Summary:
Performing unordered writes in rocksdb when unordered_write option is set to true. When enabled the writes to memtable are done without joining any write thread. This offers much higher write throughput since the upcoming writes would not have to wait for the slowest memtable write to finish. The tradeoff is that the writes visible to a snapshot might change over time. If the application cannot tolerate that, it should implement its own mechanisms to work around that. Using TransactionDB with WRITE_PREPARED write policy is one way to achieve that. Doing so increases the max throughput by 2.2x without however compromising the snapshot guarantees.
The patch is prepared based on an original by siying
Existing unit tests are extended to include unordered_write option.
Benchmark Results:
```
TEST_TMPDIR=/dev/shm/ ./db_bench_unordered --benchmarks=fillrandom --threads=32 --num=10000000 -max_write_buffer_number=16 --max_background_jobs=64 --batch_size=8 --writes=3000000 -level0_file_num_compaction_trigger=99999 --level0_slowdown_writes_trigger=99999 --level0_stop_writes_trigger=99999 -enable_pipelined_write=false -disable_auto_compactions --unordered_write=1
```
With WAL
- Vanilla RocksDB: 78.6 MB/s
- WRITER_PREPARED with unordered_write: 177.8 MB/s (2.2x)
- unordered_write: 368.9 MB/s (4.7x with relaxed snapshot guarantees)
Without WAL
- Vanilla RocksDB: 111.3 MB/s
- WRITER_PREPARED with unordered_write: 259.3 MB/s MB/s (2.3x)
- unordered_write: 645.6 MB/s (5.8x with relaxed snapshot guarantees)
- WRITER_PREPARED with unordered_write disable concurrency control: 185.3 MB/s MB/s (2.35x)
Limitations:
- The feature is not yet extended to `max_successive_merges` > 0. The feature is also incompatible with `enable_pipelined_write` = true as well as with `allow_concurrent_memtable_write` = false.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5218
Differential Revision: D15219029
Pulled By: maysamyabandeh
fbshipit-source-id: 38f2abc4af8780148c6128acdba2b3227bc81759
Summary:
Part of compaction cpu goes to processing snapshot list, the larger the list the bigger the overhead. Although the lifetime of most of the snapshots is much shorter than the lifetime of compactions, the compaction conservatively operates on the list of snapshots that it initially obtained. This patch allows the snapshot list to be updated via a callback if the compaction is taking long. This should let the compaction to continue more efficiently with much smaller snapshot list.
For simplicity, to avoid the feature is disabled in two cases: i) When more than one sub-compaction are sharing the same snapshot list, ii) when Range Delete is used in which the range delete aggregator has its own copy of snapshot list.
This fixes the reverted https://github.com/facebook/rocksdb/pull/5099 issue with range deletes.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5278
Differential Revision: D15203291
Pulled By: maysamyabandeh
fbshipit-source-id: fa645611e606aa222c7ce53176dc5bb6f259c258
Summary:
Our daily stress tests are failing after this feature. Reverting temporarily until we figure the reason for test failures.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5269
Differential Revision: D15151285
Pulled By: maysamyabandeh
fbshipit-source-id: e4002b99690a97df30d4b4b58bf0f61e9591bc6e
Summary:
Part of compaction cpu goes to processing snapshot list, the larger the list the bigger the overhead. Although the lifetime of most of the snapshots is much shorter than the lifetime of compactions, the compaction conservatively operates on the list of snapshots that it initially obtained. This patch allows the snapshot list to be updated via a callback if the compaction is taking long. This should let the compaction to continue more efficiently with much smaller snapshot list.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5099
Differential Revision: D15086710
Pulled By: maysamyabandeh
fbshipit-source-id: 7649f56c3b6b2fb334962048150142a3bf9c1a12
Summary: PR https://github.com/facebook/rocksdb/pull/4899 implemented the general framework for RocksDB secondary instances. This PR adds the support for WAL tailing in `OpenAsSecondary`, which means after the `OpenAsSecondary` call, the secondary is now able to see primary's writes that are yet to be flushed. The secondary can see primary's writes in the WAL up to the moment of `OpenAsSecondary` call starts.
Differential Revision: D15059905
Pulled By: miasantreble
fbshipit-source-id: 44f71f548a30b38179a7940165e138f622de1f10
Summary:
Depending on the config, manual compaction (leveled compaction style) does following compactions:
L0->L1
L1->L2
...
Ln-1 -> Ln
Ln -> Ln
The final Ln -> Ln compaction is partly unnecessary as it recompacts all the files that were just generated by the Ln-1 -> Ln. We should avoid recompacting such files. This rule should be applied to Lmax only.
Resolves issue https://github.com/facebook/rocksdb/issues/4995
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5138
Differential Revision: D14940106
Pulled By: miasantreble
fbshipit-source-id: 8d3cf5507a17e76f3333cfd4bac5256d005636e5
Summary:
Right now, two separate pieces of code are used to create WAL files in DBImpl::Open function of db_impl_open.cc and DBImpl::SwitchMemtable function of db_impl_write.cc. This code change simply creates 1 function called DBImpl::CreateWAL in db_impl_open.cc which is used to replace existing WAL creation logic in DBImpl::Open and DBImpl::SwitchMemtable.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5188
Differential Revision: D14942832
Pulled By: vjnadimpalli
fbshipit-source-id: d49230e04c36176015c8c1b422575872f92157fb
Summary:
This PR introduces a new MultiGet() API, with the underlying implementation grouping keys based on SST file and batching lookups in a file. The reason for the new API is twofold - the definition allows callers to allocate storage for status and values on stack instead of std::vector, as well as return values as PinnableSlices in order to avoid copying, and it keeps the original MultiGet() implementation intact while we experiment with batching.
Batching is useful when there is some spatial locality to the keys being queries, as well as larger batch sizes. The main benefits are due to -
1. Fewer function calls, especially to BlockBasedTableReader::MultiGet() and FullFilterBlockReader::KeysMayMatch()
2. Bloom filter cachelines can be prefetched, hiding the cache miss latency
The next step is to optimize the binary searches in the level_storage_info, index blocks and data blocks, since we could reduce the number of key comparisons if the keys are relatively close to each other. The batching optimizations also need to be extended to other formats, such as PlainTable and filter formats. This also needs to be added to db_stress.
Benchmark results from db_bench for various batch size/locality of reference combinations are given below. Locality was simulated by offsetting the keys in a batch by a stride length. Each SST file is about 8.6MB uncompressed and key/value size is 16/100 uncompressed. To focus on the cpu benefit of batching, the runs were single threaded and bound to the same cpu to eliminate interference from other system events. The results show a 10-25% improvement in micros/op from smaller to larger batch sizes (4 - 32).
Batch Sizes
1 | 2 | 4 | 8 | 16 | 32
Random pattern (Stride length 0)
4.158 | 4.109 | 4.026 | 4.05 | 4.1 | 4.074 - Get
4.438 | 4.302 | 4.165 | 4.122 | 4.096 | 4.075 - MultiGet (no batching)
4.461 | 4.256 | 4.277 | 4.11 | 4.182 | 4.14 - MultiGet (w/ batching)
Good locality (Stride length 16)
4.048 | 3.659 | 3.248 | 2.99 | 2.84 | 2.753
4.429 | 3.728 | 3.406 | 3.053 | 2.911 | 2.781
4.452 | 3.45 | 2.833 | 2.451 | 2.233 | 2.135
Good locality (Stride length 256)
4.066 | 3.786 | 3.581 | 3.447 | 3.415 | 3.232
4.406 | 4.005 | 3.644 | 3.49 | 3.381 | 3.268
4.393 | 3.649 | 3.186 | 2.882 | 2.676 | 2.62
Medium locality (Stride length 4096)
4.012 | 3.922 | 3.768 | 3.61 | 3.582 | 3.555
4.364 | 4.057 | 3.791 | 3.65 | 3.57 | 3.465
4.479 | 3.758 | 3.316 | 3.077 | 2.959 | 2.891
dbbench command used (on a DB with 4 levels, 12 million keys)-
TEST_TMPDIR=/dev/shm numactl -C 10 ./db_bench.tmp -use_existing_db=true -benchmarks="readseq,multireadrandom" -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=12000000 -reads=12000000 -duration=90 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5011
Differential Revision: D14348703
Pulled By: anand1976
fbshipit-source-id: 774406dab3776d979c809522a67bedac6c17f84b
Summary:
Expose DB methods to lock and unlock the WAL.
These methods are intended to use by MyRocks in order to obtain WAL
coordinates in consistent way.
Usage scenario is following:
MySQL has performance_schema.log_status which provides information that
enables a backup tool to copy the required log files without locking for
the duration of copy. To populate this table MySQL does following:
1. Lock the binary log. Transactions are not allowed to commit now
2. Save the binary log coordinates
3. Walk through the storage engines and lock writes on each engine. For
InnoDB, redo log is locked. For MyRocks, WAL should be locked.
4. Ask storage engines for their coordinates. InnoDB reports its current
LSN and checkpoint LSN. MyRocks should report active WAL files names
and sizes.
5. Release storage engine's locks
6. Unlock binary log
Backup tool will then use this information to copy InnoDB, RocksDB and
MySQL binary logs up to specified positions to end up with consistent DB
state after restore.
Currently, RocksDB allows to obtain the list of WAL files. Only missing
bit is the method to lock the writes to WAL files.
LockWAL method must flush the WAL in order for the reported size to be
accurate (GetSortedWALFiles is using file system stat call to return the
file size), also, since backup tool is going to copy the WAL, it is
better to be flushed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5146
Differential Revision: D14815447
Pulled By: maysamyabandeh
fbshipit-source-id: eec9535a6025229ed471119f19fe7b3d8ae888a3
Summary:
Following files were run through automatic formatter:
db/db_impl.cc
db/db_impl.h
db/db_impl_compaction_flush.cc
db/db_impl_debug.cc
db/db_impl_files.cc
db/db_impl_readonly.h
db/db_impl_write.cc
db/dbformat.cc
db/dbformat.h
table/block.cc
table/block.h
table/block_based_filter_block.cc
table/block_based_filter_block.h
table/block_based_filter_block_test.cc
table/block_based_table_builder.cc
table/block_based_table_reader.cc
table/block_based_table_reader.h
table/block_builder.cc
table/block_builder.h
table/block_fetcher.cc
table/block_prefix_index.cc
table/block_prefix_index.h
table/block_test.cc
table/format.cc
table/format.h
I could easily run all the files, but I don't want people to feel that
I'm doing it for lines of code changes :)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5114
Differential Revision: D14633040
Pulled By: siying
fbshipit-source-id: 3f346cb53bf21e8c10704400da548dfce1e89a52
Summary:
This PR allows RocksDB to run in single-primary, multi-secondary process mode.
The writer is a regular RocksDB (e.g. an `DBImpl`) instance playing the role of a primary.
Multiple `DBImplSecondary` processes (secondaries) share the same set of SST files, MANIFEST, WAL files with the primary. Secondaries tail the MANIFEST of the primary and apply updates to their own in-memory state of the file system, e.g. `VersionStorageInfo`.
This PR has several components:
1. (Originally in #4745). Add a `PathNotFound` subcode to `IOError` to denote the failure when a secondary tries to open a file which has been deleted by the primary.
2. (Similar to #4602). Add `FragmentBufferedReader` to handle partially-read, trailing record at the end of a log from where future read can continue.
3. (Originally in #4710 and #4820). Add implementation of the secondary, i.e. `DBImplSecondary`.
3.1 Tail the primary's MANIFEST during recovery.
3.2 Tail the primary's MANIFEST during normal processing by calling `ReadAndApply`.
3.3 Tailing WAL will be in a future PR.
4. Add an example in 'examples/multi_processes_example.cc' to demonstrate the usage of secondary RocksDB instance in a multi-process setting. Instructions to run the example can be found at the beginning of the source code.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4899
Differential Revision: D14510945
Pulled By: riversand963
fbshipit-source-id: 4ac1c5693e6012ad23f7b4b42d3c374fecbe8886
Summary:
With https://github.com/facebook/rocksdb/pull/3009 we go through every CF
to check whether a bottommost compaction is needed to be triggered. This is done
within DB mutex. What we do within DB mutex may heavily influece the write throughput
we can achieve, so we always want to minimize work there.
Here we try to avoid this for-loop by first check a global threshold. In most of
the time, the CF loop can be avoided.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5090
Differential Revision: D14582684
Pulled By: siying
fbshipit-source-id: 968f6d9bb6affe1a5ebc4910b418300b076f166f
Summary:
This PR adds public `GetStatsHistory` API to retrieve stats history in the form of an std map. The key of the map is the timestamp in microseconds when the stats snapshot is taken, the value is another std map from stats name to stats value (stored in std string). Two DBOptions are introduced: `stats_persist_period_sec` (default 10 minutes) controls the intervals between two snapshots are taken; `max_stats_history_count` (default 10) controls the max number of history snapshots to keep in memory. RocksDB will stop collecting stats snapshots if `stats_persist_period_sec` is set to 0.
(This PR is the in-memory part of https://github.com/facebook/rocksdb/pull/4535)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4748
Differential Revision: D13961471
Pulled By: miasantreble
fbshipit-source-id: ac836d401ecb84ea92216bf9966f969dedf4ad04
Summary:
Make file ingestion atomic.
as title.
Ingesting external SST files into multiple column families should be atomic. If
a crash occurs and db reopens, either all column families have successfully
ingested the files before the crash, or non of the ingestions have any effect
on the state of the db.
Also add unit tests for atomic ingestion.
Note that the unit test here does not cover the case of incomplete atomic group
in the MANIFEST, which is covered in VersionSetTest already.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4895
Differential Revision: D13718245
Pulled By: riversand963
fbshipit-source-id: 7df97cc483af73ad44dd6993008f99b083852198
Summary:
FlushMemTablesToOutputFiles calls FlushMemTableToOutputFile for each column family. The patch moves the take-snapshot logic to outside FlushMemTableToOutputFile so that it does it once for all the flushes. This also addresses a deadlock issue for resetting the managed snapshot of job_snapshot in the 2nd call to FlushMemTableToOutputFile.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4934
Differential Revision: D13900747
Pulled By: maysamyabandeh
fbshipit-source-id: f3cd650c5fff24cf95c1aaf8a10c149d42bf042c
Summary:
With WritePrepared transaction, flush/compaction can contain uncommitted keys, and those keys can get committed during compaction. If a snapshot is taken before the key is committed, it should not see the key. On the other hand, compaction grab the list of snapshots at its beginning, and only consider those snapshots to dedup keys. Consider the case:
```
seq = 1: put "foo" = "bar"
seq = 2: transaction T: delete "foo", prepare
seq = 3: compaction start
seq = 4: take snapshot S
seq = 5: transaction T: commit.
...
seq = N: compaction iterator reached key "foo".
```
When compaction start, the list of snapshot is empty. Compaction doesn't take snapshot S into account. When it reached "foo", transaction T is committed. Compaction may think the value "foo=bar" is not visible by any snapshot (which is wrong), and compact the value out.
The fix is to explicitly take a snapshot before compaction grabbing the list of snapshots. Compaction will then has to keep keys visible to this snapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4883
Differential Revision: D13668775
Pulled By: maysamyabandeh
fbshipit-source-id: 1cab9615f94b7d3e8522cc3d44c3a14c7d4720e4
Summary:
The AdvanceMaxEvictedSeq algorithm assumes that new snapshots always have sequence number larger than the last max_evicted_seq_. To enforce this assumption we make two changes:
i) max is not advanced beyond the last published seq, with the exception that the evicted commit entry itself is not published yet, which is quite rare.
ii) When obtaining the snapshot if the max_evicted_seq_ is not published yet, commit a dummy entry so that it waits for it to be published and also increased the latest published seq by one above the max.
To test these non-realistic corner cases we create a commit cache with size 1 so that every single commit results into eviction.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4886
Differential Revision: D13685270
Pulled By: maysamyabandeh
fbshipit-source-id: 5461bc09c2a9b75798bfcb9853a256c81cdac0b0
Summary:
as titled.
Since different bg flush threads can flush different sets of column families
(due to column family creation and drop), we decide not to let one thread
perform atomic flush result installation for other threads. Bg flush threads
will install their atomic flush results sequentially to MANIFEST, using
a conditional variable, i.e. atomic_flush_install_cv_ to coordinate.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4791
Differential Revision: D13498930
Pulled By: riversand963
fbshipit-source-id: dd7482fc41f4bd22dad1e1ef7d4764ef424688d7
Summary:
The `flush_reason` parameter in `DBImpl::InstallSuperVersionAndScheduleWork` is
not used. Remove it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4816
Differential Revision: D13543218
Pulled By: riversand963
fbshipit-source-id: 8fc75d49462ce092e85aef0fe0c50936140db153
Summary:
1. Remove unused API SubtractCompactionTask().
2. Assert outstanding tasks drop to zero in ConcurrentTaskLimiterImpl destructor.
3. Remove GetOutstandingTask() check from manual compaction test, as TEST_WaitForCompact() doesn't synced with 'delete prepicked_compaction' in DBImpl::BGWorkCompaction(), which may make the test flaky.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4795
Differential Revision: D13542183
Pulled By: siying
fbshipit-source-id: 5eb2a47e62efe4126937149aa0df6e243ebefc33
Summary:
Now that v2 is fully functional, the v1 aggregator is removed.
The v2 aggregator has been renamed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4778
Differential Revision: D13495930
Pulled By: abhimadan
fbshipit-source-id: 9d69500a60a283e79b6c4fa938fc68a8aa4d40d6
Summary:
The PR is targeting to resolve the issue of:
https://github.com/facebook/rocksdb/issues/3972#issue-330771918
We have a rocksdb created with leveled-compaction with multiple column families (CFs), some of CFs are using HDD to store big and less frequently accessed data and others are using SSD.
When there are continuously write traffics going on to all CFs, the compaction thread pool is mostly occupied by those slow HDD compactions, which blocks fully utilize SSD bandwidth.
Since atomic write and transaction is needed across CFs, so splitting it to multiple rocksdb instance is not an option for us.
With the compaction thread control, we got 30%+ HDD write throughput gain, and also a lot smooth SSD write since less write stall happening.
ConcurrentTaskLimiter can be shared with multi-CFs across rocksdb instances, so the feature does not only work for multi-CFs scenarios, but also for multi-rocksdbs scenarios, who need disk IO resource control per tenant.
The usage is straight forward:
e.g.:
//
// Enable compaction thread limiter thru ColumnFamilyOptions
//
std::shared_ptr<ConcurrentTaskLimiter> ctl(NewConcurrentTaskLimiter("foo_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = ctl;
...
//
// Compaction thread limiter can be tuned or disabled on-the-fly
//
ctl->SetMaxOutstandingTask(12); // enlarge to 12 tasks
...
ctl->ResetMaxOutstandingTask(); // disable (bypass) thread limiter
ctl->SetMaxOutstandingTask(-1); // Same as above
...
ctl->SetMaxOutstandingTask(0); // full throttle (0 task)
//
// Sharing compaction thread limiter among CFs (to resolve multiple storage perf issue)
//
std::shared_ptr<ConcurrentTaskLimiter> ctl_ssd(NewConcurrentTaskLimiter("ssd_limiter", 8));
std::shared_ptr<ConcurrentTaskLimiter> ctl_hdd(NewConcurrentTaskLimiter("hdd_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt_ssd1(options);
ColumnFamilyOptions cf_opt_ssd2(options);
ColumnFamilyOptions cf_opt_hdd1(options);
ColumnFamilyOptions cf_opt_hdd2(options);
ColumnFamilyOptions cf_opt_hdd3(options);
// SSD CFs
cf_opt_ssd1.compaction_thread_limiter = ctl_ssd;
cf_opt_ssd2.compaction_thread_limiter = ctl_ssd;
// HDD CFs
cf_opt_hdd1.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd2.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd3.compaction_thread_limiter = ctl_hdd;
...
//
// The limiter is disabled by default (or set to nullptr explicitly)
//
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = nullptr;
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4332
Differential Revision: D13226590
Pulled By: siying
fbshipit-source-id: 14307aec55b8bd59c8223d04aa6db3c03d1b0c1d
Summary:
Removed `one_time_use` flag, which removed the need for some
tests, and changed all `NewRangeTombstoneIterator` methods to return
`FragmentedRangeTombstoneIterators`.
These changes also led to removing `RangeDelAggregatorV2::AddUnfragmentedTombstones`
and one of the `MemTableListVersion::AddRangeTombstoneIterators` methods.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4692
Differential Revision: D13106570
Pulled By: abhimadan
fbshipit-source-id: cbab5432d7fc2d9cdfd8d9d40361a1bffaa8f845
Summary:
The old RangeDelAggregator did expensive pre-processing work
to create a collapsed, binary-searchable representation of range
tombstones. With FragmentedRangeTombstoneIterator, much of this work is
now unnecessary. RangeDelAggregatorV2 takes advantage of this by seeking
in each iterator to find a covering tombstone in ShouldDelete, while
doing minimal work in AddTombstones. The old RangeDelAggregator is still
used during flush/compaction for now, though RangeDelAggregatorV2 will
support those uses in a future PR.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4649
Differential Revision: D13146964
Pulled By: abhimadan
fbshipit-source-id: be29a4c020fc440500c137216fcc1cf529571eb3
Summary:
In the past, both `DBImpl::atomic_flush_` and
`DBImpl::immutable_db_options_.atomic_flush` exist. However, we fail to set
`immutable_db_options_.atomic_flush`, but use `DBImpl::atomic_flush_` which is
set correctly. This does not lead to incorrect behavior, but is a duplicate of
information.
Since `immutable_db_options_` is always there and has `atomic_flush`, we should
use it as source of truth and remove `DBImpl::atomic_flush_`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4631
Differential Revision: D12928371
Pulled By: riversand963
fbshipit-source-id: f85a811959d3828aad4a3a1b05f71facf19c636d
Summary:
Ran the following commands to recursively change all the files under RocksDB:
```
find . -type f -name "*.cc" -exec sed -i 's/ unique_ptr/ std::unique_ptr/g' {} +
find . -type f -name "*.cc" -exec sed -i 's/<unique_ptr/<std::unique_ptr/g' {} +
find . -type f -name "*.cc" -exec sed -i 's/ shared_ptr/ std::shared_ptr/g' {} +
find . -type f -name "*.cc" -exec sed -i 's/<shared_ptr/<std::shared_ptr/g' {} +
```
Running `make format` updated some formatting on the files touched.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4638
Differential Revision: D12934992
Pulled By: sagar0
fbshipit-source-id: 45a15d23c230cdd64c08f9c0243e5183934338a8
Summary:
This property can help debug why SST files aren't being deleted. Previously we only had the property "rocksdb.is-file-deletions-enabled". However, even when that returned true, obsolete SSTs may still not be deleted due to the coarse-grained mechanism we use to prevent newly created SSTs from being accidentally deleted. That coarse-grained mechanism uses a lower bound file number for SSTs that should not be deleted, and this property exposes that lower bound.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4618
Differential Revision: D12898179
Pulled By: ajkr
fbshipit-source-id: fe68acc041ddbcc9276bbd48976524d95aafc776
Summary:
Leverage existing `FlushJob` to implement atomic flush of multiple column families.
This PR depends on other PRs and is a subset of #3752 . This PR itself is not sufficient in fulfilling atomic flush.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4262
Differential Revision: D9283109
Pulled By: riversand963
fbshipit-source-id: 65401f913e4160b0a61c0be6cd02adc15dad28ed
Summary:
fix#4288
Add `OnCompactionBegin` support to `rocksdb::EventListener`.
Currently, we only have these three callbacks:
- OnFlushBegin
- OnFlushCompleted
- OnCompactionCompleted
As paolococchi requested in #4288 , and ajkr agreed, we should also support `OnCompactionBegin`.
This PR is a try to implement the support of `OnCompactionBegin`.
Hope it is useful to you.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4431
Differential Revision: D10055515
Pulled By: yiwu-arbug
fbshipit-source-id: 39c0f95f8e9ff1c7ca3a10787502a17f258d2334
Summary:
There is a bug when the write queue leader is blocked on a write
delay/stop, and the queue has writers with WriteOptions::no_slowdown set
to true. They are not woken up until the write stall is cleared.
The fix introduces a dummy writer inserted at the tail to indicate a
write stall and prevent further inserts into the queue, and a condition
variable that writers who can tolerate slowdown wait on before adding
themselves to the queue. The leader calls WriteThread::BeginWriteStall()
to add the dummy writer and then walk the queue to fail any writers with
no_slowdown set. Once the stall clears, the leader calls
WriteThread::EndWriteStall() to remove the dummy writer and signal the
condition variable.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4475
Differential Revision: D10285827
Pulled By: anand1976
fbshipit-source-id: 747465e5e7f07a829b1fb0bc1afcd7b93f4ab1a9
Summary:
Currently statistics are supposed to be dumped to info log at intervals of `options.stats_dump_period_sec`. However the implementation choice was to bind it with compaction thread, meaning if the database has been serving very light traffic, the stats may not get dumped at all.
We decided to separate stats dumping into a new timed thread using `TimerQueue`, which is already used in blob_db. This will allow us schedule new timed tasks with more deterministic behavior.
Tested with db_bench using `--stats_dump_period_sec=20` in command line:
> LOG:2018/09/17-14:07:45.575025 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:05.643286 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:25.691325 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG:2018/09/17-14:08:45.740989 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
LOG content:
> 2018/09/17-14:07:45.575025 7fe99fbfe700 [WARN] [db/db_impl.cc:605] ------- DUMPING STATS -------
2018/09/17-14:07:45.575080 7fe99fbfe700 [WARN] [db/db_impl.cc:606]
** DB Stats **
Uptime(secs): 20.0 total, 20.0 interval
Cumulative writes: 4447K writes, 4447K keys, 4447K commit groups, 1.0 writes per commit group, ingest: 5.57 GB, 285.01 MB/s
Cumulative WAL: 4447K writes, 0 syncs, 4447638.00 writes per sync, written: 5.57 GB, 285.01 MB/s
Cumulative stall: 00:00:0.012 H:M:S, 0.1 percent
Interval writes: 4447K writes, 4447K keys, 4447K commit groups, 1.0 writes per commit group, ingest: 5700.71 MB, 285.01 MB/s
Interval WAL: 4447K writes, 0 syncs, 4447638.00 writes per sync, written: 5.57 MB, 285.01 MB/s
Interval stall: 00:00:0.012 H:M:S, 0.1 percent
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4382
Differential Revision: D9933051
Pulled By: miasantreble
fbshipit-source-id: 6d12bb1e4977674eea4bf2d2ac6d486b814bb2fa
Summary:
- Fix DBImpl API race condition
The timeline of execution flow is as follow:
```
timeline user_thread1 user_thread2
t1 | cfh = GetColumnFamilyHandleUnlocked(0)
t2 | id1 = cfh->GetID()
t3 | GetColumnFamilyHandleUnlocked(1)
t4 | id2 = cfh->GetID()
V
```
The original implementation return a pointer to a stateful variable, so that the return `ColumnFamilyHandle` will be changed when another thread calls `GetColumnFamilyHandleUnlocked` with different `column family id`
- Expose ColumnFamily ID to compaction event listener
- Fix the return status of `DBImpl::GetLatestSequenceForKey`
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4391
Differential Revision: D10221243
Pulled By: yiwu-arbug
fbshipit-source-id: dec60ee9ff0c8261a2f2413a8506ec1063991993
Summary:
Improve log handling when avoid_flush_during_recovery=true.
1. restore total_log_size_ after recovery, by summing up existing log sizes. Fixes#4253.
2. truncate the last existing log, since this log can contain preallocated space and it will be a waste to keep the space. It avoids a crash loop of user application cause a lot of log with non-trivial size being created and ultimately take up all disk space.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4405
Differential Revision: D9953933
Pulled By: yiwu-arbug
fbshipit-source-id: 967780fee8acec7f358b6eb65190fb4684f82e56
Summary:
1. Add override keyword to overridden virtual functions in EventListener
2. Fix a memory corruption that can happen during DB shutdown when in
read-only mode due to a background write error
3. Fix uninitialized buffers in error_handler_test.cc that cause
valgrind to complain
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4375
Differential Revision: D9875779
Pulled By: anand1976
fbshipit-source-id: 022ede1edc01a9f7e21ecf4c61ef7d46545d0640
Summary:
This commit implements automatic recovery from a Status::NoSpace() error
during background operations such as write callback, flush and
compaction. The broad design is as follows -
1. Compaction errors are treated as soft errors and don't put the
database in read-only mode. A compaction is delayed until enough free
disk space is available to accomodate the compaction outputs, which is
estimated based on the input size. This means that users can continue to
write, and we rely on the WriteController to delay or stop writes if the
compaction debt becomes too high due to persistent low disk space
condition
2. Errors during write callback and flush are treated as hard errors,
i.e the database is put in read-only mode and goes back to read-write
only fater certain recovery actions are taken.
3. Both types of recovery rely on the SstFileManagerImpl to poll for
sufficient disk space. We assume that there is a 1-1 mapping between an
SFM and the underlying OS storage container. For cases where multiple
DBs are hosted on a single storage container, the user is expected to
allocate a single SFM instance and use the same one for all the DBs. If
no SFM is specified by the user, DBImpl::Open() will allocate one, but
this will be one per DB and each DB will recover independently. The
recovery implemented by SFM is as follows -
a) On the first occurance of an out of space error during compaction,
subsequent
compactions will be delayed until the disk free space check indicates
enough available space. The required space is computed as the sum of
input sizes.
b) The free space check requirement will be removed once the amount of
free space is greater than the size reserved by in progress
compactions when the first error occured
c) If the out of space error is a hard error, a background thread in
SFM will poll for sufficient headroom before triggering the recovery
of the database and putting it in write-only mode. The headroom is
calculated as the sum of the write_buffer_size of all the DB instances
associated with the SFM
4. EventListener callbacks will be called at the start and completion of
automatic recovery. Users can disable the auto recov ery in the start
callback, and later initiate it manually by calling DB::Resume()
Todo:
1. More extensive testing
2. Add disk full condition to db_stress (follow-on PR)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4164
Differential Revision: D9846378
Pulled By: anand1976
fbshipit-source-id: 80ea875dbd7f00205e19c82215ff6e37da10da4a
Summary:
Basically at the moment it seems it's possible to cause write stall by calling flush (either manually vis DB::Flush(), or from Backup Engine directly calling FlushMemTable() while background flush may be already happening.
One of the ways to fix it is that in DBImpl::CompactRange() we already check for possible stall and delay flush if needed before we actually proceed to call FlushMemTable(). We can simply move this delay logic to separate method and call it from FlushMemTable.
This is draft patch, for first look; need to check tests/update SyncPoints and most certainly would need to add allow_write_stall method to FlushOptions().
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4297
Differential Revision: D9420705
Pulled By: mikhail-antonov
fbshipit-source-id: f81d206b55e1d7b39e4dc64242fdfbceeea03fcc
Summary:
RocksDB currently queues individual column family for flushing. This is not sufficient to support the needs of some applications that want to enforce order/dependency between column families, given that multiple foreground and background activities can trigger flushing in RocksDB.
This PR aims to address this limitation. Each flush request is described as a `FlushRequest` that can contain multiple column families. A background flushing thread pops one flush request from the queue at a time and processes it.
This PR does not enable atomic_flush yet, but is a subset of [PR 3752](https://github.com/facebook/rocksdb/pull/3752).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3952
Differential Revision: D8529933
Pulled By: riversand963
fbshipit-source-id: 78908a21e389a3a3f7de2a79bae0cd13af5f3539
Summary:
We want to sample the file I/O issued by RocksDB and report the function calls. This requires us to include the file paths otherwise it's hard to tell what has been going on.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4039
Differential Revision: D8670178
Pulled By: riversand963
fbshipit-source-id: 97ee806d1c583a2983e28e213ee764dc6ac28f7a
Summary:
In the current trace_and replay, Get an WriteBatch are traced. This pull request track down the Seek() and SeekForPrev() to the trace file. <target_key, timestamp, column_family_id> are write to the file.
Replay of Iterator is not supported in the current implementation.
Tested with trace_analyzer.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4228
Differential Revision: D9201381
Pulled By: zhichao-cao
fbshipit-source-id: 6f9cc9cb3c20260af741bee065ec35c5c96354ab
Summary:
A framework for tracing and replaying RocksDB operations.
A binary trace file is created by capturing the DB operations, and it can be replayed back at the same rate using db_bench.
- Column-families are supported
- Multi-threaded tracing is supported.
- TraceReader and TraceWriter are exposed to the user, so that tracing to various destinations can be enabled (say, to other messaging/logging services). By default, a FileTraceReader and FileTraceWriter are implemented to capture to a file and replay from it.
- This is not yet ideal to be enabled in production due to large performance overhead, but it can be safely tried out in a shadow setup, say, for analyzing RocksDB operations.
Currently supported DB operations:
- Writes:
-- Put
-- Merge
-- Delete
-- SingleDelete
-- DeleteRange
-- Write
- Reads:
-- Get (point lookups)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3837
Differential Revision: D7974837
Pulled By: sagar0
fbshipit-source-id: 8ec65aaf336504bc1f6ed0feae67f6ed5ef97a72
Summary:
This adds support for writing unprepared batches based on size defined in `TransactionOptions::max_write_batch_size`. This is done by overriding methods that modify data (Put/Delete/SingleDelete/Merge) and checking first if write batch size has exceeded threshold. If so, the write batch is written to DB as an unprepared batch.
Support for Commit/Rollback for unprepared batch is added as well. This has been done by simply extending the WritePrepared Commit/Rollback logic to take care of all unprep_seq numbers either when updating prepare heap, or adding to commit map. For updating the commit map, this logic exists inside `WriteUnpreparedCommitEntryPreReleaseCallback`.
A test change was also made to have transactions unregister themselves when committing without prepare. This is because with write unprepared, there may be unprepared entries (which act similarly to prepared entries) already when a commit is done without prepare.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4104
Differential Revision: D8785717
Pulled By: lth
fbshipit-source-id: c02006e281ec1ce00f628e2a7beec0ee73096a91
Summary:
This adds support for recovering WriteUnprepared transactions through the following changes:
- The information in `RecoveredTransaction` is extended so that it can reference multiple batches.
- `MarkBeginPrepare` is extended with a bool indicating whether it is an unprepared begin, and this is passed down to `InsertRecoveredTransaction` to indicate whether the current transaction is prepared or not.
- `WriteUnpreparedTxnDB::Initialize` is overridden so that it will rollback unprepared transactions from the recovered transactions. This can be done without updating the prepare heap/commit map, because this is before the DB has finished initializing, and after writing the rollback batch, those data structures should not contain information about the rolled back transaction anyway.
Commit/Rollback of live transactions is still unimplemented and will come later.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4078
Differential Revision: D8703382
Pulled By: lth
fbshipit-source-id: 7e0aada6c23bd39299f1f20d6c060492e0e6b60a
Summary:
This adds a new WAL marker of type kTypeBeginUnprepareXID.
Also, DBImpl now contains a field called batch_per_txn (meaning one WriteBatch per transaction, or possibly multiple WriteBatches). This would also indicate that this DB is using WriteUnprepared policy.
Recovery code would be able to make use of this extra field on DBImpl in a separate diff. For now, it is just used to determine whether the WAL is compatible or not.
Closes https://github.com/facebook/rocksdb/pull/4069
Differential Revision: D8675099
Pulled By: lth
fbshipit-source-id: ca27cae1738e46d65f2bb92860fc759deb874749
Summary:
Currently, if RocksDB encounters errors during a write operation (user requested or BG operations), it sets DBImpl::bg_error_ and fails subsequent writes. This PR allows the DB to be resumed for certain classes of errors. It consists of 3 parts -
1. Introduce Status::Severity in rocksdb::Status to indicate whether a given error can be recovered from or not
2. Refactor the error handling code so that setting bg_error_ and deciding on severity is in one place
3. Provide an API for the user to clear the error and resume the DB instance
This whole change is broken up into multiple PRs. Initially, we only allow clearing the error for Status::NoSpace() errors during background flush/compaction. Subsequent PRs will expand this to include more errors and foreground operations such as Put(), and implement a polling mechanism for out-of-space errors.
Closes https://github.com/facebook/rocksdb/pull/3997
Differential Revision: D8653831
Pulled By: anand1976
fbshipit-source-id: 6dc835c76122443a7668497c0226b4f072bc6afd
