Summary:
While GC, blob DB use optimistic transaction to delete or replace the index entry in LSM, to guarantee correctness if there's a normal write writing to the same key. However, the previous implementation doesn't call SetSnapshot() nor use GetForUpdate() of transaction API, instead it do its own sequence number checking before beginning the transaction. A normal write can sneak in after the sequence number check and overwrite the key, and the GC will delete or relocate the old version of the key by mistake. Update the code to property use GetForUpdate() to check the existing index entry.
After the patch the sequence number store with each blob record is useless, So I'm considering remove the sequence number from blob record, in another patch.
Closes https://github.com/facebook/rocksdb/pull/2703
Differential Revision: D5589178
Pulled By: yiwu-arbug
fbshipit-source-id: 8dc960cd5f4e61b36024ba7c32d05584ce149c24
Summary:
It would be super helpful to not have to recompile rocksdb to get this performance tweak for mechanical disks.
I have signed the CLA.
Closes https://github.com/facebook/rocksdb/pull/2718
Differential Revision: D5606994
Pulled By: yiwu-arbug
fbshipit-source-id: c05e92bad0d03bd38211af1e1ced0d0d1e02f634
Summary:
Right now, if direct I/O is enabled, prefetching the last 512KB cannot be applied, except compaction inputs or readahead is enabled for iterators. This can create a lot of I/O for HDD cases. To solve the problem, the 512KB is prefetched in block based table if direct I/O is enabled. The prefetched buffer is passed in totegher with random access file reader, so that we try to read from the buffer before reading from the file. This can be extended in the future to support flexible user iterator readahead too.
Closes https://github.com/facebook/rocksdb/pull/2708
Differential Revision: D5593091
Pulled By: siying
fbshipit-source-id: ee36ff6d8af11c312a2622272b21957a7b5c81e7
Summary:
TSAN shows error when we grab too many locks at the same time. In TSAN crash test, make one shard key cover 2^22 keys so that no many keys will be hold at the same time.
Closes https://github.com/facebook/rocksdb/pull/2719
Differential Revision: D5609035
Pulled By: siying
fbshipit-source-id: 930e5d63fff92dbc193dc154c4c615efbdf06c6a
Summary:
- moved the max call for numeric limits into paranthesis so that max wont be called as macro when including <Windows.h>
Closes https://github.com/facebook/rocksdb/pull/2709
Differential Revision: D5600773
Pulled By: yiwu-arbug
fbshipit-source-id: fd28b6f7c10ddce21bad4030f2db06f965bb08da
Summary:
Commit 4f81ab38bf has the test wrong.
clang doesn't support a -dumpversion option. By lucky coincidence
clang/gcc --version both place a version number at the same output location
when --verison is passed.
Example output (1st line only).
$ clang --version
clang version 3.9.1 (tags/RELEASE_391/final)
$ gcc --version
gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1)
During the test of the compiler we ensure that a minimum version is met
as Makefile doesn't support patterns.
Also xcode9 doesn't seem affected by https://github.com/facebook/rocksdb/issues/2672
and also doesn't have "clang" as the first part of its output so the
fix implemented here also is Apple clang friendly.
$ clang --version
Apple LLVM version 9.0.0 (clang-900.0.31)
Signed-off-by: Daniel Black <daniel.black@au.ibm.com>
Closes https://github.com/facebook/rocksdb/pull/2699
Differential Revision: D5600818
Pulled By: yiwu-arbug
fbshipit-source-id: 3b0f2751becb53c1c35468bf29f3f828e7cf2c2a
Summary:
We need a tool to check any sst file corruption in the db.
It will check all the sst files in current version and read all the blocks (data, meta, index) with checksum verification. If any verification fails, the function will return non-OK status.
Closes https://github.com/facebook/rocksdb/pull/2498
Differential Revision: D5324269
Pulled By: lightmark
fbshipit-source-id: 6f8a272008b722402a772acfc804524c9d1a483b
Summary:
We should search wal_dir in Repairer::FindFiles function, and avoid use
LogFileNmae(dbname, number) to get WAL file's name, which will get a wrong
WAL filename. as following:
```
[WARN] [/home/liuchang/Workspace/rocksdb/db/repair.cc:310] Log #3: ignoring conversion error: IO error: While opening a file for sequentially reading: /tmp/rocksdbtest-1000/repair_test/000003.log: No such file or directory
```
I have added a new test case to repair_test.cc, which try to repair db with all WAL options.
Signed-off-by: Chang Liu <liuchang0812@gmail.com>
Closes https://github.com/facebook/rocksdb/pull/2692
Differential Revision: D5575888
Pulled By: ajkr
fbshipit-source-id: 5b93e9f85cddc01663ccecd87631fa723ac466a3
Summary:
This patch splits Commit and Prepare into lock-related logic and db-write-related logic. It moves lock-related logic to PessimisticTransaction to be reused by all children classes and movies the existing impl of db-write-related to PrepareInternal, CommitSingleInternal, and CommitInternal in WriteCommittedTxnImpl.
Closes https://github.com/facebook/rocksdb/pull/2691
Differential Revision: D5569464
Pulled By: maysamyabandeh
fbshipit-source-id: d1b8698e69801a4126c7bc211745d05c636f5325
Summary:
I'd like to propose adding my company as a RocksDB user
Closes https://github.com/facebook/rocksdb/pull/2694
Differential Revision: D5572113
Pulled By: ajkr
fbshipit-source-id: 646143b955e3efddee56691cce912d7badaa6e8b
Summary:
This opens space for the new implementations of TransactionDBImpl such as WritePreparedTxnDBImpl that has a different policy of how to write to DB.
Closes https://github.com/facebook/rocksdb/pull/2689
Differential Revision: D5568918
Pulled By: maysamyabandeh
fbshipit-source-id: f7eac866e175daf3793ae79da108f65cc7dc7b25
Summary:
In the condition:
```
if (range_del_agg != nullptr &&
range_del_agg->ShouldDelete(
iter->key(),
RangeDelAggregator::RangePositioningMode::kForwardTraversal) &&
filter != CompactionFilter::Decision::kRemoveAndSkipUntil) {
...
}
```
it could be possible that all the work done in `range_del_agg->ShouldDelete` is wasted due to not having the right `filter` value later on.
Instead, check `filter` value before even calling `range_del_agg->ShouldDelete`, which is a much more involved function.
Closes https://github.com/facebook/rocksdb/pull/2690
Differential Revision: D5568931
Pulled By: sagar0
fbshipit-source-id: 17512d52360425c7ae9de7675383f5d7bc3dad58
Summary:
The FsyncFiles background job call Fsync() periodically for blob files. However it can access WritableFileWriter concurrently with a Put() or Write(). And WritableFileWriter does not support concurrent access. It will lead to WritableFileWriter buffer being flush with same content twice, and blob file end up corrupted. Fixing by simply let FsyncFiles hold write_mutex_.
Closes https://github.com/facebook/rocksdb/pull/2685
Differential Revision: D5561908
Pulled By: yiwu-arbug
fbshipit-source-id: f0bb5bcab0e05694e053b8c49eab43640721e872
Summary:
The background thread pools' sizes weren't easily configurable by `max_background_compactions` and `max_background_flushes` in multi-instance setups. Introduced separate arguments for their sizes.
Closes https://github.com/facebook/rocksdb/pull/2680
Differential Revision: D5550675
Pulled By: ajkr
fbshipit-source-id: bab5f0a7bc5db63bb084d0c10facbe437096367d
Summary:
The current blob db implementation use mix of int32_t, uint32_t and uint64_t for TTL and expiration. Update all timestamps to uint64_t for consistency.
Closes https://github.com/facebook/rocksdb/pull/2683
Differential Revision: D5557103
Pulled By: yiwu-arbug
fbshipit-source-id: e4eab2691629a755e614e8cf1eed9c3a681d0c42
Summary:
When we had a single thread pool for compactions, a thread could be busy for a long time (minutes) executing a compaction involving the bottom level. In multi-instance setups, the entire thread pool could be consumed by such bottom-level compactions. Then, top-level compactions (e.g., a few L0 files) would be blocked for a long time ("head-of-line blocking"). Such top-level compactions are critical to prevent compaction stalls as they can quickly reduce number of L0 files / sorted runs.
This diff introduces a bottom-priority queue for universal compactions including the bottom level. This alleviates the head-of-line blocking situation for fast, top-level compactions.
- Added `Env::Priority::BOTTOM` thread pool. This feature is only enabled if user explicitly configures it to have a positive number of threads.
- Changed `ThreadPoolImpl`'s default thread limit from one to zero. This change is invisible to users as we call `IncBackgroundThreadsIfNeeded` on the low-pri/high-pri pools during `DB::Open` with values of at least one. It is necessary, though, for bottom-pri to start with zero threads so the feature is disabled by default.
- Separated `ManualCompaction` into two parts in `PrepickedCompaction`. `PrepickedCompaction` is used for any compaction that's picked outside of its execution thread, either manual or automatic.
- Forward universal compactions involving last level to the bottom pool (worker thread's entry point is `BGWorkBottomCompaction`).
- Track `bg_bottom_compaction_scheduled_` so we can wait for bottom-level compactions to finish. We don't count them against the background jobs limits. So users of this feature will get an extra compaction for free.
Closes https://github.com/facebook/rocksdb/pull/2580
Differential Revision: D5422916
Pulled By: ajkr
fbshipit-source-id: a74bd11f1ea4933df3739b16808bb21fcd512333
Summary:
I'm going with brute-force solution, just letting Put() and Write() holding a mutex before writing. May improve concurrent writing with finer granularity locking later.
Closes https://github.com/facebook/rocksdb/pull/2682
Differential Revision: D5552690
Pulled By: yiwu-arbug
fbshipit-source-id: 039abd675b5d274a7af6428198d1733cafecef4c
Summary:
Fix the bug where if blob db garbage collection revmoe keys with newer version. It shouldn't delete the key from base db when sequence number in base db is not equal to the one in blob log.
Closes https://github.com/facebook/rocksdb/pull/2678
Differential Revision: D5549752
Pulled By: yiwu-arbug
fbshipit-source-id: abb8649260963b5c389748023970fd746279d227
Summary:
This patch refactors TransactionImpl by separating the logic for pessimistic concurrency control from the implementation of how to write the data to rocksdb. The existing implementation is named WriteCommittedTxnImpl as it writes committed data to the db. A template named WritePreparedTxnImpl is also added which will be later completed to provide a an alternative implementation.
Closes https://github.com/facebook/rocksdb/pull/2676
Differential Revision: D5549998
Pulled By: maysamyabandeh
fbshipit-source-id: 16298e86b43ca4849324c1f35c731913c6d17bec
Summary:
Move an option necessary for running db_bench on multiple CFs into the general initialization area, so it works with both flag-based init and OPTIONS-based init.
Closes https://github.com/facebook/rocksdb/pull/2675
Differential Revision: D5541378
Pulled By: ajkr
fbshipit-source-id: 169926cb4ae95c17974f744faf7cc794d41e5c0a
Summary:
I observed while doing a `make jtest` that the java sample was broken, due to the changes in #2551 .
Closes https://github.com/facebook/rocksdb/pull/2674
Differential Revision: D5539807
Pulled By: sagar0
fbshipit-source-id: 2c7e9d84778099dfa1c611996b444efe3c9fd466
Summary:
* Dump blob db options to info log
* Remove BlobDBOptionsImpl to disallow dynamic cast *BlobDBOptions into *BlobDBOptionsImpl. Move options there to be constants or into BlobDBOptions. The dynamic cast is broken after #2645
* Change some of the default options
* Remove blob_db_options.min_blob_size, which is unimplemented. Will implement it soon.
Closes https://github.com/facebook/rocksdb/pull/2671
Differential Revision: D5529912
Pulled By: yiwu-arbug
fbshipit-source-id: dcd58ca981db5bcc7f123b65a0d6f6ae0dc703c7
Summary:
this value ``` Compaction::is_trivial_move_ ``` uninitialized .
under universal compaction , we enable ``` CompactionOptionsUniversal::allow_trivial_move ``` ,
9b11d4345a/db/compaction.cc (L245)
here is a disastrous bug , some sst trivial move to target level without overlap check ...
THEN , DATABASE DAMAGED , WE GOT A LEVEL WITH OVERLAP !
Closes https://github.com/facebook/rocksdb/pull/2634
Differential Revision: D5530722
Pulled By: siying
fbshipit-source-id: 425ab55bca5967110377d634258360bcf88c200e
Summary:
we were passing `record_read_stats` (a bool) as the `hist_type` argument, which meant we were updating either `rocksdb.db.get.micros` (`hist_type == 0`) or `rocksdb.db.write.micros` (`hist_type == 1`) with wrong data.
Closes https://github.com/facebook/rocksdb/pull/2666
Differential Revision: D5520384
Pulled By: ajkr
fbshipit-source-id: 2f7c956aec32f8b58c5c18845ac478e0230c9516
Summary:
Replace dynamic_cast<> so that users can choose to build with RTTI off, so that they can save several bytes per object, and get tiny more memory available.
Some nontrivial changes:
1. Add Comparator::GetRootComparator() to get around the internal comparator hack
2. Add the two experiemental functions to DB
3. Add TableFactory::GetOptionString() to avoid unnecessary casting to get the option string
4. Since 3 is done, move the parsing option functions for table factory to table factory files too, to be symmetric.
Closes https://github.com/facebook/rocksdb/pull/2645
Differential Revision: D5502723
Pulled By: siying
fbshipit-source-id: fd13cec5601cf68a554d87bfcf056f2ffa5fbf7c
Summary:
This fixes OOMs that we (logdevice) are currently having in production.
SkipListRep constructor does a couple small allocations from ConcurrentArena (see InlineSkipList constructor). ConcurrentArena would sometimes allocate an entire block for that, which is a few megabytes (we use Options::arena_block_size = 4 MB). So an empty memtable can take take 4 MB of memory. We have ~40k column families (spread across 15 DB instances), so 4 MB per empty memtable easily OOMs a machine for us.
This PR makes ConcurrentArena always allocate from Arena's inline block when possible. So as long as InlineSkipList's initial allocations are below 2 KB there would be no blocks allocated for empty memtables.
Closes https://github.com/facebook/rocksdb/pull/2569
Differential Revision: D5404029
Pulled By: al13n321
fbshipit-source-id: 568ec22a3fd1a485c06123f6b2dfc5e9ef67cd23
Summary:
- FIFOCompactionWithTTLTest was flaky when run in parallel earlier, and hence it was disabled. Fixed it now.
- Also, faking sleep now instead of really sleeping to make tests more realistic by using TTLs like 1 hour and 1 day.
Closes https://github.com/facebook/rocksdb/pull/2650
Differential Revision: D5506038
Pulled By: sagar0
fbshipit-source-id: deb429a527f045e3e2c5138b547c3e8ac8586aa2
Summary:
I might have missed these while doing some recent cassandra code reviews.
Closes https://github.com/facebook/rocksdb/pull/2663
Differential Revision: D5520138
Pulled By: sagar0
fbshipit-source-id: 340930afe9efe03c75f535a1da1f89bd3e53c1f9
Summary:
Simple component that will add a new entry in a log file every time we lookup/insert a key in SimCache.
API:
```
SimCache::StartActivityLogging(<file_name>, <env>, <optional_max_size>)
SimCache::StopActivityLogging()
```
Sending for review, Still need to add more comments.
I was thinking about a better approach, but I ended up deciding I will use a mutex to sync the writes to the file, since this feature should not be heavily used and only used to collect info that will be analyzed offline. I think it's okay to hold the mutex every time we lookup/add to the SimCache.
Closes https://github.com/facebook/rocksdb/pull/2295
Differential Revision: D5063826
Pulled By: IslamAbdelRahman
fbshipit-source-id: f3b5daed8b201987c9a071146ddd5c5740a2dd8c
Summary:
Introducing blob_db::TTLExtractor to replace extract_ttl_fn. The TTL
extractor can be use to extract TTL from keys insert with Put or
WriteBatch. Change over existing extract_ttl_fn are:
* If value is changed, it will be return via std::string* (rather than Slice*). With Slice* the new value has to be part of the existing value. With std::string* the limitation is removed.
* It can optionally return TTL or expiration.
Other changes in this PR:
* replace `std::chrono::system_clock` with `Env::NowMicros` so that I can mock time in tests.
* add several TTL tests.
* other minor naming change.
Closes https://github.com/facebook/rocksdb/pull/2659
Differential Revision: D5512627
Pulled By: yiwu-arbug
fbshipit-source-id: 0dfcb00d74d060b8534c6130c808e4d5d0a54440
Summary:
Breaking commit: d12691b86f
In the above commit, I moved the `TableCache` cleanup logic from `Version` destructor into `PurgeObsoleteFiles`. I missed cleaning up `TableCache` entries for the current `Version` during DB destruction.
This PR adds that logic to `VersionSet` destructor. One unfortunate side effect is now we're potentially deleting `TableReader`s after `column_family_set_.reset()`, which means we can't call `BlockBasedTableReader::Close` a second time as the block cache might already be destroyed.
Closes https://github.com/facebook/rocksdb/pull/2662
Differential Revision: D5515108
Pulled By: ajkr
fbshipit-source-id: 2cb820e19aa813e0d258d17f76b2d7b6b7ee0b18
Summary:
We don't need to set them explicitly.
Closes https://github.com/facebook/rocksdb/pull/2660
Differential Revision: D5514141
Pulled By: yiwu-arbug
fbshipit-source-id: 10edebfc3cfe0afc00a34519f87fcea4d65069ae
Summary:
platform_dependent tests in Travis now builds all tests, which is not needed. Only build those tests we need to run.
Closes https://github.com/facebook/rocksdb/pull/2647
Differential Revision: D5513954
Pulled By: siying
fbshipit-source-id: 4d540b146124e70dd25586c47939d19f93655b0a
