|
|
|
// 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/compaction/compaction_picker_level.h"
|
|
|
|
|
|
|
|
#include <string>
|
|
|
|
#include <utility>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "db/version_edit.h"
|
|
|
|
#include "logging/log_buffer.h"
|
|
|
|
#include "test_util/sync_point.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
bool LevelCompactionPicker::NeedsCompaction(
|
|
|
|
const VersionStorageInfo* vstorage) const {
|
|
|
|
if (!vstorage->ExpiredTtlFiles().empty()) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
if (!vstorage->FilesMarkedForPeriodicCompaction().empty()) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
if (!vstorage->FilesMarkedForCompaction().empty()) {
|
|
|
|
return true;
|
|
|
|
}
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
if (!vstorage->FilesMarkedForForcedBlobGC().empty()) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
|
|
|
|
if (vstorage->CompactionScore(i) >= 1) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
// A class to build a leveled compaction step-by-step.
|
|
|
|
class LevelCompactionBuilder {
|
|
|
|
public:
|
|
|
|
LevelCompactionBuilder(const std::string& cf_name,
|
|
|
|
VersionStorageInfo* vstorage,
|
|
|
|
CompactionPicker* compaction_picker,
|
|
|
|
LogBuffer* log_buffer,
|
|
|
|
const MutableCFOptions& mutable_cf_options,
|
|
|
|
const ImmutableOptions& ioptions,
|
|
|
|
const MutableDBOptions& mutable_db_options)
|
|
|
|
: cf_name_(cf_name),
|
|
|
|
vstorage_(vstorage),
|
|
|
|
compaction_picker_(compaction_picker),
|
|
|
|
log_buffer_(log_buffer),
|
|
|
|
mutable_cf_options_(mutable_cf_options),
|
|
|
|
ioptions_(ioptions),
|
|
|
|
mutable_db_options_(mutable_db_options) {}
|
|
|
|
|
|
|
|
// Pick and return a compaction.
|
|
|
|
Compaction* PickCompaction();
|
|
|
|
|
|
|
|
// Pick the initial files to compact to the next level. (or together
|
|
|
|
// in Intra-L0 compactions)
|
|
|
|
void SetupInitialFiles();
|
|
|
|
|
|
|
|
// If the initial files are from L0 level, pick other L0
|
|
|
|
// files if needed.
|
|
|
|
bool SetupOtherL0FilesIfNeeded();
|
|
|
|
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
// Compaction with round-robin compaction priority allows more files to be
|
|
|
|
// picked to form a large compaction
|
|
|
|
void SetupOtherFilesWithRoundRobinExpansion();
|
|
|
|
// Based on initial files, setup other files need to be compacted
|
|
|
|
// in this compaction, accordingly.
|
|
|
|
bool SetupOtherInputsIfNeeded();
|
|
|
|
|
|
|
|
Compaction* GetCompaction();
|
|
|
|
|
|
|
|
// For the specfied level, pick a file that we want to compact.
|
|
|
|
// Returns false if there is no file to compact.
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
// If it returns true, inputs->files.size() will be exactly one for
|
|
|
|
// all compaction priorities except round-robin. For round-robin,
|
|
|
|
// multiple consecutive files may be put into inputs->files.
|
|
|
|
// If level is 0 and there is already a compaction on that level, this
|
|
|
|
// function will return false.
|
|
|
|
bool PickFileToCompact();
|
|
|
|
|
|
|
|
// Return true if a L0 trivial move is picked up.
|
|
|
|
bool TryPickL0TrivialMove();
|
|
|
|
|
|
|
|
// For L0->L0, picks the longest span of files that aren't currently
|
|
|
|
// undergoing compaction for which work-per-deleted-file decreases. The span
|
|
|
|
// always starts from the newest L0 file.
|
|
|
|
//
|
|
|
|
// Intra-L0 compaction is independent of all other files, so it can be
|
|
|
|
// performed even when L0->base_level compactions are blocked.
|
|
|
|
//
|
|
|
|
// Returns true if `inputs` is populated with a span of files to be compacted;
|
|
|
|
// otherwise, returns false.
|
|
|
|
bool PickIntraL0Compaction();
|
|
|
|
|
|
|
|
// Return true if TrivialMove is extended. `start_index` is the index of
|
|
|
|
// the intiial file picked, which should already be in `start_level_inputs_`.
|
|
|
|
bool TryExtendNonL0TrivialMove(int start_index);
|
|
|
|
|
|
|
|
// Picks a file from level_files to compact.
|
|
|
|
// level_files is a vector of (level, file metadata) in ascending order of
|
|
|
|
// level. If compact_to_next_level is true, compact the file to the next
|
|
|
|
// level, otherwise, compact to the same level as the input file.
|
|
|
|
void PickFileToCompact(
|
|
|
|
const autovector<std::pair<int, FileMetaData*>>& level_files,
|
|
|
|
bool compact_to_next_level);
|
|
|
|
|
|
|
|
const std::string& cf_name_;
|
|
|
|
VersionStorageInfo* vstorage_;
|
|
|
|
CompactionPicker* compaction_picker_;
|
|
|
|
LogBuffer* log_buffer_;
|
|
|
|
int start_level_ = -1;
|
|
|
|
int output_level_ = -1;
|
|
|
|
int parent_index_ = -1;
|
|
|
|
int base_index_ = -1;
|
|
|
|
double start_level_score_ = 0;
|
|
|
|
bool is_manual_ = false;
|
|
|
|
bool is_l0_trivial_move_ = false;
|
|
|
|
CompactionInputFiles start_level_inputs_;
|
|
|
|
std::vector<CompactionInputFiles> compaction_inputs_;
|
|
|
|
CompactionInputFiles output_level_inputs_;
|
|
|
|
std::vector<FileMetaData*> grandparents_;
|
|
|
|
CompactionReason compaction_reason_ = CompactionReason::kUnknown;
|
|
|
|
|
|
|
|
const MutableCFOptions& mutable_cf_options_;
|
|
|
|
const ImmutableOptions& ioptions_;
|
|
|
|
const MutableDBOptions& mutable_db_options_;
|
|
|
|
// Pick a path ID to place a newly generated file, with its level
|
|
|
|
static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
|
|
|
|
const MutableCFOptions& mutable_cf_options,
|
|
|
|
int level);
|
|
|
|
|
|
|
|
static const int kMinFilesForIntraL0Compaction = 4;
|
|
|
|
};
|
|
|
|
|
|
|
|
void LevelCompactionBuilder::PickFileToCompact(
|
|
|
|
const autovector<std::pair<int, FileMetaData*>>& level_files,
|
|
|
|
bool compact_to_next_level) {
|
|
|
|
for (auto& level_file : level_files) {
|
|
|
|
// If it's being compacted it has nothing to do here.
|
|
|
|
// If this assert() fails that means that some function marked some
|
|
|
|
// files as being_compacted, but didn't call ComputeCompactionScore()
|
|
|
|
assert(!level_file.second->being_compacted);
|
|
|
|
start_level_ = level_file.first;
|
|
|
|
if ((compact_to_next_level &&
|
|
|
|
start_level_ == vstorage_->num_non_empty_levels() - 1) ||
|
|
|
|
(start_level_ == 0 &&
|
|
|
|
!compaction_picker_->level0_compactions_in_progress()->empty())) {
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (compact_to_next_level) {
|
|
|
|
output_level_ =
|
|
|
|
(start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
|
|
|
|
} else {
|
|
|
|
output_level_ = start_level_;
|
|
|
|
}
|
|
|
|
start_level_inputs_.files = {level_file.second};
|
|
|
|
start_level_inputs_.level = start_level_;
|
|
|
|
if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
|
|
|
|
&start_level_inputs_)) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
start_level_inputs_.files.clear();
|
|
|
|
}
|
|
|
|
|
|
|
|
void LevelCompactionBuilder::SetupInitialFiles() {
|
|
|
|
// Find the compactions by size on all levels.
|
|
|
|
bool skipped_l0_to_base = false;
|
|
|
|
for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
|
|
|
|
start_level_score_ = vstorage_->CompactionScore(i);
|
|
|
|
start_level_ = vstorage_->CompactionScoreLevel(i);
|
|
|
|
assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
|
|
|
|
if (start_level_score_ >= 1) {
|
|
|
|
if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
|
|
|
|
// If L0->base_level compaction is pending, don't schedule further
|
|
|
|
// compaction from base level. Otherwise L0->base_level compaction
|
|
|
|
// may starve.
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
output_level_ =
|
|
|
|
(start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
|
Sort L0 files by newly introduced epoch_num (#10922)
Summary:
**Context:**
Sorting L0 files by `largest_seqno` has at least two inconvenience:
- File ingestion and compaction involving ingested files can create files of overlapping seqno range with the existing files. `force_consistency_check=true` will catch such overlap seqno range even those harmless overlap.
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n")
- insert k1@1 to memtable m1
- ingest file s1 with k2@2, ingest file s2 with k3@3
- insert k4@4 to m1
- compact files s1, s2 and result in new file s3 of seqno range [2, 3]
- flush m1 and result in new file s4 of seqno range [1, 4]. And `force_consistency_check=true` will think s4 and s3 has file reordering corruption that might cause retuning an old value of k1
- However such caught corruption is a false positive since s1, s2 will not have overlapped keys with k1 or whatever inserted into m1 before ingest file s1 by the requirement of file ingestion (otherwise the m1 will be flushed first before any of the file ingestion completes). Therefore there in fact isn't any file reordering corruption.
- Single delete can decrease a file's largest seqno and ordering by `largest_seqno` can introduce a wrong ordering hence file reordering corruption
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n", Credit to ajkr for this example)
- an existing SST s1 contains only k1@1
- insert k1@2 to memtable m1
- ingest file s2 with k3@3, ingest file s3 with k4@4
- insert single delete k5@5 in m1
- flush m1 and result in new file s4 of seqno range [2, 5]
- compact s1, s2, s3 and result in new file s5 of seqno range [1, 4]
- compact s4 and result in new file s6 of seqno range [2] due to single delete
- By the last step, we have file ordering by largest seqno (">" means "newer") : s5 > s6 while s6 contains a newer version of the k1's value (i.e, k1@2) than s5, which is a real reordering corruption. While this can be caught by `force_consistency_check=true`, there isn't a good way to prevent this from happening if ordering by `largest_seqno`
Therefore, we are redesigning the sorting criteria of L0 files and avoid above inconvenience. Credit to ajkr , we now introduce `epoch_num` which describes the order of a file being flushed or ingested/imported (compaction output file will has the minimum `epoch_num` among input files'). This will avoid the above inconvenience in the following ways:
- In the first case above, there will no longer be overlap seqno range check in `force_consistency_check=true` but `epoch_number` ordering check. This will result in file ordering s1 < s2 < s4 (pre-compaction) and s3 < s4 (post-compaction) which won't trigger false positive corruption. See test class `DBCompactionTestL0FilesMisorderCorruption*` for more.
- In the second case above, this will result in file ordering s1 < s2 < s3 < s4 (pre-compacting s1, s2, s3), s5 < s4 (post-compacting s1, s2, s3), s5 < s6 (post-compacting s4), which are correct file ordering without causing any corruption.
**Summary:**
- Introduce `epoch_number` stored per `ColumnFamilyData` and sort CF's L0 files by their assigned `epoch_number` instead of `largest_seqno`.
- `epoch_number` is increased and assigned upon `VersionEdit::AddFile()` for flush (or similarly for WriteLevel0TableForRecovery) and file ingestion (except for allow_behind_true, which will always get assigned as the `kReservedEpochNumberForFileIngestedBehind`)
- Compaction output file is assigned with the minimum `epoch_number` among input files'
- Refit level: reuse refitted file's epoch_number
- Other paths needing `epoch_number` treatment:
- Import column families: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`
- Repair: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`.
- Assigning new epoch_number to a file and adding this file to LSM tree should be atomic. This is guaranteed by us assigning epoch_number right upon `VersionEdit::AddFile()` where this version edit will be apply to LSM tree shape right after by holding the db mutex (e.g, flush, file ingestion, import column family) or by there is only 1 ongoing edit per CF (e.g, WriteLevel0TableForRecovery, Repair).
- Assigning the minimum input epoch number to compaction output file won't misorder L0 files (even through later `Refit(target_level=0)`). It's due to for every key "k" in the input range, a legit compaction will cover a continuous epoch number range of that key. As long as we assign the key "k" the minimum input epoch number, it won't become newer or older than the versions of this key that aren't included in this compaction hence no misorder.
- Persist `epoch_number` of each file in manifest and recover `epoch_number` on db recovery
- Backward compatibility with old db without `epoch_number` support is guaranteed by assigning `epoch_number` to recovered files by `NewestFirstBySeqno` order. See `VersionStorageInfo::RecoverEpochNumbers()` for more
- Forward compatibility with manifest is guaranteed by flexibility of `NewFileCustomTag`
- Replace `force_consistent_check` on L0 with `epoch_number` and remove false positive check like case 1 with `largest_seqno` above
- Due to backward compatibility issue, we might encounter files with missing epoch number at the beginning of db recovery. We will still use old L0 sorting mechanism (`NewestFirstBySeqno`) to check/sort them till we infer their epoch number. See usages of `EpochNumberRequirement`.
- Remove fix https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and their outdated tests to file reordering corruption because such fix can be replaced by this PR.
- Misc:
- update existing tests with `epoch_number` so make check will pass
- update https://github.com/facebook/rocksdb/pull/5958#issue-511150930 tests to verify corruption is fixed using `epoch_number` and cover universal/fifo compaction/CompactRange/CompactFile cases
- assert db_mutex is held for a few places before calling ColumnFamilyData::NewEpochNumber()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10922
Test Plan:
- `make check`
- New unit tests under `db/db_compaction_test.cc`, `db/db_test2.cc`, `db/version_builder_test.cc`, `db/repair_test.cc`
- Updated tests (i.e, `DBCompactionTestL0FilesMisorderCorruption*`) under https://github.com/facebook/rocksdb/pull/5958#issue-511150930
- [Ongoing] Compatibility test: manually run https://github.com/ajkr/rocksdb/commit/36a5686ec012f35a4371e409aa85c404ca1c210d (with file ingestion off for running the `.orig` binary to prevent this bug affecting upgrade/downgrade formality checking) for 1 hour on `simple black/white box`, `cf_consistency/txn/enable_ts with whitebox + test_best_efforts_recovery with blackbox`
- [Ongoing] normal db stress test
- [Ongoing] db stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761
Reviewed By: ajkr
Differential Revision: D41063187
Pulled By: hx235
fbshipit-source-id: 826cb23455de7beaabe2d16c57682a82733a32a9
2 years ago
|
|
|
bool picked_file_to_compact = PickFileToCompact();
|
|
|
|
TEST_SYNC_POINT_CALLBACK("PostPickFileToCompact",
|
|
|
|
&picked_file_to_compact);
|
|
|
|
if (picked_file_to_compact) {
|
|
|
|
// found the compaction!
|
|
|
|
if (start_level_ == 0) {
|
|
|
|
// L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
|
|
|
|
compaction_reason_ = CompactionReason::kLevelL0FilesNum;
|
|
|
|
} else {
|
|
|
|
// L1+ score = `Level files size` / `MaxBytesForLevel`
|
|
|
|
compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
// didn't find the compaction, clear the inputs
|
|
|
|
start_level_inputs_.clear();
|
|
|
|
if (start_level_ == 0) {
|
|
|
|
skipped_l0_to_base = true;
|
|
|
|
// L0->base_level may be blocked due to ongoing L0->base_level
|
|
|
|
// compactions. It may also be blocked by an ongoing compaction from
|
|
|
|
// base_level downwards.
|
|
|
|
//
|
|
|
|
// In these cases, to reduce L0 file count and thus reduce likelihood
|
|
|
|
// of write stalls, we can attempt compacting a span of files within
|
|
|
|
// L0.
|
|
|
|
if (PickIntraL0Compaction()) {
|
|
|
|
output_level_ = 0;
|
|
|
|
compaction_reason_ = CompactionReason::kLevelL0FilesNum;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
// Compaction scores are sorted in descending order, no further scores
|
|
|
|
// will be >= 1.
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// if we didn't find a compaction, check if there are any files marked for
|
|
|
|
// compaction
|
|
|
|
parent_index_ = base_index_ = -1;
|
|
|
|
|
|
|
|
compaction_picker_->PickFilesMarkedForCompaction(
|
|
|
|
cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Bottommost Files Compaction on deleting tombstones
|
|
|
|
PickFileToCompact(vstorage_->BottommostFilesMarkedForCompaction(), false);
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
compaction_reason_ = CompactionReason::kBottommostFiles;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// TTL Compaction
|
|
|
|
if (ioptions_.compaction_pri == kRoundRobin &&
|
|
|
|
!vstorage_->ExpiredTtlFiles().empty()) {
|
|
|
|
auto expired_files = vstorage_->ExpiredTtlFiles();
|
|
|
|
// the expired files list should already be sorted by level
|
|
|
|
start_level_ = expired_files.front().first;
|
|
|
|
#ifndef NDEBUG
|
|
|
|
for (const auto& file : expired_files) {
|
|
|
|
assert(start_level_ <= file.first);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
if (start_level_ > 0) {
|
|
|
|
output_level_ = start_level_ + 1;
|
|
|
|
if (PickFileToCompact()) {
|
|
|
|
compaction_reason_ = CompactionReason::kRoundRobinTtl;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
PickFileToCompact(vstorage_->ExpiredTtlFiles(), true);
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
compaction_reason_ = CompactionReason::kTtl;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Periodic Compaction
|
|
|
|
PickFileToCompact(vstorage_->FilesMarkedForPeriodicCompaction(), false);
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
compaction_reason_ = CompactionReason::kPeriodicCompaction;
|
|
|
|
return;
|
|
|
|
}
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
|
|
|
|
// Forced blob garbage collection
|
|
|
|
PickFileToCompact(vstorage_->FilesMarkedForForcedBlobGC(), false);
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
compaction_reason_ = CompactionReason::kForcedBlobGC;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
|
|
|
|
if (start_level_ == 0 && output_level_ != 0 && !is_l0_trivial_move_) {
|
|
|
|
return compaction_picker_->GetOverlappingL0Files(
|
|
|
|
vstorage_, &start_level_inputs_, output_level_, &parent_index_);
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
void LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion() {
|
|
|
|
// We only expand when the start level is not L0 under round robin
|
|
|
|
assert(start_level_ >= 1);
|
|
|
|
|
|
|
|
// For round-robin compaction priority, we have 3 constraints when picking
|
|
|
|
// multiple files.
|
|
|
|
// Constraint 1: We can only pick consecutive files
|
|
|
|
// -> Constraint 1a: When a file is being compacted (or some input files
|
|
|
|
// are being compacted after expanding, we cannot
|
|
|
|
// choose it and have to stop choosing more files
|
|
|
|
// -> Constraint 1b: When we reach the last file (with largest keys), we
|
|
|
|
// cannot choose more files (the next file will be the
|
|
|
|
// first one)
|
|
|
|
// Constraint 2: We should ensure the total compaction bytes (including the
|
|
|
|
// overlapped files from the next level) is no more than
|
|
|
|
// mutable_cf_options_.max_compaction_bytes
|
|
|
|
// Constraint 3: We try our best to pick as many files as possible so that
|
|
|
|
// the post-compaction level size is less than
|
|
|
|
// MaxBytesForLevel(start_level_)
|
|
|
|
// Constraint 4: We do not expand if it is possible to apply a trivial move
|
|
|
|
// Constraint 5 (TODO): Try to pick minimal files to split into the target
|
|
|
|
// number of subcompactions
|
|
|
|
TEST_SYNC_POINT("LevelCompactionPicker::RoundRobin");
|
|
|
|
|
|
|
|
// Only expand the inputs when we have selected a file in start_level_inputs_
|
|
|
|
if (start_level_inputs_.size() == 0) return;
|
|
|
|
|
|
|
|
uint64_t start_lvl_bytes_no_compacting = 0;
|
|
|
|
uint64_t curr_bytes_to_compact = 0;
|
|
|
|
uint64_t start_lvl_max_bytes_to_compact = 0;
|
|
|
|
const std::vector<FileMetaData*>& level_files =
|
|
|
|
vstorage_->LevelFiles(start_level_);
|
|
|
|
// Constraint 3 (pre-calculate the ideal max bytes to compact)
|
|
|
|
for (auto f : level_files) {
|
|
|
|
if (!f->being_compacted) {
|
|
|
|
start_lvl_bytes_no_compacting += f->fd.GetFileSize();
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
}
|
|
|
|
}
|
|
|
|
if (start_lvl_bytes_no_compacting >
|
|
|
|
vstorage_->MaxBytesForLevel(start_level_)) {
|
|
|
|
start_lvl_max_bytes_to_compact = start_lvl_bytes_no_compacting -
|
|
|
|
vstorage_->MaxBytesForLevel(start_level_);
|
|
|
|
}
|
|
|
|
|
|
|
|
size_t start_index = vstorage_->FilesByCompactionPri(start_level_)[0];
|
|
|
|
InternalKey smallest, largest;
|
|
|
|
// Constraint 4 (No need to check again later)
|
|
|
|
compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
|
|
|
|
CompactionInputFiles output_level_inputs;
|
|
|
|
output_level_inputs.level = output_level_;
|
|
|
|
vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
|
|
|
|
&output_level_inputs.files);
|
|
|
|
if (output_level_inputs.empty()) {
|
|
|
|
if (TryExtendNonL0TrivialMove((int)start_index)) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
// Constraint 3
|
|
|
|
if (start_level_inputs_[0]->fd.GetFileSize() >=
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
start_lvl_max_bytes_to_compact) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
CompactionInputFiles tmp_start_level_inputs;
|
|
|
|
tmp_start_level_inputs = start_level_inputs_;
|
|
|
|
// TODO (zichen): Future parallel round-robin may also need to update this
|
|
|
|
// Constraint 1b (only expand till the end)
|
|
|
|
for (size_t i = start_index + 1; i < level_files.size(); i++) {
|
|
|
|
auto* f = level_files[i];
|
|
|
|
if (f->being_compacted) {
|
|
|
|
// Constraint 1a
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp_start_level_inputs.files.push_back(f);
|
|
|
|
if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
|
|
|
|
&tmp_start_level_inputs) ||
|
|
|
|
compaction_picker_->FilesRangeOverlapWithCompaction(
|
|
|
|
{tmp_start_level_inputs}, output_level_,
|
|
|
|
Compaction::EvaluatePenultimateLevel(
|
|
|
|
vstorage_, ioptions_, start_level_, output_level_))) {
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
// Constraint 1a
|
|
|
|
tmp_start_level_inputs.clear();
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
curr_bytes_to_compact = 0;
|
|
|
|
for (auto start_lvl_f : tmp_start_level_inputs.files) {
|
|
|
|
curr_bytes_to_compact += start_lvl_f->fd.GetFileSize();
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
}
|
|
|
|
|
|
|
|
// Check whether any output level files are locked
|
|
|
|
compaction_picker_->GetRange(tmp_start_level_inputs, &smallest, &largest);
|
|
|
|
vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
|
|
|
|
&output_level_inputs.files);
|
|
|
|
if (!output_level_inputs.empty() &&
|
|
|
|
!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
|
|
|
|
&output_level_inputs)) {
|
|
|
|
// Constraint 1a
|
|
|
|
tmp_start_level_inputs.clear();
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
uint64_t start_lvl_curr_bytes_to_compact = curr_bytes_to_compact;
|
|
|
|
for (auto output_lvl_f : output_level_inputs.files) {
|
|
|
|
curr_bytes_to_compact += output_lvl_f->fd.GetFileSize();
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
}
|
|
|
|
if (curr_bytes_to_compact > mutable_cf_options_.max_compaction_bytes) {
|
|
|
|
// Constraint 2
|
|
|
|
tmp_start_level_inputs.clear();
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
start_level_inputs_.files = tmp_start_level_inputs.files;
|
|
|
|
// Constraint 3
|
|
|
|
if (start_lvl_curr_bytes_to_compact > start_lvl_max_bytes_to_compact) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
|
|
|
|
// Setup input files from output level. For output to L0, we only compact
|
|
|
|
// spans of files that do not interact with any pending compactions, so don't
|
|
|
|
// need to consider other levels.
|
|
|
|
if (output_level_ != 0) {
|
|
|
|
output_level_inputs_.level = output_level_;
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
bool round_robin_expanding =
|
|
|
|
ioptions_.compaction_pri == kRoundRobin &&
|
|
|
|
compaction_reason_ == CompactionReason::kLevelMaxLevelSize;
|
|
|
|
if (round_robin_expanding) {
|
|
|
|
SetupOtherFilesWithRoundRobinExpansion();
|
|
|
|
}
|
|
|
|
if (!is_l0_trivial_move_ &&
|
|
|
|
!compaction_picker_->SetupOtherInputs(
|
|
|
|
cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
&output_level_inputs_, &parent_index_, base_index_,
|
|
|
|
round_robin_expanding)) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
compaction_inputs_.push_back(start_level_inputs_);
|
|
|
|
if (!output_level_inputs_.empty()) {
|
|
|
|
compaction_inputs_.push_back(output_level_inputs_);
|
|
|
|
}
|
|
|
|
|
Add missing range conflict check between file ingestion and RefitLevel() (#10988)
Summary:
**Context:**
File ingestion never checks whether the key range it acts on overlaps with an ongoing RefitLevel() (used in `CompactRange()` with `change_level=true`). That's because RefitLevel() doesn't register and make its key range known to file ingestion. Though it checks overlapping with other compactions by https://github.com/facebook/rocksdb/blob/7.8.fb/db/external_sst_file_ingestion_job.cc#L998.
RefitLevel() (used in `CompactRange()` with `change_level=true`) doesn't check whether the key range it acts on overlaps with an ongoing file ingestion. That's because file ingestion does not register and make its key range known to other compactions.
- Note that non-refitlevel-compaction (e.g, manual compaction w/o RefitLevel() or general compaction) also does not check key range overlap with ongoing file ingestion for the same reason.
- But it's fine. Credited to cbi42's discovery, `WaitForIngestFile` was called by background and foreground compactions. They were introduced in https://github.com/facebook/rocksdb/commit/0f88160f67d36ea30e3aca3a3cef924c3a009be6, https://github.com/facebook/rocksdb/commit/5c64fb67d2fc198f1a73ff3ae543749a6a41f513 and https://github.com/facebook/rocksdb/commit/87dfc1d23e0e16ff73e15f63c6fa0fb3b3fc8c8c.
- Regardless, this PR registers file ingestion like a compaction is a general approach that will also add range conflict check between file ingestion and non-refitlevel-compaction, though it has not been the issue motivated this PR.
Above are bugs resulting in two bad consequences:
- If file ingestion and RefitLevel() creates files in the same level, then range-overlapped files will be created at that level and caught as corruption by `force_consistency_checks=true`
- If file ingestion and RefitLevel() creates file in different levels, then with one further compaction on the ingested file, it can result in two same keys both with seqno 0 in two different levels. Then with iterator's [optimization](https://github.com/facebook/rocksdb/blame/c62f3221698fd273b673d4f7e54eabb8329a4369/db/db_iter.cc#L342-L343) that assumes no two same keys both with seqno 0, it will either break this assertion in debug build or, even worst, return value of this same key for the key after it, which is the wrong value to return, in release build.
Therefore we decide to introduce range conflict check for file ingestion and RefitLevel() inspired from the existing range conflict check among compactions.
**Summary:**
- Treat file ingestion job and RefitLevel() as `Compaction` of new compaction reasons: `CompactionReason::kExternalSstIngestion` and `CompactionReason::kRefitLevel` and register/unregister them. File ingestion is treated as compaction from L0 to different levels and RefitLevel() as compaction from source level to target level.
- Check for `RangeOverlapWithCompaction` with other ongoing compactions, `RegisterCompaction()` on this "compaction" before changing the LSM state in `VersionStorageInfo`, and `UnregisterCompaction()` after changing.
- Replace scattered fixes (https://github.com/facebook/rocksdb/commit/0f88160f67d36ea30e3aca3a3cef924c3a009be6, https://github.com/facebook/rocksdb/commit/5c64fb67d2fc198f1a73ff3ae543749a6a41f513 and https://github.com/facebook/rocksdb/commit/87dfc1d23e0e16ff73e15f63c6fa0fb3b3fc8c8c.) that prevents overlapping between file ingestion and non-refit-level compaction with this fix cuz those practices are easy to overlook.
- Misc: logic cleanup, see PR comments
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10988
Test Plan:
- New unit test `DBCompactionTestWithOngoingFileIngestionParam*` that failed pre-fix and passed afterwards.
- Made compatible with existing tests, see PR comments
- make check
- [Ongoing] Stress test rehearsal with normal value and aggressive CI value https://github.com/facebook/rocksdb/pull/10761
Reviewed By: cbi42
Differential Revision: D41535685
Pulled By: hx235
fbshipit-source-id: 549833a577ba1496d20a870583d4caa737da1258
2 years ago
|
|
|
// In some edge cases we could pick a compaction that will be compacting
|
|
|
|
// a key range that overlap with another running compaction, and both
|
|
|
|
// of them have the same output level. This could happen if
|
|
|
|
// (1) we are running a non-exclusive manual compaction
|
|
|
|
// (2) AddFile ingest a new file into the LSM tree
|
|
|
|
// We need to disallow this from happening.
|
|
|
|
if (compaction_picker_->FilesRangeOverlapWithCompaction(
|
|
|
|
compaction_inputs_, output_level_,
|
|
|
|
Compaction::EvaluatePenultimateLevel(
|
|
|
|
vstorage_, ioptions_, start_level_, output_level_))) {
|
|
|
|
// This compaction output could potentially conflict with the output
|
|
|
|
// of a currently running compaction, we cannot run it.
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
if (!is_l0_trivial_move_) {
|
|
|
|
compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
|
|
|
|
output_level_inputs_, &grandparents_);
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
compaction_inputs_.push_back(start_level_inputs_);
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
Compaction* LevelCompactionBuilder::PickCompaction() {
|
|
|
|
// Pick up the first file to start compaction. It may have been extended
|
|
|
|
// to a clean cut.
|
|
|
|
SetupInitialFiles();
|
|
|
|
if (start_level_inputs_.empty()) {
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
assert(start_level_ >= 0 && output_level_ >= 0);
|
|
|
|
|
|
|
|
// If it is a L0 -> base level compaction, we need to set up other L0
|
|
|
|
// files if needed.
|
|
|
|
if (!SetupOtherL0FilesIfNeeded()) {
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Pick files in the output level and expand more files in the start level
|
|
|
|
// if needed.
|
|
|
|
if (!SetupOtherInputsIfNeeded()) {
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Form a compaction object containing the files we picked.
|
|
|
|
Compaction* c = GetCompaction();
|
|
|
|
|
|
|
|
TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
|
|
|
|
|
|
|
|
return c;
|
|
|
|
}
|
|
|
|
|
|
|
|
Compaction* LevelCompactionBuilder::GetCompaction() {
|
|
|
|
auto c = new Compaction(
|
|
|
|
vstorage_, ioptions_, mutable_cf_options_, mutable_db_options_,
|
|
|
|
std::move(compaction_inputs_), output_level_,
|
|
|
|
MaxFileSizeForLevel(mutable_cf_options_, output_level_,
|
|
|
|
ioptions_.compaction_style, vstorage_->base_level(),
|
|
|
|
ioptions_.level_compaction_dynamic_level_bytes),
|
|
|
|
mutable_cf_options_.max_compaction_bytes,
|
|
|
|
GetPathId(ioptions_, mutable_cf_options_, output_level_),
|
|
|
|
GetCompressionType(vstorage_, mutable_cf_options_, output_level_,
|
|
|
|
vstorage_->base_level()),
|
|
|
|
GetCompressionOptions(mutable_cf_options_, vstorage_, output_level_),
|
|
|
|
Temperature::kUnknown,
|
|
|
|
/* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
|
|
|
|
/* trim_ts */ "", start_level_score_, false /* deletion_compaction */,
|
|
|
|
/* l0_files_might_overlap */ start_level_ == 0 && !is_l0_trivial_move_,
|
|
|
|
compaction_reason_);
|
|
|
|
|
|
|
|
// If it's level 0 compaction, make sure we don't execute any other level 0
|
|
|
|
// compactions in parallel
|
|
|
|
compaction_picker_->RegisterCompaction(c);
|
|
|
|
|
|
|
|
// Creating a compaction influences the compaction score because the score
|
|
|
|
// takes running compactions into account (by skipping files that are already
|
|
|
|
// being compacted). Since we just changed compaction score, we recalculate it
|
|
|
|
// here
|
|
|
|
vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
|
|
|
|
return c;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find the optimal path to place a file
|
|
|
|
* Given a level, finds the path where levels up to it will fit in levels
|
|
|
|
* up to and including this path
|
|
|
|
*/
|
|
|
|
uint32_t LevelCompactionBuilder::GetPathId(
|
|
|
|
const ImmutableCFOptions& ioptions,
|
|
|
|
const MutableCFOptions& mutable_cf_options, int level) {
|
|
|
|
uint32_t p = 0;
|
|
|
|
assert(!ioptions.cf_paths.empty());
|
|
|
|
|
|
|
|
// size remaining in the most recent path
|
|
|
|
uint64_t current_path_size = ioptions.cf_paths[0].target_size;
|
|
|
|
|
|
|
|
uint64_t level_size;
|
|
|
|
int cur_level = 0;
|
|
|
|
|
|
|
|
// max_bytes_for_level_base denotes L1 size.
|
|
|
|
// We estimate L0 size to be the same as L1.
|
|
|
|
level_size = mutable_cf_options.max_bytes_for_level_base;
|
|
|
|
|
|
|
|
// Last path is the fallback
|
|
|
|
while (p < ioptions.cf_paths.size() - 1) {
|
|
|
|
if (level_size <= current_path_size) {
|
|
|
|
if (cur_level == level) {
|
|
|
|
// Does desired level fit in this path?
|
|
|
|
return p;
|
|
|
|
} else {
|
|
|
|
current_path_size -= level_size;
|
|
|
|
if (cur_level > 0) {
|
|
|
|
if (ioptions.level_compaction_dynamic_level_bytes) {
|
|
|
|
// Currently, level_compaction_dynamic_level_bytes is ignored when
|
|
|
|
// multiple db paths are specified. https://github.com/facebook/
|
|
|
|
// rocksdb/blob/main/db/column_family.cc.
|
|
|
|
// Still, adding this check to avoid accidentally using
|
|
|
|
// max_bytes_for_level_multiplier_additional
|
|
|
|
level_size = static_cast<uint64_t>(
|
|
|
|
level_size * mutable_cf_options.max_bytes_for_level_multiplier);
|
|
|
|
} else {
|
|
|
|
level_size = static_cast<uint64_t>(
|
|
|
|
level_size * mutable_cf_options.max_bytes_for_level_multiplier *
|
|
|
|
mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
cur_level++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
p++;
|
|
|
|
current_path_size = ioptions.cf_paths[p].target_size;
|
|
|
|
}
|
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::TryPickL0TrivialMove() {
|
|
|
|
if (vstorage_->base_level() <= 0) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
if (start_level_ == 0 && mutable_cf_options_.compression_per_level.empty() &&
|
|
|
|
!vstorage_->LevelFiles(output_level_).empty() &&
|
|
|
|
ioptions_.db_paths.size() <= 1) {
|
|
|
|
// Try to pick trivial move from L0 to L1. We start from the oldest
|
|
|
|
// file. We keep expanding to newer files if it would form a
|
|
|
|
// trivial move.
|
|
|
|
// For now we don't support it with
|
|
|
|
// mutable_cf_options_.compression_per_level to prevent the logic
|
|
|
|
// of determining whether L0 can be trivial moved to the next level.
|
|
|
|
// We skip the case where output level is empty, since in this case, at
|
|
|
|
// least the oldest file would qualify for trivial move, and this would
|
|
|
|
// be a surprising behavior with few benefits.
|
|
|
|
|
|
|
|
// We search from the oldest file from the newest. In theory, there are
|
|
|
|
// files in the middle can form trivial move too, but it is probably
|
|
|
|
// uncommon and we ignore these cases for simplicity.
|
|
|
|
const std::vector<FileMetaData*>& level_files =
|
|
|
|
vstorage_->LevelFiles(start_level_);
|
|
|
|
|
|
|
|
InternalKey my_smallest, my_largest;
|
|
|
|
for (auto it = level_files.rbegin(); it != level_files.rend(); ++it) {
|
|
|
|
CompactionInputFiles output_level_inputs;
|
|
|
|
output_level_inputs.level = output_level_;
|
|
|
|
FileMetaData* file = *it;
|
|
|
|
if (it == level_files.rbegin()) {
|
|
|
|
my_smallest = file->smallest;
|
|
|
|
my_largest = file->largest;
|
|
|
|
} else {
|
|
|
|
if (compaction_picker_->icmp()->Compare(file->largest, my_smallest) <
|
|
|
|
0) {
|
|
|
|
my_smallest = file->smallest;
|
|
|
|
} else if (compaction_picker_->icmp()->Compare(file->smallest,
|
|
|
|
my_largest) > 0) {
|
|
|
|
my_largest = file->largest;
|
|
|
|
} else {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
vstorage_->GetOverlappingInputs(output_level_, &my_smallest, &my_largest,
|
|
|
|
&output_level_inputs.files);
|
|
|
|
if (output_level_inputs.empty()) {
|
|
|
|
assert(!file->being_compacted);
|
|
|
|
start_level_inputs_.files.push_back(file);
|
|
|
|
} else {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!start_level_inputs_.empty()) {
|
|
|
|
// Sort files by key range. Not sure it's 100% necessary but it's cleaner
|
|
|
|
// to always keep files sorted by key the key ranges don't overlap.
|
|
|
|
std::sort(start_level_inputs_.files.begin(),
|
|
|
|
start_level_inputs_.files.end(),
|
|
|
|
[icmp = compaction_picker_->icmp()](FileMetaData* f1,
|
|
|
|
FileMetaData* f2) -> bool {
|
|
|
|
return (icmp->Compare(f1->smallest, f2->smallest) < 0);
|
|
|
|
});
|
|
|
|
|
|
|
|
is_l0_trivial_move_ = true;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::TryExtendNonL0TrivialMove(int start_index) {
|
|
|
|
if (start_level_inputs_.size() == 1 &&
|
|
|
|
(ioptions_.db_paths.empty() || ioptions_.db_paths.size() == 1) &&
|
|
|
|
(mutable_cf_options_.compression_per_level.empty())) {
|
|
|
|
// Only file of `index`, and it is likely a trivial move. Try to
|
|
|
|
// expand if it is still a trivial move, but not beyond
|
|
|
|
// max_compaction_bytes or 4 files, so that we don't create too
|
|
|
|
// much compaction pressure for the next level.
|
|
|
|
// Ignore if there are more than one DB path, as it would be hard
|
|
|
|
// to predict whether it is a trivial move.
|
|
|
|
const std::vector<FileMetaData*>& level_files =
|
|
|
|
vstorage_->LevelFiles(start_level_);
|
|
|
|
const size_t kMaxMultiTrivialMove = 4;
|
|
|
|
FileMetaData* initial_file = start_level_inputs_.files[0];
|
|
|
|
size_t total_size = initial_file->fd.GetFileSize();
|
|
|
|
CompactionInputFiles output_level_inputs;
|
|
|
|
output_level_inputs.level = output_level_;
|
|
|
|
for (int i = start_index + 1;
|
|
|
|
i < static_cast<int>(level_files.size()) &&
|
|
|
|
start_level_inputs_.size() < kMaxMultiTrivialMove;
|
|
|
|
i++) {
|
|
|
|
FileMetaData* next_file = level_files[i];
|
|
|
|
if (next_file->being_compacted) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
vstorage_->GetOverlappingInputs(output_level_, &(initial_file->smallest),
|
|
|
|
&(next_file->largest),
|
|
|
|
&output_level_inputs.files);
|
|
|
|
if (!output_level_inputs.empty()) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (i < static_cast<int>(level_files.size()) - 1 &&
|
|
|
|
compaction_picker_->icmp()
|
|
|
|
->user_comparator()
|
|
|
|
->CompareWithoutTimestamp(
|
|
|
|
next_file->largest.user_key(),
|
|
|
|
level_files[i + 1]->smallest.user_key()) == 0) {
|
|
|
|
TEST_SYNC_POINT_CALLBACK(
|
|
|
|
"LevelCompactionBuilder::TryExtendNonL0TrivialMove:NoCleanCut",
|
|
|
|
nullptr);
|
|
|
|
// Not a clean up after adding the next file. Skip.
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
total_size += next_file->fd.GetFileSize();
|
|
|
|
if (total_size > mutable_cf_options_.max_compaction_bytes) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
start_level_inputs_.files.push_back(next_file);
|
|
|
|
}
|
|
|
|
return start_level_inputs_.size() > 1;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::PickFileToCompact() {
|
|
|
|
// level 0 files are overlapping. So we cannot pick more
|
|
|
|
// than one concurrent compactions at this level. This
|
|
|
|
// could be made better by looking at key-ranges that are
|
|
|
|
// being compacted at level 0.
|
|
|
|
if (start_level_ == 0 &&
|
|
|
|
!compaction_picker_->level0_compactions_in_progress()->empty()) {
|
|
|
|
TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
start_level_inputs_.clear();
|
|
|
|
start_level_inputs_.level = start_level_;
|
|
|
|
|
|
|
|
assert(start_level_ >= 0);
|
|
|
|
|
|
|
|
if (TryPickL0TrivialMove()) {
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
const std::vector<FileMetaData*>& level_files =
|
|
|
|
vstorage_->LevelFiles(start_level_);
|
|
|
|
|
|
|
|
// Pick the file with the highest score in this level that is not already
|
|
|
|
// being compacted.
|
|
|
|
const std::vector<int>& file_scores =
|
|
|
|
vstorage_->FilesByCompactionPri(start_level_);
|
|
|
|
|
|
|
|
unsigned int cmp_idx;
|
|
|
|
for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
|
|
|
|
cmp_idx < file_scores.size(); cmp_idx++) {
|
|
|
|
int index = file_scores[cmp_idx];
|
|
|
|
auto* f = level_files[index];
|
|
|
|
|
|
|
|
// do not pick a file to compact if it is being compacted
|
|
|
|
// from n-1 level.
|
|
|
|
if (f->being_compacted) {
|
|
|
|
if (ioptions_.compaction_pri == kRoundRobin) {
|
|
|
|
// TODO(zichen): this file may be involved in one compaction from
|
|
|
|
// an upper level, cannot advance the cursor for round-robin policy.
|
|
|
|
// Currently, we do not pick any file to compact in this case. We
|
|
|
|
// should fix this later to ensure a compaction is picked but the
|
|
|
|
// cursor shall not be advanced.
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
start_level_inputs_.files.push_back(f);
|
|
|
|
if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
|
|
|
|
&start_level_inputs_) ||
|
|
|
|
compaction_picker_->FilesRangeOverlapWithCompaction(
|
|
|
|
{start_level_inputs_}, output_level_,
|
|
|
|
Compaction::EvaluatePenultimateLevel(
|
|
|
|
vstorage_, ioptions_, start_level_, output_level_))) {
|
|
|
|
// A locked (pending compaction) input-level file was pulled in due to
|
|
|
|
// user-key overlap.
|
|
|
|
start_level_inputs_.clear();
|
|
|
|
|
|
|
|
if (ioptions_.compaction_pri == kRoundRobin) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Now that input level is fully expanded, we check whether any output
|
|
|
|
// files are locked due to pending compaction.
|
|
|
|
//
|
|
|
|
// Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
|
|
|
|
// level files are locked, not just the extra ones pulled in for user-key
|
|
|
|
// overlap.
|
|
|
|
InternalKey smallest, largest;
|
|
|
|
compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
|
|
|
|
CompactionInputFiles output_level_inputs;
|
|
|
|
output_level_inputs.level = output_level_;
|
|
|
|
vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
|
|
|
|
&output_level_inputs.files);
|
|
|
|
if (output_level_inputs.empty()) {
|
|
|
|
if (TryExtendNonL0TrivialMove(index)) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
|
|
|
|
&output_level_inputs)) {
|
|
|
|
start_level_inputs_.clear();
|
|
|
|
if (ioptions_.compaction_pri == kRoundRobin) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
Support subcmpct using reserved resources for round-robin priority (#10341)
Summary:
Earlier implementation of round-robin priority can only pick one file at a time and disallows parallel compactions within the same level. In this PR, round-robin compaction policy will expand towards more input files with respecting some additional constraints, which are summarized as follows:
* Constraint 1: We can only pick consecutive files
- Constraint 1a: When a file is being compacted (or some input files are being compacted after expanding), we cannot choose it and have to stop choosing more files
- Constraint 1b: When we reach the last file (with the largest keys), we cannot choose more files (the next file will be the first one with small keys)
* Constraint 2: We should ensure the total compaction bytes (including the overlapped files from the next level) is no more than `mutable_cf_options_.max_compaction_bytes`
* Constraint 3: We try our best to pick as many files as possible so that the post-compaction level size can be just less than `MaxBytesForLevel(start_level_)`
* Constraint 4: If trivial move is allowed, we reuse the logic of `TryNonL0TrivialMove()` instead of expanding files with Constraint 3
More details can be found in `LevelCompactionBuilder::SetupOtherFilesWithRoundRobinExpansion()`.
The above optimization accelerates the process of moving the compaction cursor, in which the write-amp can be further reduced. While a large compaction may lead to high write stall, we break this large compaction into several subcompactions **regardless of** the `max_subcompactions` limit. The number of subcompactions for round-robin compaction priority is determined through the following steps:
* Step 1: Initialized against `max_output_file_limit`, the number of input files in the start level, and also the range size limit `ranges.size()`
* Step 2: Call `AcquireSubcompactionResources()`when max subcompactions is not sufficient, but we may or may not obtain desired resources, additional number of resources is stored in `extra_num_subcompaction_threads_reserved_`). Subcompaction limit is changed and update `num_planned_subcompactions` with `GetSubcompactionLimit()`
* Step 3: Call `ShrinkSubcompactionResources()` to ensure extra resources can be released (extra resources may exist for round-robin compaction when the number of actual number of subcompactions is less than the number of planned subcompactions)
More details can be found in `CompactionJob::AcquireSubcompactionResources()`,`CompactionJob::ShrinkSubcompactionResources()`, and `CompactionJob::ReleaseSubcompactionResources()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10341
Test Plan: Add `CompactionPriMultipleFilesRoundRobin[1-3]` unit test in `compaction_picker_test.cc` and `RoundRobinSubcompactionsAgainstResources.SubcompactionsUsingResources/[0-4]`, `RoundRobinSubcompactionsAgainstPressureToken.PressureTokenTest/[0-1]` in `db_compaction_test.cc`
Reviewed By: ajkr, hx235
Differential Revision: D37792644
Pulled By: littlepig2013
fbshipit-source-id: 7fecb7c4ffd97b34bbf6e3b760b2c35a772a0657
2 years ago
|
|
|
|
|
|
|
base_index_ = index;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// store where to start the iteration in the next call to PickCompaction
|
|
|
|
if (ioptions_.compaction_pri != kRoundRobin) {
|
|
|
|
vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
|
|
|
|
}
|
|
|
|
return start_level_inputs_.size() > 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool LevelCompactionBuilder::PickIntraL0Compaction() {
|
|
|
|
start_level_inputs_.clear();
|
|
|
|
const std::vector<FileMetaData*>& level_files =
|
|
|
|
vstorage_->LevelFiles(0 /* level */);
|
|
|
|
if (level_files.size() <
|
|
|
|
static_cast<size_t>(
|
|
|
|
mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
|
|
|
|
level_files[0]->being_compacted) {
|
|
|
|
// If L0 isn't accumulating much files beyond the regular trigger, don't
|
|
|
|
// resort to L0->L0 compaction yet.
|
|
|
|
return false;
|
|
|
|
}
|
Fix corruption with intra-L0 on ingested files (#5958)
Summary:
## Problem Description
Our process was abort when it call `CheckConsistency`. And the information in `stderr` show that "`L0 files seqno 3001491972 3004797440 vs. 3002875611 3004524421` ". Here are the causes of the accident I investigated.
* RocksDB will call `CheckConsistency` whenever `MANIFEST` file is update. It will check sequence number interval of every file, except files which were ingested.
* When one file is ingested into RocksDB, it will be assigned the value of global sequence number, and the minimum and maximum seqno of this file are equal, which are both equal to global sequence number.
* `CheckConsistency` determines whether the file is ingested by whether the smallest and largest seqno of an sstable file are equal.
* If IntraL0Compaction picks one sst which was ingested just now and compacted it into another sst, the `smallest_seqno` of this new file will be smaller than his `largest_seqno`.
* If more than one ingested file was ingested before memtable schedule flush, and they all compact into one new sstable file by `IntraL0Compaction`. The sequence interval of this new file will be included in the interval of the memtable. So `CheckConsistency` will return a `Corruption`.
* If a sstable was ingested after the memtable was schedule to flush, which would assign a larger seqno to it than memtable. Then the file was compacted with other files (these files were all flushed before the memtable) in L0 into one file. This compaction start before the flush job of memtable start, but completed after the flush job finish. So this new file produced by the compaction (we call it s1) would have a larger interval of sequence number than the file produced by flush (we call it s2). **But there was still some data in s1 written into RocksDB before the s2, so it's possible that some data in s2 was cover by old data in s1.** Of course, it would also make a `Corruption` because of overlap of seqno. There is the relationship of the files:
> s1.smallest_seqno < s2.smallest_seqno < s2.largest_seqno < s1.largest_seqno
So I skip pick sst file which was ingested in function `FindIntraL0Compaction `
## Reason
Here is my bug report: https://github.com/facebook/rocksdb/issues/5913
There are two situations that can cause the check to fail.
### First situation:
- First we ingest five external sst into Rocksdb, and they happened to be ingested in L0. and there had been some data in memtable, which make the smallest sequence number of memtable is less than which of sst that we ingest.
- If there had been one compaction job which compacted sst from L0 to L1, `LevelCompactionPicker` would trigger a `IntraL0Compaction` which would compact this five sst from L0 to L0. We call this sst A, which was merged from five ingested sst.
- Then some data was put into memtable, and memtable was flushed to L0. We called this sst B.
- RocksDB check consistency , and find the `smallest_seqno` of B is less than that of A and crash. Because A was merged from five sst, the smallest sequence number of it was less than the biggest sequece number of itself, so RocksDB could not tell if A was produce by ingested.
### Secondary situaion
- First we have flushed many sst in L0, we call them [s1, s2, s3].
- There is an immutable memtable request to be flushed, but because flush thread is busy, so it has not been picked. we call it m1. And at the moment, one sst is ingested into L0. We call it s4. Because s4 is ingested after m1 became immutable memtable, so it has a larger log sequence number than m1.
- m1 is flushed in L0. because it is small, this flush job finish quickly. we call it s5.
- [s1, s2, s3, s4] are compacted into one sst to L0, by IntraL0Compaction. We call it s6.
- compacted 4@0 files to L0
- When s6 is added into manifest, the corruption happened. because the largest sequence number of s6 is equal to s4, and they are both larger than that of s5. But because s1 is older than m1, so the smallest sequence number of s6 is smaller than that of s5.
- s6.smallest_seqno < s5.smallest_seqno < s5.largest_seqno < s6.largest_seqno
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5958
Differential Revision: D18601316
fbshipit-source-id: 5fe54b3c9af52a2e1400728f565e895cde1c7267
5 years ago
|
|
|
return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
|
|
|
|
std::numeric_limits<uint64_t>::max(),
|
Fix corruption with intra-L0 on ingested files (#5958)
Summary:
## Problem Description
Our process was abort when it call `CheckConsistency`. And the information in `stderr` show that "`L0 files seqno 3001491972 3004797440 vs. 3002875611 3004524421` ". Here are the causes of the accident I investigated.
* RocksDB will call `CheckConsistency` whenever `MANIFEST` file is update. It will check sequence number interval of every file, except files which were ingested.
* When one file is ingested into RocksDB, it will be assigned the value of global sequence number, and the minimum and maximum seqno of this file are equal, which are both equal to global sequence number.
* `CheckConsistency` determines whether the file is ingested by whether the smallest and largest seqno of an sstable file are equal.
* If IntraL0Compaction picks one sst which was ingested just now and compacted it into another sst, the `smallest_seqno` of this new file will be smaller than his `largest_seqno`.
* If more than one ingested file was ingested before memtable schedule flush, and they all compact into one new sstable file by `IntraL0Compaction`. The sequence interval of this new file will be included in the interval of the memtable. So `CheckConsistency` will return a `Corruption`.
* If a sstable was ingested after the memtable was schedule to flush, which would assign a larger seqno to it than memtable. Then the file was compacted with other files (these files were all flushed before the memtable) in L0 into one file. This compaction start before the flush job of memtable start, but completed after the flush job finish. So this new file produced by the compaction (we call it s1) would have a larger interval of sequence number than the file produced by flush (we call it s2). **But there was still some data in s1 written into RocksDB before the s2, so it's possible that some data in s2 was cover by old data in s1.** Of course, it would also make a `Corruption` because of overlap of seqno. There is the relationship of the files:
> s1.smallest_seqno < s2.smallest_seqno < s2.largest_seqno < s1.largest_seqno
So I skip pick sst file which was ingested in function `FindIntraL0Compaction `
## Reason
Here is my bug report: https://github.com/facebook/rocksdb/issues/5913
There are two situations that can cause the check to fail.
### First situation:
- First we ingest five external sst into Rocksdb, and they happened to be ingested in L0. and there had been some data in memtable, which make the smallest sequence number of memtable is less than which of sst that we ingest.
- If there had been one compaction job which compacted sst from L0 to L1, `LevelCompactionPicker` would trigger a `IntraL0Compaction` which would compact this five sst from L0 to L0. We call this sst A, which was merged from five ingested sst.
- Then some data was put into memtable, and memtable was flushed to L0. We called this sst B.
- RocksDB check consistency , and find the `smallest_seqno` of B is less than that of A and crash. Because A was merged from five sst, the smallest sequence number of it was less than the biggest sequece number of itself, so RocksDB could not tell if A was produce by ingested.
### Secondary situaion
- First we have flushed many sst in L0, we call them [s1, s2, s3].
- There is an immutable memtable request to be flushed, but because flush thread is busy, so it has not been picked. we call it m1. And at the moment, one sst is ingested into L0. We call it s4. Because s4 is ingested after m1 became immutable memtable, so it has a larger log sequence number than m1.
- m1 is flushed in L0. because it is small, this flush job finish quickly. we call it s5.
- [s1, s2, s3, s4] are compacted into one sst to L0, by IntraL0Compaction. We call it s6.
- compacted 4@0 files to L0
- When s6 is added into manifest, the corruption happened. because the largest sequence number of s6 is equal to s4, and they are both larger than that of s5. But because s1 is older than m1, so the smallest sequence number of s6 is smaller than that of s5.
- s6.smallest_seqno < s5.smallest_seqno < s5.largest_seqno < s6.largest_seqno
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5958
Differential Revision: D18601316
fbshipit-source-id: 5fe54b3c9af52a2e1400728f565e895cde1c7267
5 years ago
|
|
|
mutable_cf_options_.max_compaction_bytes,
|
Sort L0 files by newly introduced epoch_num (#10922)
Summary:
**Context:**
Sorting L0 files by `largest_seqno` has at least two inconvenience:
- File ingestion and compaction involving ingested files can create files of overlapping seqno range with the existing files. `force_consistency_check=true` will catch such overlap seqno range even those harmless overlap.
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n")
- insert k1@1 to memtable m1
- ingest file s1 with k2@2, ingest file s2 with k3@3
- insert k4@4 to m1
- compact files s1, s2 and result in new file s3 of seqno range [2, 3]
- flush m1 and result in new file s4 of seqno range [1, 4]. And `force_consistency_check=true` will think s4 and s3 has file reordering corruption that might cause retuning an old value of k1
- However such caught corruption is a false positive since s1, s2 will not have overlapped keys with k1 or whatever inserted into m1 before ingest file s1 by the requirement of file ingestion (otherwise the m1 will be flushed first before any of the file ingestion completes). Therefore there in fact isn't any file reordering corruption.
- Single delete can decrease a file's largest seqno and ordering by `largest_seqno` can introduce a wrong ordering hence file reordering corruption
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n", Credit to ajkr for this example)
- an existing SST s1 contains only k1@1
- insert k1@2 to memtable m1
- ingest file s2 with k3@3, ingest file s3 with k4@4
- insert single delete k5@5 in m1
- flush m1 and result in new file s4 of seqno range [2, 5]
- compact s1, s2, s3 and result in new file s5 of seqno range [1, 4]
- compact s4 and result in new file s6 of seqno range [2] due to single delete
- By the last step, we have file ordering by largest seqno (">" means "newer") : s5 > s6 while s6 contains a newer version of the k1's value (i.e, k1@2) than s5, which is a real reordering corruption. While this can be caught by `force_consistency_check=true`, there isn't a good way to prevent this from happening if ordering by `largest_seqno`
Therefore, we are redesigning the sorting criteria of L0 files and avoid above inconvenience. Credit to ajkr , we now introduce `epoch_num` which describes the order of a file being flushed or ingested/imported (compaction output file will has the minimum `epoch_num` among input files'). This will avoid the above inconvenience in the following ways:
- In the first case above, there will no longer be overlap seqno range check in `force_consistency_check=true` but `epoch_number` ordering check. This will result in file ordering s1 < s2 < s4 (pre-compaction) and s3 < s4 (post-compaction) which won't trigger false positive corruption. See test class `DBCompactionTestL0FilesMisorderCorruption*` for more.
- In the second case above, this will result in file ordering s1 < s2 < s3 < s4 (pre-compacting s1, s2, s3), s5 < s4 (post-compacting s1, s2, s3), s5 < s6 (post-compacting s4), which are correct file ordering without causing any corruption.
**Summary:**
- Introduce `epoch_number` stored per `ColumnFamilyData` and sort CF's L0 files by their assigned `epoch_number` instead of `largest_seqno`.
- `epoch_number` is increased and assigned upon `VersionEdit::AddFile()` for flush (or similarly for WriteLevel0TableForRecovery) and file ingestion (except for allow_behind_true, which will always get assigned as the `kReservedEpochNumberForFileIngestedBehind`)
- Compaction output file is assigned with the minimum `epoch_number` among input files'
- Refit level: reuse refitted file's epoch_number
- Other paths needing `epoch_number` treatment:
- Import column families: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`
- Repair: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`.
- Assigning new epoch_number to a file and adding this file to LSM tree should be atomic. This is guaranteed by us assigning epoch_number right upon `VersionEdit::AddFile()` where this version edit will be apply to LSM tree shape right after by holding the db mutex (e.g, flush, file ingestion, import column family) or by there is only 1 ongoing edit per CF (e.g, WriteLevel0TableForRecovery, Repair).
- Assigning the minimum input epoch number to compaction output file won't misorder L0 files (even through later `Refit(target_level=0)`). It's due to for every key "k" in the input range, a legit compaction will cover a continuous epoch number range of that key. As long as we assign the key "k" the minimum input epoch number, it won't become newer or older than the versions of this key that aren't included in this compaction hence no misorder.
- Persist `epoch_number` of each file in manifest and recover `epoch_number` on db recovery
- Backward compatibility with old db without `epoch_number` support is guaranteed by assigning `epoch_number` to recovered files by `NewestFirstBySeqno` order. See `VersionStorageInfo::RecoverEpochNumbers()` for more
- Forward compatibility with manifest is guaranteed by flexibility of `NewFileCustomTag`
- Replace `force_consistent_check` on L0 with `epoch_number` and remove false positive check like case 1 with `largest_seqno` above
- Due to backward compatibility issue, we might encounter files with missing epoch number at the beginning of db recovery. We will still use old L0 sorting mechanism (`NewestFirstBySeqno`) to check/sort them till we infer their epoch number. See usages of `EpochNumberRequirement`.
- Remove fix https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and their outdated tests to file reordering corruption because such fix can be replaced by this PR.
- Misc:
- update existing tests with `epoch_number` so make check will pass
- update https://github.com/facebook/rocksdb/pull/5958#issue-511150930 tests to verify corruption is fixed using `epoch_number` and cover universal/fifo compaction/CompactRange/CompactFile cases
- assert db_mutex is held for a few places before calling ColumnFamilyData::NewEpochNumber()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10922
Test Plan:
- `make check`
- New unit tests under `db/db_compaction_test.cc`, `db/db_test2.cc`, `db/version_builder_test.cc`, `db/repair_test.cc`
- Updated tests (i.e, `DBCompactionTestL0FilesMisorderCorruption*`) under https://github.com/facebook/rocksdb/pull/5958#issue-511150930
- [Ongoing] Compatibility test: manually run https://github.com/ajkr/rocksdb/commit/36a5686ec012f35a4371e409aa85c404ca1c210d (with file ingestion off for running the `.orig` binary to prevent this bug affecting upgrade/downgrade formality checking) for 1 hour on `simple black/white box`, `cf_consistency/txn/enable_ts with whitebox + test_best_efforts_recovery with blackbox`
- [Ongoing] normal db stress test
- [Ongoing] db stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761
Reviewed By: ajkr
Differential Revision: D41063187
Pulled By: hx235
fbshipit-source-id: 826cb23455de7beaabe2d16c57682a82733a32a9
2 years ago
|
|
|
&start_level_inputs_);
|
|
|
|
}
|
|
|
|
} // namespace
|
|
|
|
|
|
|
|
Compaction* LevelCompactionPicker::PickCompaction(
|
|
|
|
const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
|
|
|
|
const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
|
Sort L0 files by newly introduced epoch_num (#10922)
Summary:
**Context:**
Sorting L0 files by `largest_seqno` has at least two inconvenience:
- File ingestion and compaction involving ingested files can create files of overlapping seqno range with the existing files. `force_consistency_check=true` will catch such overlap seqno range even those harmless overlap.
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n")
- insert k1@1 to memtable m1
- ingest file s1 with k2@2, ingest file s2 with k3@3
- insert k4@4 to m1
- compact files s1, s2 and result in new file s3 of seqno range [2, 3]
- flush m1 and result in new file s4 of seqno range [1, 4]. And `force_consistency_check=true` will think s4 and s3 has file reordering corruption that might cause retuning an old value of k1
- However such caught corruption is a false positive since s1, s2 will not have overlapped keys with k1 or whatever inserted into m1 before ingest file s1 by the requirement of file ingestion (otherwise the m1 will be flushed first before any of the file ingestion completes). Therefore there in fact isn't any file reordering corruption.
- Single delete can decrease a file's largest seqno and ordering by `largest_seqno` can introduce a wrong ordering hence file reordering corruption
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n", Credit to ajkr for this example)
- an existing SST s1 contains only k1@1
- insert k1@2 to memtable m1
- ingest file s2 with k3@3, ingest file s3 with k4@4
- insert single delete k5@5 in m1
- flush m1 and result in new file s4 of seqno range [2, 5]
- compact s1, s2, s3 and result in new file s5 of seqno range [1, 4]
- compact s4 and result in new file s6 of seqno range [2] due to single delete
- By the last step, we have file ordering by largest seqno (">" means "newer") : s5 > s6 while s6 contains a newer version of the k1's value (i.e, k1@2) than s5, which is a real reordering corruption. While this can be caught by `force_consistency_check=true`, there isn't a good way to prevent this from happening if ordering by `largest_seqno`
Therefore, we are redesigning the sorting criteria of L0 files and avoid above inconvenience. Credit to ajkr , we now introduce `epoch_num` which describes the order of a file being flushed or ingested/imported (compaction output file will has the minimum `epoch_num` among input files'). This will avoid the above inconvenience in the following ways:
- In the first case above, there will no longer be overlap seqno range check in `force_consistency_check=true` but `epoch_number` ordering check. This will result in file ordering s1 < s2 < s4 (pre-compaction) and s3 < s4 (post-compaction) which won't trigger false positive corruption. See test class `DBCompactionTestL0FilesMisorderCorruption*` for more.
- In the second case above, this will result in file ordering s1 < s2 < s3 < s4 (pre-compacting s1, s2, s3), s5 < s4 (post-compacting s1, s2, s3), s5 < s6 (post-compacting s4), which are correct file ordering without causing any corruption.
**Summary:**
- Introduce `epoch_number` stored per `ColumnFamilyData` and sort CF's L0 files by their assigned `epoch_number` instead of `largest_seqno`.
- `epoch_number` is increased and assigned upon `VersionEdit::AddFile()` for flush (or similarly for WriteLevel0TableForRecovery) and file ingestion (except for allow_behind_true, which will always get assigned as the `kReservedEpochNumberForFileIngestedBehind`)
- Compaction output file is assigned with the minimum `epoch_number` among input files'
- Refit level: reuse refitted file's epoch_number
- Other paths needing `epoch_number` treatment:
- Import column families: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`
- Repair: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`.
- Assigning new epoch_number to a file and adding this file to LSM tree should be atomic. This is guaranteed by us assigning epoch_number right upon `VersionEdit::AddFile()` where this version edit will be apply to LSM tree shape right after by holding the db mutex (e.g, flush, file ingestion, import column family) or by there is only 1 ongoing edit per CF (e.g, WriteLevel0TableForRecovery, Repair).
- Assigning the minimum input epoch number to compaction output file won't misorder L0 files (even through later `Refit(target_level=0)`). It's due to for every key "k" in the input range, a legit compaction will cover a continuous epoch number range of that key. As long as we assign the key "k" the minimum input epoch number, it won't become newer or older than the versions of this key that aren't included in this compaction hence no misorder.
- Persist `epoch_number` of each file in manifest and recover `epoch_number` on db recovery
- Backward compatibility with old db without `epoch_number` support is guaranteed by assigning `epoch_number` to recovered files by `NewestFirstBySeqno` order. See `VersionStorageInfo::RecoverEpochNumbers()` for more
- Forward compatibility with manifest is guaranteed by flexibility of `NewFileCustomTag`
- Replace `force_consistent_check` on L0 with `epoch_number` and remove false positive check like case 1 with `largest_seqno` above
- Due to backward compatibility issue, we might encounter files with missing epoch number at the beginning of db recovery. We will still use old L0 sorting mechanism (`NewestFirstBySeqno`) to check/sort them till we infer their epoch number. See usages of `EpochNumberRequirement`.
- Remove fix https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and their outdated tests to file reordering corruption because such fix can be replaced by this PR.
- Misc:
- update existing tests with `epoch_number` so make check will pass
- update https://github.com/facebook/rocksdb/pull/5958#issue-511150930 tests to verify corruption is fixed using `epoch_number` and cover universal/fifo compaction/CompactRange/CompactFile cases
- assert db_mutex is held for a few places before calling ColumnFamilyData::NewEpochNumber()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10922
Test Plan:
- `make check`
- New unit tests under `db/db_compaction_test.cc`, `db/db_test2.cc`, `db/version_builder_test.cc`, `db/repair_test.cc`
- Updated tests (i.e, `DBCompactionTestL0FilesMisorderCorruption*`) under https://github.com/facebook/rocksdb/pull/5958#issue-511150930
- [Ongoing] Compatibility test: manually run https://github.com/ajkr/rocksdb/commit/36a5686ec012f35a4371e409aa85c404ca1c210d (with file ingestion off for running the `.orig` binary to prevent this bug affecting upgrade/downgrade formality checking) for 1 hour on `simple black/white box`, `cf_consistency/txn/enable_ts with whitebox + test_best_efforts_recovery with blackbox`
- [Ongoing] normal db stress test
- [Ongoing] db stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761
Reviewed By: ajkr
Differential Revision: D41063187
Pulled By: hx235
fbshipit-source-id: 826cb23455de7beaabe2d16c57682a82733a32a9
2 years ago
|
|
|
LogBuffer* log_buffer) {
|
|
|
|
LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
|
|
|
|
mutable_cf_options, ioptions_,
|
|
|
|
mutable_db_options);
|
|
|
|
return builder.PickCompaction();
|
|
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|