|
|
|
// 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 "block_fetcher.h"
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
#include "db/table_properties_collector.h"
|
|
|
|
#include "file/random_access_file_reader.h"
|
|
|
|
#include "rocksdb/table.h"
|
|
|
|
#include "rocksdb/table_properties.h"
|
|
|
|
#include "table/block_based/block.h"
|
|
|
|
#include "table/format.h"
|
|
|
|
#include "table/internal_iterator.h"
|
|
|
|
#include "table/persistent_cache_helper.h"
|
|
|
|
#include "table/table_properties_internal.h"
|
|
|
|
#include "test_util/sync_point.h"
|
|
|
|
#include "util/coding.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
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();
|
|
|
|
}
|
|
|
|
|
|
|
|
// Property block will be read sequentially and cached in a heap located
|
|
|
|
// object, so there's no need for restart points. Thus we set the restart
|
|
|
|
// interval to infinity to save space.
|
|
|
|
PropertyBlockBuilder::PropertyBlockBuilder()
|
|
|
|
: properties_block_(
|
|
|
|
new BlockBuilder(port::kMaxInt32 /* 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) {
|
|
|
|
TEST_SYNC_POINT_CALLBACK("PropertyBlockBuilder::AddTableProperty:Start",
|
|
|
|
const_cast<TableProperties*>(&props));
|
|
|
|
|
|
|
|
Add(TablePropertiesNames::kOriginalFileNumber, props.orig_file_number);
|
|
|
|
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::kIndexKeyIsUserKey, props.index_key_is_user_key);
|
|
|
|
Add(TablePropertiesNames::kIndexValueIsDeltaEncoded,
|
|
|
|
props.index_value_is_delta_encoded);
|
|
|
|
Add(TablePropertiesNames::kNumEntries, props.num_entries);
|
|
|
|
Add(TablePropertiesNames::kNumFilterEntries, props.num_filter_entries);
|
|
|
|
Add(TablePropertiesNames::kDeletedKeys, props.num_deletions);
|
|
|
|
Add(TablePropertiesNames::kMergeOperands, props.num_merge_operands);
|
|
|
|
Add(TablePropertiesNames::kNumRangeDeletions, props.num_range_deletions);
|
|
|
|
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);
|
|
|
|
Add(TablePropertiesNames::kCreationTime, props.creation_time);
|
|
|
|
Add(TablePropertiesNames::kOldestKeyTime, props.oldest_key_time);
|
Periodic Compactions (#5166)
Summary:
Introducing Periodic Compactions.
This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold.
- Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF.
- This works across all levels.
- The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used).
- Compaction filters, if any, are invoked as usual.
- A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS).
This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166
Differential Revision: D14884441
Pulled By: sagar0
fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
|
|
|
if (props.file_creation_time > 0) {
|
|
|
|
Add(TablePropertiesNames::kFileCreationTime, props.file_creation_time);
|
|
|
|
}
|
|
|
|
if (props.slow_compression_estimated_data_size > 0) {
|
|
|
|
Add(TablePropertiesNames::kSlowCompressionEstimatedDataSize,
|
|
|
|
props.slow_compression_estimated_data_size);
|
|
|
|
}
|
|
|
|
if (props.fast_compression_estimated_data_size > 0) {
|
|
|
|
Add(TablePropertiesNames::kFastCompressionEstimatedDataSize,
|
|
|
|
props.fast_compression_estimated_data_size);
|
|
|
|
}
|
Restore file size in backup table file names (and other cleanup) (#7400)
Summary:
Prior to 6.12, backup files using share_files_with_checksum had
the file size encoded in the file name, after the last '\_' and before
the last '.'. We considered this an implementation detail subject to
change, and indeed removed this information from the file name (with an
option to use old behavior) because it was considered
ineffective/inefficient for file name uniqueness. However, some
downstream RocksDB users were relying on this information since the file
size is not explicitly in the backup manifest file.
This primary purpose of this change is "retrofitting" the 6.12 release
(not yet a public release) to simultaneously support the benefits of the
new naming scheme (I/O performance and data correctness at scale) and
preserve the file size information, both as default behaviors. With this
change, we are essentially making the file size information encoded in
the file name an official, though obscure, extension of the backup meta
file format.
We preserve an option (kLegacyCrc32cAndFileSize) to use the original
"legacy" naming scheme, with its caveats, and make it easy to omit the
file size information (no kFlagIncludeFileSize), for more compact file
names. But note that changing the naming scheme used on an existing db
and backup directory can lead to transient space amplification, as some
files will be stored under two names in the shared_checksum directory.
Because some backups were saved using the original 6.12 naming scheme,
we offer two ways of dealing with those files: SST files generated by
older 6.12 versions can either use the default naming scheme in effect
when the SST files were generated (kFlagMatchInterimNaming, default, no
transient space amplification) or can use a new naming scheme (no
kFlagMatchInterimNaming, potential space amplification because some
already stored files getting a new name).
We don't have a natural way to detect which files were generated by
previous 6.12 versions, but this change hacks one in by changing DB
session ids to now use a more concise encoding, reducing file name
length, saving ~dozen bytes from SST files, and making them visually
distinct from DB ids so that they are less likely to be mixed up.
Two final auxiliary notes:
Recognizing that the backup file names have become a de facto part of
the backup meta schema, this change makes them easier to parse and
extend by putting a distinct marker, 's', before DB session ids embedded
in the name. When we extend this to allow custom checksums in the name,
they can get their own marker to ensure safe parsing. For backward
compatibility, file size does not get a marker but is assumed for
`_[0-9]+[.]`
Another change from initial 6.12 default behavior is never including
file custom checksum in the file name. Looking ahead to 6.13, we do not
want the default behavior to cause backup space amplification for
someone turning on file custom checksum checking in BackupEngine; we
want that to be an easy decision. When implemented, including file
custom checksums in backup file names will be a non-default option.
Actual file name patterns and priorities, as regexes:
kLegacyCrc32cAndFileSize OR pre-6.12 SST file ->
[0-9]+_[0-9]+_[0-9]+[.]sst
kFlagMatchInterimNaming set (default) AND early 6.12 SST file ->
[0-9]+_[0-9a-fA-F-]+[.]sst
kUseDbSessionId AND NOT kFlagIncludeFileSize ->
[0-9]+_s[0-9A-Z]{20}[.]sst
kUseDbSessionId AND kFlagIncludeFileSize (default) ->
[0-9]+_s[0-9A-Z]{20}_[0-9]+[.]sst
We might add opt-in options for more '\_' separated data in the name,
but embedded file size, if present, will always be after last '\_' and
before '.sst'.
This change was originally applied to version 6.12. (See https://github.com/facebook/rocksdb/issues/7390)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7400
Test Plan:
unit tests included. Sync point callbacks are used to mimic
previous version SST files.
Reviewed By: ajkr
Differential Revision: D23759587
Pulled By: pdillinger
fbshipit-source-id: f62d8af4e0978de0a34f26288cfbe66049b70025
4 years ago
|
|
|
if (!props.db_id.empty()) {
|
|
|
|
Add(TablePropertiesNames::kDbId, props.db_id);
|
|
|
|
}
|
|
|
|
if (!props.db_session_id.empty()) {
|
|
|
|
Add(TablePropertiesNames::kDbSessionId, props.db_session_id);
|
|
|
|
}
|
|
|
|
if (!props.db_host_id.empty()) {
|
|
|
|
Add(TablePropertiesNames::kDbHostId, props.db_host_id);
|
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
if (!props.compression_options.empty()) {
|
|
|
|
Add(TablePropertiesNames::kCompressionOptions, props.compression_options);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
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(
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
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) {
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
void NotifyCollectTableCollectorsOnBlockAdd(
|
|
|
|
const std::vector<std::unique_ptr<IntTblPropCollector>>& collectors,
|
|
|
|
const uint64_t block_raw_bytes, const uint64_t block_compressed_bytes_fast,
|
|
|
|
const uint64_t block_compressed_bytes_slow) {
|
|
|
|
for (auto& collector : collectors) {
|
|
|
|
collector->BlockAdd(block_raw_bytes, block_compressed_bytes_fast,
|
|
|
|
block_compressed_bytes_slow);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
bool NotifyCollectTableCollectorsOnFinish(
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
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 ReadOptions& read_options,
|
|
|
|
const Slice& handle_value, RandomAccessFileReader* file,
|
|
|
|
FilePrefetchBuffer* prefetch_buffer, const Footer& footer,
|
|
|
|
const ImmutableOptions& ioptions,
|
|
|
|
TableProperties** table_properties, bool verify_checksum,
|
|
|
|
BlockHandle* ret_block_handle,
|
|
|
|
CacheAllocationPtr* verification_buf,
|
|
|
|
bool /*compression_type_missing*/,
|
|
|
|
MemoryAllocator* memory_allocator) {
|
|
|
|
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;
|
|
|
|
Status s;
|
|
|
|
// FIXME: should be a parameter for reading table properties to use persistent
|
|
|
|
// cache
|
|
|
|
PersistentCacheOptions cache_options;
|
|
|
|
ReadOptions ro = read_options;
|
|
|
|
ro.verify_checksums = verify_checksum;
|
|
|
|
|
|
|
|
BlockFetcher block_fetcher(file, prefetch_buffer, footer, ro, handle,
|
|
|
|
&block_contents, ioptions, false /* decompress */,
|
|
|
|
false /*maybe_compressed*/, BlockType::kProperties,
|
|
|
|
UncompressionDict::GetEmptyDict(), cache_options,
|
|
|
|
memory_allocator);
|
|
|
|
s = block_fetcher.ReadBlockContents();
|
|
|
|
// property block is never compressed. Need to add uncompress logic if we are
|
|
|
|
// to compress it..
|
|
|
|
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Block properties_block(std::move(block_contents));
|
|
|
|
DataBlockIter iter;
|
|
|
|
properties_block.NewDataIterator(BytewiseComparator(),
|
|
|
|
kDisableGlobalSequenceNumber, &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::kOriginalFileNumber,
|
|
|
|
&new_table_properties->orig_file_number},
|
|
|
|
{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::kIndexKeyIsUserKey,
|
|
|
|
&new_table_properties->index_key_is_user_key},
|
|
|
|
{TablePropertiesNames::kIndexValueIsDeltaEncoded,
|
|
|
|
&new_table_properties->index_value_is_delta_encoded},
|
|
|
|
{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::kNumFilterEntries,
|
|
|
|
&new_table_properties->num_filter_entries},
|
|
|
|
{TablePropertiesNames::kDeletedKeys,
|
|
|
|
&new_table_properties->num_deletions},
|
|
|
|
{TablePropertiesNames::kMergeOperands,
|
|
|
|
&new_table_properties->num_merge_operands},
|
|
|
|
{TablePropertiesNames::kNumRangeDeletions,
|
|
|
|
&new_table_properties->num_range_deletions},
|
|
|
|
{TablePropertiesNames::kFormatVersion,
|
|
|
|
&new_table_properties->format_version},
|
|
|
|
{TablePropertiesNames::kFixedKeyLen,
|
|
|
|
&new_table_properties->fixed_key_len},
|
|
|
|
{TablePropertiesNames::kColumnFamilyId,
|
|
|
|
&new_table_properties->column_family_id},
|
|
|
|
{TablePropertiesNames::kCreationTime,
|
|
|
|
&new_table_properties->creation_time},
|
|
|
|
{TablePropertiesNames::kOldestKeyTime,
|
|
|
|
&new_table_properties->oldest_key_time},
|
Periodic Compactions (#5166)
Summary:
Introducing Periodic Compactions.
This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold.
- Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF.
- This works across all levels.
- The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used).
- Compaction filters, if any, are invoked as usual.
- A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS).
This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166
Differential Revision: D14884441
Pulled By: sagar0
fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
|
|
|
{TablePropertiesNames::kFileCreationTime,
|
|
|
|
&new_table_properties->file_creation_time},
|
|
|
|
{TablePropertiesNames::kSlowCompressionEstimatedDataSize,
|
|
|
|
&new_table_properties->slow_compression_estimated_data_size},
|
|
|
|
{TablePropertiesNames::kFastCompressionEstimatedDataSize,
|
|
|
|
&new_table_properties->fast_compression_estimated_data_size},
|
|
|
|
};
|
|
|
|
|
|
|
|
std::string last_key;
|
|
|
|
for (iter.SeekToFirstOrReport(); iter.Valid(); iter.NextOrReport()) {
|
|
|
|
s = iter.status();
|
|
|
|
if (!s.ok()) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
auto key = iter.key().ToString();
|
|
|
|
// properties block should be strictly sorted with no duplicate key.
|
|
|
|
if (!last_key.empty() &&
|
|
|
|
BytewiseComparator()->Compare(key, last_key) <= 0) {
|
|
|
|
s = Status::Corruption("properties unsorted");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
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()) {
|
|
|
|
if (key == TablePropertiesNames::kDeletedKeys ||
|
|
|
|
key == TablePropertiesNames::kMergeOperands) {
|
|
|
|
// Insert in user-collected properties for API backwards compatibility
|
|
|
|
new_table_properties->user_collected_properties.insert(
|
|
|
|
{key, raw_val.ToString()});
|
|
|
|
}
|
|
|
|
// 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.logger, "%s", error_msg.c_str());
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
*(pos->second) = val;
|
|
|
|
} else if (key == TablePropertiesNames::kDbId) {
|
|
|
|
new_table_properties->db_id = raw_val.ToString();
|
|
|
|
} else if (key == TablePropertiesNames::kDbSessionId) {
|
|
|
|
new_table_properties->db_session_id = raw_val.ToString();
|
|
|
|
} else if (key == TablePropertiesNames::kDbHostId) {
|
|
|
|
new_table_properties->db_host_id = raw_val.ToString();
|
|
|
|
} 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();
|
|
|
|
} 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 if (key == TablePropertiesNames::kCompressionOptions) {
|
|
|
|
new_table_properties->compression_options = 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;
|
|
|
|
if (ret_block_handle != nullptr) {
|
|
|
|
*ret_block_handle = handle;
|
|
|
|
}
|
|
|
|
if (verification_buf != nullptr) {
|
|
|
|
size_t len = static_cast<size_t>(handle.size() + kBlockTrailerSize);
|
|
|
|
*verification_buf =
|
|
|
|
ROCKSDB_NAMESPACE::AllocateBlock(len, memory_allocator);
|
|
|
|
if (verification_buf->get() != nullptr) {
|
|
|
|
memcpy(verification_buf->get(), block_contents.data.data(), len);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
delete new_table_properties;
|
|
|
|
}
|
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
|
|
|
|
uint64_t table_magic_number,
|
|
|
|
const ImmutableOptions& ioptions,
|
|
|
|
TableProperties** properties,
|
|
|
|
bool compression_type_missing,
|
|
|
|
MemoryAllocator* memory_allocator,
|
|
|
|
FilePrefetchBuffer* prefetch_buffer) {
|
|
|
|
// -- Read metaindex block
|
|
|
|
Footer footer;
|
|
|
|
IOOptions opts;
|
|
|
|
auto s = ReadFooterFromFile(opts, file, 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;
|
|
|
|
PersistentCacheOptions cache_options;
|
|
|
|
|
|
|
|
BlockFetcher block_fetcher(
|
|
|
|
file, prefetch_buffer, footer, read_options, metaindex_handle,
|
|
|
|
&metaindex_contents, ioptions, false /* decompress */,
|
|
|
|
false /*maybe_compressed*/, BlockType::kMetaIndex,
|
|
|
|
UncompressionDict::GetEmptyDict(), cache_options, memory_allocator);
|
|
|
|
s = block_fetcher.ReadBlockContents();
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
// property blocks are never compressed. Need to add uncompress logic if we
|
|
|
|
// are to compress it.
|
|
|
|
Block metaindex_block(std::move(metaindex_contents));
|
Add an option to put first key of each sst block in the index (#5289)
Summary:
The first key is used to defer reading the data block until this file gets to the top of merging iterator's heap. For short range scans, most files never make it to the top of the heap, so this change can reduce read amplification by a lot sometimes.
Consider the following workload. There are a few data streams (we'll be calling them "logs"), each stream consisting of a sequence of blobs (we'll be calling them "records"). Each record is identified by log ID and a sequence number within the log. RocksDB key is concatenation of log ID and sequence number (big endian). Reads are mostly relatively short range scans, each within a single log. Writes are mostly sequential for each log, but writes to different logs are randomly interleaved. Compactions are disabled; instead, when we accumulate a few tens of sst files, we create a new column family and start writing to it.
So, a typical sst file consists of a few ranges of blocks, each range corresponding to one log ID (we use FlushBlockPolicy to cut blocks at log boundaries). A typical read would go like this. First, iterator Seek() reads one block from each sst file. Then a series of Next()s move through one sst file (since writes to each log are mostly sequential) until the subiterator reaches the end of this log in this sst file; then Next() switches to the next sst file and reads sequentially from that, and so on. Often a range scan will only return records from a small number of blocks in small number of sst files; in this case, the cost of initial Seek() reading one block from each file may be bigger than the cost of reading the actually useful blocks.
Neither iterate_upper_bound nor bloom filters can prevent reading one block from each file in Seek(). But this PR can: if the index contains first key from each block, we don't have to read the block until this block actually makes it to the top of merging iterator's heap, so for short range scans we won't read any blocks from most of the sst files.
This PR does the deferred block loading inside value() call. This is not ideal: there's no good way to report an IO error from inside value(). As discussed with siying offline, it would probably be better to change InternalIterator's interface to explicitly fetch deferred value and get status. I'll do it in a separate PR.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5289
Differential Revision: D15256423
Pulled By: al13n321
fbshipit-source-id: 750e4c39ce88e8d41662f701cf6275d9388ba46a
5 years ago
|
|
|
std::unique_ptr<InternalIterator> meta_iter(metaindex_block.NewDataIterator(
|
|
|
|
BytewiseComparator(), kDisableGlobalSequenceNumber));
|
|
|
|
|
|
|
|
// -- 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(
|
|
|
|
read_options, meta_iter->value(), file, prefetch_buffer, footer,
|
|
|
|
ioptions, properties, false /* verify_checksum */,
|
|
|
|
nullptr /* ret_block_hanel */, nullptr /* ret_block_contents */,
|
|
|
|
compression_type_missing, memory_allocator);
|
|
|
|
} 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);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
Status FindMetaBlock(RandomAccessFileReader* file, uint64_t file_size,
|
|
|
|
uint64_t table_magic_number,
|
|
|
|
const ImmutableOptions& ioptions,
|
|
|
|
const std::string& meta_block_name,
|
|
|
|
BlockHandle* block_handle,
|
|
|
|
bool /*compression_type_missing*/,
|
|
|
|
MemoryAllocator* memory_allocator) {
|
|
|
|
Footer footer;
|
|
|
|
IOOptions opts;
|
|
|
|
auto s = ReadFooterFromFile(opts, 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;
|
|
|
|
PersistentCacheOptions cache_options;
|
|
|
|
BlockFetcher block_fetcher(
|
|
|
|
file, nullptr /* prefetch_buffer */, footer, read_options,
|
|
|
|
metaindex_handle, &metaindex_contents, ioptions,
|
|
|
|
false /* do decompression */, false /*maybe_compressed*/,
|
|
|
|
BlockType::kMetaIndex, UncompressionDict::GetEmptyDict(), cache_options,
|
|
|
|
memory_allocator);
|
|
|
|
s = block_fetcher.ReadBlockContents();
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
// meta blocks are never compressed. Need to add uncompress logic if we are to
|
|
|
|
// compress it.
|
|
|
|
Block metaindex_block(std::move(metaindex_contents));
|
|
|
|
|
|
|
|
std::unique_ptr<InternalIterator> meta_iter;
|
|
|
|
meta_iter.reset(metaindex_block.NewDataIterator(
|
|
|
|
BytewiseComparator(), kDisableGlobalSequenceNumber));
|
|
|
|
|
|
|
|
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 ImmutableOptions& ioptions,
|
|
|
|
const std::string& meta_block_name, BlockType block_type,
|
|
|
|
BlockContents* contents, bool /*compression_type_missing*/,
|
|
|
|
MemoryAllocator* memory_allocator) {
|
|
|
|
Status status;
|
|
|
|
Footer footer;
|
|
|
|
IOOptions opts;
|
|
|
|
status = ReadFooterFromFile(opts, 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;
|
|
|
|
PersistentCacheOptions cache_options;
|
|
|
|
|
|
|
|
BlockFetcher block_fetcher(
|
|
|
|
file, prefetch_buffer, footer, read_options, metaindex_handle,
|
|
|
|
&metaindex_contents, ioptions, false /* decompress */,
|
|
|
|
false /*maybe_compressed*/, BlockType::kMetaIndex,
|
|
|
|
UncompressionDict::GetEmptyDict(), cache_options, memory_allocator);
|
|
|
|
status = block_fetcher.ReadBlockContents();
|
|
|
|
if (!status.ok()) {
|
|
|
|
return status;
|
|
|
|
}
|
|
|
|
// meta block is never compressed. Need to add uncompress logic if we are to
|
|
|
|
// compress it.
|
|
|
|
|
|
|
|
// Finding metablock
|
|
|
|
Block metaindex_block(std::move(metaindex_contents));
|
|
|
|
|
|
|
|
std::unique_ptr<InternalIterator> meta_iter;
|
|
|
|
meta_iter.reset(metaindex_block.NewDataIterator(
|
|
|
|
BytewiseComparator(), kDisableGlobalSequenceNumber));
|
|
|
|
|
|
|
|
BlockHandle block_handle;
|
|
|
|
status = FindMetaBlock(meta_iter.get(), meta_block_name, &block_handle);
|
|
|
|
|
|
|
|
if (!status.ok()) {
|
|
|
|
return status;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Reading metablock
|
|
|
|
BlockFetcher block_fetcher2(
|
|
|
|
file, prefetch_buffer, footer, read_options, block_handle, contents,
|
|
|
|
ioptions, false /* decompress */, false /*maybe_compressed*/, block_type,
|
|
|
|
UncompressionDict::GetEmptyDict(), cache_options, memory_allocator);
|
|
|
|
return block_fetcher2.ReadBlockContents();
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|