2020-05-15 06:23:32 +00:00
|
|
|
// 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"
|
|
|
|
|
2022-04-20 02:02:00 +00:00
|
|
|
#include <cmath>
|
2022-04-06 17:33:00 +00:00
|
|
|
#include <memory>
|
|
|
|
#include <string>
|
|
|
|
|
|
|
|
#include "cache/cache_reservation_manager.h"
|
|
|
|
#include "db/db_test_util.h"
|
2020-05-15 06:23:32 +00:00
|
|
|
#include "db/table_properties_collector.h"
|
2020-07-09 21:33:42 +00:00
|
|
|
#include "file/file_util.h"
|
2020-05-15 06:23:32 +00:00
|
|
|
#include "options/options_helper.h"
|
|
|
|
#include "port/port.h"
|
|
|
|
#include "port/stack_trace.h"
|
2022-04-06 17:33:00 +00:00
|
|
|
#include "rocksdb/compression_type.h"
|
2021-09-29 11:01:57 +00:00
|
|
|
#include "rocksdb/db.h"
|
2020-07-09 21:33:42 +00:00
|
|
|
#include "rocksdb/file_system.h"
|
2020-05-15 06:23:32 +00:00
|
|
|
#include "table/block_based/block_based_table_builder.h"
|
|
|
|
#include "table/block_based/block_based_table_factory.h"
|
2020-07-09 21:33:42 +00:00
|
|
|
#include "table/block_based/partitioned_index_iterator.h"
|
2020-05-15 06:23:32 +00:00
|
|
|
#include "table/format.h"
|
|
|
|
#include "test_util/testharness.h"
|
|
|
|
#include "test_util/testutil.h"
|
2020-07-09 21:33:42 +00:00
|
|
|
#include "util/random.h"
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
class BlockBasedTableReaderBaseTest : public testing::Test {
|
2020-05-15 06:23:32 +00:00
|
|
|
protected:
|
2022-04-06 17:33:00 +00:00
|
|
|
// Prepare key-value pairs to occupy multiple blocks.
|
|
|
|
// Each value is 256B, every 16 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.
|
|
|
|
static std::map<std::string, std::string> GenerateKVMap(
|
|
|
|
int num_block = 100,
|
|
|
|
bool mixed_with_human_readable_string_value = false) {
|
|
|
|
std::map<std::string, std::string> kv;
|
2020-05-15 06:23:32 +00:00
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
Random rnd(101);
|
|
|
|
uint32_t key = 0;
|
|
|
|
for (int block = 0; block < num_block; 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 (mixed_with_human_readable_string_value) {
|
|
|
|
v = (block % 2) ? rnd.HumanReadableString(256)
|
|
|
|
: rnd.RandomString(256);
|
|
|
|
} else {
|
|
|
|
v = rnd.RandomString(256);
|
|
|
|
}
|
|
|
|
kv[std::string(k)] = v;
|
|
|
|
key++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return kv;
|
|
|
|
}
|
2020-05-15 06:23:32 +00:00
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
void SetUp() override {
|
2020-07-09 21:33:42 +00:00
|
|
|
SetupSyncPointsToMockDirectIO();
|
2020-05-15 06:23:32 +00:00
|
|
|
test_dir_ = test::PerThreadDBPath("block_based_table_reader_test");
|
|
|
|
env_ = Env::Default();
|
|
|
|
fs_ = FileSystem::Default();
|
|
|
|
ASSERT_OK(fs_->CreateDir(test_dir_, IOOptions(), nullptr));
|
2022-04-06 17:33:00 +00:00
|
|
|
ConfigureTableFactory();
|
2020-05-15 06:23:32 +00:00
|
|
|
}
|
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
virtual void ConfigureTableFactory() = 0;
|
|
|
|
|
2020-07-09 21:33:42 +00:00
|
|
|
void TearDown() override { EXPECT_OK(DestroyDir(env_, test_dir_)); }
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
// 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.
|
2022-04-06 17:33:00 +00:00
|
|
|
ImmutableOptions ioptions(options_);
|
|
|
|
InternalKeyComparator comparator(options_.comparator);
|
2020-05-15 06:23:32 +00:00
|
|
|
ColumnFamilyOptions cf_options;
|
|
|
|
MutableCFOptions moptions(cf_options);
|
2021-05-18 01:27:42 +00:00
|
|
|
IntTblPropCollectorFactories factories;
|
2022-04-06 17:33:00 +00:00
|
|
|
std::unique_ptr<TableBuilder> table_builder(
|
|
|
|
options_.table_factory->NewTableBuilder(
|
|
|
|
TableBuilderOptions(ioptions, moptions, comparator, &factories,
|
|
|
|
compression_type, CompressionOptions(),
|
|
|
|
0 /* column_family_id */,
|
|
|
|
kDefaultColumnFamilyName, -1 /* level */),
|
|
|
|
writer.get()));
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
// 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,
|
2021-05-05 20:59:21 +00:00
|
|
|
const ImmutableOptions& ioptions,
|
2020-05-15 06:23:32 +00:00
|
|
|
const InternalKeyComparator& comparator,
|
|
|
|
const std::string& table_name,
|
2022-04-06 17:33:00 +00:00
|
|
|
std::unique_ptr<BlockBasedTable>* table,
|
|
|
|
bool prefetch_index_and_filter_in_cache = true,
|
|
|
|
Status* status = nullptr) {
|
|
|
|
const MutableCFOptions moptions(options_);
|
|
|
|
TableReaderOptions table_reader_options = TableReaderOptions(
|
|
|
|
ioptions, moptions.prefix_extractor, EnvOptions(), comparator);
|
|
|
|
|
2020-05-15 06:23:32 +00:00
|
|
|
std::unique_ptr<RandomAccessFileReader> file;
|
|
|
|
NewFileReader(table_name, foptions, &file);
|
|
|
|
|
|
|
|
uint64_t file_size = 0;
|
|
|
|
ASSERT_OK(env_->GetFileSize(Path(table_name), &file_size));
|
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
std::unique_ptr<TableReader> general_table;
|
|
|
|
Status s = options_.table_factory->NewTableReader(
|
|
|
|
ReadOptions(), 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()));
|
|
|
|
}
|
2020-05-15 06:23:32 +00:00
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
if (status) {
|
|
|
|
*status = s;
|
|
|
|
}
|
2020-05-15 06:23:32 +00:00
|
|
|
}
|
|
|
|
|
2020-06-05 18:06:26 +00:00
|
|
|
std::string Path(const std::string& fname) { return test_dir_ + "/" + fname; }
|
|
|
|
|
2020-05-15 06:23:32 +00:00
|
|
|
std::string test_dir_;
|
|
|
|
Env* env_;
|
|
|
|
std::shared_ptr<FileSystem> fs_;
|
2022-04-06 17:33:00 +00:00
|
|
|
Options options_;
|
2020-05-15 06:23:32 +00:00
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
private:
|
2020-05-15 06:23:32 +00:00
|
|
|
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));
|
2021-03-15 11:32:24 +00:00
|
|
|
reader->reset(new RandomAccessFileReader(std::move(f), path,
|
|
|
|
env_->GetSystemClock().get()));
|
2020-05-15 06:23:32 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ToInternalKey(const std::string& key) {
|
|
|
|
InternalKey internal_key(key, 0, ValueType::kTypeValue);
|
|
|
|
return internal_key.Encode().ToString();
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2022-04-06 17:33:00 +00:00
|
|
|
class BlockBasedTableReaderTest
|
|
|
|
: public BlockBasedTableReaderBaseTest,
|
|
|
|
public testing::WithParamInterface<std::tuple<
|
|
|
|
CompressionType, bool, BlockBasedTableOptions::IndexType, bool>> {
|
|
|
|
protected:
|
|
|
|
void SetUp() override {
|
|
|
|
compression_type_ = std::get<0>(GetParam());
|
|
|
|
use_direct_reads_ = std::get<1>(GetParam());
|
|
|
|
BlockBasedTableReaderBaseTest::SetUp();
|
|
|
|
}
|
|
|
|
|
|
|
|
void ConfigureTableFactory() override {
|
|
|
|
BlockBasedTableOptions opts;
|
|
|
|
opts.index_type = std::get<2>(GetParam());
|
|
|
|
opts.no_block_cache = std::get<3>(GetParam());
|
|
|
|
options_.table_factory.reset(
|
|
|
|
static_cast<BlockBasedTableFactory*>(NewBlockBasedTableFactory(opts)));
|
|
|
|
}
|
|
|
|
|
|
|
|
CompressionType compression_type_;
|
|
|
|
bool use_direct_reads_;
|
|
|
|
};
|
|
|
|
|
2020-05-15 06:23:32 +00:00
|
|
|
// Tests MultiGet in both direct IO and non-direct IO mode.
|
|
|
|
// The keys should be in cache after MultiGet.
|
|
|
|
TEST_P(BlockBasedTableReaderTest, MultiGet) {
|
2022-04-06 17:33:00 +00:00
|
|
|
std::map<std::string, std::string> kv =
|
|
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(
|
|
|
|
100 /* num_block */,
|
|
|
|
true /* mixed_with_human_readable_string_value */);
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
// 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;
|
2021-05-05 20:59:21 +00:00
|
|
|
ImmutableOptions ioptions(options);
|
2020-05-15 06:23:32 +00:00
|
|
|
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);
|
|
|
|
}
|
Multi file concurrency in MultiGet using coroutines and async IO (#9968)
Summary:
This PR implements a coroutine version of batched MultiGet in order to concurrently read from multiple SST files in a level using async IO, thus reducing the latency of the MultiGet. The API from the user perspective is still synchronous and single threaded, with the RocksDB part of the processing happening in the context of the caller's thread. In Version::MultiGet, the decision is made whether to call synchronous or coroutine code.
A good way to review this PR is to review the first 4 commits in order - de773b3, 70c2f70, 10b50e1, and 377a597 - before reviewing the rest.
TODO:
1. Figure out how to build it in CircleCI (requires some dependencies to be installed)
2. Do some stress testing with coroutines enabled
No regression in synchronous MultiGet between this branch and main -
```
./db_bench -use_existing_db=true --db=/data/mysql/rocksdb/prefix_scan -benchmarks="readseq,multireadrandom" -key_size=32 -value_size=512 -num=5000000 -batch_size=64 -multiread_batched=true -use_direct_reads=false -duration=60 -ops_between_duration_checks=1 -readonly=true -adaptive_readahead=true -threads=16 -cache_size=10485760000 -async_io=false -multiread_stride=40000 -statistics
```
Branch - ```multireadrandom : 4.025 micros/op 3975111 ops/sec 60.001 seconds 238509056 operations; 2062.3 MB/s (14767808 of 14767808 found)```
Main - ```multireadrandom : 3.987 micros/op 4013216 ops/sec 60.001 seconds 240795392 operations; 2082.1 MB/s (15231040 of 15231040 found)```
More benchmarks in various scenarios are given below. The measurements were taken with ```async_io=false``` (no coroutines) and ```async_io=true``` (use coroutines). For an IO bound workload (with every key requiring an IO), the coroutines version shows a clear benefit, being ~2.6X faster. For CPU bound workloads, the coroutines version has ~6-15% higher CPU utilization, depending on how many keys overlap an SST file.
1. Single thread IO bound workload on remote storage with sparse MultiGet batch keys (~1 key overlap/file) -
No coroutines - ```multireadrandom : 831.774 micros/op 1202 ops/sec 60.001 seconds 72136 operations; 0.6 MB/s (72136 of 72136 found)```
Using coroutines - ```multireadrandom : 318.742 micros/op 3137 ops/sec 60.003 seconds 188248 operations; 1.6 MB/s (188248 of 188248 found)```
2. Single thread CPU bound workload (all data cached) with ~1 key overlap/file -
No coroutines - ```multireadrandom : 4.127 micros/op 242322 ops/sec 60.000 seconds 14539384 operations; 125.7 MB/s (14539384 of 14539384 found)```
Using coroutines - ```multireadrandom : 4.741 micros/op 210935 ops/sec 60.000 seconds 12656176 operations; 109.4 MB/s (12656176 of 12656176 found)```
3. Single thread CPU bound workload with ~2 key overlap/file -
No coroutines - ```multireadrandom : 3.717 micros/op 269000 ops/sec 60.000 seconds 16140024 operations; 139.6 MB/s (16140024 of 16140024 found)```
Using coroutines - ```multireadrandom : 4.146 micros/op 241204 ops/sec 60.000 seconds 14472296 operations; 125.1 MB/s (14472296 of 14472296 found)```
4. CPU bound multi-threaded (16 threads) with ~4 key overlap/file -
No coroutines - ```multireadrandom : 4.534 micros/op 3528792 ops/sec 60.000 seconds 211728728 operations; 1830.7 MB/s (12737024 of 12737024 found) ```
Using coroutines - ```multireadrandom : 4.872 micros/op 3283812 ops/sec 60.000 seconds 197030096 operations; 1703.6 MB/s (12548032 of 12548032 found) ```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9968
Reviewed By: akankshamahajan15
Differential Revision: D36348563
Pulled By: anand1976
fbshipit-source-id: c0ce85a505fd26ebfbb09786cbd7f25202038696
2022-05-19 22:36:27 +00:00
|
|
|
MultiGetContext ctx(&sorted_keys, 0, sorted_keys.size(), 0, ReadOptions(),
|
|
|
|
fs_.get(), nullptr);
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
// Execute MultiGet.
|
|
|
|
MultiGetContext::Range range = ctx.GetMultiGetRange();
|
2021-08-20 18:49:53 +00:00
|
|
|
PerfContext* perf_ctx = get_perf_context();
|
|
|
|
perf_ctx->Reset();
|
2020-05-15 06:23:32 +00:00
|
|
|
table->MultiGet(ReadOptions(), &range, nullptr);
|
|
|
|
|
2021-08-20 18:49:53 +00:00
|
|
|
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);
|
|
|
|
|
2020-05-15 06:23:32 +00:00
|
|
|
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()]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
class ChargeTableReaderTest
|
2022-04-06 17:33:00 +00:00
|
|
|
: public BlockBasedTableReaderBaseTest,
|
|
|
|
public testing::WithParamInterface<
|
2022-05-17 22:01:51 +00:00
|
|
|
CacheEntryRoleOptions::Decision /* charge_table_reader_mem */> {
|
2022-04-06 17:33:00 +00:00
|
|
|
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 &&
|
2022-04-20 02:02:00 +00:00
|
|
|
cache_capacity >= 2 * CacheReservationManagerImpl<
|
|
|
|
CacheEntryRole::kBlockBasedTableReader>::
|
|
|
|
GetDummyEntrySize());
|
2022-04-06 17:33:00 +00:00
|
|
|
|
|
|
|
// 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();
|
2022-04-20 02:02:00 +00:00
|
|
|
std::size_t max_table_reader_num_capped = static_cast<std::size_t>(
|
2022-04-06 17:33:00 +00:00
|
|
|
std::floor(1.0 * cache_capacity_rounded_to_dummy_entry_multiples /
|
|
|
|
approx_table_reader_mem));
|
|
|
|
|
2022-04-20 02:02:00 +00:00
|
|
|
return max_table_reader_num_capped;
|
2022-04-06 17:33:00 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
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 */)));
|
2022-04-06 17:33:00 +00:00
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
// To ApproximateTableReaderMem() without being affected by
|
|
|
|
// the feature of charging its memory, we turn off the feature
|
|
|
|
charge_table_reader_ = CacheEntryRoleOptions::Decision::kDisabled;
|
2022-04-06 17:33:00 +00:00
|
|
|
BlockBasedTableReaderBaseTest::SetUp();
|
|
|
|
approx_table_reader_mem_ = ApproximateTableReaderMem();
|
|
|
|
|
|
|
|
// Now we condtionally turn on the feature to test
|
2022-05-17 22:01:51 +00:00
|
|
|
charge_table_reader_ = GetParam();
|
2022-04-06 17:33:00 +00:00
|
|
|
ConfigureTableFactory();
|
|
|
|
}
|
|
|
|
|
|
|
|
void ConfigureTableFactory() override {
|
|
|
|
BlockBasedTableOptions table_options;
|
2022-05-17 22:01:51 +00:00
|
|
|
table_options.cache_usage_options.options_overrides.insert(
|
|
|
|
{CacheEntryRole::kBlockBasedTableReader,
|
|
|
|
{/*.charged = */ charge_table_reader_}});
|
|
|
|
table_options.block_cache = table_reader_charge_tracking_cache_;
|
2022-04-06 17:33:00 +00:00
|
|
|
|
|
|
|
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));
|
|
|
|
}
|
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
CacheEntryRoleOptions::Decision charge_table_reader_;
|
|
|
|
std::shared_ptr<
|
|
|
|
TargetCacheChargeTrackingCache<CacheEntryRole::kBlockBasedTableReader>>
|
|
|
|
table_reader_charge_tracking_cache_;
|
2022-04-06 17:33:00 +00:00
|
|
|
std::size_t approx_table_reader_mem_;
|
|
|
|
std::map<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";
|
|
|
|
CreateTable(table_name, 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;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
INSTANTIATE_TEST_CASE_P(
|
|
|
|
ChargeTableReaderTest, ChargeTableReaderTest,
|
|
|
|
::testing::Values(CacheEntryRoleOptions::Decision::kEnabled,
|
|
|
|
CacheEntryRoleOptions::Decision::kDisabled));
|
2022-04-06 17:33:00 +00:00
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
TEST_P(ChargeTableReaderTest, Basic) {
|
2022-04-20 02:02:00 +00:00
|
|
|
const std::size_t max_table_reader_num_capped =
|
2022-05-17 22:01:51 +00:00
|
|
|
ChargeTableReaderTest::CalculateMaxTableReaderNumBeforeCacheFull(
|
|
|
|
table_reader_charge_tracking_cache_->GetCapacity(),
|
|
|
|
approx_table_reader_mem_);
|
2022-04-20 02:02:00 +00:00
|
|
|
|
|
|
|
// 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 =
|
2022-06-04 02:42:22 +00:00
|
|
|
(std::size_t)(max_table_reader_num_capped * 1.05);
|
2022-04-20 02:02:00 +00:00
|
|
|
std::size_t max_table_reader_num_capped_lower_bound =
|
2022-06-04 02:42:22 +00:00
|
|
|
(std::size_t)(max_table_reader_num_capped * 0.95);
|
2022-04-20 02:02:00 +00:00
|
|
|
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 "
|
2022-05-17 22:01:51 +00:00
|
|
|
"charge_table_reader_ == kDisabled and == kEnabled)";
|
2022-04-06 17:33:00 +00:00
|
|
|
|
|
|
|
Status s = Status::OK();
|
|
|
|
std::size_t opened_table_reader_num = 0;
|
|
|
|
std::string table_name;
|
|
|
|
std::vector<std::unique_ptr<BlockBasedTable>> tables;
|
|
|
|
// Keep creating BlockBasedTableReader till hiting the memory limit based on
|
2022-05-17 22:01:51 +00:00
|
|
|
// cache capacity and creation fails (when charge_table_reader_ ==
|
|
|
|
// kEnabled) or reaching a specfied big number of table readers (when
|
|
|
|
// charge_table_reader_ == kDisabled)
|
2022-04-20 02:02:00 +00:00
|
|
|
while (s.ok() && opened_table_reader_num < max_table_reader_num_uncapped) {
|
2022-04-06 17:33:00 +00:00
|
|
|
table_name = "table_" + std::to_string(opened_table_reader_num);
|
|
|
|
CreateTable(table_name, 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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-05-17 22:01:51 +00:00
|
|
|
if (charge_table_reader_ == CacheEntryRoleOptions::Decision::kEnabled) {
|
2022-04-20 02:02:00 +00:00
|
|
|
EXPECT_TRUE(s.IsMemoryLimit()) << "s: " << s.ToString();
|
2022-05-17 22:01:51 +00:00
|
|
|
EXPECT_TRUE(s.ToString().find(
|
|
|
|
kCacheEntryRoleToCamelString[static_cast<std::uint32_t>(
|
|
|
|
CacheEntryRole::kBlockBasedTableReader)]) !=
|
|
|
|
std::string::npos);
|
2022-04-06 17:33:00 +00:00
|
|
|
EXPECT_TRUE(s.ToString().find("memory limit based on cache capacity") !=
|
|
|
|
std::string::npos);
|
|
|
|
|
2022-04-20 02:02:00 +00:00
|
|
|
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);
|
2022-04-06 17:33:00 +00:00
|
|
|
|
2022-04-20 02:02:00 +00:00
|
|
|
std::size_t updated_max_table_reader_num_capped =
|
2022-05-17 22:01:51 +00:00
|
|
|
ChargeTableReaderTest::CalculateMaxTableReaderNumBeforeCacheFull(
|
|
|
|
table_reader_charge_tracking_cache_->GetCapacity() / 2,
|
|
|
|
approx_table_reader_mem_);
|
2022-04-06 17:33:00 +00:00
|
|
|
|
|
|
|
// Keep deleting BlockBasedTableReader to lower down memory usage from the
|
|
|
|
// memory limit to make the next creation succeeds
|
2022-04-20 02:02:00 +00:00
|
|
|
while (opened_table_reader_num >= updated_max_table_reader_num_capped) {
|
2022-04-06 17:33:00 +00:00
|
|
|
tables.pop_back();
|
|
|
|
--opened_table_reader_num;
|
|
|
|
}
|
|
|
|
table_name = "table_for_successful_table_reader_open";
|
|
|
|
CreateTable(table_name, 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();
|
2022-05-17 22:01:51 +00:00
|
|
|
EXPECT_EQ(table_reader_charge_tracking_cache_->GetCacheCharge(), 0);
|
2022-04-06 17:33:00 +00:00
|
|
|
} else {
|
2022-04-20 02:02:00 +00:00
|
|
|
EXPECT_TRUE(s.ok() &&
|
|
|
|
opened_table_reader_num == max_table_reader_num_uncapped)
|
2022-04-06 17:33:00 +00:00
|
|
|
<< "s: " << s.ToString() << " opened_table_reader_num: "
|
|
|
|
<< std::to_string(opened_table_reader_num);
|
2022-05-17 22:01:51 +00:00
|
|
|
EXPECT_EQ(table_reader_charge_tracking_cache_->GetCacheCharge(), 0);
|
2022-04-06 17:33:00 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-06-05 18:06:26 +00:00
|
|
|
class BlockBasedTableReaderTestVerifyChecksum
|
|
|
|
: public BlockBasedTableReaderTest {
|
|
|
|
public:
|
|
|
|
BlockBasedTableReaderTestVerifyChecksum() : BlockBasedTableReaderTest() {}
|
|
|
|
};
|
|
|
|
|
|
|
|
TEST_P(BlockBasedTableReaderTestVerifyChecksum, ChecksumMismatch) {
|
2022-04-06 17:33:00 +00:00
|
|
|
std::map<std::string, std::string> kv =
|
|
|
|
BlockBasedTableReaderBaseTest::GenerateKVMap(800 /* num_block */);
|
2020-06-05 18:06:26 +00:00
|
|
|
|
|
|
|
std::string table_name =
|
|
|
|
"BlockBasedTableReaderTest" + CompressionTypeToString(compression_type_);
|
|
|
|
CreateTable(table_name, compression_type_, kv);
|
|
|
|
|
|
|
|
std::unique_ptr<BlockBasedTable> table;
|
|
|
|
Options options;
|
2021-05-05 20:59:21 +00:00
|
|
|
ImmutableOptions ioptions(options);
|
2020-06-05 18:06:26 +00:00
|
|
|
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();
|
2020-09-29 23:26:58 +00:00
|
|
|
BlockHandle handle = static_cast<PartitionedIndexIterator*>(iiter)
|
2020-06-05 18:06:26 +00:00
|
|
|
->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 17:31:34 +00:00
|
|
|
ASSERT_OK(test::CorruptFile(options.env, Path(table_name),
|
|
|
|
static_cast<int>(handle.offset()), 128));
|
2020-06-05 18:06:26 +00:00
|
|
|
|
|
|
|
NewBlockBasedTableReader(foptions, ioptions, comparator, table_name, &table);
|
|
|
|
Status s = table->VerifyChecksum(ReadOptions(),
|
|
|
|
TableReaderCaller::kUserVerifyChecksum);
|
|
|
|
ASSERT_EQ(s.code(), Status::kCorruption);
|
|
|
|
}
|
|
|
|
|
2020-05-15 06:23:32 +00:00
|
|
|
// Param 1: compression type
|
|
|
|
// Param 2: whether to use direct reads
|
2020-06-05 18:06:26 +00:00
|
|
|
// Param 3: Block Based Table Index type
|
|
|
|
// Param 4: BBTO no_block_cache option
|
2020-05-21 20:55:18 +00:00
|
|
|
#ifdef ROCKSDB_LITE
|
|
|
|
// Skip direct I/O tests in lite mode since direct I/O is unsupported.
|
2020-06-03 22:53:09 +00:00
|
|
|
INSTANTIATE_TEST_CASE_P(
|
2020-05-21 20:55:18 +00:00
|
|
|
MultiGet, BlockBasedTableReaderTest,
|
2020-06-05 18:06:26 +00:00
|
|
|
::testing::Combine(
|
|
|
|
::testing::ValuesIn(GetSupportedCompressions()),
|
|
|
|
::testing::Values(false),
|
|
|
|
::testing::Values(BlockBasedTableOptions::IndexType::kBinarySearch),
|
|
|
|
::testing::Values(false)));
|
2020-05-21 20:55:18 +00:00
|
|
|
#else // ROCKSDB_LITE
|
2020-06-03 22:53:09 +00:00
|
|
|
INSTANTIATE_TEST_CASE_P(
|
2020-05-15 06:23:32 +00:00
|
|
|
MultiGet, BlockBasedTableReaderTest,
|
2020-06-05 18:06:26 +00:00
|
|
|
::testing::Combine(
|
|
|
|
::testing::ValuesIn(GetSupportedCompressions()), ::testing::Bool(),
|
|
|
|
::testing::Values(BlockBasedTableOptions::IndexType::kBinarySearch),
|
|
|
|
::testing::Values(false)));
|
2020-05-21 20:55:18 +00:00
|
|
|
#endif // ROCKSDB_LITE
|
2020-06-05 18:06:26 +00:00
|
|
|
INSTANTIATE_TEST_CASE_P(
|
|
|
|
VerifyChecksum, BlockBasedTableReaderTestVerifyChecksum,
|
|
|
|
::testing::Combine(
|
|
|
|
::testing::ValuesIn(GetSupportedCompressions()),
|
|
|
|
::testing::Values(false),
|
|
|
|
::testing::Values(
|
|
|
|
BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch),
|
|
|
|
::testing::Values(true)));
|
2020-05-15 06:23:32 +00:00
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
|
|
|
|
int main(int argc, char** argv) {
|
|
|
|
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
|
|
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
|
|
return RUN_ALL_TESTS();
|
|
|
|
}
|