rocksdb/table/plain_table_builder.cc

297 lines
9.4 KiB
C++
Raw Normal View History

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
#ifndef ROCKSDB_LITE
#include "table/plain_table_builder.h"
#include <assert.h>
#include <string>
#include <limits>
#include <map>
#include "rocksdb/comparator.h"
#include "rocksdb/env.h"
#include "rocksdb/filter_policy.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/plain_table_factory.h"
#include "db/dbformat.h"
#include "table/block_builder.h"
#include "table/bloom_block.h"
#include "table/plain_table_index.h"
#include "table/format.h"
#include "table/meta_blocks.h"
#include "util/coding.h"
#include "util/crc32c.h"
#include "util/file_reader_writer.h"
#include "util/stop_watch.h"
namespace rocksdb {
namespace {
// a utility that helps writing block content to the file
// @offset will advance if @block_contents was successfully written.
// @block_handle the block handle this particular block.
Status WriteBlock(const Slice& block_contents, WritableFileWriter* file,
uint64_t* offset, BlockHandle* block_handle) {
block_handle->set_offset(*offset);
block_handle->set_size(block_contents.size());
Status s = file->Append(block_contents);
if (s.ok()) {
*offset += block_contents.size();
}
return s;
}
} // namespace
// kPlainTableMagicNumber was picked by running
// echo rocksdb.table.plain | sha1sum
// and taking the leading 64 bits.
extern const uint64_t kPlainTableMagicNumber = 0x8242229663bf9564ull;
extern const uint64_t kLegacyPlainTableMagicNumber = 0x4f3418eb7a8f13b8ull;
PlainTableBuilder::PlainTableBuilder(
const ImmutableCFOptions& ioptions,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t column_family_id, WritableFileWriter* file, uint32_t user_key_len,
EncodingType encoding_type, size_t index_sparseness,
uint32_t bloom_bits_per_key, const std::string& column_family_name,
uint32_t num_probes, size_t huge_page_tlb_size, double hash_table_ratio,
bool store_index_in_file)
: ioptions_(ioptions),
bloom_block_(num_probes),
file_(file),
bloom_bits_per_key_(bloom_bits_per_key),
huge_page_tlb_size_(huge_page_tlb_size),
encoder_(encoding_type, user_key_len, ioptions.prefix_extractor,
index_sparseness),
store_index_in_file_(store_index_in_file),
prefix_extractor_(ioptions.prefix_extractor) {
// Build index block and save it in the file if hash_table_ratio > 0
if (store_index_in_file_) {
assert(hash_table_ratio > 0 || IsTotalOrderMode());
index_builder_.reset(
new PlainTableIndexBuilder(&arena_, ioptions, index_sparseness,
hash_table_ratio, huge_page_tlb_size_));
properties_.user_collected_properties
[PlainTablePropertyNames::kBloomVersion] = "1"; // For future use
}
properties_.fixed_key_len = user_key_len;
// for plain table, we put all the data in a big chuck.
properties_.num_data_blocks = 1;
// Fill it later if store_index_in_file_ == true
properties_.index_size = 0;
properties_.filter_size = 0;
// To support roll-back to previous version, now still use version 0 for
// plain encoding.
properties_.format_version = (encoding_type == kPlain) ? 0 : 1;
properties_.column_family_id = column_family_id;
properties_.column_family_name = column_family_name;
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
2016-08-26 20:46:32 +02:00
properties_.prefix_extractor_name = ioptions_.prefix_extractor != nullptr
? ioptions_.prefix_extractor->Name()
: "nullptr";
std::string val;
PutFixed32(&val, static_cast<uint32_t>(encoder_.GetEncodingType()));
properties_.user_collected_properties
[PlainTablePropertyNames::kEncodingType] = val;
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
2014-05-13 21:30:55 +02:00
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
2014-05-13 21:30:55 +02:00
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
2014-05-13 21:30:55 +02:00
}
}
PlainTableBuilder::~PlainTableBuilder() {
}
void PlainTableBuilder::Add(const Slice& key, const Slice& value) {
// temp buffer for metadata bytes between key and value.
char meta_bytes_buf[6];
size_t meta_bytes_buf_size = 0;
ParsedInternalKey internal_key;
Compaction Support for Range Deletion Summary: This diff introduces RangeDelAggregator, which takes ownership of iterators provided to it via AddTombstones(). The tombstones are organized in a two-level map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data copy by holding Slices returned by the iterator, which remain valid thanks to pinning. For compaction, we create a hierarchical range tombstone iterator with structure matching the iterator over compaction input data. An aggregator based on that iterator is used by CompactionIterator to determine which keys are covered by range tombstones. In case of merge operand, the same aggregator is used by MergeHelper. Upon finishing each file in the compaction, relevant range tombstones are added to the output file's range tombstone metablock and file boundaries are updated accordingly. To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete() considers tombstones in the key's snapshot stripe. When this function is used outside of compaction, it also checks newer stripes, which can contain covering tombstones. Currently the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges within a stripe such that binary search can be used. RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range to a new table's range tombstone meta-block. Since range tombstones may fall in the gap between files, we may need to extend some files' key-ranges. The strategy is (1) first file extends as far left as possible and other files do not extend left, (2) all files extend right until either the start of the next file or the end of the last range tombstone in the gap, whichever comes first. One other notable change is adding release/move semantics to ScopedArenaIterator such that it can be used to transfer ownership of an arena-allocated iterator, similar to how unique_ptr is used for malloc'd data. Depends on D61473 Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927 Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark Reviewed By: lightmark Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
if (!ParseInternalKey(key, &internal_key)) {
assert(false);
return;
}
if (internal_key.type == kTypeRangeDeletion) {
status_ = Status::NotSupported("Range deletion unsupported");
return;
}
// Store key hash
if (store_index_in_file_) {
if (ioptions_.prefix_extractor == nullptr) {
keys_or_prefixes_hashes_.push_back(GetSliceHash(internal_key.user_key));
} else {
Slice prefix =
ioptions_.prefix_extractor->Transform(internal_key.user_key);
keys_or_prefixes_hashes_.push_back(GetSliceHash(prefix));
}
}
// Write value
assert(offset_ <= std::numeric_limits<uint32_t>::max());
auto prev_offset = static_cast<uint32_t>(offset_);
// Write out the key
encoder_.AppendKey(key, file_, &offset_, meta_bytes_buf,
&meta_bytes_buf_size);
if (SaveIndexInFile()) {
index_builder_->AddKeyPrefix(GetPrefix(internal_key), prev_offset);
}
// Write value length
uint32_t value_size = static_cast<uint32_t>(value.size());
char* end_ptr =
EncodeVarint32(meta_bytes_buf + meta_bytes_buf_size, value_size);
assert(end_ptr <= meta_bytes_buf + sizeof(meta_bytes_buf));
meta_bytes_buf_size = end_ptr - meta_bytes_buf;
file_->Append(Slice(meta_bytes_buf, meta_bytes_buf_size));
// Write value
file_->Append(value);
offset_ += value_size + meta_bytes_buf_size;
properties_.num_entries++;
properties_.raw_key_size += key.size();
properties_.raw_value_size += value.size();
// notify property collectors
NotifyCollectTableCollectorsOnAdd(
key, value, offset_, table_properties_collectors_, ioptions_.info_log);
}
Status PlainTableBuilder::status() const { return status_; }
Status PlainTableBuilder::Finish() {
assert(!closed_);
closed_ = true;
properties_.data_size = offset_;
// Write the following blocks
// 1. [meta block: bloom] - optional
// 2. [meta block: index] - optional
// 3. [meta block: properties]
// 4. [metaindex block]
// 5. [footer]
MetaIndexBuilder meta_index_builer;
if (store_index_in_file_ && (properties_.num_entries > 0)) {
assert(properties_.num_entries <= std::numeric_limits<uint32_t>::max());
Status s;
BlockHandle bloom_block_handle;
if (bloom_bits_per_key_ > 0) {
bloom_block_.SetTotalBits(
&arena_,
static_cast<uint32_t>(properties_.num_entries) * bloom_bits_per_key_,
ioptions_.bloom_locality, huge_page_tlb_size_, ioptions_.info_log);
PutVarint32(&properties_.user_collected_properties
[PlainTablePropertyNames::kNumBloomBlocks],
bloom_block_.GetNumBlocks());
bloom_block_.AddKeysHashes(keys_or_prefixes_hashes_);
Slice bloom_finish_result = bloom_block_.Finish();
properties_.filter_size = bloom_finish_result.size();
s = WriteBlock(bloom_finish_result, file_, &offset_, &bloom_block_handle);
if (!s.ok()) {
return s;
}
meta_index_builer.Add(BloomBlockBuilder::kBloomBlock, bloom_block_handle);
}
BlockHandle index_block_handle;
Slice index_finish_result = index_builder_->Finish();
properties_.index_size = index_finish_result.size();
s = WriteBlock(index_finish_result, file_, &offset_, &index_block_handle);
if (!s.ok()) {
return s;
}
meta_index_builer.Add(PlainTableIndexBuilder::kPlainTableIndexBlock,
index_block_handle);
}
// Calculate bloom block size and index block size
PropertyBlockBuilder property_block_builder;
// -- Add basic properties
property_block_builder.AddTableProperty(properties_);
property_block_builder.Add(properties_.user_collected_properties);
// -- Add user 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
2014-05-13 21:30:55 +02:00
NotifyCollectTableCollectorsOnFinish(table_properties_collectors_,
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
2014-05-13 21:30:55 +02:00
&property_block_builder);
// -- Write property block
BlockHandle property_block_handle;
auto s = WriteBlock(
property_block_builder.Finish(),
file_,
&offset_,
&property_block_handle
);
if (!s.ok()) {
return s;
}
meta_index_builer.Add(kPropertiesBlock, property_block_handle);
// -- write metaindex block
BlockHandle metaindex_block_handle;
s = WriteBlock(
meta_index_builer.Finish(),
file_,
&offset_,
&metaindex_block_handle
);
if (!s.ok()) {
return s;
}
// Write Footer
// no need to write out new footer if we're using default checksum
Footer footer(kLegacyPlainTableMagicNumber, 0);
footer.set_metaindex_handle(metaindex_block_handle);
footer.set_index_handle(BlockHandle::NullBlockHandle());
std::string footer_encoding;
footer.EncodeTo(&footer_encoding);
s = file_->Append(footer_encoding);
if (s.ok()) {
offset_ += footer_encoding.size();
}
return s;
}
void PlainTableBuilder::Abandon() {
closed_ = true;
}
uint64_t PlainTableBuilder::NumEntries() const {
return properties_.num_entries;
}
uint64_t PlainTableBuilder::FileSize() const {
return offset_;
}
} // namespace rocksdb
#endif // ROCKSDB_LITE