Summary:
This PR adds a missing piece for the UDT in memtable only feature, which is to automatically increase `full_history_ts_low` when flush happens during recovery.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11774
Test Plan:
Added unit test
make all check
Reviewed By: ltamasi
Differential Revision: D48799109
Pulled By: jowlyzhang
fbshipit-source-id: fd681ed66d9d40904ca2c919b2618eb692686035
Summary:
Add support to allow enabling / disabling user-defined timestamps feature for an existing column family in combination with the in-Memtable only feature.
To do this, this PR includes:
1) Log the `persist_user_defined_timestamps` option per column family in Manifest to facilitate detecting an attempt to enable / disable UDT. This entry is enforced to be logged in the same VersionEdit as the user comparator name entry.
2) User-defined timestamps related options are validated when re-opening a column family, including user comparator name and the `persist_user_defined_timestamps` flag. These type of settings and settings change are considered valid:
a) no user comparator change and no effective `persist_user_defined_timestamp` flag change.
b) switch user comparator to enable UDT provided the immediately effective `persist_user_defined_timestamps` flag
is false.
c) switch user comparator to disable UDT provided that the before-change `persist_user_defined_timestamps` is
already false.
3) when an attempt to enable UDT is detected, we mark all its existing SST files as "having no UDT" by marking its `FileMetaData.user_defined_timestamps_persisted` flag to false and handle their file boundaries `FileMetaData.smallest`, `FileMetaData.largest` by padding a min timestamp.
4) while enabling / disabling UDT feature, timestamp size inconsistency in existing WAL logs are handled to make it compatible with the running user comparator.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11623
Test Plan:
```
make all check
./db_with_timestamp_basic_test --gtest-filter="*EnableDisableUDT*"
./db_wal_test --gtest_filter="*EnableDisableUDT*"
```
Reviewed By: ltamasi
Differential Revision: D47636862
Pulled By: jowlyzhang
fbshipit-source-id: dcd19f67292da3c3cc9584c09ad00331c9ab9322
Summary:
Make flush respect the cutoff timestamp `full_history_ts_low` as much as possible for the user-defined timestamps in Memtables only feature. We achieve this by not proceeding with the actual flushing but instead reschedule the same `FlushRequest` so a follow up flush job can continue with the check after some interval.
This approach doesn't work well for atomic flush, so this feature currently is not supported in combination with atomic flush. Furthermore, this approach also requires a customized method to get the next immediately bigger user-defined timestamp. So currently it's limited to comparator that use uint64_t as the user-defined timestamp format. This support can be extended when we add such a customized method to `AdvancedColumnFamilyOptions`.
For non atomic flush request, at any single time, a column family can only have as many as one FlushRequest for it in the `flush_queue_`. There is deduplication done at `FlushRequest` enqueueing(`SchedulePendingFlush`) and dequeueing time (`PopFirstFromFlushQueue`). We hold the db mutex between when a `FlushRequest` is popped from the queue and the same FlushRequest get rescheduled, so no other `FlushRequest` with a higher `max_memtable_id` can be added to the `flush_queue_` blocking us from re-enqueueing the same `FlushRequest`.
Flush is continued nevertheless if there is risk of entering write stall mode had the flush being postponed, e.g. due to accumulation of write buffers, exceeding the `max_write_buffer_number` setting. When this happens, the newest user-defined timestamp in the involved Memtables need to be tracked and we use it to increase the `full_history_ts_low`, which is an inclusive cutoff timestamp for which RocksDB promises to keep all user-defined timestamps equal to and newer than it.
Tet plan:
```
./column_family_test --gtest_filter="*RetainUDT*"
./memtable_list_test --gtest_filter="*WithTimestamp*"
./flush_job_test --gtest_filter="*WithTimestamp*"
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11599
Reviewed By: ajkr
Differential Revision: D47561586
Pulled By: jowlyzhang
fbshipit-source-id: 9400445f983dd6eac489e9dd0fb5d9b99637fe89
Summary:
Thanks pdillinger for pointing out this test hole. The test `DBWALTestWithTimestamp.Recover` that is intended to test recovery from WAL including user-defined timestamps doesn't achieve its promised coverage. Specifically, after https://github.com/facebook/rocksdb/issues/11557, timestamps will be removed during flush, and RocksDB by default flush memtables during recovery with `avoid_flush_during_recovery` defaults to false. This test didn't fail even if all the timestamps are quickly lost due to the default flush behavior.
This PR renamed test `Recover` to `RecoverAndNoFlush`, and updated it to verify timestamps are successfully recovered from WAL with some time-travel reads. `avoid_flush_during_recovery` is set to true to help do this verification.
On the other hand, for test `DBWALTestWithTimestamp.RecoverAndFlush`, since flush on reopen is DB's default behavior. Setting the flags `max_write_buffer` and `arena_block_size` are not really the factors that enforces the flush, so these flags are removed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11577
Test Plan: ./db_wal_test
Reviewed By: pdillinger
Differential Revision: D47142892
Pulled By: jowlyzhang
fbshipit-source-id: 9465e278806faa5885b541b4e32d99e698edef7d
Summary:
Logically strip the user-defined timestamp when L0 files are created during flush when `AdvancedColumnFamilyOptions.persist_user_defined_timestamps` is false. Logically stripping timestamp here means replacing the original user-defined timestamp with a mininum timestamp, which for now is hard coded to be all zeros bytes.
While working on this, I caught a missing piece on the `BlockBuilder` level for this feature. The current quick path `std::min(buffer_size, last_key_size)` needs a bit tweaking to work for this feature. When user-defined timestamp is stripped during block building, on writing first entry or right after resetting, `buffer` is empty and `buffer_size` is zero as usual. However, in follow-up writes, depending on the size of the stripped user-defined timestamp, and the size of the value, what's in `buffer` can sometimes be smaller than `last_key_size`, leading `std::min(buffer_size, last_key_size)` to truncate the `last_key`. Previous test doesn't caught the bug because in those tests, the size of the stripped user-defined timestamps bytes is smaller than the length of the value. In order to avoid the conditional operation, this PR changed the original trivial `std::min` operation into an arithmetic operation. Since this is a change in a hot and performance critical path, I did the following benchmark to check no observable regression is introduced.
```TEST_TMPDIR=/dev/shm/rocksdb1 ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=50000000```
Compiled with DEBUG_LEVEL=0
Test vs. control runs simulaneous for better accuracy, units = ops/sec
PR vs base:
Round 1: 350652 vs 349055
Round 2: 365733 vs 364308
Round 3: 355681 vs 354475
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11557
Test Plan:
New timestamp specific test added or existing tests augmented, both are parameterized with `UserDefinedTimestampTestMode`:
`UserDefinedTimestampTestMode::kNormal` -> UDT feature enabled, write / read with min timestamp
`UserDefinedTimestampTestMode::kStripUserDefinedTimestamps` -> UDT feature enabled, write / read with min timestamp, set Options.persist_user_defined_timestamps to false.
```
make all check
./db_wal_test --gtest_filter="*WithTimestamp*"
./flush_job_test --gtest_filter="*WithTimestamp*"
./repair_test --gtest_filter="*WithTimestamp*"
./block_based_table_reader_test
```
Reviewed By: pdillinger
Differential Revision: D47027664
Pulled By: jowlyzhang
fbshipit-source-id: e729193b6334dfc63aaa736d684d907a022571f5
Summary:
Calling `Flush` (even with `wait==true`) does not guarantee that obsolete WAL files are physically deleted before the call returns. The patch attempts to fix the resulting flakiness by using `SyncPoint`s to make sure `PurgeObsoleteFiles` finishes before checking for WAL deletions.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11537
Test Plan:
```
gtest-parallel --repeat=1000 ./db_wal_test --gtest_filter="*SkipDeletedWALs*"
```
Reviewed By: pdillinger
Differential Revision: D46736050
Pulled By: ltamasi
fbshipit-source-id: 47a931b7a3a03ef681fbf4adb5a0b223d452703e
Summary:
Start logging the timestamp size record in WAL and use the record during recovery. Currently, user comparator cannot be different from what was used to create a column family, so the timestamp size record is just used to confirm it's consistent with the timestamp size the running user comparator indicates.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11471
Test Plan:
```
make all check
./db_secondary_test
./db_wal_test --gtest_filter="*WithTimestamp*"
./repair_test --gtest_filter="*WithTimestamp*"
```
Reviewed By: ltamasi
Differential Revision: D46236769
Pulled By: jowlyzhang
fbshipit-source-id: f6c60b5c8defdb05021c63df302ccc0be1275ad0
Summary:
When a DB is opened, RocksDB creates an empty WAL file. When the DB is reopened and the WAL is empty, the min log number to keep is not advanced until a memtable flush happens. If a process crashes soon after reopening the DB, its likely that no memtable flush would have happened, which means the empty WAL file is not deleted. In a crash loop scenario, this leads to empty WAL files accumulating. Fix this by ensuring the min log number is advanced if the WAL is empty.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11409
Test Plan: Add a unit test
Reviewed By: ajkr
Differential Revision: D45281685
Pulled By: anand1976
fbshipit-source-id: 0225877c613e65ffb30972a0051db2830105423e
Summary:
The previous API comments for LockWAL didn't provide much about why you might want to use it, and didn't really meet what one would infer its contract was. Also, LockWAL was not in db_stress / crash test. In this change:
* Implement a counting semantics for LockWAL()+UnlockWAL(), so that they can safely be used concurrently across threads or recursively within a thread. This should make the API much less bug-prone and easier to use.
* Make sure no UnlockWAL() is needed after non-OK LockWAL() (to match RocksDB conventions)
* Make UnlockWAL() reliably return non-OK when there's no matching LockWAL() (for debug-ability)
* Clarify API comments on LockWAL(), UnlockWAL(), FlushWAL(), and SyncWAL(). Their exact meanings are not obvious, and I don't think it's appropriate to talk about implementation mutexes in the API comments, but about what operations might block each other.
* Add LockWAL()/UnlockWAL() to db_stress and crash test, mostly to check for assertion failures, but also checks that latest seqno doesn't change while WAL is locked. This is simpler to add when LockWAL() is allowed in multiple threads.
* Remove unnecessary use of sync points in test DBWALTest::LockWal. There was a bug during development of above changes that caused this test to fail sporadically, with and without this sync point change.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11143
Test Plan: unit tests added / updated, added to stress/crash test
Reviewed By: ajkr
Differential Revision: D42848627
Pulled By: pdillinger
fbshipit-source-id: 6d976c51791941a31fd8fbf28b0f82e888d9f4b4
Summary:
We haven't been actively mantaining RocksDB LITE recently and the size must have been gone up significantly. We are removing the support.
Most of changes were done through following comments:
unifdef -m -UROCKSDB_LITE `git grep -l ROCKSDB_LITE | egrep '[.](cc|h)'`
by Peter Dillinger. Others changes were manually applied to build scripts, CircleCI manifests, ROCKSDB_LITE is used in an expression and file db_stress_test_base.cc.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11147
Test Plan: See CI
Reviewed By: pdillinger
Differential Revision: D42796341
fbshipit-source-id: 4920e15fc2060c2cd2221330a6d0e5e65d4b7fe2
Summary:
RocksDB has two public APIs: `DB::LockWAL()`/`DB::UnlockWAL()`. The current implementation acquires and
releases the internal `DBImpl::log_write_mutex_`.
According to the comment on `DBImpl::log_write_mutex_`: https://github.com/facebook/rocksdb/blob/7.8.fb/db/db_impl/db_impl.h#L2287:L2288
> Note: to avoid dealock, if needed to acquire both log_write_mutex_ and mutex_, the order should be first mutex_ and then log_write_mutex_.
This puts limitations on how applications can use the `LockWAL()` API. After `LockWAL()` returns ok, then application
should not perform any operation that acquires `mutex_`. Currently, the use case of `LockWAL()` is MyRocks implementing
the MySQL storage engine handlerton `lock_hton_log` interface. The operation that MyRocks performs after `LockWAL()`
is `GetSortedWalFiless()` which not only acquires mutex_, but also `log_write_mutex_`.
There are two issues:
1. Applications using these two APIs may hang if one thread calls `GetSortedWalFiles()` after
calling `LockWAL()` because log_write_mutex is not recursive.
2. Two threads may dead lock due to lock order inversion.
To fix these issues, we can modify the implementation of LockWAL so that it does not keep
`log_write_mutex_` held until UnlockWAL. To achieve the goal of locking the WAL, we can
instead manually inject a write stall so that all future writes will be stopped.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11020
Test Plan: make check
Reviewed By: ajkr
Differential Revision: D41785203
Pulled By: riversand963
fbshipit-source-id: 5ccb7a9c6eb9a2c3fa80fd2c399cc2568b8f89ce
Summary:
**Context/Summary:**
Credit to ajkr's https://github.com/facebook/rocksdb/pull/11016#pullrequestreview-1205020134,
flaky test https://app.circleci.com/pipelines/github/facebook/rocksdb/21985/workflows/5f6cc355-78c1-46d8-89ee-0fd679725a8a/jobs/540878 is due to `Flush()` called in the test returned earlier than obsoleted WAL being found in background flush and SyncWAL() was called (i.e, "sync_point_called" sets to true). Fix this by making checking `sync_point_called == true` after obsoleted WAL is found and `SyncWAL()` is called. Also rename the "sync_point_called" to be something more specific.
Also, fix a potential flakiness due to manually setting a log threshold to force new manifest creation. This is unreliable so I decided to use sync point to force new manifest creation.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11016
Test Plan: make check
Reviewed By: pdillinger
Differential Revision: D41717786
Pulled By: hx235
fbshipit-source-id: ad1e4701a987285bbe6c8e7d9b05c4db06b4edf4
Summary:
**Context**
`Options::track_and_verify_wals_in_manifest = true` verifies each of the WALs tracked in manifest indeed presents in the WAL folder. If not, a corruption "Missing WAL with log number" will be thrown.
`DB::SyncWAL()` called at a specific timing (i.e, at the `TEST_SYNC_POINT("FindObsoleteFiles::PostMutexUnlock")`) can record in a new manifest the WAL addition of a WAL file that already had a WAL deletion recorded in the previous manifest.
And the WAL deletion record is not rollover-ed to the new manifest. So the new manifest creates the illusion of such WAL never gets deleted and should presents at db re/open.
- Such WAL deletion record can be caused by flushing the memtable associated with that WAL and such WAL deletion can actually happen in` PurgeObsoleteFiles()`.
As a consequence, upon `DB::Reopen()`, this WAL file can be deleted while manifest still has its WAL addition record , which causes a false alarm of corruption "Missing WAL with log number" to be thrown.
**Summary**
This PR fixes this false alarm by rolling over the WAL deletion record from prev manifest to the new manifest by adding the WAL deletion record to the new manifest.
**Test**
- Make check
- Added new unit test `TEST_F(DBWALTest, FixSyncWalOnObseletedWalWithNewManifestCausingMissingWAL)` that failed before the fix and passed after
- [Ongoing]CI stress test + aggressive value as in https://github.com/facebook/rocksdb/pull/10761 , which is how this false alarm was first surfaced, to confirm such false alarm disappears
- [Ongoing]Regular CI stress test to confirm such fix didn't harm anything
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10892
Reviewed By: ajkr
Differential Revision: D40778965
Pulled By: hx235
fbshipit-source-id: a512364bfdeb0b1a55c171890e60d856c528f37f
Summary:
Existing DBWALTest.RaceInstallFlushResultsWithWalObsoletion test relies
on a specific interleaving of two background flush threads. We call them
bg1 and bg2, and assume bg1 starts to install flush results ahead of
bg2. After bg1 enters `ProcessManifestWrites`, bg1 waits for bg2 to also
enter `MemTableList::TryInstallMemtableFlushResults()` before bg1 can
proceed with MANIFEST write. However, if bg2 called `SyncClosedLogs()`
and needed to commit to the MANIFEST but falls behind bg1, then bg2
needs to wait for bg1 to finish writing to MANIFEST. This is a circular
dependency.
Fix this by allowing bg2 to start only after bg1 grabs the chance to
sync the WAL and commit to MANIFEST.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10456
Test Plan:
1. make check
2. export TEST_TMPDIR=/dev/shm && gtest-parallel -r 1000 -w 32 ./db_wal_test --gtest_filter=DBWALTest.RaceInstallFlushResultsWithWalObsoletion
Reviewed By: ltamasi
Differential Revision: D38391856
Pulled By: riversand963
fbshipit-source-id: 55f647d5b94e534c008a4dd2fb082675ddf58c96
Summary:
Enabled zstd checksum flag in StreamingCompress so that WAL (de)compreression is protected by a checksum per compression frame.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10319
Test Plan:
- `make check`
- WAL perf: average ops/sec over 10 runs is 161226 pre PR and 159635 post PR (1% drop).
```
sudo TEST_TMPDIR=/dev/shm/memtable_write ./db_bench_checksum -benchmarks=fillseq -max_write_buffer_number=100 -num=1000000 -min_write_buffer_number_to_merge=10 -wal_compression=zstd
```
Reviewed By: ajkr
Differential Revision: D37673311
Pulled By: cbi42
fbshipit-source-id: 9f34a3bfc2a82e5c80b1ec63bb339a7465108ec9
Summary:
There is currently no caching mechanism for blobs, which is not ideal especially when the database resides on remote storage (where we cannot rely on the OS page cache). As part of this task, we would like to make it possible for the application to configure a blob cache.
In this task, we formally introduced the blob source to RocksDB. BlobSource is a new abstraction layer that provides universal access to blobs, regardless of whether they are in the blob cache, secondary cache, or (remote) storage. Depending on user settings, it always fetch blobs from multi-tier cache and storage with minimal cost.
Note: The new `MultiGetBlob()` implementation is not included in the current PR. To go faster, we aim to create a separate PR for it in parallel!
This PR is a part of https://github.com/facebook/rocksdb/issues/10156
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10198
Reviewed By: ltamasi
Differential Revision: D37294735
Pulled By: gangliao
fbshipit-source-id: 9cb50422d9dd1bc03798501c2778b6c7520c7a1e
Summary:
RocksDB uses WalManager to manage WAL files. In WalManager::ReadFirstLine(), the assumption is that reading the first record of a valid WAL file will return OK status and set the output sequence to non-zero value.
This assumption has been broken by WAL compression which writes a `kSetCompressionType` record which is not associated with any sequence number.
Consequently, WalManager::GetSortedWalsOfType() will skip these WALs and not return them to caller, e.g. Checkpoint, Backup, causing the operations to fail.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10130
Test Plan: - Newly Added test
Reviewed By: riversand963
Differential Revision: D36985744
Pulled By: akankshamahajan15
fbshipit-source-id: dfde7b3be68b6a30b75b49479779748eedf29f7f
Summary:
We recently saw a case in crash test in which a WAL file in the
middle of the list of live WALs was not included in the backup, so the
DB was not openable due to missing WAL. We are not sure why, but this
change should at least turn that into a backup-time failure by ensuring
all the WAL files expected by the manifest (according to VersionSet) are
included in `GetSortedWalFiles()` (used by `GetLiveFilesStorageInfo()`,
`BackupEngine`, and `Checkpoint`)
Related: to maximize the effectiveness of
track_and_verify_wals_in_manifest with GetSortedWalFiles() during
checkpoint/backup, we will now sync WAL in GetLiveFilesStorageInfo()
when track_and_verify_wals_in_manifest=true.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10083
Test Plan: added new unit test for the check in GetSortedWalFiles()
Reviewed By: ajkr
Differential Revision: D36791608
Pulled By: pdillinger
fbshipit-source-id: a27bcf0213fc7ab177760fede50d4375d579afa6
Summary:
ToString() is created as some platform doesn't support std::to_string(). However, we've already used std::to_string() by mistake for 16 months (in db/db_info_dumper.cc). This commit just remove ToString().
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9955
Test Plan: Watch CI tests
Reviewed By: riversand963
Differential Revision: D36176799
fbshipit-source-id: bdb6dcd0e3a3ab96a1ac810f5d0188f684064471
Summary:
Right now we still don't fully use std::numeric_limits but use a macro, mainly for supporting VS 2013. Right now we only support VS 2017 and up so it is not a problem. The code comment claims that MinGW still needs it. We don't have a CI running MinGW so it's hard to validate. since we now require C++17, it's hard to imagine MinGW would still build RocksDB but doesn't support std::numeric_limits<>.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9954
Test Plan: See CI Runs.
Reviewed By: riversand963
Differential Revision: D36173954
fbshipit-source-id: a35a73af17cdcae20e258cdef57fcf29a50b49e0
Summary:
1) In case of non-TransactionDB and avoid_flush_during_recovery = true, RocksDB won't
flush the data from WAL to L0 for all column families if possible. As a
result, not all column families can increase their log_numbers, and
min_log_number_to_keep won't change.
2) For transaction DB (.allow_2pc), even with the flush, there may be old WAL files that it must not delete because they can contain data of uncommitted transactions and min_log_number_to_keep won't change.
If we persist a new MANIFEST with
advanced log_numbers for some column families, then during a second
crash after persisting the MANIFEST, RocksDB will see some column
families' log_numbers larger than the corrupted wal, and the "column family inconsistency" error will be hit, causing recovery to fail.
As a solution,
1. the corrupted WALs whose numbers are larger than the
corrupted wal and smaller than the new WAL will be moved to archive folder.
2. Currently, RocksDB DB::Open() may creates and writes to two new MANIFEST files even before recovery succeeds. This PR buffers the edits in a structure and writes to a new MANIFEST after recovery is successful
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9634
Test Plan:
1. Added new unit tests
2. make crast_test -j
Reviewed By: riversand963
Differential Revision: D34463666
Pulled By: akankshamahajan15
fbshipit-source-id: e233d3af0ed4e2028ca0cf051e5a334a0fdc9d19
Summary:
There is a race condition if WAL tracking in the MANIFEST is enabled in a database that disables 2PC.
The race condition is between two background flush threads trying to install flush results to the MANIFEST.
Consider an example database with two column families: "default" (cfd0) and "cf1" (cfd1). Initially,
both column families have one mutable (active) memtable whose data backed by 6.log.
1. Trigger a manual flush for "cf1", creating a 7.log
2. Insert another key to "default", and trigger flush for "default", creating 8.log
3. BgFlushThread1 finishes writing 9.sst
4. BgFlushThread2 finishes writing 10.sst
```
Time BgFlushThread1 BgFlushThread2
| mutex_.Lock()
| precompute min_wal_to_keep as 6
| mutex_.Unlock()
| mutex_.Lock()
| precompute min_wal_to_keep as 6
| join MANIFEST write queue and mutex_.Unlock()
| write to MANIFEST
| mutex_.Lock()
| cfd1->log_number = 7
| Signal bg_flush_2 and mutex_.Unlock()
| wake up and mutex_.Lock()
| cfd0->log_number = 8
| FindObsoleteFiles() with job_context->log_number == 7
| mutex_.Unlock()
| PurgeObsoleteFiles() deletes 6.log
V
```
As shown in the above, BgFlushThread2 thinks that the min wal to keep is 6.log because "cf1" has unflushed data in 6.log (cf1.log_number=6).
Similarly, BgThread1 thinks that min wal to keep is also 6.log because "default" has unflushed data (default.log_number=6).
No WAL deletion will be written to MANIFEST because 6 is equal to `versions_->wals_.min_wal_number_to_keep`,
due to https://github.com/facebook/rocksdb/blob/7.1.fb/db/memtable_list.cc#L513:L514.
The bg flush thread that finishes last will perform file purging. `job_context.log_number` will be evaluated as 7, i.e.
the min wal that contains unflushed data, causing 6.log to be deleted. However, MANIFEST thinks 6.log should still exist.
If you close the db at this point, you won't be able to re-open it if `track_and_verify_wal_in_manifest` is true.
We must handle the case of multiple bg flush threads, and it is difficult for one bg flush thread to know
the correct min wal number until the other bg flush threads have finished committing to the manifest and updated
the `cfd::log_number`.
To fix this issue, we rename an existing variable `min_log_number_to_keep_2pc` to `min_log_number_to_keep`,
and use it to track WAL file deletion in non-2pc mode as well.
This variable is updated only 1) during recovery with mutex held, or 2) in the MANIFEST write thread.
`min_log_number_to_keep` means RocksDB will delete WALs below it, although there may be WALs
above it which are also obsolete. Formally, we will have [min_wal_to_keep, max_obsolete_wal]. During recovery, we
make sure that only WALs above max_obsolete_wal are checked and added back to `alive_log_files_`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9715
Test Plan:
```
make check
```
Also ran stress test below (with asan) to make sure it completes successfully.
```
TEST_TMPDIR=/dev/shm/rocksdb OPT=-g ASAN_OPTIONS=disable_coredump=0 \
CRASH_TEST_EXT_ARGS=--compression_type=zstd SKIP_FORMAT_BUCK_CHECKS=1 \
make J=52 -j52 blackbox_asan_crash_test
```
Reviewed By: ltamasi
Differential Revision: D34984412
Pulled By: riversand963
fbshipit-source-id: c7b21a8d84751bb55ea79c9f387103d21b231005
Summary:
When WAL compression is enabled, add a record (new record type) to store the compression type to indicate that all subsequent records are compressed. The log reader will store the compression type when this record is encountered and use the type to uncompress the subsequent records. Compress and uncompress to be implemented in subsequent diffs.
Enabled WAL compression in some WAL tests to check for regressions. Some tests that rely on offsets have been disabled.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9556
Reviewed By: anand1976
Differential Revision: D34308216
Pulled By: sidroyc
fbshipit-source-id: 7f10595e46f3277f1ea2d309fbf95e2e935a8705
Summary:
The patch replaces `std::map` with a sorted `std::vector` for
`VersionStorageInfo::blob_files_` and preallocates the space
for the `vector` before saving the `BlobFileMetaData` into the
new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`.
These changes reduce the time the DB mutex is held while
saving new `Version`s, and using a sorted `vector` also makes
lookups faster thanks to better memory locality.
In addition, the patch introduces helper methods
`VersionStorageInfo::GetBlobFileMetaData` and
`VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by
clients to perform lookups in the `vector`, and does some general
cleanup in the parts of code where blob file metadata are used.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526
Test Plan:
Ran `make check` and the crash test script for a while.
Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced:
```
numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value>
```
Final statistics before the patch:
```
Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s
Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s
```
With the patch:
```
Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s
Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s
```
Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs.
Reviewed By: riversand963
Differential Revision: D34082728
Pulled By: ltamasi
fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9266
This diff adds a new tag `CommitWithTimestamp`. Currently, there is no API to trigger writing
this tag to WAL, thus it is unavailable to users.
This is an ongoing effort to add user-defined timestamp support to write-committed transactions.
This diff also indicates all column families that may potentially participate in the same
transaction must either disable timestamp or have the same timestamp format, since
`CommitWithTimestamp` tag is followed by a single byte-array denoting the commit
timestamp of the transaction. We will enforce this checking in a future diff. We keep this
diff small.
Reviewed By: ltamasi
Differential Revision: D31721350
fbshipit-source-id: e1450811443647feb6ca01adec4c8aaae270ffc6
Summary:
The PerThreadDBPath has already specified a slash. It does not need to be specified when initializing the test path.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8555
Reviewed By: ajkr
Differential Revision: D29758399
Pulled By: jay-zhuang
fbshipit-source-id: 6d2b878523e3e8580536e2829cb25489844d9011
Summary:
Currently, we either use the file system inode or a monotonically incrementing runtime ID as the block cache key prefix. However, if we use a monotonically incrementing runtime ID (in the case that the file system does not support inode id generation), in some cases, it cannot ensure uniqueness (e.g., we have secondary cache migrated from host to host). We use DbSessionID (20 bytes) + current file number (at most 10 bytes) as the new cache block key prefix when the secondary cache is enabled. So can accommodate scenarios such as transfer of cache state across hosts.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8360
Test Plan: add the test to lru_cache_test
Reviewed By: pdillinger
Differential Revision: D29006215
Pulled By: zhichao-cao
fbshipit-source-id: 6cff686b38d83904667a2bd39923cd030df16814
Summary:
I noticed ```openat``` system call with ```O_WRONLY``` flag and ```sync_file_range``` and ```truncate``` on WAL file when using ```rocksdb::DB::OpenForReadOnly``` by way of ```db_bench --readonly=true --benchmarks=readseq --use_existing_db=1 --num=1 ...```
Noticed in ```strace``` after seeing the last modification time of the WAL file change after each run (with ```--readonly=true```).
I think introduced by 7d7f14480e from https://github.com/facebook/rocksdb/pull/8122
I added a test to catch the WAL file being truncated and the modification time on it changing.
I am not sure if a mock filesystem with mock clock could be used to avoid having to sleep 1.1s.
The test could also check the set of files is the same and that the sizes are also unchanged.
Before:
```
[ RUN ] DBBasicTest.ReadOnlyReopenMtimeUnchanged
db/db_basic_test.cc:182: Failure
Expected equality of these values:
file_mtime_after_readonly_reopen
Which is: 1621611136
file_mtime_before_readonly_reopen
Which is: 1621611135
file is: 000010.log
[ FAILED ] DBBasicTest.ReadOnlyReopenMtimeUnchanged (1108 ms)
```
After:
```
[ RUN ] DBBasicTest.ReadOnlyReopenMtimeUnchanged
[ OK ] DBBasicTest.ReadOnlyReopenMtimeUnchanged (1108 ms)
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8313
Reviewed By: pdillinger
Differential Revision: D28656925
Pulled By: jay-zhuang
fbshipit-source-id: ea9e215cb53e7c830e76bc5fc75c45e21f12a1d6
Summary:
Current flush reason attribution is misleading or incorrect (depending on what the original intention was):
- Flush due to WAL reaching its maximum size is attributed to `kWriteBufferManager`
- Flushes due to full write buffer and write buffer manager are not distinguishable, both are attributed to `kWriteBufferFull`
This changes the first to a new flush reason `kWALFull`, and splits the second between `kWriteBufferManager` and `kWriteBufferFull`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8150
Reviewed By: zhichao-cao
Differential Revision: D27569645
Pulled By: ot
fbshipit-source-id: 7e3c8ca186a6e71976e6b8e937297eebd4b769cc
Summary:
Currently, we only truncate the latest alive WAL files when the DB is opened. If the latest WAL file is empty or was flushed during Open, its not truncated since the file will be deleted later on in the Open path. However, before deletion, a new WAL file is created, and if the process crash loops between the new WAL file creation and deletion of the old WAL file, the preallocated space will keep accumulating and eventually use up all disk space. To prevent this, always truncate the latest WAL file, even if its empty or the data was flushed.
Tests:
Add unit tests to db_wal_test
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8122
Reviewed By: riversand963
Differential Revision: D27366132
Pulled By: anand1976
fbshipit-source-id: f923cc03ef033ccb32b140d36c6a63a8152f0e8e
Summary:
`strerror()` is not thread-safe, using `strerror_r()` instead. The API could be different on the different platforms, used the code from 0deef031cb/folly/String.cpp (L457)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8087
Reviewed By: mrambacher
Differential Revision: D27267151
Pulled By: jay-zhuang
fbshipit-source-id: 4b8856d1ec069d5f239b764750682c56e5be9ddb
Summary:
The patch breaks down the "bytes written" (as well as the "number of output files")
compaction statistics into two, so the values are logged separately for table files
and blob files in the info log, and are shown in separate columns (`Write(GB)` for table
files, `Wblob(GB)` for blob files) when the compaction statistics are dumped.
This will also come in handy for fixing the write amplification statistics, which currently
do not consider the amount of data read from blob files during compaction. (This will
be fixed by an upcoming patch.)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8013
Test Plan: Ran `make check` and `db_bench`.
Reviewed By: riversand963
Differential Revision: D26742156
Pulled By: ltamasi
fbshipit-source-id: 31d18ee8f90438b438ca7ed1ea8cbd92114442d5
Summary:
in PR https://github.com/facebook/rocksdb/issues/7419 , we introduce the new Append and PositionedAppend APIs to WritableFile at File System, which enable RocksDB to pass the data verification information (e.g., checksum of the data) to the lower layer. In this PR, we use the new API in WritableFileWriter, such that the file created via WritableFileWrite can pass the checksum to the storage layer. To control which types file should apply the checksum handoff, we add checksum_handoff_file_types to DBOptions. User can use this option to control which file types (Currently supported file tyes: kLogFile, kTableFile, kDescriptorFile.) should use the new Append and PositionedAppend APIs to handoff the verification information.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7523
Test Plan: add new unit test, pass make check/ make asan_check
Reviewed By: pdillinger
Differential Revision: D24313271
Pulled By: zhichao-cao
fbshipit-source-id: aafd69091ae85c3318e3e17cbb96fe7338da11d0
Summary:
Removed the uses of the Legacy FileWrapper classes from the source code. The wrappers were creating an additional layer of indirection/wrapping, as the Env already has a FileSystem.
Moved the Custom FileWrapper classes into the CustomEnv, as these classes are really for the private use the the CustomEnv class.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7851
Reviewed By: anand1976
Differential Revision: D26114816
Pulled By: mrambacher
fbshipit-source-id: db32840e58d969d3a0fa6c25aaf13d6dcdc74150
Summary:
During recovery, RocksDB performs a kind of dummy flush; namely, entries
from the WAL are added to memtables, which then get written to SSTs and
blob files (if enabled) just like during a regular flush. Note that
multiple memtables might be flushed during recovery for the same column
family, for example, if the DB is reopened with a lower write buffer size,
and therefore, we need to make sure to collect all SST and blob file
additions. The patch fixes a bug in the earlier logic which resulted in
later blob file additions overwriting earlier ones.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7903
Test Plan: Added a unit test and ran `db_stress`.
Reviewed By: jay-zhuang
Differential Revision: D26110847
Pulled By: ltamasi
fbshipit-source-id: eddb50a608a88f54f3cec3a423de8235aba951fd
Summary:
In the original stacked BlobDB implementation, which writes blobs to blob files
immediately and treats blob files as logs, it makes sense to flush the file after
writing each blob to protect against process crashes; however, in the integrated
implementation, which builds blob files in the background jobs, this unnecessarily
reduces performance. This patch fixes this by simply adding a `do_flush` flag to
`BlobLogWriter`, which is set to `true` by the stacked implementation and to `false`
by the new code. Note: the change itself is trivial but the tests needed some work;
since in the new implementation, blobs are now buffered, adding a blob to
`BlobFileBuilder` is no longer guaranteed to result in an actual I/O. Therefore, we can
no longer rely on `FaultInjectionTestEnv` when testing failure cases; instead, we
manipulate the return values of I/O methods directly using `SyncPoint`s.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7892
Test Plan: `make check`
Reviewed By: jay-zhuang
Differential Revision: D26022814
Pulled By: ltamasi
fbshipit-source-id: b3dce419f312137fa70d84cdd9b908fd5d60d8cd
Summary:
The main improvement here is to not include `.` or `..` in the results of `Env::GetChildren`. The occurrence of `.` or `..`; it is non-portable, dependent on the Operating System and the File System. See: https://www.gnu.org/software/libc/manual/html_node/Reading_002fClosing-Directory.html
There were lots of duplicate checks spread through the RocksDB codebase previously to skip `.` and `..`. This new removes the need for those at the source.
Also some minor fixes to `Env::GetChildren`:
* Improve error handling in POSIX implementation
* Remove unnecessary array allocation on Windows
* Fix struct name for Windows Non-UTF-8 API
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7819
Reviewed By: ajkr
Differential Revision: D25837394
Pulled By: jay-zhuang
fbshipit-source-id: 1e137e7218d38b450af9c083f73d5357abcbba2e
Summary:
https://github.com/facebook/rocksdb/issues/7340 reports and reproduces an assertion failure caused by a combination of the following:
- atomic flush is disabled.
- a column family can appear multiple times in the flush queue at the same time. This behavior was introduced in release 5.17.
Consequently, it is possible that two flushes race with each other. One bg flush thread flushes all memtables. The other thread calls `FlushMemTableToOutputFile()` afterwards, and hits the assertion error below.
```
assert(cfd->imm()->NumNotFlushed() != 0);
assert(cfd->imm()->IsFlushPending());
```
Fix this by reverting the behavior. In non-atomic-flush case, a column family can appear in the flush queue at most once at the same time.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7362
Test Plan:
make check
Also run stress test successfully for 10 times.
```
make crash_test
```
Reviewed By: ajkr
Differential Revision: D25172996
Pulled By: riversand963
fbshipit-source-id: f1559b6366cc609e961e3fc83fae548f1fad08ce
Summary:
WAL may be truncated to an incomplete record due to crash while writing
the last record or corruption. In the former case, no hole will be
produced since no ACK'd data was lost. In the latter case, a hole could
be produced without this PR since we proceeded to recover the next WAL
as if nothing happened. This PR changes the record reading code to
always report a corruption for incomplete records in
`kPointInTimeRecovery` mode, and the upper layer will only ignore them
if the next WAL has consecutive seqnum (i.e., we are guaranteed no
hole).
While this solves the hole problem for the case of incomplete
records, the possibility is still there if the WAL is corrupted by
truncation to an exact record boundary. This PR also regresses how much data
can be recovered when writes are mixed with/without
`WriteOptions::disableWAL`, as then we can not distinguish between a
seqnum gap caused by corruption and a seqnum gap caused by a `disableWAL` write.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7701
Test Plan:
Interestingly there already was a test for this case
(`DBWALTestWithParams.kPointInTimeRecovery`); it just had a typo bug in
the verification that prevented it from noticing holes in recovery.
Reviewed By: anand1976
Differential Revision: D25111765
Pulled By: ajkr
fbshipit-source-id: 5e330b13b1ee2b5be096cea9d0ff6075843e57b6
Summary:
Recent test report shows that some tests have been skipped.
For DBWALTest that inherits from DBTestBase, the following will always be
true, since `env_` is an instance of `SpecialEnv`, not `Env::Default()`. Thus the test
will always be skipped.
```
if (options.env != Env::Default()) {
ROCKSDB_GTEST_SKIP("Test requires default environment");
return;
}
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7628
Test Plan:
./db_wal_test --gtest_filter=DBWALTest.TruncateLastLogAfterRecoverWithoutFlush
MEM_ENV=1 ./db_wal_test --gtest_filter=DBWALTest.TruncateLastLogAfterRecoverWithoutFlush
make check
Reviewed By: jay-zhuang
Differential Revision: D24693006
Pulled By: riversand963
fbshipit-source-id: 7f2a772492a0f11bff17bbf5e9f493e9e9a1c125
Summary:
This PR does a few things:
1. The MockFileSystem class was split out from the MockEnv. This change would theoretically allow a MockFileSystem to be used by other Environments as well (if we created a means of constructing one). The MockFileSystem implements a FileSystem in its entirety and does not rely on any Wrapper implementation.
2. Make the RocksDB test suite work when MOCK_ENV=1 and ENCRYPTED_ENV=1 are set. To accomplish this, a few things were needed:
- The tests that tried to use the "wrong" environment (Env::Default() instead of env_) were updated
- The MockFileSystem was changed to support the features it was missing or mishandled (such as recursively deleting files in a directory or supporting renaming of a directory).
3. Updated the test framework to have a ROCKSDB_GTEST_SKIP macro. This can be used to flag tests that are skipped. Currently, this defaults to doing nothing (marks the test as SUCCESS) but will mark the tests as SKIPPED when RocksDB is upgraded to a version of gtest that supports this (gtest-1.10).
I have run a full "make check" with MEM_ENV, ENCRYPTED_ENV, both, and neither under both MacOS and RedHat. A few tests were disabled/skipped for the MEM/ENCRYPTED cases. The error_handler_fs_test fails/hangs for MEM_ENV (presumably a timing problem) and I will introduce another PR/issue to track that problem. (I will also push a change to disable those tests soon). There is one more test in DBTest2 that also fails which I need to investigate or skip before this PR is merged.
Theoretically, this PR should also allow the test suite to run against an Env loaded from the registry, though I do not have one to try it with currently.
Finally, once this is accepted, it would be nice if there was a CircleCI job to run these tests on a checkin so this effort does not become stale. I do not know how to do that, so if someone could write that job, it would be appreciated :)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7566
Reviewed By: zhichao-cao
Differential Revision: D24408980
Pulled By: jay-zhuang
fbshipit-source-id: 911b1554a4d0da06fd51feca0c090a4abdcb4a5f
Summary:
Similarly to how https://github.com/facebook/rocksdb/issues/7345
integrated blob file writing into the flush process,
the patch adds support for writing blob files to the compaction logic.
Namely, if `enable_blob_files` is set, large values encountered during
compaction are extracted to blob files and replaced with blob indexes.
The resulting blob files are then logged to the MANIFEST as part of the
compaction job's `VersionEdit` and added to the `Version` alongside any
table files written by the compaction. Any errors during blob file building fail
the compaction job.
There will be a separate follow-up patch to perform blob garbage collection
during compactions.
In addition, the patch continues to chip away at the mess around computing
various compaction related statistics by eliminating some code duplication
and by making the `num_output_files` and `bytes_written` stats more consistent
for flushes, compactions, and recovery.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7573
Test Plan: `make check`
Reviewed By: riversand963
Differential Revision: D24404696
Pulled By: ltamasi
fbshipit-source-id: 21216af3a172ad3ce8f85d11cd30923784ae426c
Summary:
The patch adds blob file support to the `Get` API by extending `Version` so that
whenever a blob reference is read from a file, the blob is retrieved from the corresponding
blob file and passed back to the caller. (This is assuming the blob reference is valid
and the blob file is actually part of the given `Version`.) It also introduces a cache
of `BlobFileReader`s called `BlobFileCache` that enables sharing `BlobFileReader`s
between callers. `BlobFileCache` uses the same backing cache as `TableCache`, so
`max_open_files` (if specified) limits the total number of open (table + blob) files.
TODO: proactively open/cache blob files and pin the cache handles of the readers in the
metadata objects similarly to what `VersionBuilder::LoadTableHandlers` does for
table files.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7540
Test Plan: `make check`
Reviewed By: riversand963
Differential Revision: D24260219
Pulled By: ltamasi
fbshipit-source-id: a8a2a4f11d3d04d6082201b52184bc4d7b0857ba
Summary:
The patch adds support for extracting large values into blob files when
performing a flush during recovery (when `avoid_flush_during_recovery` is
`false`). Blob files are built and added to the `Version` similarly to flush.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7388
Test Plan: `make check`
Reviewed By: riversand963
Differential Revision: D23709912
Pulled By: ltamasi
fbshipit-source-id: ce48b4227849cf25429ae98574e72b0e1cb9c67d
Summary:
After https://github.com/facebook/rocksdb/pull/7036, we still see extra DBTest that can timeout when running 10 or 20 in parallel. Expand skip-fsync mode in whole DBTest. Still preserve other tests from doing this mode to be conservative.
This commit reinstates https://github.com/facebook/rocksdb/issues/7049, whose un-revert was lost in an automatic
infrastructure mis-merge.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7274
Test Plan: Run all existing files.
Reviewed By: pdillinger
Differential Revision: D23177444
fbshipit-source-id: 1f61690b2ac6333c3b2c87176fef6b2cba086b33
