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/meta_blocks.cc

415 lines
15 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).
#include "table/meta_blocks.h"
#include <map>
#include <string>
#include "db/table_properties_collector.h"
#include "rocksdb/table.h"
#include "rocksdb/table_properties.h"
#include "table/block.h"
#include "table/format.h"
#include "table/internal_iterator.h"
#include "table/persistent_cache_helper.h"
#include "table/table_properties_internal.h"
#include "util/coding.h"
#include "util/file_reader_writer.h"
namespace rocksdb {
MetaIndexBuilder::MetaIndexBuilder()
: meta_index_block_(new BlockBuilder(1 /* restart interval */)) {}
void MetaIndexBuilder::Add(const std::string& key,
const BlockHandle& handle) {
std::string handle_encoding;
handle.EncodeTo(&handle_encoding);
meta_block_handles_.insert({key, handle_encoding});
}
Slice MetaIndexBuilder::Finish() {
for (const auto& metablock : meta_block_handles_) {
meta_index_block_->Add(metablock.first, metablock.second);
}
return meta_index_block_->Finish();
}
PropertyBlockBuilder::PropertyBlockBuilder()
: properties_block_(new BlockBuilder(1 /* restart interval */)) {}
void PropertyBlockBuilder::Add(const std::string& name,
const std::string& val) {
props_.insert({name, val});
}
void PropertyBlockBuilder::Add(const std::string& name, uint64_t val) {
assert(props_.find(name) == props_.end());
std::string dst;
PutVarint64(&dst, val);
Add(name, dst);
}
void PropertyBlockBuilder::Add(
const UserCollectedProperties& user_collected_properties) {
for (const auto& prop : user_collected_properties) {
Add(prop.first, prop.second);
}
}
void PropertyBlockBuilder::AddTableProperty(const TableProperties& props) {
Add(TablePropertiesNames::kRawKeySize, props.raw_key_size);
Add(TablePropertiesNames::kRawValueSize, props.raw_value_size);
Add(TablePropertiesNames::kDataSize, props.data_size);
Add(TablePropertiesNames::kIndexSize, props.index_size);
if (props.index_partitions != 0) {
Add(TablePropertiesNames::kIndexPartitions, props.index_partitions);
Add(TablePropertiesNames::kTopLevelIndexSize, props.top_level_index_size);
}
Add(TablePropertiesNames::kNumEntries, props.num_entries);
Add(TablePropertiesNames::kNumDataBlocks, props.num_data_blocks);
Add(TablePropertiesNames::kFilterSize, props.filter_size);
Add(TablePropertiesNames::kFormatVersion, props.format_version);
Add(TablePropertiesNames::kFixedKeyLen, props.fixed_key_len);
Add(TablePropertiesNames::kColumnFamilyId, props.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
7 years ago
Add(TablePropertiesNames::kCreationTime, props.creation_time);
Add(TablePropertiesNames::kOldestKeyTime, props.oldest_key_time);
if (!props.filter_policy_name.empty()) {
Add(TablePropertiesNames::kFilterPolicy, props.filter_policy_name);
}
if (!props.comparator_name.empty()) {
Add(TablePropertiesNames::kComparator, props.comparator_name);
}
if (!props.merge_operator_name.empty()) {
Add(TablePropertiesNames::kMergeOperator, props.merge_operator_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
8 years ago
if (!props.prefix_extractor_name.empty()) {
Add(TablePropertiesNames::kPrefixExtractorName,
props.prefix_extractor_name);
}
if (!props.property_collectors_names.empty()) {
Add(TablePropertiesNames::kPropertyCollectors,
props.property_collectors_names);
}
if (!props.column_family_name.empty()) {
Add(TablePropertiesNames::kColumnFamilyName, props.column_family_name);
}
if (!props.compression_name.empty()) {
Add(TablePropertiesNames::kCompression, props.compression_name);
}
}
Slice PropertyBlockBuilder::Finish() {
for (const auto& prop : props_) {
properties_block_->Add(prop.first, prop.second);
}
return properties_block_->Finish();
}
void LogPropertiesCollectionError(
Logger* info_log, const std::string& method, const std::string& name) {
assert(method == "Add" || method == "Finish");
std::string msg =
"Encountered error when calling TablePropertiesCollector::" +
method + "() with collector name: " + name;
ROCKS_LOG_ERROR(info_log, "%s", msg.c_str());
}
bool NotifyCollectTableCollectorsOnAdd(
const Slice& key, const Slice& value, uint64_t file_size,
const std::vector<std::unique_ptr<IntTblPropCollector>>& collectors,
Logger* info_log) {
bool all_succeeded = true;
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
for (auto& collector : collectors) {
Status s = collector->InternalAdd(key, value, file_size);
all_succeeded = all_succeeded && s.ok();
if (!s.ok()) {
LogPropertiesCollectionError(info_log, "Add" /* method */,
collector->Name());
}
}
return all_succeeded;
}
bool NotifyCollectTableCollectorsOnFinish(
const std::vector<std::unique_ptr<IntTblPropCollector>>& 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
Logger* info_log, PropertyBlockBuilder* builder) {
bool all_succeeded = true;
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
for (auto& collector : collectors) {
UserCollectedProperties user_collected_properties;
Status s = collector->Finish(&user_collected_properties);
all_succeeded = all_succeeded && s.ok();
if (!s.ok()) {
LogPropertiesCollectionError(info_log, "Finish" /* method */,
collector->Name());
} else {
builder->Add(user_collected_properties);
}
}
return all_succeeded;
}
Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
FilePrefetchBuffer* prefetch_buffer, const Footer& footer,
const ImmutableCFOptions& ioptions,
TableProperties** table_properties) {
assert(table_properties);
Slice v = handle_value;
BlockHandle handle;
if (!handle.DecodeFrom(&v).ok()) {
return Status::InvalidArgument("Failed to decode properties block handle");
}
BlockContents block_contents;
ReadOptions read_options;
read_options.verify_checksums = false;
Status s;
s = ReadBlockContents(file, prefetch_buffer, footer, read_options, handle,
&block_contents, ioptions, false /* decompress */);
if (!s.ok()) {
return s;
}
Block properties_block(std::move(block_contents),
kDisableGlobalSequenceNumber);
BlockIter iter;
properties_block.NewIterator(BytewiseComparator(), &iter);
auto new_table_properties = new TableProperties();
// All pre-defined properties of type uint64_t
std::unordered_map<std::string, uint64_t*> predefined_uint64_properties = {
{TablePropertiesNames::kDataSize, &new_table_properties->data_size},
{TablePropertiesNames::kIndexSize, &new_table_properties->index_size},
{TablePropertiesNames::kIndexPartitions,
&new_table_properties->index_partitions},
{TablePropertiesNames::kTopLevelIndexSize,
&new_table_properties->top_level_index_size},
{TablePropertiesNames::kFilterSize, &new_table_properties->filter_size},
{TablePropertiesNames::kRawKeySize, &new_table_properties->raw_key_size},
{TablePropertiesNames::kRawValueSize,
&new_table_properties->raw_value_size},
{TablePropertiesNames::kNumDataBlocks,
&new_table_properties->num_data_blocks},
{TablePropertiesNames::kNumEntries, &new_table_properties->num_entries},
{TablePropertiesNames::kFormatVersion,
&new_table_properties->format_version},
{TablePropertiesNames::kFixedKeyLen,
&new_table_properties->fixed_key_len},
{TablePropertiesNames::kColumnFamilyId,
&new_table_properties->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
7 years ago
{TablePropertiesNames::kCreationTime,
&new_table_properties->creation_time},
{TablePropertiesNames::kOldestKeyTime,
&new_table_properties->oldest_key_time},
};
std::string last_key;
for (iter.SeekToFirst(); iter.Valid(); iter.Next()) {
s = iter.status();
if (!s.ok()) {
break;
}
auto key = iter.key().ToString();
// properties block is strictly sorted with no duplicate key.
assert(last_key.empty() ||
BytewiseComparator()->Compare(key, last_key) > 0);
last_key = key;
auto raw_val = iter.value();
auto pos = predefined_uint64_properties.find(key);
new_table_properties->properties_offsets.insert(
{key, handle.offset() + iter.ValueOffset()});
if (pos != predefined_uint64_properties.end()) {
// handle predefined rocksdb properties
uint64_t val;
if (!GetVarint64(&raw_val, &val)) {
// skip malformed value
auto error_msg =
"Detect malformed value in properties meta-block:"
"\tkey: " + key + "\tval: " + raw_val.ToString();
ROCKS_LOG_ERROR(ioptions.info_log, "%s", error_msg.c_str());
continue;
}
*(pos->second) = val;
} else if (key == TablePropertiesNames::kFilterPolicy) {
new_table_properties->filter_policy_name = raw_val.ToString();
} else if (key == TablePropertiesNames::kColumnFamilyName) {
new_table_properties->column_family_name = raw_val.ToString();
} else if (key == TablePropertiesNames::kComparator) {
new_table_properties->comparator_name = raw_val.ToString();
} else if (key == TablePropertiesNames::kMergeOperator) {
new_table_properties->merge_operator_name = raw_val.ToString();
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
} else if (key == TablePropertiesNames::kPrefixExtractorName) {
new_table_properties->prefix_extractor_name = raw_val.ToString();
} else if (key == TablePropertiesNames::kPropertyCollectors) {
new_table_properties->property_collectors_names = raw_val.ToString();
} else if (key == TablePropertiesNames::kCompression) {
new_table_properties->compression_name = raw_val.ToString();
} else {
// handle user-collected properties
new_table_properties->user_collected_properties.insert(
{key, raw_val.ToString()});
}
}
if (s.ok()) {
*table_properties = new_table_properties;
} else {
delete new_table_properties;
}
return s;
}
Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableCFOptions &ioptions,
TableProperties** properties) {
// -- Read metaindex block
Footer footer;
auto s = ReadFooterFromFile(file, nullptr /* prefetch_buffer */, file_size,
&footer, table_magic_number);
if (!s.ok()) {
return s;
}
auto metaindex_handle = footer.metaindex_handle();
BlockContents metaindex_contents;
ReadOptions read_options;
read_options.verify_checksums = false;
s = ReadBlockContents(file, nullptr /* prefetch_buffer */, footer,
read_options, metaindex_handle, &metaindex_contents,
ioptions, false /* decompress */);
if (!s.ok()) {
return s;
}
Block metaindex_block(std::move(metaindex_contents),
kDisableGlobalSequenceNumber);
std::unique_ptr<InternalIterator> meta_iter(
metaindex_block.NewIterator(BytewiseComparator()));
// -- Read property block
bool found_properties_block = true;
s = SeekToPropertiesBlock(meta_iter.get(), &found_properties_block);
if (!s.ok()) {
return s;
}
TableProperties table_properties;
if (found_properties_block == true) {
s = ReadProperties(meta_iter->value(), file, nullptr /* prefetch_buffer */,
footer, ioptions, properties);
} else {
s = Status::NotFound();
}
return s;
}
Status FindMetaBlock(InternalIterator* meta_index_iter,
const std::string& meta_block_name,
BlockHandle* block_handle) {
meta_index_iter->Seek(meta_block_name);
if (meta_index_iter->status().ok() && meta_index_iter->Valid() &&
meta_index_iter->key() == meta_block_name) {
Slice v = meta_index_iter->value();
return block_handle->DecodeFrom(&v);
} else {
return Status::Corruption("Cannot find the meta block", meta_block_name);
}
}
Status FindMetaBlock(RandomAccessFileReader* file, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableCFOptions &ioptions,
const std::string& meta_block_name,
BlockHandle* block_handle) {
Footer footer;
auto s = ReadFooterFromFile(file, nullptr /* prefetch_buffer */, file_size,
&footer, table_magic_number);
if (!s.ok()) {
return s;
}
auto metaindex_handle = footer.metaindex_handle();
BlockContents metaindex_contents;
ReadOptions read_options;
read_options.verify_checksums = false;
s = ReadBlockContents(file, nullptr /* prefetch_buffer */, footer,
read_options, metaindex_handle, &metaindex_contents,
ioptions, false /* do decompression */);
if (!s.ok()) {
return s;
}
Block metaindex_block(std::move(metaindex_contents),
kDisableGlobalSequenceNumber);
std::unique_ptr<InternalIterator> meta_iter;
meta_iter.reset(metaindex_block.NewIterator(BytewiseComparator()));
return FindMetaBlock(meta_iter.get(), meta_block_name, block_handle);
}
Status ReadMetaBlock(RandomAccessFileReader* file,
FilePrefetchBuffer* prefetch_buffer, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableCFOptions& ioptions,
const std::string& meta_block_name,
BlockContents* contents) {
Status status;
Footer footer;
status = ReadFooterFromFile(file, prefetch_buffer, file_size, &footer,
table_magic_number);
if (!status.ok()) {
return status;
}
// Reading metaindex block
auto metaindex_handle = footer.metaindex_handle();
BlockContents metaindex_contents;
ReadOptions read_options;
read_options.verify_checksums = false;
status = ReadBlockContents(file, prefetch_buffer, footer, read_options,
metaindex_handle, &metaindex_contents, ioptions,
false /* decompress */);
if (!status.ok()) {
return status;
}
// Finding metablock
Block metaindex_block(std::move(metaindex_contents),
kDisableGlobalSequenceNumber);
std::unique_ptr<InternalIterator> meta_iter;
meta_iter.reset(metaindex_block.NewIterator(BytewiseComparator()));
BlockHandle block_handle;
status = FindMetaBlock(meta_iter.get(), meta_block_name, &block_handle);
if (!status.ok()) {
return status;
}
// Reading metablock
return ReadBlockContents(file, prefetch_buffer, footer, read_options,
block_handle, contents, ioptions,
false /* decompress */);
}
} // namespace rocksdb