You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/table/block_based_table_builder.cc

879 lines
33 KiB

// 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include "table/block_based_table_builder.h"
#include <assert.h>
#include <stdio.h>
#include <list>
#include <map>
#include <memory>
#include <string>
#include <unordered_map>
#include <utility>
#include "db/dbformat.h"
#include "rocksdb/cache.h"
#include "rocksdb/comparator.h"
#include "rocksdb/env.h"
#include "rocksdb/filter_policy.h"
#include "rocksdb/flush_block_policy.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/table.h"
#include "table/block.h"
#include "table/block_based_filter_block.h"
#include "table/block_based_table_factory.h"
#include "table/block_based_table_reader.h"
#include "table/block_builder.h"
#include "table/filter_block.h"
#include "table/format.h"
#include "table/full_filter_block.h"
#include "table/meta_blocks.h"
#include "table/table_builder.h"
#include "util/string_util.h"
#include "util/coding.h"
#include "util/compression.h"
#include "util/crc32c.h"
#include "util/stop_watch.h"
#include "util/xxhash.h"
#include "table/index_builder.h"
#include "table/partitioned_filter_block.h"
namespace rocksdb {
extern const std::string kHashIndexPrefixesBlock;
extern const std::string kHashIndexPrefixesMetadataBlock;
typedef BlockBasedTableOptions::IndexType IndexType;
// Without anonymous namespace here, we fail the warning -Wmissing-prototypes
namespace {
// Create a filter block builder based on its type.
FilterBlockBuilder* CreateFilterBlockBuilder(
const ImmutableCFOptions& opt, const BlockBasedTableOptions& table_opt,
PartitionedIndexBuilder* const p_index_builder) {
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
if (table_opt.filter_policy == nullptr) return nullptr;
FilterBitsBuilder* filter_bits_builder =
table_opt.filter_policy->GetFilterBitsBuilder();
if (filter_bits_builder == nullptr) {
return new BlockBasedFilterBlockBuilder(opt.prefix_extractor, table_opt);
} else {
if (table_opt.partition_filters) {
assert(p_index_builder != nullptr);
// Since after partition cut request from filter builder it takes time
// until index builder actully cuts the partition, we take the lower bound
// as partition size.
assert(table_opt.block_size_deviation <= 100);
auto partition_size = static_cast<uint32_t>(
((table_opt.metadata_block_size *
(100 - table_opt.block_size_deviation)) + 99) / 100);
partition_size = std::max(partition_size, static_cast<uint32_t>(1));
return new PartitionedFilterBlockBuilder(
opt.prefix_extractor, table_opt.whole_key_filtering,
filter_bits_builder, table_opt.index_block_restart_interval,
p_index_builder, partition_size);
} else {
return new FullFilterBlockBuilder(opt.prefix_extractor,
table_opt.whole_key_filtering,
filter_bits_builder);
}
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
}
}
bool GoodCompressionRatio(size_t compressed_size, size_t raw_size) {
// Check to see if compressed less than 12.5%
return compressed_size < raw_size - (raw_size / 8u);
}
} // namespace
// format_version is the block format as defined in include/rocksdb/table.h
Slice CompressBlock(const Slice& raw,
const CompressionOptions& compression_options,
CompressionType* type, uint32_t format_version,
const Slice& compression_dict,
std::string* compressed_output) {
if (*type == kNoCompression) {
return raw;
}
// Will return compressed block contents if (1) the compression method is
// supported in this platform and (2) the compression rate is "good enough".
switch (*type) {
case kSnappyCompression:
if (Snappy_Compress(compression_options, raw.data(), raw.size(),
compressed_output) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
case kZlibCompression:
if (Zlib_Compress(
compression_options,
GetCompressFormatForVersion(kZlibCompression, format_version),
raw.data(), raw.size(), compressed_output, compression_dict) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
case kBZip2Compression:
if (BZip2_Compress(
compression_options,
GetCompressFormatForVersion(kBZip2Compression, format_version),
raw.data(), raw.size(), compressed_output) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
case kLZ4Compression:
if (LZ4_Compress(
compression_options,
GetCompressFormatForVersion(kLZ4Compression, format_version),
raw.data(), raw.size(), compressed_output, compression_dict) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
case kLZ4HCCompression:
if (LZ4HC_Compress(
compression_options,
GetCompressFormatForVersion(kLZ4HCCompression, format_version),
raw.data(), raw.size(), compressed_output, compression_dict) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
case kXpressCompression:
if (XPRESS_Compress(raw.data(), raw.size(),
compressed_output) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break;
case kZSTD:
case kZSTDNotFinalCompression:
if (ZSTD_Compress(compression_options, raw.data(), raw.size(),
compressed_output, compression_dict) &&
GoodCompressionRatio(compressed_output->size(), raw.size())) {
return *compressed_output;
}
break; // fall back to no compression.
default: {} // Do not recognize this compression type
}
// Compression method is not supported, or not good compression ratio, so just
// fall back to uncompressed form.
*type = kNoCompression;
return raw;
}
// kBlockBasedTableMagicNumber was picked by running
// echo rocksdb.table.block_based | sha1sum
// and taking the leading 64 bits.
// Please note that kBlockBasedTableMagicNumber may also be accessed by other
// .cc files
// for that reason we declare it extern in the header but to get the space
// allocated
// it must be not extern in one place.
const uint64_t kBlockBasedTableMagicNumber = 0x88e241b785f4cff7ull;
// We also support reading and writing legacy block based table format (for
// backwards compatibility)
const uint64_t kLegacyBlockBasedTableMagicNumber = 0xdb4775248b80fb57ull;
// A collector that collects properties of interest to block-based table.
// For now this class looks heavy-weight since we only write one additional
// property.
10 years ago
// But in the foreseeable future, we will add more and more properties that are
// specific to block-based table.
class BlockBasedTableBuilder::BlockBasedTablePropertiesCollector
: public IntTblPropCollector {
public:
explicit BlockBasedTablePropertiesCollector(
BlockBasedTableOptions::IndexType index_type, bool whole_key_filtering,
bool prefix_filtering)
: index_type_(index_type),
whole_key_filtering_(whole_key_filtering),
prefix_filtering_(prefix_filtering) {}
virtual Status InternalAdd(const Slice& key, const Slice& value,
uint64_t file_size) override {
// Intentionally left blank. Have no interest in collecting stats for
// individual key/value pairs.
return Status::OK();
}
virtual Status Finish(UserCollectedProperties* properties) override {
std::string val;
PutFixed32(&val, static_cast<uint32_t>(index_type_));
properties->insert({BlockBasedTablePropertyNames::kIndexType, val});
properties->insert({BlockBasedTablePropertyNames::kWholeKeyFiltering,
whole_key_filtering_ ? kPropTrue : kPropFalse});
properties->insert({BlockBasedTablePropertyNames::kPrefixFiltering,
prefix_filtering_ ? kPropTrue : kPropFalse});
return Status::OK();
}
// The name of the properties collector can be used for debugging purpose.
virtual const char* Name() const override {
return "BlockBasedTablePropertiesCollector";
}
virtual UserCollectedProperties GetReadableProperties() const override {
// Intentionally left blank.
return UserCollectedProperties();
}
private:
BlockBasedTableOptions::IndexType index_type_;
bool whole_key_filtering_;
bool prefix_filtering_;
};
struct BlockBasedTableBuilder::Rep {
const ImmutableCFOptions ioptions;
const BlockBasedTableOptions table_options;
const InternalKeyComparator& internal_comparator;
WritableFileWriter* file;
uint64_t offset = 0;
Status status;
BlockBuilder data_block;
BlockBuilder range_del_block;
InternalKeySliceTransform internal_prefix_transform;
std::unique_ptr<IndexBuilder> index_builder;
PartitionedIndexBuilder* p_index_builder_ = nullptr;
std::string last_key;
const CompressionType compression_type;
const CompressionOptions compression_opts;
// Data for presetting the compression library's dictionary, or nullptr.
const std::string* compression_dict;
TableProperties props;
bool closed = false; // Either Finish() or Abandon() has been called.
std::unique_ptr<FilterBlockBuilder> filter_builder;
char compressed_cache_key_prefix[BlockBasedTable::kMaxCacheKeyPrefixSize];
size_t compressed_cache_key_prefix_size;
BlockHandle pending_handle; // Handle to add to index block
std::string compressed_output;
std::unique_ptr<FlushBlockPolicy> flush_block_policy;
uint32_t column_family_id;
const std::string& column_family_name;
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
8 years ago
uint64_t creation_time = 0;
uint64_t oldest_key_time = 0;
std::vector<std::unique_ptr<IntTblPropCollector>> table_properties_collectors;
TablePropertiesCollectorFactory Summary: This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options. Here's description of task #4296714: I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB. For example, this table has 3155 entries and 1391828 deleted keys. The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for. Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API. In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe. Test Plan: Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one). Also, all other tests Reviewers: sdong, dhruba, haobo, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D18579
11 years ago
Rep(const ImmutableCFOptions& _ioptions,
const BlockBasedTableOptions& table_opt,
const InternalKeyComparator& icomparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t _column_family_id, WritableFileWriter* f,
const CompressionType _compression_type,
const CompressionOptions& _compression_opts,
const std::string* _compression_dict, const bool skip_filters,
const std::string& _column_family_name, const uint64_t _creation_time,
const uint64_t _oldest_key_time)
: ioptions(_ioptions),
table_options(table_opt),
internal_comparator(icomparator),
file(f),
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
data_block(table_options.block_restart_interval,
table_options.use_delta_encoding),
range_del_block(1), // TODO(andrewkr): restart_interval unnecessary
internal_prefix_transform(_ioptions.prefix_extractor),
compression_type(_compression_type),
compression_opts(_compression_opts),
compression_dict(_compression_dict),
table: Fix coverity issues Summary: table/block.cc: 420 } CID 1396127 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR) 7. uninit_member: Non-static class member restart_offset_ is not initialized in this constructor nor in any functions that it calls. 421} table/block_based_table_builder.cc: CID 1418259 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR) 7. uninit_member: Non-static class member compressed_cache_key_prefix_size is not initialized in this constructor nor in any functions that it calls. table/block_based_table_reader.h: 3. uninit_member: Non-static class member index_type is not initialized in this constructor nor in any functions that it calls. CID 1396147 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR) 5. uninit_member: Non-static class member hash_index_allow_collision is not initialized in this constructor nor in any functions that it calls. 413 global_seqno(kDisableGlobalSequenceNumber) {} 414 table/cuckoo_table_reader.cc: 55 if (hash_funs == user_props.end()) { 56 status_ = Status::Corruption("Number of hash functions not found"); 5. uninit_member: Non-static class member is_last_level_ is not initialized in this constructor nor in any functions that it calls. 7. uninit_member: Non-static class member identity_as_first_hash_ is not initialized in this constructor nor in any functions that it calls. 9. uninit_member: Non-static class member use_module_hash_ is not initialized in this constructor nor in any functions that it calls. 11. uninit_member: Non-static class member num_hash_func_ is not initialized in this constructor nor in any functions that it calls. 13. uninit_member: Non-static class member key_length_ is not initialized in this constructor nor in any functions that it calls. 15. uninit_member: Non-static class member user_key_length_ is not initialized in this constructor nor in any functions that it calls. 17. uninit_member: Non-static class member value_length_ is not initialized in this constructor nor in any functions that it calls. 19. uninit_member: Non-static class member bucket_length_ is not initialized in this constructor nor in any functions that it calls. 21. uninit_member: Non-static class member cuckoo_block_size_ is not initialized in this constructor nor in any functions that it calls. 23. uninit_member: Non-static class member cuckoo_block_bytes_minus_one_ is not initialized in this constructor nor in any functions that it calls. CID 1322785 (#2 of 2): Uninitialized scalar field (UNINIT_CTOR) 25. uninit_member: Non-static class member table_size_ is not initialized in this constructor nor in any functions that it calls. 57 return; table/plain_table_index.h: 2. uninit_member: Non-static class member index_size_ is not initialized in this constructor nor in any functions that it calls. CID 1322801 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR) 4. uninit_member: Non-static class member sub_index_size_ is not initialized in this constructor nor in any functions that it calls. 128 huge_page_tlb_size_(huge_page_tlb_size) {} 129 Closes https://github.com/facebook/rocksdb/pull/3113 Differential Revision: D6505719 Pulled By: yiwu-arbug fbshipit-source-id: 38f44d8f9dfefb4c2e25d83b8df25a5201c75618
7 years ago
compressed_cache_key_prefix_size(0),
flush_block_policy(
table_options.flush_block_policy_factory->NewFlushBlockPolicy(
table_options, data_block)),
column_family_id(_column_family_id),
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
8 years ago
column_family_name(_column_family_name),
creation_time(_creation_time),
oldest_key_time(_oldest_key_time) {
if (table_options.index_type ==
BlockBasedTableOptions::kTwoLevelIndexSearch) {
p_index_builder_ = PartitionedIndexBuilder::CreateIndexBuilder(
&internal_comparator, table_options);
index_builder.reset(p_index_builder_);
} else {
index_builder.reset(IndexBuilder::CreateIndexBuilder(
table_options.index_type, &internal_comparator,
&this->internal_prefix_transform, table_options));
}
if (skip_filters) {
filter_builder = nullptr;
} else {
filter_builder.reset(
CreateFilterBlockBuilder(_ioptions, table_options, p_index_builder_));
}
for (auto& collector_factories : *int_tbl_prop_collector_factories) {
TablePropertiesCollectorFactory Summary: This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options. Here's description of task #4296714: I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB. For example, this table has 3155 entries and 1391828 deleted keys. The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for. Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API. In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe. Test Plan: Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one). Also, all other tests Reviewers: sdong, dhruba, haobo, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D18579
11 years ago
table_properties_collectors.emplace_back(
collector_factories->CreateIntTblPropCollector(column_family_id));
TablePropertiesCollectorFactory Summary: This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options. Here's description of task #4296714: I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB. For example, this table has 3155 entries and 1391828 deleted keys. The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for. Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API. In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe. Test Plan: Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one). Also, all other tests Reviewers: sdong, dhruba, haobo, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D18579
11 years ago
}
table_properties_collectors.emplace_back(
new BlockBasedTablePropertiesCollector(
table_options.index_type, table_options.whole_key_filtering,
_ioptions.prefix_extractor != nullptr));
}
};
BlockBasedTableBuilder::BlockBasedTableBuilder(
const ImmutableCFOptions& ioptions,
const BlockBasedTableOptions& table_options,
const InternalKeyComparator& internal_comparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t column_family_id, WritableFileWriter* file,
const CompressionType compression_type,
const CompressionOptions& compression_opts,
const std::string* compression_dict, const bool skip_filters,
const std::string& column_family_name, const uint64_t creation_time,
const uint64_t oldest_key_time) {
BlockBasedTableOptions sanitized_table_options(table_options);
if (sanitized_table_options.format_version == 0 &&
sanitized_table_options.checksum != kCRC32c) {
ROCKS_LOG_WARN(
ioptions.info_log,
"Silently converting format_version to 1 because checksum is "
"non-default");
// silently convert format_version to 1 to keep consistent with current
// behavior
sanitized_table_options.format_version = 1;
}
rep_ = new Rep(ioptions, sanitized_table_options, internal_comparator,
int_tbl_prop_collector_factories, column_family_id, file,
compression_type, compression_opts, compression_dict,
skip_filters, column_family_name, creation_time,
oldest_key_time);
if (rep_->filter_builder != nullptr) {
rep_->filter_builder->StartBlock(0);
}
if (table_options.block_cache_compressed.get() != nullptr) {
BlockBasedTable::GenerateCachePrefix(
table_options.block_cache_compressed.get(), file->writable_file(),
&rep_->compressed_cache_key_prefix[0],
&rep_->compressed_cache_key_prefix_size);
}
}
BlockBasedTableBuilder::~BlockBasedTableBuilder() {
assert(rep_->closed); // Catch errors where caller forgot to call Finish()
delete rep_;
}
void BlockBasedTableBuilder::Add(const Slice& key, const Slice& value) {
Rep* r = rep_;
assert(!r->closed);
if (!ok()) return;
ValueType value_type = ExtractValueType(key);
if (IsValueType(value_type)) {
if (r->props.num_entries > 0) {
assert(r->internal_comparator.Compare(key, Slice(r->last_key)) > 0);
}
auto should_flush = r->flush_block_policy->Update(key, value);
if (should_flush) {
assert(!r->data_block.empty());
Flush();
// Add item to index block.
// We do not emit the index entry for a block until we have seen the
// first key for the next data block. This allows us to use shorter
// keys in the index block. For example, consider a block boundary
// between the keys "the quick brown fox" and "the who". We can use
// "the r" as the key for the index block entry since it is >= all
// entries in the first block and < all entries in subsequent
// blocks.
if (ok()) {
r->index_builder->AddIndexEntry(&r->last_key, &key, r->pending_handle);
}
}
// Note: PartitionedFilterBlockBuilder requires key being added to filter
// builder after being added to index builder.
if (r->filter_builder != nullptr) {
r->filter_builder->Add(ExtractUserKey(key));
}
r->last_key.assign(key.data(), key.size());
r->data_block.Add(key, value);
r->props.num_entries++;
r->props.raw_key_size += key.size();
r->props.raw_value_size += value.size();
r->index_builder->OnKeyAdded(key);
NotifyCollectTableCollectorsOnAdd(key, value, r->offset,
r->table_properties_collectors,
r->ioptions.info_log);
} else if (value_type == kTypeRangeDeletion) {
// TODO(wanning&andrewkr) add num_tomestone to table properties
r->range_del_block.Add(key, value);
++r->props.num_entries;
r->props.raw_key_size += key.size();
r->props.raw_value_size += value.size();
NotifyCollectTableCollectorsOnAdd(key, value, r->offset,
r->table_properties_collectors,
r->ioptions.info_log);
} else {
assert(false);
}
}
void BlockBasedTableBuilder::Flush() {
Rep* r = rep_;
assert(!r->closed);
if (!ok()) return;
if (r->data_block.empty()) return;
WriteBlock(&r->data_block, &r->pending_handle, true /* is_data_block */);
if (r->filter_builder != nullptr) {
r->filter_builder->StartBlock(r->offset);
}
r->props.data_size = r->offset;
++r->props.num_data_blocks;
}
void BlockBasedTableBuilder::WriteBlock(BlockBuilder* block,
BlockHandle* handle,
bool is_data_block) {
WriteBlock(block->Finish(), handle, is_data_block);
block->Reset();
}
void BlockBasedTableBuilder::WriteBlock(const Slice& raw_block_contents,
BlockHandle* handle,
bool is_data_block) {
// File format contains a sequence of blocks where each block has:
// block_data: uint8[n]
// type: uint8
// crc: uint32
assert(ok());
Rep* r = rep_;
auto type = r->compression_type;
Slice block_contents;
bool abort_compression = false;
StopWatchNano timer(r->ioptions.env,
ShouldReportDetailedTime(r->ioptions.env, r->ioptions.statistics));
if (raw_block_contents.size() < kCompressionSizeLimit) {
Slice compression_dict;
if (is_data_block && r->compression_dict && r->compression_dict->size()) {
compression_dict = *r->compression_dict;
}
block_contents = CompressBlock(raw_block_contents, r->compression_opts,
&type, r->table_options.format_version,
compression_dict, &r->compressed_output);
// Some of the compression algorithms are known to be unreliable. If
// the verify_compression flag is set then try to de-compress the
// compressed data and compare to the input.
if (type != kNoCompression && r->table_options.verify_compression) {
// Retrieve the uncompressed contents into a new buffer
BlockContents contents;
Status stat = UncompressBlockContentsForCompressionType(
block_contents.data(), block_contents.size(), &contents,
r->table_options.format_version, compression_dict, type,
r->ioptions);
if (stat.ok()) {
bool compressed_ok = contents.data.compare(raw_block_contents) == 0;
if (!compressed_ok) {
// The result of the compression was invalid. abort.
abort_compression = true;
ROCKS_LOG_ERROR(r->ioptions.info_log,
"Decompressed block did not match raw block");
r->status =
Status::Corruption("Decompressed block did not match raw block");
}
} else {
// Decompression reported an error. abort.
r->status = Status::Corruption("Could not decompress");
abort_compression = true;
}
}
} else {
// Block is too big to be compressed.
abort_compression = true;
}
// Abort compression if the block is too big, or did not pass
// verification.
if (abort_compression) {
RecordTick(r->ioptions.statistics, NUMBER_BLOCK_NOT_COMPRESSED);
type = kNoCompression;
block_contents = raw_block_contents;
} else if (type != kNoCompression) {
if (ShouldReportDetailedTime(r->ioptions.env, r->ioptions.statistics)) {
MeasureTime(r->ioptions.statistics, COMPRESSION_TIMES_NANOS,
timer.ElapsedNanos());
}
MeasureTime(r->ioptions.statistics, BYTES_COMPRESSED,
raw_block_contents.size());
RecordTick(r->ioptions.statistics, NUMBER_BLOCK_COMPRESSED);
}
WriteRawBlock(block_contents, type, handle);
r->compressed_output.clear();
}
void BlockBasedTableBuilder::WriteRawBlock(const Slice& block_contents,
CompressionType type,
BlockHandle* handle) {
Rep* r = rep_;
StopWatch sw(r->ioptions.env, r->ioptions.statistics, WRITE_RAW_BLOCK_MICROS);
handle->set_offset(r->offset);
handle->set_size(block_contents.size());
assert(r->status.ok());
r->status = r->file->Append(block_contents);
if (r->status.ok()) {
char trailer[kBlockTrailerSize];
trailer[0] = type;
char* trailer_without_type = trailer + 1;
switch (r->table_options.checksum) {
case kNoChecksum:
EncodeFixed32(trailer_without_type, 0);
break;
case kCRC32c: {
auto crc = crc32c::Value(block_contents.data(), block_contents.size());
crc = crc32c::Extend(crc, trailer, 1); // Extend to cover block type
EncodeFixed32(trailer_without_type, crc32c::Mask(crc));
break;
}
case kxxHash: {
void* xxh = XXH32_init(0);
XXH32_update(xxh, block_contents.data(),
static_cast<uint32_t>(block_contents.size()));
XXH32_update(xxh, trailer, 1); // Extend to cover block type
EncodeFixed32(trailer_without_type, XXH32_digest(xxh));
break;
}
}
assert(r->status.ok());
r->status = r->file->Append(Slice(trailer, kBlockTrailerSize));
if (r->status.ok()) {
r->status = InsertBlockInCache(block_contents, type, handle);
}
if (r->status.ok()) {
r->offset += block_contents.size() + kBlockTrailerSize;
}
}
}
Status BlockBasedTableBuilder::status() const {
return rep_->status;
}
static void DeleteCachedBlock(const Slice& key, void* value) {
Block* block = reinterpret_cast<Block*>(value);
delete block;
}
//
// Make a copy of the block contents and insert into compressed block cache
//
Status BlockBasedTableBuilder::InsertBlockInCache(const Slice& block_contents,
const CompressionType type,
const BlockHandle* handle) {
Rep* r = rep_;
Cache* block_cache_compressed = r->table_options.block_cache_compressed.get();
if (type != kNoCompression && block_cache_compressed != nullptr) {
size_t size = block_contents.size();
std::unique_ptr<char[]> ubuf(new char[size + 1]);
memcpy(ubuf.get(), block_contents.data(), size);
ubuf[size] = type;
BlockContents results(std::move(ubuf), size, true, type);
Block* block = new Block(std::move(results), kDisableGlobalSequenceNumber);
// make cache key by appending the file offset to the cache prefix id
char* end = EncodeVarint64(
r->compressed_cache_key_prefix +
r->compressed_cache_key_prefix_size,
handle->offset());
Slice key(r->compressed_cache_key_prefix, static_cast<size_t>
(end - r->compressed_cache_key_prefix));
// Insert into compressed block cache.
block_cache_compressed->Insert(key, block, block->usable_size(),
&DeleteCachedBlock);
// Invalidate OS cache.
r->file->InvalidateCache(static_cast<size_t>(r->offset), size);
}
return Status::OK();
}
Status BlockBasedTableBuilder::Finish() {
Rep* r = rep_;
bool empty_data_block = r->data_block.empty();
Flush();
assert(!r->closed);
r->closed = true;
// To make sure properties block is able to keep the accurate size of index
// block, we will finish writing all index entries here and flush them
// to storage after metaindex block is written.
if (ok() && !empty_data_block) {
r->index_builder->AddIndexEntry(
&r->last_key, nullptr /* no next data block */, r->pending_handle);
}
BlockHandle filter_block_handle, metaindex_block_handle, index_block_handle,
compression_dict_block_handle, range_del_block_handle;
// Write filter block
if (ok() && r->filter_builder != nullptr) {
Status s = Status::Incomplete();
while (s.IsIncomplete()) {
Slice filter_content = r->filter_builder->Finish(filter_block_handle, &s);
assert(s.ok() || s.IsIncomplete());
r->props.filter_size += filter_content.size();
WriteRawBlock(filter_content, kNoCompression, &filter_block_handle);
}
}
IndexBuilder::IndexBlocks index_blocks;
auto index_builder_status = r->index_builder->Finish(&index_blocks);
if (index_builder_status.IsIncomplete()) {
// We we have more than one index partition then meta_blocks are not
// supported for the index. Currently meta_blocks are used only by
// HashIndexBuilder which is not multi-partition.
assert(index_blocks.meta_blocks.empty());
} else if (!index_builder_status.ok()) {
return index_builder_status;
}
// Write meta blocks and metaindex block with the following order.
// 1. [meta block: filter]
// 2. [meta block: properties]
// 3. [meta block: compression dictionary]
// 4. [meta block: range deletion tombstone]
// 5. [metaindex block]
// write meta blocks
MetaIndexBuilder meta_index_builder;
for (const auto& item : index_blocks.meta_blocks) {
BlockHandle block_handle;
WriteBlock(item.second, &block_handle, false /* is_data_block */);
meta_index_builder.Add(item.first, block_handle);
}
if (ok()) {
if (r->filter_builder != nullptr) {
// Add mapping from "<filter_block_prefix>.Name" to location
// of filter data.
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
std::string key;
if (r->filter_builder->IsBlockBased()) {
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
key = BlockBasedTable::kFilterBlockPrefix;
} else {
key = r->table_options.partition_filters
? BlockBasedTable::kPartitionedFilterBlockPrefix
: BlockBasedTable::kFullFilterBlockPrefix;
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
}
key.append(r->table_options.filter_policy->Name());
meta_index_builder.Add(key, filter_block_handle);
}
// Write properties and compression dictionary blocks.
{
PropertyBlockBuilder property_block_builder;
r->props.column_family_id = r->column_family_id;
r->props.column_family_name = r->column_family_name;
r->props.filter_policy_name = r->table_options.filter_policy != nullptr ?
r->table_options.filter_policy->Name() : "";
r->props.index_size =
r->index_builder->EstimatedSize() + kBlockTrailerSize;
r->props.comparator_name = r->ioptions.user_comparator != nullptr
? r->ioptions.user_comparator->Name()
: "nullptr";
r->props.merge_operator_name = r->ioptions.merge_operator != nullptr
? r->ioptions.merge_operator->Name()
: "nullptr";
r->props.compression_name = CompressionTypeToString(r->compression_type);
store prefix_extractor_name in table Summary: Make sure prefix extractor name is stored in SST files and if DB is opened with a prefix extractor of a different name, prefix bloom is skipped when read the file. Also add unit tests for that. Test Plan: before change: ``` Note: Google Test filter = BlockBasedTableTest.SkipPrefixBloomFilter [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from BlockBasedTableTest [ RUN ] BlockBasedTableTest.SkipPrefixBloomFilter table/table_test.cc:1421: Failure Value of: db_iter->Valid() Actual: false Expected: true [ FAILED ] BlockBasedTableTest.SkipPrefixBloomFilter (1 ms) [----------] 1 test from BlockBasedTableTest (1 ms total) [----------] Global test environment tear-down [==========] 1 test from 1 test case ran. (1 ms total) [ PASSED ] 0 tests. [ FAILED ] 1 test, listed below: [ FAILED ] BlockBasedTableTest.SkipPrefixBloomFilter 1 FAILED TEST ``` after: ``` Note: Google Test filter = BlockBasedTableTest.SkipPrefixBloomFilter [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from BlockBasedTableTest [ RUN ] BlockBasedTableTest.SkipPrefixBloomFilter [ OK ] BlockBasedTableTest.SkipPrefixBloomFilter (0 ms) [----------] 1 test from BlockBasedTableTest (0 ms total) [----------] Global test environment tear-down [==========] 1 test from 1 test case ran. (0 ms total) [ PASSED ] 1 test. ``` Reviewers: sdong, andrewkr, yiwu, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D61215
8 years ago
r->props.prefix_extractor_name =
r->ioptions.prefix_extractor != nullptr
? r->ioptions.prefix_extractor->Name()
: "nullptr";
std::string property_collectors_names = "[";
for (size_t i = 0;
i < r->ioptions.table_properties_collector_factories.size(); ++i) {
if (i != 0) {
property_collectors_names += ",";
}
property_collectors_names +=
r->ioptions.table_properties_collector_factories[i]->Name();
}
property_collectors_names += "]";
r->props.property_collectors_names = property_collectors_names;
if (r->table_options.index_type ==
BlockBasedTableOptions::kTwoLevelIndexSearch) {
assert(r->p_index_builder_ != nullptr);
r->props.index_partitions = r->p_index_builder_->NumPartitions();
r->props.top_level_index_size =
r->p_index_builder_->EstimateTopLevelIndexSize(r->offset);
}
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
8 years ago
r->props.creation_time = r->creation_time;
r->props.oldest_key_time = r->oldest_key_time;
// Add basic properties
property_block_builder.AddTableProperty(r->props);
// Add use collected properties
TablePropertiesCollectorFactory Summary: This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options. Here's description of task #4296714: I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB. For example, this table has 3155 entries and 1391828 deleted keys. The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for. Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API. In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe. Test Plan: Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one). Also, all other tests Reviewers: sdong, dhruba, haobo, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D18579
11 years ago
NotifyCollectTableCollectorsOnFinish(r->table_properties_collectors,
r->ioptions.info_log,
TablePropertiesCollectorFactory Summary: This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options. Here's description of task #4296714: I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB. For example, this table has 3155 entries and 1391828 deleted keys. The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for. Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API. In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe. Test Plan: Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one). Also, all other tests Reviewers: sdong, dhruba, haobo, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D18579
11 years ago
&property_block_builder);
BlockHandle properties_block_handle;
WriteRawBlock(
property_block_builder.Finish(),
kNoCompression,
&properties_block_handle
);
meta_index_builder.Add(kPropertiesBlock, properties_block_handle);
// Write compression dictionary block
if (r->compression_dict && r->compression_dict->size()) {
WriteRawBlock(*r->compression_dict, kNoCompression,
&compression_dict_block_handle);
meta_index_builder.Add(kCompressionDictBlock,
compression_dict_block_handle);
}
} // end of properties/compression dictionary block writing
if (ok() && !r->range_del_block.empty()) {
WriteRawBlock(r->range_del_block.Finish(), kNoCompression,
&range_del_block_handle);
meta_index_builder.Add(kRangeDelBlock, range_del_block_handle);
} // range deletion tombstone meta block
} // meta blocks
// Write index block
if (ok()) {
// flush the meta index block
WriteRawBlock(meta_index_builder.Finish(), kNoCompression,
&metaindex_block_handle);
if (r->table_options.enable_index_compression) {
WriteBlock(index_blocks.index_block_contents, &index_block_handle, false);
} else {
WriteRawBlock(index_blocks.index_block_contents, kNoCompression,
&index_block_handle);
}
// If there are more index partitions, finish them and write them out
Status& s = index_builder_status;
while (s.IsIncomplete()) {
s = r->index_builder->Finish(&index_blocks, index_block_handle);
if (!s.ok() && !s.IsIncomplete()) {
return s;
}
if (r->table_options.enable_index_compression) {
WriteBlock(index_blocks.index_block_contents, &index_block_handle,
false);
} else {
WriteRawBlock(index_blocks.index_block_contents, kNoCompression,
&index_block_handle);
}
// The last index_block_handle will be for the partition index block
}
}
// Write footer
if (ok()) {
// No need to write out new footer if we're using default checksum.
// We're writing legacy magic number because we want old versions of RocksDB
// be able to read files generated with new release (just in case if
// somebody wants to roll back after an upgrade)
// TODO(icanadi) at some point in the future, when we're absolutely sure
// nobody will roll back to RocksDB 2.x versions, retire the legacy magic
// number and always write new table files with new magic number
bool legacy = (r->table_options.format_version == 0);
// this is guaranteed by BlockBasedTableBuilder's constructor
assert(r->table_options.checksum == kCRC32c ||
r->table_options.format_version != 0);
Footer footer(legacy ? kLegacyBlockBasedTableMagicNumber
: kBlockBasedTableMagicNumber,
r->table_options.format_version);
footer.set_metaindex_handle(metaindex_block_handle);
footer.set_index_handle(index_block_handle);
footer.set_checksum(r->table_options.checksum);
std::string footer_encoding;
footer.EncodeTo(&footer_encoding);
assert(r->status.ok());
r->status = r->file->Append(footer_encoding);
if (r->status.ok()) {
r->offset += footer_encoding.size();
}
}
return r->status;
}
void BlockBasedTableBuilder::Abandon() {
Rep* r = rep_;
assert(!r->closed);
r->closed = true;
}
uint64_t BlockBasedTableBuilder::NumEntries() const {
return rep_->props.num_entries;
}
uint64_t BlockBasedTableBuilder::FileSize() const {
return rep_->offset;
}
bool BlockBasedTableBuilder::NeedCompact() const {
for (const auto& collector : rep_->table_properties_collectors) {
if (collector->NeedCompact()) {
return true;
}
}
return false;
}
TableProperties BlockBasedTableBuilder::GetTableProperties() const {
TableProperties ret = rep_->props;
for (const auto& collector : rep_->table_properties_collectors) {
for (const auto& prop : collector->GetReadableProperties()) {
ret.readable_properties.insert(prop);
}
collector->Finish(&ret.user_collected_properties);
}
return ret;
}
const std::string BlockBasedTable::kFilterBlockPrefix = "filter.";
Implement full filter for block based table. Summary: 1. Make filter_block.h a base class. Derive block_based_filter_block and full_filter_block. The previous one is the traditional filter block. The full_filter_block is newly added. It would generate a filter block that contain all the keys in SST file. 2. When querying a key, table would first check if full_filter is available. If not, it would go to the exact data block and check using block_based filter. 3. User could choose to use full_filter or tradional(block_based_filter). They would be stored in SST file with different meta index name. "filter.filter_policy" or "full_filter.filter_policy". Then, Table reader is able to know the fllter block type. 4. Some optimizations have been done for full_filter_block, thus it requires a different interface compared to the original one in filter_policy.h. 5. Actual implementation of filter bits coding/decoding is placed in util/bloom_impl.cc Benchmark: base commit 1d23b5c470844c1208301311f0889eca750431c0 Command: db_bench --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=393216000 --use_hash_search=1 --block_size=1024 --block_restart_interval=16 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1 Read QPS increase for about 30% from 2230002 to 2991411. Test Plan: make all check valgrind db_test db_stress --use_block_based_filter = 0 ./auto_sanity_test.sh Reviewers: igor, yhchiang, ljin, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D20979
10 years ago
const std::string BlockBasedTable::kFullFilterBlockPrefix = "fullfilter.";
const std::string BlockBasedTable::kPartitionedFilterBlockPrefix =
"partitionedfilter.";
} // namespace rocksdb