2016-02-09 23:12:00 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-15 23:03:42 +00:00
|
|
|
// 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).
|
2013-11-20 00:29:42 +00:00
|
|
|
|
|
|
|
#include "db/table_properties_collector.h"
|
|
|
|
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "util/coding.h"
|
2014-11-25 04:44:49 +00:00
|
|
|
#include "util/string_util.h"
|
2013-11-20 00:29:42 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2013-11-20 00:29:42 +00:00
|
|
|
|
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
2015-04-06 17:04:30 +00:00
|
|
|
namespace {
|
Support for SingleDelete()
Summary:
This patch fixes #7460559. It introduces SingleDelete as a new database
operation. This operation can be used to delete keys that were never
overwritten (no put following another put of the same key). If an overwritten
key is single deleted the behavior is undefined. Single deletion of a
non-existent key has no effect but multiple consecutive single deletions are
not allowed (see limitations).
In contrast to the conventional Delete() operation, the deletion entry is
removed along with the value when the two are lined up in a compaction. Note:
The semantics are similar to @igor's prototype that allowed to have this
behavior on the granularity of a column family (
https://reviews.facebook.net/D42093 ). This new patch, however, is more
aggressive when it comes to removing tombstones: It removes the SingleDelete
together with the value whenever there is no snapshot between them while the
older patch only did this when the sequence number of the deletion was older
than the earliest snapshot.
Most of the complex additions are in the Compaction Iterator, all other changes
should be relatively straightforward. The patch also includes basic support for
single deletions in db_stress and db_bench.
Limitations:
- Not compatible with cuckoo hash tables
- Single deletions cannot be used in combination with merges and normal
deletions on the same key (other keys are not affected by this)
- Consecutive single deletions are currently not allowed (and older version of
this patch supported this so it could be resurrected if needed)
Test Plan: make all check
Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor
Reviewed By: igor
Subscribers: maykov, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 18:42:56 +00:00
|
|
|
|
2016-05-19 21:24:48 +00:00
|
|
|
uint64_t GetUint64Property(const UserCollectedProperties& props,
|
2018-02-16 00:43:23 +00:00
|
|
|
const std::string& property_name,
|
2016-05-19 21:24:48 +00:00
|
|
|
bool* property_present) {
|
|
|
|
auto pos = props.find(property_name);
|
|
|
|
if (pos == props.end()) {
|
|
|
|
*property_present = false;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
Slice raw = pos->second;
|
|
|
|
uint64_t val = 0;
|
|
|
|
*property_present = true;
|
|
|
|
return GetVarint64(&raw, &val) ? val : 0;
|
|
|
|
}
|
|
|
|
|
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
2015-04-06 17:04:30 +00:00
|
|
|
} // namespace
|
2013-11-20 00:29:42 +00:00
|
|
|
|
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
2015-04-06 17:04:30 +00:00
|
|
|
Status UserKeyTablePropertiesCollector::InternalAdd(const Slice& key,
|
|
|
|
const Slice& value,
|
|
|
|
uint64_t file_size) {
|
2013-11-20 00:29:42 +00:00
|
|
|
ParsedInternalKey ikey;
|
2020-10-28 17:11:13 +00:00
|
|
|
Status s = ParseInternalKey(key, &ikey, false /* log_err_key */); // TODO
|
|
|
|
if (!s.ok()) {
|
2020-10-01 02:15:42 +00:00
|
|
|
return s;
|
2013-11-20 00:29:42 +00:00
|
|
|
}
|
|
|
|
|
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
2015-04-06 17:04:30 +00:00
|
|
|
return collector_->AddUserKey(ikey.user_key, value, GetEntryType(ikey.type),
|
|
|
|
ikey.sequence, file_size);
|
2013-11-20 00:29:42 +00:00
|
|
|
}
|
|
|
|
|
2019-03-18 19:07:35 +00:00
|
|
|
void UserKeyTablePropertiesCollector::BlockAdd(
|
Refactor to avoid confusing "raw block" (#10408)
Summary:
We have a lot of confusing code because of mixed, sometimes
completely opposite uses of of the term "raw block" or "raw contents",
sometimes within the same source file. For example, in `BlockBasedTableBuilder`,
`raw_block_contents` and `raw_size` generally referred to uncompressed block
contents and size, while `WriteRawBlock` referred to writing a block that
is already compressed if it is going to be. Meanwhile, in
`BlockBasedTable`, `raw_block_contents` either referred to a (maybe
compressed) block with trailer, or a maybe compressed block maybe
without trailer. (Note: left as follow-up work to use C++ typing to
better sort out the various kinds of BlockContents.)
This change primarily tries to apply some consistent terminology around
the kinds of block representations, avoiding the unclear "raw". (Any
meaning of "raw" assumes some bias toward the storage layer or toward
the logical data layer.) Preferred terminology:
* **Serialized block** - bytes that go into storage. For block-based table
(usually the case) this includes the block trailer. WART: block `size` may or
may not include the trailer; need to be clear about whether it does or not.
* **Maybe compressed block** - like a serialized block, but without the
trailer (or no promise of including a trailer). Must be accompanied by a
CompressionType.
* **Uncompressed block** - "payload" bytes that are either stored with no
compression, used as input to compression function, or result of
decompression function.
* **Parsed block** - an in-memory form of a block in block cache, as it is
used by the table reader. Different C++ types are used depending on the
block type (see block_like_traits.h).
Other refactorings:
* Misc corrections/improvements of internal API comments
* Remove a few misleading / unhelpful / redundant comments.
* Use move semantics in some places to simplify contracts
* Use better parameter names to indicate which parameters are used for
outputs
* Remove some extraneous `extern`
* Various clean-ups to `CacheDumperImpl` (mostly unnecessary code)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10408
Test Plan: existing tests
Reviewed By: akankshamahajan15
Differential Revision: D38172617
Pulled By: pdillinger
fbshipit-source-id: ccb99299f324ac5ca46996d34c5089621a4f260c
2022-09-22 18:25:32 +00:00
|
|
|
uint64_t block_uncomp_bytes, uint64_t block_compressed_bytes_fast,
|
2021-03-25 21:58:23 +00:00
|
|
|
uint64_t block_compressed_bytes_slow) {
|
Refactor to avoid confusing "raw block" (#10408)
Summary:
We have a lot of confusing code because of mixed, sometimes
completely opposite uses of of the term "raw block" or "raw contents",
sometimes within the same source file. For example, in `BlockBasedTableBuilder`,
`raw_block_contents` and `raw_size` generally referred to uncompressed block
contents and size, while `WriteRawBlock` referred to writing a block that
is already compressed if it is going to be. Meanwhile, in
`BlockBasedTable`, `raw_block_contents` either referred to a (maybe
compressed) block with trailer, or a maybe compressed block maybe
without trailer. (Note: left as follow-up work to use C++ typing to
better sort out the various kinds of BlockContents.)
This change primarily tries to apply some consistent terminology around
the kinds of block representations, avoiding the unclear "raw". (Any
meaning of "raw" assumes some bias toward the storage layer or toward
the logical data layer.) Preferred terminology:
* **Serialized block** - bytes that go into storage. For block-based table
(usually the case) this includes the block trailer. WART: block `size` may or
may not include the trailer; need to be clear about whether it does or not.
* **Maybe compressed block** - like a serialized block, but without the
trailer (or no promise of including a trailer). Must be accompanied by a
CompressionType.
* **Uncompressed block** - "payload" bytes that are either stored with no
compression, used as input to compression function, or result of
decompression function.
* **Parsed block** - an in-memory form of a block in block cache, as it is
used by the table reader. Different C++ types are used depending on the
block type (see block_like_traits.h).
Other refactorings:
* Misc corrections/improvements of internal API comments
* Remove a few misleading / unhelpful / redundant comments.
* Use move semantics in some places to simplify contracts
* Use better parameter names to indicate which parameters are used for
outputs
* Remove some extraneous `extern`
* Various clean-ups to `CacheDumperImpl` (mostly unnecessary code)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10408
Test Plan: existing tests
Reviewed By: akankshamahajan15
Differential Revision: D38172617
Pulled By: pdillinger
fbshipit-source-id: ccb99299f324ac5ca46996d34c5089621a4f260c
2022-09-22 18:25:32 +00:00
|
|
|
return collector_->BlockAdd(block_uncomp_bytes, block_compressed_bytes_fast,
|
2021-03-25 21:58:23 +00:00
|
|
|
block_compressed_bytes_slow);
|
2019-03-18 19:07:35 +00:00
|
|
|
}
|
|
|
|
|
2013-11-20 00:29:42 +00:00
|
|
|
Status UserKeyTablePropertiesCollector::Finish(
|
2013-12-05 21:09:13 +00:00
|
|
|
UserCollectedProperties* properties) {
|
2013-11-20 00:29:42 +00:00
|
|
|
return collector_->Finish(properties);
|
|
|
|
}
|
|
|
|
|
2013-12-05 21:09:13 +00:00
|
|
|
UserCollectedProperties
|
2013-11-20 00:29:42 +00:00
|
|
|
UserKeyTablePropertiesCollector::GetReadableProperties() const {
|
|
|
|
return collector_->GetReadableProperties();
|
|
|
|
}
|
|
|
|
|
|
|
|
uint64_t GetDeletedKeys(
|
2013-12-05 21:09:13 +00:00
|
|
|
const UserCollectedProperties& props) {
|
2016-05-19 21:24:48 +00:00
|
|
|
bool property_present_ignored;
|
2018-10-30 22:29:58 +00:00
|
|
|
return GetUint64Property(props, TablePropertiesNames::kDeletedKeys,
|
2016-05-19 21:24:48 +00:00
|
|
|
&property_present_ignored);
|
|
|
|
}
|
|
|
|
|
|
|
|
uint64_t GetMergeOperands(const UserCollectedProperties& props,
|
|
|
|
bool* property_present) {
|
|
|
|
return GetUint64Property(
|
2018-10-30 22:29:58 +00:00
|
|
|
props, TablePropertiesNames::kMergeOperands, property_present);
|
2013-11-20 00:29:42 +00:00
|
|
|
}
|
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|