadOptions read_opts;
|
|
read_opts.verify_checksums = true;
|
|
std::unique_ptr<TableReader> general_table;
|
|
Status s = options_.table_factory->NewTableReader(
|
|
read_opts, table_reader_options, std::move(file), file_size,
|
|
&general_table, prefetch_index_and_filter_in_cache);
|
|
|
|
if (s.ok()) {
|
|
table->reset(reinterpret_cast<BlockBasedTable*>(general_table.release()));
|
|
}
|
|
|
|
if (status) {
|
|
*status = s;
|
|
}
|
|
}
|
|
|
|
std::string Path(const std::string& fname) { return test_dir_ + "/" + fname; }
|
|
|
|
std::string test_dir_;
|
|
Env* env_;
|
|
std::shared_ptr<FileSystem> fs_;
|
|
Options options_;
|
|
|
|
private:
|
|
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()));
|
|
}
|
|
};
|
|
|
|
// 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
|
|
// Param 5: test mode for the user-defined timestamp feature
|
|
// Param 6: number of parallel compression threads
|
|
// Param 7: CompressionOptions.max_dict_bytes and
|
|
// CompressionOptions.max_dict_buffer_bytes to enable/disable
|
|
// compression dictionary.
|
|
// Param 8: test mode to specify the pattern for generating key / value. When
|
|
// true, generate keys with the same user provided key, different
|
|
// user-defined timestamps (if udt enabled), different sequence
|
|
// numbers. This test mode is used for testing `Get`. When false,
|
|
// generate keys with different user provided key, same user-defined
|
|
// timestamps (if udt enabled), same sequence number. This test mode is
|
|
// used for testing `Get`, `MultiGet`, and `NewIterator`.
|
|
class BlockBasedTableReaderTest
|
|
: public BlockBasedTableReaderBaseTest,
|
|
public testing::WithParamInterface<std::tuple<
|
|
CompressionType, bool, BlockBasedTableOptions::IndexType, bool,
|
|
test::UserDefinedTimestampTestMode, uint32_t, uint32_t, bool>> {
|
|
protected:
|
|
void SetUp() override {
|
|
compression_type_ = std::get<0>(GetParam());
|
|
use_direct_reads_ = std::get<1>(GetParam());
|
|
test::UserDefinedTimestampTestMode udt_test_mode = std::get<4>(GetParam());
|
|
udt_enabled_ = test::IsUDTEnabled(udt_test_mode);
|
|
persist_udt_ = test::ShouldPersistUDT(udt_test_mode);
|
|
compression_parallel_threads_ = std::get<5>(GetParam());
|
|
compression_dict_bytes_ = std::get<6>(GetParam());
|
|
same_key_diff_ts_ = std::get<7>(GetParam());
|
|
BlockBasedTableReaderBaseTest::SetUp();
|
|
}
|
|
|
|
void ConfigureTableFactory() override {
|
|
BlockBasedTableOptions opts;
|
|
opts.index_type = std::get<2>(GetParam());
|
|
opts.no_block_cache = std::get<3>(GetParam());
|
|
opts.filter_policy.reset(NewBloomFilterPolicy(10, false));
|
|
opts.partition_filters =
|
|
opts.index_type ==
|
|
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
|
|
opts.metadata_cache_options.partition_pinning = PinningTier::kAll;
|
|
options_.table_factory.reset(
|
|
static_cast<BlockBasedTableFactory*>(NewBlockBasedTableFactory(opts)));
|
|
options_.prefix_extractor =
|
|
std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(3));
|
|
}
|
|
|
|
CompressionType compression_type_;
|
|
bool use_direct_reads_;
|
|
bool udt_enabled_;
|
|
bool persist_udt_;
|
|
uint32_t compression_parallel_threads_;
|
|
uint32_t compression_dict_bytes_;
|
|
bool same_key_diff_ts_;
|
|
};
|
|
|
|
class BlockBasedTableReaderGetTest : public BlockBasedTableReaderTest {};
|
|
|
|
TEST_P(BlockBasedTableReaderGetTest, Get) {
|
|
Options options;
|
|
if (udt_enabled_) {
|
|
options.comparator = test::BytewiseComparatorWithU64TsWrapper();
|
|
}
|
|
options.persist_user_defined_timestamps = persist_udt_;
|
|
size_t ts_sz = options.comparator->timestamp_size();
|
|
std::vector<std::pair<std::string, std::string>> kv =
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(
|
|
100 /* num_block */,
|
|
true /* mixed_with_human_readable_string_value */, ts_sz,
|
|
same_key_diff_ts_);
|
|
|
|
std::string table_name = "BlockBasedTableReaderGetTest_Get" +
|
|
CompressionTypeToString(compression_type_);
|
|
|
|
ImmutableOptions ioptions(options);
|
|
CreateTable(table_name, ioptions, compression_type_, kv,
|
|
compression_parallel_threads_, compression_dict_bytes_);
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
FileOptions foptions;
|
|
foptions.use_direct_reads = use_direct_reads_;
|
|
InternalKeyComparator comparator(options.comparator);
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table,
|
|
true /* prefetch_index_and_filter_in_cache */,
|
|
nullptr /* status */, persist_udt_);
|
|
|
|
ReadOptions read_opts;
|
|
ASSERT_OK(
|
|
table->VerifyChecksum(read_opts, TableReaderCaller::kUserVerifyChecksum));
|
|
|
|
for (size_t i = 0; i < kv.size(); i += 1) {
|
|
Slice key = kv[i].first;
|
|
Slice lkey = key;
|
|
std::string lookup_ikey;
|
|
if (udt_enabled_ && !persist_udt_) {
|
|
// When user-defined timestamps are collapsed to be the minimum timestamp,
|
|
// we also read with the minimum timestamp to be able to retrieve each
|
|
// value.
|
|
ReplaceInternalKeyWithMinTimestamp(&lookup_ikey, key, ts_sz);
|
|
lkey = lookup_ikey;
|
|
}
|
|
// Reading the first entry in a block caches the whole block.
|
|
if (i % kEntriesPerBlock == 0) {
|
|
ASSERT_FALSE(table->TEST_KeyInCache(read_opts, lkey.ToString()));
|
|
} else {
|
|
ASSERT_TRUE(table->TEST_KeyInCache(read_opts, lkey.ToString()));
|
|
}
|
|
PinnableSlice value;
|
|
GetContext get_context(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, ExtractUserKey(key), &value,
|
|
nullptr, nullptr, nullptr, nullptr,
|
|
true /* do_merge */, nullptr, nullptr, nullptr,
|
|
nullptr, nullptr, nullptr);
|
|
ASSERT_OK(table->Get(read_opts, lkey, &get_context, nullptr));
|
|
ASSERT_EQ(value.ToString(), kv[i].second);
|
|
ASSERT_TRUE(table->TEST_KeyInCache(read_opts, lkey.ToString()));
|
|
}
|
|
}
|
|
|
|
// Tests MultiGet in both direct IO and non-direct IO mode.
|
|
// The keys should be in cache after MultiGet.
|
|
TEST_P(BlockBasedTableReaderTest, MultiGet) {
|
|
Options options;
|
|
ReadOptions read_opts;
|
|
std::string dummy_ts(sizeof(uint64_t), '\0');
|
|
Slice read_timestamp = dummy_ts;
|
|
if (udt_enabled_) {
|
|
options.comparator = test::BytewiseComparatorWithU64TsWrapper();
|
|
read_opts.timestamp = &read_timestamp;
|
|
}
|
|
options.persist_user_defined_timestamps = persist_udt_;
|
|
size_t ts_sz = options.comparator->timestamp_size();
|
|
std::vector<std::pair<std::string, std::string>> kv =
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(
|
|
100 /* num_block */,
|
|
true /* mixed_with_human_readable_string_value */, ts_sz);
|
|
|
|
// Prepare keys, values, and statuses for MultiGet.
|
|
autovector<Slice, MultiGetContext::MAX_BATCH_SIZE> keys;
|
|
autovector<Slice, MultiGetContext::MAX_BATCH_SIZE> keys_without_timestamps;
|
|
autovector<PinnableSlice, MultiGetContext::MAX_BATCH_SIZE> values;
|
|
autovector<Status, MultiGetContext::MAX_BATCH_SIZE> statuses;
|
|
autovector<const std::string*, MultiGetContext::MAX_BATCH_SIZE>
|
|
expected_values;
|
|
{
|
|
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);
|
|
if (ts_sz > 0) {
|
|
Slice ukey_without_ts =
|
|
ExtractUserKeyAndStripTimestamp(it->first, ts_sz);
|
|
keys_without_timestamps.push_back(ukey_without_ts);
|
|
} else {
|
|
keys_without_timestamps.emplace_back(ExtractUserKey(it->first));
|
|
}
|
|
values.emplace_back();
|
|
statuses.emplace_back();
|
|
expected_values.push_back(&(it->second));
|
|
std::advance(it, step);
|
|
}
|
|
}
|
|
|
|
std::string table_name = "BlockBasedTableReaderTest_MultiGet" +
|
|
CompressionTypeToString(compression_type_);
|
|
|
|
ImmutableOptions ioptions(options);
|
|
CreateTable(table_name, ioptions, compression_type_, kv,
|
|
compression_parallel_threads_, compression_dict_bytes_);
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
FileOptions foptions;
|
|
foptions.use_direct_reads = use_direct_reads_;
|
|
InternalKeyComparator comparator(options.comparator);
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table,
|
|
true /* bool prefetch_index_and_filter_in_cache */,
|
|
nullptr /* status */, persist_udt_);
|
|
|
|
ASSERT_OK(
|
|
table->VerifyChecksum(read_opts, TableReaderCaller::kUserVerifyChecksum));
|
|
|
|
// Ensure that keys are not in cache before MultiGet.
|
|
for (auto& key : keys) {
|
|
ASSERT_FALSE(table->TEST_KeyInCache(read_opts, key.ToString()));
|
|
}
|
|
|
|
// 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(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, ExtractUserKey(keys[i]),
|
|
&values[i], nullptr, nullptr, nullptr, nullptr,
|
|
true /* do_merge */, nullptr, nullptr, nullptr,
|
|
nullptr, nullptr, nullptr);
|
|
key_context.emplace_back(nullptr, keys_without_timestamps[i], &values[i],
|
|
nullptr, 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, read_opts,
|
|
fs_.get(), nullptr);
|
|
|
|
// Execute MultiGet.
|
|
MultiGetContext::Range range = ctx.GetMultiGetRange();
|
|
PerfContext* perf_ctx = get_perf_context();
|
|
perf_ctx->Reset();
|
|
table->MultiGet(read_opts, &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(read_opts, keys[i]));
|
|
ASSERT_EQ(values[i].ToString(), *expected_values[i]);
|
|
}
|
|
}
|
|
|
|
TEST_P(BlockBasedTableReaderTest, NewIterator) {
|
|
Options options;
|
|
ReadOptions read_opts;
|
|
std::string dummy_ts(sizeof(uint64_t), '\0');
|
|
Slice read_timestamp = dummy_ts;
|
|
if (udt_enabled_) {
|
|
options.comparator = test::BytewiseComparatorWithU64TsWrapper();
|
|
read_opts.timestamp = &read_timestamp;
|
|
}
|
|
options.persist_user_defined_timestamps = persist_udt_;
|
|
size_t ts_sz = options.comparator->timestamp_size();
|
|
std::vector<std::pair<std::string, std::string>> kv =
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(
|
|
100 /* num_block */,
|
|
true /* mixed_with_human_readable_string_value */, ts_sz);
|
|
|
|
std::string table_name = "BlockBasedTableReaderTest_NewIterator" +
|
|
CompressionTypeToString(compression_type_);
|
|
|
|
ImmutableOptions ioptions(options);
|
|
CreateTable(table_name, ioptions, compression_type_, kv,
|
|
compression_parallel_threads_, compression_dict_bytes_);
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
FileOptions foptions;
|
|
foptions.use_direct_reads = use_direct_reads_;
|
|
InternalKeyComparator comparator(options.comparator);
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table,
|
|
true /* bool prefetch_index_and_filter_in_cache */,
|
|
nullptr /* status */, persist_udt_);
|
|
ASSERT_OK(
|
|
table->VerifyChecksum(read_opts, TableReaderCaller::kUserVerifyChecksum));
|
|
|
|
std::unique_ptr<InternalIterator> iter;
|
|
iter.reset(table->NewIterator(
|
|
read_opts, options_.prefix_extractor.get(), /*arena=*/nullptr,
|
|
/*skip_filters=*/false, TableReaderCaller::kUncategorized));
|
|
|
|
// Test forward scan.
|
|
ASSERT_TRUE(!iter->Valid());
|
|
iter->SeekToFirst();
|
|
ASSERT_OK(iter->status());
|
|
for (auto kv_iter = kv.begin(); kv_iter != kv.end(); kv_iter++) {
|
|
ASSERT_EQ(iter->key().ToString(), kv_iter->first);
|
|
ASSERT_EQ(iter->value().ToString(), kv_iter->second);
|
|
iter->Next();
|
|
ASSERT_OK(iter->status());
|
|
}
|
|
ASSERT_TRUE(!iter->Valid());
|
|
ASSERT_OK(iter->status());
|
|
|
|
// Test backward scan.
|
|
iter->SeekToLast();
|
|
ASSERT_OK(iter->status());
|
|
for (auto kv_iter = kv.rbegin(); kv_iter != kv.rend(); kv_iter++) {
|
|
ASSERT_EQ(iter->key().ToString(), kv_iter->first);
|
|
ASSERT_EQ(iter->value().ToString(), kv_iter->second);
|
|
iter->Prev();
|
|
ASSERT_OK(iter->status());
|
|
}
|
|
ASSERT_TRUE(!iter->Valid());
|
|
ASSERT_OK(iter->status());
|
|
}
|
|
|
|
class ChargeTableReaderTest
|
|
: public BlockBasedTableReaderBaseTest,
|
|
public testing::WithParamInterface<
|
|
CacheEntryRoleOptions::Decision /* charge_table_reader_mem */> {
|
|
protected:
|
|
static std::size_t CalculateMaxTableReaderNumBeforeCacheFull(
|
|
std::size_t cache_capacity, std::size_t approx_table_reader_mem) {
|
|
// To make calculation easier for testing
|
|
assert(cache_capacity % CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>::
|
|
GetDummyEntrySize() ==
|
|
0 &&
|
|
cache_capacity >= 2 * CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>::
|
|
GetDummyEntrySize());
|
|
|
|
// We need to subtract 1 for max_num_dummy_entry to account for dummy
|
|
// entries' overhead, assumed the overhead is no greater than 1 dummy entry
|
|
// size
|
|
std::size_t max_num_dummy_entry =
|
|
(size_t)std::floor((
|
|
1.0 * cache_capacity /
|
|
CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>::GetDummyEntrySize())) -
|
|
1;
|
|
std::size_t cache_capacity_rounded_to_dummy_entry_multiples =
|
|
max_num_dummy_entry *
|
|
CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>::GetDummyEntrySize();
|
|
std::size_t max_table_reader_num_capped = static_cast<std::size_t>(
|
|
std::floor(1.0 * cache_capacity_rounded_to_dummy_entry_multiples /
|
|
approx_table_reader_mem));
|
|
|
|
return max_table_reader_num_capped;
|
|
}
|
|
|
|
void SetUp() override {
|
|
// To cache and re-use the same kv map and compression type in the test
|
|
// suite for elimiating variance caused by these two factors
|
|
kv_ = BlockBasedTableReaderBaseTest::GenerateKVMap();
|
|
compression_type_ = CompressionType::kNoCompression;
|
|
|
|
table_reader_charge_tracking_cache_ = std::make_shared<
|
|
TargetCacheChargeTrackingCache<
|
|
CacheEntryRole::kBlockBasedTableReader>>((NewLRUCache(
|
|
4 * CacheReservationManagerImpl<
|
|
CacheEntryRole::kBlockBasedTableReader>::GetDummyEntrySize(),
|
|
0 /* num_shard_bits */, true /* strict_capacity_limit */)));
|
|
|
|
// To ApproximateTableReaderMem() without being affected by
|
|
// the feature of charging its memory, we turn off the feature
|
|
charge_table_reader_ = CacheEntryRoleOptions::Decision::kDisabled;
|
|
BlockBasedTableReaderBaseTest::SetUp();
|
|
approx_table_reader_mem_ = ApproximateTableReaderMem();
|
|
|
|
// Now we condtionally turn on the feature to test
|
|
charge_table_reader_ = GetParam();
|
|
ConfigureTableFactory();
|
|
}
|
|
|
|
void ConfigureTableFactory() override {
|
|
BlockBasedTableOptions table_options;
|
|
table_options.cache_usage_options.options_overrides.insert(
|
|
{CacheEntryRole::kBlockBasedTableReader,
|
|
{/*.charged = */ charge_table_reader_}});
|
|
table_options.block_cache = table_reader_charge_tracking_cache_;
|
|
|
|
table_options.cache_index_and_filter_blocks = false;
|
|
table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
|
|
table_options.partition_filters = true;
|
|
table_options.index_type = BlockBasedTableOptions::kTwoLevelIndexSearch;
|
|
|
|
options_.table_factory.reset(NewBlockBasedTableFactory(table_options));
|
|
}
|
|
|
|
CacheEntryRoleOptions::Decision charge_table_reader_;
|
|
std::shared_ptr<
|
|
TargetCacheChargeTrackingCache<CacheEntryRole::kBlockBasedTableReader>>
|
|
table_reader_charge_tracking_cache_;
|
|
std::size_t approx_table_reader_mem_;
|
|
std::vector<std::pair<std::string, std::string>> kv_;
|
|
CompressionType compression_type_;
|
|
|
|
private:
|
|
std::size_t ApproximateTableReaderMem() {
|
|
std::size_t approx_table_reader_mem = 0;
|
|
|
|
std::string table_name = "table_for_approx_table_reader_mem";
|
|
ImmutableOptions ioptions(options_);
|
|
CreateTable(table_name, ioptions, compression_type_, kv_);
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
Status s;
|
|
NewBlockBasedTableReader(
|
|
FileOptions(), ImmutableOptions(options_),
|
|
InternalKeyComparator(options_.comparator), table_name, &table,
|
|
false /* prefetch_index_and_filter_in_cache */, &s);
|
|
assert(s.ok());
|
|
|
|
approx_table_reader_mem = table->ApproximateMemoryUsage();
|
|
assert(approx_table_reader_mem > 0);
|
|
return approx_table_reader_mem;
|
|
}
|
|
};
|
|
|
|
INSTANTIATE_TEST_CASE_P(
|
|
ChargeTableReaderTest, ChargeTableReaderTest,
|
|
::testing::Values(CacheEntryRoleOptions::Decision::kEnabled,
|
|
CacheEntryRoleOptions::Decision::kDisabled));
|
|
|
|
TEST_P(ChargeTableReaderTest, Basic) {
|
|
const std::size_t max_table_reader_num_capped =
|
|
ChargeTableReaderTest::CalculateMaxTableReaderNumBeforeCacheFull(
|
|
table_reader_charge_tracking_cache_->GetCapacity(),
|
|
approx_table_reader_mem_);
|
|
|
|
// Acceptable estimtation errors coming from
|
|
// 1. overstimate max_table_reader_num_capped due to # dummy entries is high
|
|
// and results in metadata charge overhead greater than 1 dummy entry size
|
|
// (violating our assumption in calculating max_table_reader_num_capped)
|
|
// 2. overestimate/underestimate max_table_reader_num_capped due to the gap
|
|
// between ApproximateTableReaderMem() and actual table reader mem
|
|
std::size_t max_table_reader_num_capped_upper_bound =
|
|
(std::size_t)(max_table_reader_num_capped * 1.05);
|
|
std::size_t max_table_reader_num_capped_lower_bound =
|
|
(std::size_t)(max_table_reader_num_capped * 0.95);
|
|
std::size_t max_table_reader_num_uncapped =
|
|
(std::size_t)(max_table_reader_num_capped * 1.1);
|
|
ASSERT_GT(max_table_reader_num_uncapped,
|
|
max_table_reader_num_capped_upper_bound)
|
|
<< "We need `max_table_reader_num_uncapped` > "
|
|
"`max_table_reader_num_capped_upper_bound` to differentiate cases "
|
|
"between "
|
|
"charge_table_reader_ == kDisabled and == kEnabled)";
|
|
|
|
Status s = Status::OK();
|
|
std::size_t opened_table_reader_num = 0;
|
|
std::string table_name;
|
|
std::vector<std::unique_ptr<BlockBasedTable>> tables;
|
|
ImmutableOptions ioptions(options_);
|
|
// Keep creating BlockBasedTableReader till hiting the memory limit based on
|
|
// cache capacity and creation fails (when charge_table_reader_ ==
|
|
// kEnabled) or reaching a specfied big number of table readers (when
|
|
// charge_table_reader_ == kDisabled)
|
|
while (s.ok() && opened_table_reader_num < max_table_reader_num_uncapped) {
|
|
table_name = "table_" + std::to_string(opened_table_reader_num);
|
|
CreateTable(table_name, ioptions, compression_type_, kv_);
|
|
tables.push_back(std::unique_ptr<BlockBasedTable>());
|
|
NewBlockBasedTableReader(
|
|
FileOptions(), ImmutableOptions(options_),
|
|
InternalKeyComparator(options_.comparator), table_name, &tables.back(),
|
|
false /* prefetch_index_and_filter_in_cache */, &s);
|
|
if (s.ok()) {
|
|
++opened_table_reader_num;
|
|
}
|
|
}
|
|
|
|
if (charge_table_reader_ == CacheEntryRoleOptions::Decision::kEnabled) {
|
|
EXPECT_TRUE(s.IsMemoryLimit()) << "s: " << s.ToString();
|
|
EXPECT_TRUE(s.ToString().find(
|
|
kCacheEntryRoleToCamelString[static_cast<std::uint32_t>(
|
|
CacheEntryRole::kBlockBasedTableReader)]) !=
|
|
std::string::npos);
|
|
EXPECT_TRUE(s.ToString().find("memory limit based on cache capacity") !=
|
|
std::string::npos);
|
|
|
|
EXPECT_GE(opened_table_reader_num, max_table_reader_num_capped_lower_bound);
|
|
EXPECT_LE(opened_table_reader_num, max_table_reader_num_capped_upper_bound);
|
|
|
|
std::size_t updated_max_table_reader_num_capped =
|
|
ChargeTableReaderTest::CalculateMaxTableReaderNumBeforeCacheFull(
|
|
table_reader_charge_tracking_cache_->GetCapacity() / 2,
|
|
approx_table_reader_mem_);
|
|
|
|
// Keep deleting BlockBasedTableReader to lower down memory usage from the
|
|
// memory limit to make the next creation succeeds
|
|
while (opened_table_reader_num >= updated_max_table_reader_num_capped) {
|
|
tables.pop_back();
|
|
--opened_table_reader_num;
|
|
}
|
|
table_name = "table_for_successful_table_reader_open";
|
|
CreateTable(table_name, ioptions, compression_type_, kv_);
|
|
tables.push_back(std::unique_ptr<BlockBasedTable>());
|
|
NewBlockBasedTableReader(
|
|
FileOptions(), ImmutableOptions(options_),
|
|
InternalKeyComparator(options_.comparator), table_name, &tables.back(),
|
|
false /* prefetch_index_and_filter_in_cache */, &s);
|
|
EXPECT_TRUE(s.ok()) << s.ToString();
|
|
|
|
tables.clear();
|
|
EXPECT_EQ(table_reader_charge_tracking_cache_->GetCacheCharge(), 0);
|
|
} else {
|
|
EXPECT_TRUE(s.ok() &&
|
|
opened_table_reader_num == max_table_reader_num_uncapped)
|
|
<< "s: " << s.ToString() << " opened_table_reader_num: "
|
|
<< std::to_string(opened_table_reader_num);
|
|
EXPECT_EQ(table_reader_charge_tracking_cache_->GetCacheCharge(), 0);
|
|
}
|
|
}
|
|
|
|
class BlockBasedTableReaderTestVerifyChecksum
|
|
: public BlockBasedTableReaderTest {
|
|
public:
|
|
BlockBasedTableReaderTestVerifyChecksum() : BlockBasedTableReaderTest() {}
|
|
};
|
|
|
|
TEST_P(BlockBasedTableReaderTestVerifyChecksum, ChecksumMismatch) {
|
|
Options options;
|
|
ReadOptions read_opts;
|
|
std::string dummy_ts(sizeof(uint64_t), '\0');
|
|
Slice read_timestamp = dummy_ts;
|
|
if (udt_enabled_) {
|
|
options.comparator = test::BytewiseComparatorWithU64TsWrapper();
|
|
read_opts.timestamp = &read_timestamp;
|
|
}
|
|
options.persist_user_defined_timestamps = persist_udt_;
|
|
size_t ts_sz = options.comparator->timestamp_size();
|
|
std::vector<std::pair<std::string, std::string>> kv =
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(
|
|
800 /* num_block */,
|
|
false /* mixed_with_human_readable_string_value=*/, ts_sz);
|
|
|
|
options.statistics = CreateDBStatistics();
|
|
ImmutableOptions ioptions(options);
|
|
std::string table_name =
|
|
"BlockBasedTableReaderTest" + CompressionTypeToString(compression_type_);
|
|
CreateTable(table_name, ioptions, compression_type_, kv,
|
|
compression_parallel_threads_, compression_dict_bytes_);
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
FileOptions foptions;
|
|
foptions.use_direct_reads = use_direct_reads_;
|
|
InternalKeyComparator comparator(options.comparator);
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table,
|
|
true /* bool prefetch_index_and_filter_in_cache */,
|
|
nullptr /* status */, persist_udt_);
|
|
|
|
// 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(
|
|
read_opts, /*need_upper_bound_check=*/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
|
|
ASSERT_OK(test::CorruptFile(options.env, Path(table_name),
|
|
static_cast<int>(handle.offset()), 128));
|
|
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table,
|
|
true /* bool prefetch_index_and_filter_in_cache */,
|
|
nullptr /* status */, persist_udt_);
|
|
ASSERT_EQ(0,
|
|
options.statistics->getTickerCount(BLOCK_CHECKSUM_MISMATCH_COUNT));
|
|
Status s =
|
|
table->VerifyChecksum(read_opts, TableReaderCaller::kUserVerifyChecksum);
|
|
ASSERT_EQ(1,
|
|
options.statistics->getTickerCount(BLOCK_CHECKSUM_MISMATCH_COUNT));
|
|
ASSERT_EQ(s.code(), Status::kCorruption);
|
|
}
|
|
|
|
// Param 1: compression type
|
|
// Param 2: whether to use direct reads
|
|
// Param 3: Block Based Table Index type, partitioned filters are also enabled
|
|
// when index type is kTwoLevelIndexSearch
|
|
// Param 4: BBTO no_block_cache option
|
|
// Param 5: test mode for the user-defined timestamp feature
|
|
// Param 6: number of parallel compression threads
|
|
// Param 7: CompressionOptions.max_dict_bytes and
|
|
// CompressionOptions.max_dict_buffer_bytes. This enable/disables
|
|
// compression dictionary.
|
|
// Param 8: test mode to specify the pattern for generating key / value pairs.
|
|
INSTANTIATE_TEST_CASE_P(
|
|
BlockBasedTableReaderTest, BlockBasedTableReaderTest,
|
|
::testing::Combine(
|
|
::testing::ValuesIn(GetSupportedCompressions()), ::testing::Bool(),
|
|
::testing::Values(
|
|
BlockBasedTableOptions::IndexType::kBinarySearch,
|
|
BlockBasedTableOptions::IndexType::kHashSearch,
|
|
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
|
|
BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey),
|
|
::testing::Values(false), ::testing::ValuesIn(test::GetUDTTestModes()),
|
|
::testing::Values(1, 2), ::testing::Values(0, 4096),
|
|
::testing::Values(false)));
|
|
INSTANTIATE_TEST_CASE_P(
|
|
BlockBasedTableReaderGetTest, BlockBasedTableReaderGetTest,
|
|
::testing::Combine(
|
|
::testing::ValuesIn(GetSupportedCompressions()), ::testing::Bool(),
|
|
::testing::Values(
|
|
BlockBasedTableOptions::IndexType::kBinarySearch,
|
|
BlockBasedTableOptions::IndexType::kHashSearch,
|
|
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
|
|
BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey),
|
|
::testing::Values(false), ::testing::ValuesIn(test::GetUDTTestModes()),
|
|
::testing::Values(1, 2), ::testing::Values(0, 4096),
|
|
::testing::Values(false, true)));
|
|
INSTANTIATE_TEST_CASE_P(
|
|
VerifyChecksum, BlockBasedTableReaderTestVerifyChecksum,
|
|
::testing::Combine(
|
|
::testing::ValuesIn(GetSupportedCompressions()),
|
|
::testing::Values(false),
|
|
::testing::Values(
|
|
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch),
|
|
::testing::Values(true), ::testing::ValuesIn(test::GetUDTTestModes()),
|
|
::testing::Values(1, 2), ::testing::Values(0),
|
|
::testing::Values(false)));
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
int main(int argc, char** argv) {
|
|
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
return RUN_ALL_TESTS();
|
|
}
|