rocksdb/db/builder.cc

402 lines
16 KiB
C++
Raw Normal View History

// 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include "db/builder.h"
#include <algorithm>
#include <deque>
#include <vector>
#include "db/blob/blob_file_builder.h"
#include "db/compaction/compaction_iterator.h"
#include "db/event_helpers.h"
#include "db/internal_stats.h"
#include "db/merge_helper.h"
#include "db/output_validator.h"
#include "db/range_del_aggregator.h"
#include "db/table_cache.h"
#include "db/version_edit.h"
#include "file/file_util.h"
#include "file/filename.h"
#include "file/read_write_util.h"
#include "file/writable_file_writer.h"
#include "monitoring/iostats_context_imp.h"
#include "monitoring/thread_status_util.h"
#include "options/options_helper.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/block_based/block_based_table_builder.h"
#include "table/format.h"
#include "table/internal_iterator.h"
#include "test_util/sync_point.h"
#include "util/stop_watch.h"
namespace ROCKSDB_NAMESPACE {
class TableFactory;
TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
WritableFileWriter* file) {
assert((tboptions.column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
tboptions.column_family_name.empty());
return tboptions.ioptions.table_factory->NewTableBuilder(tboptions, file);
}
Status BuildTable(
const std::string& dbname, VersionSet* versions,
const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
const FileOptions& file_options, TableCache* table_cache,
InternalIterator* iter,
std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
range_del_iters,
FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
std::vector<SequenceNumber> snapshots,
SequenceNumber earliest_write_conflict_snapshot,
SnapshotChecker* snapshot_checker, bool paranoid_file_checks,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
InternalStats* internal_stats, IOStatus* io_status,
const std::shared_ptr<IOTracer>& io_tracer,
BlobFileCreationReason blob_creation_reason, EventLogger* event_logger,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
int job_id, const Env::IOPriority io_priority,
TableProperties* table_properties, Env::WriteLifeTimeHint write_hint,
const std::string* full_history_ts_low,
Added memtable garbage statistics (#8411) Summary: **Summary**: 2 new statistics counters are added to RocksDB: `MEMTABLE_PAYLOAD_BYTES_AT_FLUSH` and `MEMTABLE_GARBAGE_BYTES_AT_FLUSH`. The former tracks how many raw bytes of useful data are present on the memtable at flush time, whereas the latter is tracks how many of these raw bytes are considered garbage, meaning that they ended up not being imported on the SSTables resulting from the flush operations. **Unit test**: run `make db_flush_test -j$(nproc); ./db_flush_test` to run the unit test. This executable includes 3 tests, that test support and correct stat calculations for workloads with inserts, deletes, and DeleteRanges. The parameters are set such that the workloads are performed on a single memtable, and a single SSTable is created as a result of the flush operation. The flush operation is manually called in the test file. The tests verify that the values of these 2 statistics counters introduced in this PR can be exactly predicted, showing that we have a full understanding of the underlying operations. **Performance testing**: `./db_bench -statistics -benchmarks=fillrandom -num=10000000` repeated 10 times. Timing done using "date" function in a bash script. _Results_: Original Rocksdb fork: mean 66.6 sec, std 1.18 sec. This feature branch: mean 67.4 sec, std 1.35 sec. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8411 Reviewed By: akankshamahajan15 Differential Revision: D29150629 Pulled By: bjlemaire fbshipit-source-id: 7b3c2e86d50c6aa34fa50fd134282eacb543a5b1
2021-06-18 13:56:43 +02:00
BlobFileCompletionCallback* blob_callback, uint64_t* num_input_entries,
uint64_t* memtable_payload_bytes, uint64_t* memtable_garbage_bytes) {
assert((tboptions.column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
tboptions.column_family_name.empty());
auto& mutable_cf_options = tboptions.moptions;
auto& ioptions = tboptions.ioptions;
// Reports the IOStats for flush for every following bytes.
const size_t kReportFlushIOStatsEvery = 1048576;
OutputValidator output_validator(
tboptions.internal_comparator,
/*enable_order_check=*/
mutable_cf_options.check_flush_compaction_key_order,
/*enable_hash=*/paranoid_file_checks);
Status s;
meta->fd.file_size = 0;
iter->SeekToFirst();
std::unique_ptr<CompactionRangeDelAggregator> range_del_agg(
new CompactionRangeDelAggregator(&tboptions.internal_comparator,
snapshots));
uint64_t num_unfragmented_tombstones = 0;
Added memtable garbage statistics (#8411) Summary: **Summary**: 2 new statistics counters are added to RocksDB: `MEMTABLE_PAYLOAD_BYTES_AT_FLUSH` and `MEMTABLE_GARBAGE_BYTES_AT_FLUSH`. The former tracks how many raw bytes of useful data are present on the memtable at flush time, whereas the latter is tracks how many of these raw bytes are considered garbage, meaning that they ended up not being imported on the SSTables resulting from the flush operations. **Unit test**: run `make db_flush_test -j$(nproc); ./db_flush_test` to run the unit test. This executable includes 3 tests, that test support and correct stat calculations for workloads with inserts, deletes, and DeleteRanges. The parameters are set such that the workloads are performed on a single memtable, and a single SSTable is created as a result of the flush operation. The flush operation is manually called in the test file. The tests verify that the values of these 2 statistics counters introduced in this PR can be exactly predicted, showing that we have a full understanding of the underlying operations. **Performance testing**: `./db_bench -statistics -benchmarks=fillrandom -num=10000000` repeated 10 times. Timing done using "date" function in a bash script. _Results_: Original Rocksdb fork: mean 66.6 sec, std 1.18 sec. This feature branch: mean 67.4 sec, std 1.35 sec. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8411 Reviewed By: akankshamahajan15 Differential Revision: D29150629 Pulled By: bjlemaire fbshipit-source-id: 7b3c2e86d50c6aa34fa50fd134282eacb543a5b1
2021-06-18 13:56:43 +02:00
uint64_t total_tombstone_payload_bytes = 0;
for (auto& range_del_iter : range_del_iters) {
num_unfragmented_tombstones +=
range_del_iter->num_unfragmented_tombstones();
Added memtable garbage statistics (#8411) Summary: **Summary**: 2 new statistics counters are added to RocksDB: `MEMTABLE_PAYLOAD_BYTES_AT_FLUSH` and `MEMTABLE_GARBAGE_BYTES_AT_FLUSH`. The former tracks how many raw bytes of useful data are present on the memtable at flush time, whereas the latter is tracks how many of these raw bytes are considered garbage, meaning that they ended up not being imported on the SSTables resulting from the flush operations. **Unit test**: run `make db_flush_test -j$(nproc); ./db_flush_test` to run the unit test. This executable includes 3 tests, that test support and correct stat calculations for workloads with inserts, deletes, and DeleteRanges. The parameters are set such that the workloads are performed on a single memtable, and a single SSTable is created as a result of the flush operation. The flush operation is manually called in the test file. The tests verify that the values of these 2 statistics counters introduced in this PR can be exactly predicted, showing that we have a full understanding of the underlying operations. **Performance testing**: `./db_bench -statistics -benchmarks=fillrandom -num=10000000` repeated 10 times. Timing done using "date" function in a bash script. _Results_: Original Rocksdb fork: mean 66.6 sec, std 1.18 sec. This feature branch: mean 67.4 sec, std 1.35 sec. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8411 Reviewed By: akankshamahajan15 Differential Revision: D29150629 Pulled By: bjlemaire fbshipit-source-id: 7b3c2e86d50c6aa34fa50fd134282eacb543a5b1
2021-06-18 13:56:43 +02:00
total_tombstone_payload_bytes +=
range_del_iter->total_tombstone_payload_bytes();
range_del_agg->AddTombstones(std::move(range_del_iter));
}
std::string fname = TableFileName(ioptions.cf_paths, meta->fd.GetNumber(),
meta->fd.GetPathId());
std::vector<std::string> blob_file_paths;
std::string file_checksum = kUnknownFileChecksum;
std::string file_checksum_func_name = kUnknownFileChecksumFuncName;
#ifndef ROCKSDB_LITE
EventHelpers::NotifyTableFileCreationStarted(ioptions.listeners, dbname,
tboptions.column_family_name,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
fname, job_id, tboptions.reason);
#endif // !ROCKSDB_LITE
Env* env = db_options.env;
assert(env);
FileSystem* fs = db_options.fs.get();
assert(fs);
TableProperties tp;
if (iter->Valid() || !range_del_agg->IsEmpty()) {
std::unique_ptr<CompactionFilter> compaction_filter;
if (ioptions.compaction_filter_factory != nullptr &&
ioptions.compaction_filter_factory->ShouldFilterTableFileCreation(
tboptions.reason)) {
CompactionFilter::Context context;
context.is_full_compaction = false;
context.is_manual_compaction = false;
context.column_family_id = tboptions.column_family_id;
context.reason = tboptions.reason;
compaction_filter =
ioptions.compaction_filter_factory->CreateCompactionFilter(context);
if (compaction_filter != nullptr &&
!compaction_filter->IgnoreSnapshots()) {
s.PermitUncheckedError();
return Status::NotSupported(
"CompactionFilter::IgnoreSnapshots() = false is not supported "
"anymore.");
}
}
TableBuilder* builder;
std::unique_ptr<WritableFileWriter> file_writer;
{
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
std::unique_ptr<FSWritableFile> file;
#ifndef NDEBUG
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 23:47:08 +01:00
bool use_direct_writes = file_options.use_direct_writes;
TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
#endif // !NDEBUG
IOStatus io_s = NewWritableFile(fs, fname, &file, file_options);
assert(s.ok());
s = io_s;
if (io_status->ok()) {
*io_status = io_s;
}
if (!s.ok()) {
EventHelpers::LogAndNotifyTableFileCreationFinished(
event_logger, ioptions.listeners, dbname,
tboptions.column_family_name, fname, job_id, meta->fd,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
kInvalidBlobFileNumber, tp, tboptions.reason, s, file_checksum,
file_checksum_func_name);
return s;
}
FileTypeSet tmp_set = ioptions.checksum_handoff_file_types;
file->SetIOPriority(io_priority);
file->SetWriteLifeTimeHint(write_hint);
file_writer.reset(new WritableFileWriter(
std::move(file), fname, file_options, ioptions.clock, io_tracer,
ioptions.stats, ioptions.listeners,
ioptions.file_checksum_gen_factory.get(),
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 09:46:33 +02:00
tmp_set.Contains(FileType::kTableFile), false));
builder = NewTableBuilder(tboptions, file_writer.get());
}
MergeHelper merge(
env, tboptions.internal_comparator.user_comparator(),
ioptions.merge_operator.get(), compaction_filter.get(), ioptions.logger,
true /* internal key corruption is not ok */,
snapshots.empty() ? 0 : snapshots.back(), snapshot_checker);
std::unique_ptr<BlobFileBuilder> blob_file_builder(
(mutable_cf_options.enable_blob_files && blob_file_additions)
? new BlobFileBuilder(
versions, fs, &ioptions, &mutable_cf_options, &file_options,
job_id, tboptions.column_family_id,
tboptions.column_family_name, io_priority, write_hint,
io_tracer, blob_callback, blob_creation_reason,
&blob_file_paths, blob_file_additions)
: nullptr);
Compaction Support for Range Deletion Summary: This diff introduces RangeDelAggregator, which takes ownership of iterators provided to it via AddTombstones(). The tombstones are organized in a two-level map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data copy by holding Slices returned by the iterator, which remain valid thanks to pinning. For compaction, we create a hierarchical range tombstone iterator with structure matching the iterator over compaction input data. An aggregator based on that iterator is used by CompactionIterator to determine which keys are covered by range tombstones. In case of merge operand, the same aggregator is used by MergeHelper. Upon finishing each file in the compaction, relevant range tombstones are added to the output file's range tombstone metablock and file boundaries are updated accordingly. To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete() considers tombstones in the key's snapshot stripe. When this function is used outside of compaction, it also checks newer stripes, which can contain covering tombstones. Currently the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges within a stripe such that binary search can be used. RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range to a new table's range tombstone meta-block. Since range tombstones may fall in the gap between files, we may need to extend some files' key-ranges. The strategy is (1) first file extends as far left as possible and other files do not extend left, (2) all files extend right until either the start of the next file or the end of the last range tombstone in the gap, whichever comes first. One other notable change is adding release/move semantics to ScopedArenaIterator such that it can be used to transfer ownership of an arena-allocated iterator, similar to how unique_ptr is used for malloc'd data. Depends on D61473 Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927 Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark Reviewed By: lightmark Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D62205
2016-10-18 21:04:56 +02:00
CompactionIterator c_iter(
iter, tboptions.internal_comparator.user_comparator(), &merge,
kMaxSequenceNumber, &snapshots, earliest_write_conflict_snapshot,
snapshot_checker, env, ShouldReportDetailedTime(env, ioptions.stats),
true /* internal key corruption is not ok */, range_del_agg.get(),
blob_file_builder.get(), ioptions.allow_data_in_errors,
/*compaction=*/nullptr, compaction_filter.get(),
/*shutting_down=*/nullptr,
/*preserve_deletes_seqnum=*/0, /*manual_compaction_paused=*/nullptr,
/*manual_compaction_canceled=*/nullptr, db_options.info_log,
full_history_ts_low);
c_iter.SeekToFirst();
for (; c_iter.Valid(); c_iter.Next()) {
const Slice& key = c_iter.key();
const Slice& value = c_iter.value();
const ParsedInternalKey& ikey = c_iter.ikey();
// Generate a rolling 64-bit hash of the key and values
Memtable "MemPurge" prototype (#8454) Summary: Implement an experimental feature called "MemPurge", which consists in purging "garbage" bytes out of a memtable and reuse the memtable struct instead of making it immutable and eventually flushing its content to storage. The prototype is by default deactivated and is not intended for use. It is intended for correctness and validation testing. At the moment, the "MemPurge" feature can be switched on by using the `options.experimental_allow_mempurge` flag. For this early stage, when the allow_mempurge flag is set to `true`, all the flush operations will be rerouted to perform a MemPurge. This is a temporary design decision that will give us the time to explore meaningful heuristics to use MemPurge at the right time for relevant workloads . Moreover, the current MemPurge operation only supports `Puts`, `Deletes`, `DeleteRange` operations, and handles `Iterators` as well as `CompactionFilter`s that are invoked at flush time . Three unit tests are added to `db_flush_test.cc` to test if MemPurge works correctly (and checks that the previously mentioned operations are fully supported thoroughly tested). One noticeable design decision is the timing of the MemPurge operation in the memtable workflow: for this prototype, the mempurge happens when the memtable is switched (and usually made immutable). This is an inefficient process because it implies that the entirety of the MemPurge operation happens while holding the db_mutex. Future commits will make the MemPurge operation a background task (akin to the regular flush operation) and aim at drastically enhancing the performance of this operation. The MemPurge is also not fully "WAL-compatible" yet, but when the WAL is full, or when the regular MemPurge operation fails (or when the purged memtable still needs to be flushed), a regular flush operation takes place. Later commits will also correct these behaviors. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8454 Reviewed By: anand1976 Differential Revision: D29433971 Pulled By: bjlemaire fbshipit-source-id: 6af48213554e35048a7e03816955100a80a26dc5
2021-07-02 14:22:03 +02:00
// Note :
// Here "key" integrates 'sequence_number'+'kType'+'user key'.
s = output_validator.Add(key, value);
if (!s.ok()) {
break;
}
builder->Add(key, value);
meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
// TODO(noetzli): Update stats after flush, too.
if (io_priority == Env::IO_HIGH &&
IOSTATS(bytes_written) >= kReportFlushIOStatsEvery) {
ThreadStatusUtil::SetThreadOperationProperty(
ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
}
}
if (!s.ok()) {
c_iter.status().PermitUncheckedError();
} else if (!c_iter.status().ok()) {
s = c_iter.status();
}
if (s.ok()) {
auto range_del_it = range_del_agg->NewIterator();
for (range_del_it->SeekToFirst(); range_del_it->Valid();
range_del_it->Next()) {
auto tombstone = range_del_it->Tombstone();
auto kv = tombstone.Serialize();
builder->Add(kv.first.Encode(), kv.second);
meta->UpdateBoundariesForRange(kv.first, tombstone.SerializeEndKey(),
tombstone.seq_,
tboptions.internal_comparator);
}
}
TEST_SYNC_POINT("BuildTable:BeforeFinishBuildTable");
const bool empty = builder->IsEmpty();
if (num_input_entries != nullptr) {
*num_input_entries =
c_iter.num_input_entry_scanned() + num_unfragmented_tombstones;
}
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 20:42:56 +02:00
if (!s.ok() || empty) {
builder->Abandon();
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 20:42:56 +02:00
} else {
s = builder->Finish();
}
if (io_status->ok()) {
*io_status = builder->io_status();
}
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 20:42:56 +02:00
if (s.ok() && !empty) {
uint64_t file_size = builder->FileSize();
meta->fd.file_size = file_size;
meta->marked_for_compaction = builder->NeedCompact();
assert(meta->fd.GetFileSize() > 0);
tp = builder->GetTableProperties(); // refresh now that builder is finished
Added memtable garbage statistics (#8411) Summary: **Summary**: 2 new statistics counters are added to RocksDB: `MEMTABLE_PAYLOAD_BYTES_AT_FLUSH` and `MEMTABLE_GARBAGE_BYTES_AT_FLUSH`. The former tracks how many raw bytes of useful data are present on the memtable at flush time, whereas the latter is tracks how many of these raw bytes are considered garbage, meaning that they ended up not being imported on the SSTables resulting from the flush operations. **Unit test**: run `make db_flush_test -j$(nproc); ./db_flush_test` to run the unit test. This executable includes 3 tests, that test support and correct stat calculations for workloads with inserts, deletes, and DeleteRanges. The parameters are set such that the workloads are performed on a single memtable, and a single SSTable is created as a result of the flush operation. The flush operation is manually called in the test file. The tests verify that the values of these 2 statistics counters introduced in this PR can be exactly predicted, showing that we have a full understanding of the underlying operations. **Performance testing**: `./db_bench -statistics -benchmarks=fillrandom -num=10000000` repeated 10 times. Timing done using "date" function in a bash script. _Results_: Original Rocksdb fork: mean 66.6 sec, std 1.18 sec. This feature branch: mean 67.4 sec, std 1.35 sec. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8411 Reviewed By: akankshamahajan15 Differential Revision: D29150629 Pulled By: bjlemaire fbshipit-source-id: 7b3c2e86d50c6aa34fa50fd134282eacb543a5b1
2021-06-18 13:56:43 +02:00
if (memtable_payload_bytes != nullptr &&
memtable_garbage_bytes != nullptr) {
const CompactionIterationStats& ci_stats = c_iter.iter_stats();
uint64_t total_payload_bytes = ci_stats.total_input_raw_key_bytes +
ci_stats.total_input_raw_value_bytes +
total_tombstone_payload_bytes;
uint64_t total_payload_bytes_written =
(tp.raw_key_size + tp.raw_value_size);
// Prevent underflow, which may still happen at this point
// since we only support inserts, deletes, and deleteRanges.
if (total_payload_bytes_written <= total_payload_bytes) {
*memtable_payload_bytes = total_payload_bytes;
*memtable_garbage_bytes =
total_payload_bytes - total_payload_bytes_written;
} else {
*memtable_payload_bytes = 0;
*memtable_garbage_bytes = 0;
}
}
if (table_properties) {
*table_properties = tp;
}
}
delete builder;
// Finish and check for file errors
TEST_SYNC_POINT("BuildTable:BeforeSyncTable");
if (s.ok() && !empty) {
StopWatch sw(ioptions.clock, ioptions.stats, TABLE_SYNC_MICROS);
*io_status = file_writer->Sync(ioptions.use_fsync);
}
TEST_SYNC_POINT("BuildTable:BeforeCloseTableFile");
if (s.ok() && io_status->ok() && !empty) {
*io_status = file_writer->Close();
}
if (s.ok() && io_status->ok() && !empty) {
// Add the checksum information to file metadata.
meta->file_checksum = file_writer->GetFileChecksum();
meta->file_checksum_func_name = file_writer->GetFileChecksumFuncName();
file_checksum = meta->file_checksum;
file_checksum_func_name = meta->file_checksum_func_name;
}
if (s.ok()) {
s = *io_status;
}
if (blob_file_builder) {
if (s.ok()) {
s = blob_file_builder->Finish();
} else {
blob_file_builder->Abandon(s);
}
blob_file_builder.reset();
}
// TODO Also check the IO status when create the Iterator.
TEST_SYNC_POINT("BuildTable:BeforeOutputValidation");
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 20:42:56 +02:00
if (s.ok() && !empty) {
// Verify that the table is usable
// We set for_compaction to false and don't OptimizeForCompactionTableRead
// here because this is a special case after we finish the table building
// No matter whether use_direct_io_for_flush_and_compaction is true,
// we will regrad this verification as user reads since the goal is
// to cache it here for further user reads
ReadOptions read_options;
std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
read_options, file_options, tboptions.internal_comparator, *meta,
Fast path for detecting unchanged prefix_extractor (#9407) Summary: Fixes a major performance regression in 6.26, where extra CPU is spent in SliceTransform::AsString when reads involve a prefix_extractor (Get, MultiGet, Seek). Common case performance is now better than 6.25. This change creates a "fast path" for verifying that the current prefix extractor is unchanged and compatible with what was used to generate a table file. This fast path detects the common case by pointer comparison on the current prefix_extractor and a "known good" prefix extractor (if applicable) that is saved at the time the table reader is opened. The "known good" prefix extractor is saved as another shared_ptr copy (in an existing field, however) to ensure the pointer is not recycled. When the prefix_extractor has changed to a different instance but same compatible configuration (rare, odd), performance is still a regression compared to 6.25, but this is likely acceptable because of the oddity of such a case. The performance of incompatible prefix_extractor is essentially unchanged. Also fixed a minor case (ForwardIterator) where a prefix_extractor could be used via a raw pointer after being freed as a shared_ptr, if replaced via SetOptions. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9407 Test Plan: ## Performance Populate DB with `TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=10000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=12` Running head-to-head comparisons simultaneously with `TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -use_existing_db -readonly -benchmarks=seekrandom -num=10000000 -duration=20 -disable_wal=1 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -prefix_size=12` Below each is compared by ops/sec vs. baseline which is version 6.25 (multiple baseline runs because of variable machine load) v6.26: 4833 vs. 6698 (<- major regression!) v6.27: 4737 vs. 6397 (still) New: 6704 vs. 6461 (better than baseline in common case) Disabled fastpath: 4843 vs. 6389 (e.g. if prefix extractor instance changes but is still compatible) Changed prefix size (no usable filter) in new: 787 vs. 5927 Changed prefix size (no usable filter) in new & baseline: 773 vs. 784 Reviewed By: mrambacher Differential Revision: D33677812 Pulled By: pdillinger fbshipit-source-id: 571d9711c461fb97f957378a061b7e7dbc4d6a76
2022-01-21 20:36:36 +01:00
nullptr /* range_del_agg */, mutable_cf_options.prefix_extractor,
nullptr,
(internal_stats == nullptr) ? nullptr
: internal_stats->GetFileReadHist(0),
TableReaderCaller::kFlush, /*arena=*/nullptr,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
/*skip_filter=*/false, tboptions.level_at_creation,
MaxFileSizeForL0MetaPin(mutable_cf_options),
/*smallest_compaction_key=*/nullptr,
Properly report IO errors when IndexType::kBinarySearchWithFirstKey is used (#6621) Summary: Context: Index type `kBinarySearchWithFirstKey` added the ability for sst file iterator to sometimes report a key from index without reading the corresponding data block. This is useful when sst blocks are cut at some meaningful boundaries (e.g. one block per key prefix), and many seeks land between blocks (e.g. for each prefix, the ranges of keys in different sst files are nearly disjoint, so a typical seek needs to read a data block from only one file even if all files have the prefix). But this added a new error condition, which rocksdb code was really not equipped to deal with: `InternalIterator::value()` may fail with an IO error or Status::Incomplete, but it's just a method returning a Slice, with no way to report error instead. Before this PR, this type of error wasn't handled at all (an empty slice was returned), and kBinarySearchWithFirstKey implementation was considered a prototype. Now that we (LogDevice) have experimented with kBinarySearchWithFirstKey for a while and confirmed that it's really useful, this PR is adding the missing error handling. It's a pretty inconvenient situation implementation-wise. The error needs to be reported from InternalIterator when trying to access value. But there are ~700 call sites of `InternalIterator::value()`, most of which either can't hit the error condition (because the iterator is reading from memtable or from index or something) or wouldn't benefit from the deferred loading of the value (e.g. compaction iterator that reads all values anyway). Adding error handling to all these call sites would needlessly bloat the code. So instead I made the deferred value loading optional: only the call sites that may use deferred loading have to call the new method `PrepareValue()` before calling `value()`. The feature is enabled with a new bool argument `allow_unprepared_value` to a bunch of methods that create iterators (it wouldn't make sense to put it in ReadOptions because it's completely internal to iterators, with virtually no user-visible effect). Lmk if you have better ideas. Note that the deferred value loading only happens for *internal* iterators. The user-visible iterator (DBIter) always prepares the value before returning from Seek/Next/etc. We could go further and add an API to defer that value loading too, but that's most likely not useful for LogDevice, so it doesn't seem worth the complexity for now. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6621 Test Plan: make -j5 check . Will also deploy to some logdevice test clusters and look at stats. Reviewed By: siying Differential Revision: D20786930 Pulled By: al13n321 fbshipit-source-id: 6da77d918bad3780522e918f17f4d5513d3e99ee
2020-04-16 02:37:23 +02:00
/*largest_compaction_key*/ nullptr,
/*allow_unprepared_value*/ false));
s = it->status();
if (s.ok() && paranoid_file_checks) {
OutputValidator file_validator(tboptions.internal_comparator,
/*enable_order_check=*/true,
/*enable_hash=*/true);
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 20:42:56 +02:00
for (it->SeekToFirst(); it->Valid(); it->Next()) {
// Generate a rolling 64-bit hash of the key and values
file_validator.Add(it->key(), it->value()).PermitUncheckedError();
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 20:42:56 +02:00
}
s = it->status();
if (s.ok() && !output_validator.CompareValidator(file_validator)) {
s = Status::Corruption("Paranoid checksums do not match");
}
}
}
}
// Check for input iterator errors
if (!iter->status().ok()) {
s = iter->status();
}
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 20:42:56 +02:00
if (!s.ok() || meta->fd.GetFileSize() == 0) {
TEST_SYNC_POINT("BuildTable:BeforeDeleteFile");
constexpr IODebugContext* dbg = nullptr;
Status ignored = fs->DeleteFile(fname, IOOptions(), dbg);
ignored.PermitUncheckedError();
assert(blob_file_additions || blob_file_paths.empty());
if (blob_file_additions) {
for (const std::string& blob_file_path : blob_file_paths) {
ignored = DeleteDBFile(&db_options, blob_file_path, dbname,
/*force_bg=*/false, /*force_fg=*/false);
ignored.PermitUncheckedError();
TEST_SYNC_POINT("BuildTable::AfterDeleteFile");
}
}
}
Status status_for_listener = s;
if (meta->fd.GetFileSize() == 0) {
fname = "(nil)";
if (s.ok()) {
status_for_listener = Status::Aborted("Empty SST file not kept");
}
}
// Output to event logger and fire events.
EventHelpers::LogAndNotifyTableFileCreationFinished(
event_logger, ioptions.listeners, dbname, tboptions.column_family_name,
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 22:49:24 +02:00
fname, job_id, meta->fd, meta->oldest_blob_file_number, tp,
tboptions.reason, status_for_listener, file_checksum,
file_checksum_func_name);
return s;
}
} // namespace ROCKSDB_NAMESPACE