|
|
|
// 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 "rocksdb/flush_block_policy.h"
|
|
|
|
|
|
|
|
#include <cassert>
|
|
|
|
#include <mutex>
|
|
|
|
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "rocksdb/slice.h"
|
|
|
|
#include "rocksdb/utilities/customizable_util.h"
|
Improve / clean up meta block code & integrity (#9163)
Summary:
* Checksums are now checked on meta blocks unless specifically
suppressed or not applicable (e.g. plain table). (Was other way around.)
This means a number of cases that were not checking checksums now are,
including direct read TableProperties in Version::GetTableProperties
(fixed in meta_blocks ReadTableProperties), reading any block from
PersistentCache (fixed in BlockFetcher), read TableProperties in
SstFileDumper (ldb/sst_dump/BackupEngine) before table reader open,
maybe more.
* For that to work, I moved the global_seqno+TableProperties checksum
logic to the shared table/ code, because that is used by many utilies
such as SstFileDumper.
* Also for that to work, we have to know when we're dealing with a block
that has a checksum (trailer), so added that capability to Footer based
on magic number, and from there BlockFetcher.
* Knowledge of trailer presence has also fixed a problem where other
table formats were reading blocks including bytes for a non-existant
trailer--and awkwardly kind-of not using them, e.g. no shared code
checking checksums. (BlockFetcher compression type was populated
incorrectly.) Now we only read what is needed.
* Minimized code duplication and differing/incompatible/awkward
abstractions in meta_blocks.{cc,h} (e.g. SeekTo in metaindex block
without parsing block handle)
* Moved some meta block handling code from table_properties*.*
* Moved some code specific to block-based table from shared table/ code
to BlockBasedTable class. The checksum stuff means we can't completely
separate it, but things that don't need to be in shared table/ code
should not be.
* Use unique_ptr rather than raw ptr in more places. (Note: you can
std::move from unique_ptr to shared_ptr.)
Without enhancements to GetPropertiesOfAllTablesTest (see below),
net reduction of roughly 100 lines of code.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9163
Test Plan:
existing tests and
* Enhanced DBTablePropertiesTest.GetPropertiesOfAllTablesTest to verify that
checksums are now checked on direct read of table properties by TableCache
(new test would fail before this change)
* Also enhanced DBTablePropertiesTest.GetPropertiesOfAllTablesTest to test
putting table properties under old meta name
* Also generally enhanced that same test to actually test what it was
supposed to be testing already, by kicking things out of table cache when
we don't want them there.
Reviewed By: ajkr, mrambacher
Differential Revision: D32514757
Pulled By: pdillinger
fbshipit-source-id: 507964b9311d186ae8d1131182290cbd97a99fa9
3 years ago
|
|
|
#include "table/block_based/block_based_table_reader.h"
|
|
|
|
#include "table/block_based/block_builder.h"
|
|
|
|
#include "table/block_based/flush_block_policy.h"
|
|
|
|
#include "table/format.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
// Flush block by size
|
|
|
|
class FlushBlockBySizePolicy : public FlushBlockPolicy {
|
|
|
|
public:
|
|
|
|
// @params block_size: Approximate size of user data packed per
|
|
|
|
// block.
|
|
|
|
// @params block_size_deviation: This is used to close a block before it
|
|
|
|
// reaches the configured
|
|
|
|
FlushBlockBySizePolicy(const uint64_t block_size,
|
|
|
|
const uint64_t block_size_deviation, const bool align,
|
|
|
|
const BlockBuilder& data_block_builder)
|
|
|
|
: block_size_(block_size),
|
|
|
|
block_size_deviation_limit_(
|
|
|
|
((block_size * (100 - block_size_deviation)) + 99) / 100),
|
|
|
|
align_(align),
|
|
|
|
data_block_builder_(data_block_builder) {}
|
|
|
|
|
|
|
|
bool Update(const Slice& key, const Slice& value) override {
|
|
|
|
// it makes no sense to flush when the data block is empty
|
|
|
|
if (data_block_builder_.empty()) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
auto curr_size = data_block_builder_.CurrentSizeEstimate();
|
|
|
|
|
|
|
|
// Do flush if one of the below two conditions is true:
|
|
|
|
// 1) if the current estimated size already exceeds the block size,
|
|
|
|
// 2) block_size_deviation is set and the estimated size after appending
|
|
|
|
// the kv will exceed the block size and the current size is under the
|
|
|
|
// the deviation.
|
|
|
|
return curr_size >= block_size_ || BlockAlmostFull(key, value);
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
bool BlockAlmostFull(const Slice& key, const Slice& value) const {
|
|
|
|
if (block_size_deviation_limit_ == 0) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
const auto curr_size = data_block_builder_.CurrentSizeEstimate();
|
|
|
|
auto estimated_size_after =
|
|
|
|
data_block_builder_.EstimateSizeAfterKV(key, value);
|
|
|
|
|
|
|
|
if (align_) {
|
Improve / clean up meta block code & integrity (#9163)
Summary:
* Checksums are now checked on meta blocks unless specifically
suppressed or not applicable (e.g. plain table). (Was other way around.)
This means a number of cases that were not checking checksums now are,
including direct read TableProperties in Version::GetTableProperties
(fixed in meta_blocks ReadTableProperties), reading any block from
PersistentCache (fixed in BlockFetcher), read TableProperties in
SstFileDumper (ldb/sst_dump/BackupEngine) before table reader open,
maybe more.
* For that to work, I moved the global_seqno+TableProperties checksum
logic to the shared table/ code, because that is used by many utilies
such as SstFileDumper.
* Also for that to work, we have to know when we're dealing with a block
that has a checksum (trailer), so added that capability to Footer based
on magic number, and from there BlockFetcher.
* Knowledge of trailer presence has also fixed a problem where other
table formats were reading blocks including bytes for a non-existant
trailer--and awkwardly kind-of not using them, e.g. no shared code
checking checksums. (BlockFetcher compression type was populated
incorrectly.) Now we only read what is needed.
* Minimized code duplication and differing/incompatible/awkward
abstractions in meta_blocks.{cc,h} (e.g. SeekTo in metaindex block
without parsing block handle)
* Moved some meta block handling code from table_properties*.*
* Moved some code specific to block-based table from shared table/ code
to BlockBasedTable class. The checksum stuff means we can't completely
separate it, but things that don't need to be in shared table/ code
should not be.
* Use unique_ptr rather than raw ptr in more places. (Note: you can
std::move from unique_ptr to shared_ptr.)
Without enhancements to GetPropertiesOfAllTablesTest (see below),
net reduction of roughly 100 lines of code.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9163
Test Plan:
existing tests and
* Enhanced DBTablePropertiesTest.GetPropertiesOfAllTablesTest to verify that
checksums are now checked on direct read of table properties by TableCache
(new test would fail before this change)
* Also enhanced DBTablePropertiesTest.GetPropertiesOfAllTablesTest to test
putting table properties under old meta name
* Also generally enhanced that same test to actually test what it was
supposed to be testing already, by kicking things out of table cache when
we don't want them there.
Reviewed By: ajkr, mrambacher
Differential Revision: D32514757
Pulled By: pdillinger
fbshipit-source-id: 507964b9311d186ae8d1131182290cbd97a99fa9
3 years ago
|
|
|
estimated_size_after += BlockBasedTable::kBlockTrailerSize;
|
|
|
|
return estimated_size_after > block_size_;
|
|
|
|
}
|
|
|
|
|
|
|
|
return estimated_size_after > block_size_ &&
|
|
|
|
curr_size > block_size_deviation_limit_;
|
|
|
|
}
|
|
|
|
|
|
|
|
const uint64_t block_size_;
|
|
|
|
const uint64_t block_size_deviation_limit_;
|
|
|
|
const bool align_;
|
|
|
|
const BlockBuilder& data_block_builder_;
|
|
|
|
};
|
|
|
|
|
|
|
|
FlushBlockPolicy* FlushBlockBySizePolicyFactory::NewFlushBlockPolicy(
|
|
|
|
const BlockBasedTableOptions& table_options,
|
|
|
|
const BlockBuilder& data_block_builder) const {
|
|
|
|
return new FlushBlockBySizePolicy(
|
|
|
|
table_options.block_size, table_options.block_size_deviation,
|
|
|
|
table_options.block_align, data_block_builder);
|
|
|
|
}
|
|
|
|
|
|
|
|
FlushBlockPolicy* FlushBlockBySizePolicyFactory::NewFlushBlockPolicy(
|
|
|
|
const uint64_t size, const int deviation,
|
|
|
|
const BlockBuilder& data_block_builder) {
|
|
|
|
return new FlushBlockBySizePolicy(size, deviation, false, data_block_builder);
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
static int RegisterFlushBlockPolicyFactories(ObjectLibrary& library,
|
|
|
|
const std::string& /*arg*/) {
|
|
|
|
library.AddFactory<FlushBlockPolicyFactory>(
|
|
|
|
FlushBlockBySizePolicyFactory::kClassName(),
|
|
|
|
[](const std::string& /*uri*/,
|
|
|
|
std::unique_ptr<FlushBlockPolicyFactory>* guard,
|
|
|
|
std::string* /* errmsg */) {
|
|
|
|
guard->reset(new FlushBlockBySizePolicyFactory());
|
|
|
|
return guard->get();
|
|
|
|
});
|
|
|
|
library.AddFactory<FlushBlockPolicyFactory>(
|
|
|
|
FlushBlockEveryKeyPolicyFactory::kClassName(),
|
|
|
|
[](const std::string& /*uri*/,
|
|
|
|
std::unique_ptr<FlushBlockPolicyFactory>* guard,
|
|
|
|
std::string* /* errmsg */) {
|
|
|
|
guard->reset(new FlushBlockEveryKeyPolicyFactory());
|
|
|
|
return guard->get();
|
|
|
|
});
|
|
|
|
return 2;
|
|
|
|
}
|
|
|
|
#endif // ROCKSDB_LITE
|
|
|
|
|
|
|
|
static bool LoadFlushPolicyFactory(
|
|
|
|
const std::string& id, std::shared_ptr<FlushBlockPolicyFactory>* result) {
|
|
|
|
if (id.empty()) {
|
|
|
|
result->reset(new FlushBlockBySizePolicyFactory());
|
|
|
|
#ifdef ROCKSDB_LITE
|
|
|
|
} else if (id == FlushBlockBySizePolicyFactory::kClassName()) {
|
|
|
|
result->reset(new FlushBlockBySizePolicyFactory());
|
|
|
|
} else if (id == FlushBlockEveryKeyPolicyFactory::kClassName()) {
|
|
|
|
result->reset(new FlushBlockEveryKeyPolicyFactory());
|
|
|
|
#endif // ROCKSDB_LITE
|
|
|
|
} else {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
FlushBlockBySizePolicyFactory::FlushBlockBySizePolicyFactory()
|
|
|
|
: FlushBlockPolicyFactory() {}
|
|
|
|
|
|
|
|
Status FlushBlockPolicyFactory::CreateFromString(
|
|
|
|
const ConfigOptions& config_options, const std::string& value,
|
|
|
|
std::shared_ptr<FlushBlockPolicyFactory>* factory) {
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
static std::once_flag once;
|
|
|
|
std::call_once(once, [&]() {
|
|
|
|
RegisterFlushBlockPolicyFactories(*(ObjectLibrary::Default().get()), "");
|
|
|
|
});
|
|
|
|
#endif // ROCKSDB_LITE
|
|
|
|
return LoadSharedObject<FlushBlockPolicyFactory>(
|
|
|
|
config_options, value, LoadFlushPolicyFactory, factory);
|
|
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|