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:
https://github.com/facebook/rocksdb/pull/3881 fixed a bug where PinnableSlice pin mmap files which could be deleted with background compaction. This is however a non-issue for ReadOnlyDB when there is no compaction running and max_open_files is -1. This patch reenables the pinning feature for that case.
Closes https://github.com/facebook/rocksdb/pull/4053
Differential Revision: D8662546
Pulled By: maysamyabandeh
fbshipit-source-id: 402962602eb0f644e17822748332999c3af029fd
Summary:
Top-level index in partitioned index/filter blocks are small and could be pinned in memory. So far we use that by cache_index_and_filter_blocks to false. This however make it difficult to keep account of the total memory usage. This patch introduces pin_top_level_index_and_filter which in combination with cache_index_and_filter_blocks=true keeps the top-level index in cache and yet pinned them to avoid cache misses and also cache lookup overhead.
Closes https://github.com/facebook/rocksdb/pull/4037
Differential Revision: D8596218
Pulled By: maysamyabandeh
fbshipit-source-id: 3a5f7f9ca6b4b525b03ff6bd82354881ae974ad2
Summary:
- Attempt to clean the checkpoint staging directory before starting a checkpoint. It was already cleaned up at the end of checkpoint. But it wasn't cleaned up in the edge case where the process crashed while staging checkpoint files.
- Attempt to clean the checkpoint directory before calling `Checkpoint::Create` in `db_stress`. This handles the case where checkpoint directory was created by a previous `db_stress` run but the process crashed before cleaning it up.
- Use `DestroyDB` for cleaning checkpoint directory since a checkpoint is a DB.
Closes https://github.com/facebook/rocksdb/pull/4035
Reviewed By: yiwu-arbug
Differential Revision: D8580223
Pulled By: ajkr
fbshipit-source-id: 28c667400e249fad0fdedc664b349031b7b61599
Summary:
We potentially need this information for tracing, profiling and diagnosis.
Closes https://github.com/facebook/rocksdb/pull/4026
Differential Revision: D8555214
Pulled By: riversand963
fbshipit-source-id: 4263e06c00b6d5410b46aa46eb4e358ff2161dd2
Summary:
Once per `ingest_external_file_one_in` operations, uses SstFileWriter to create a file containing `ingest_external_file_width` consecutive keys. The file is named containing the thread ID to avoid clashes. The file is then added to the DB using `IngestExternalFile`.
We can't enable it by default in crash test because `nooverwritepercent` and `test_batches_snapshot` both must be zero for the DB's whole lifetime. Perhaps we should setup a separate test with that config as range deletion also requires it.
Closes https://github.com/facebook/rocksdb/pull/4018
Differential Revision: D8507698
Pulled By: ajkr
fbshipit-source-id: 1437ea26fd989349a9ce8b94117241c65e40f10f
Summary:
Add the `backup_one_in` and `checkpoint_one_in` options to periodically trigger backups and checkpoints. The directory names contain thread ID to avoid clashing with parallel backups/checkpoints. Enable checkpoint in crash test so our CI runs will use it. Didn't enable backup in crash test since it copies all the files which is too slow.
Closes https://github.com/facebook/rocksdb/pull/4005
Differential Revision: D8472275
Pulled By: ajkr
fbshipit-source-id: ff91bdc37caac4ffd97aea8df96b3983313ac1d5
Summary:
Fixed bug where `db_stress` output a line with a warning followed by a line with an error, and `db_crashtest.py` considered that a success. For example:
```
WARNING: prefix_size is non-zero but memtablerep != prefix_hash
open error: Corruption: SST file is ahead of WALs
```
Closes https://github.com/facebook/rocksdb/pull/4006
Differential Revision: D8473463
Pulled By: ajkr
fbshipit-source-id: 60461bdd7491d9d26c63f7d4ee522a0f88ba3de7
Summary:
Make sure that some recent releases can read master's option files while ignoring unknown options. Also add two more recent release branches.
Closes https://github.com/facebook/rocksdb/pull/3994
Differential Revision: D8409499
Pulled By: siying
fbshipit-source-id: 1b025f19ba288da0517f6b4572797573e23e23c2
Summary:
db_stress initialization randomly chooses a set of keys to not overwrite. It was doing it separately for each column family. That caused 30+ second initialization times for the non-simple crash tests, which have 10 CFs. This PR:
- reuses the same set of randomly chosen no-overwrite keys across all CFs
- logs a couple more timestamps so we can more easily see initialization time
Closes https://github.com/facebook/rocksdb/pull/3990
Differential Revision: D8393821
Pulled By: ajkr
fbshipit-source-id: d0b263a298df607285ffdd8b0983ff6575cc6c34
Summary:
Fixed the fprintf format of uint64_t by using PRIu64 in file tools/ldb_cmd.cc
Closes https://github.com/facebook/rocksdb/pull/3963
Differential Revision: D8306179
Pulled By: zhichao-cao
fbshipit-source-id: 597dcd55321576801bbf2cf4714736ebc4750a0c
Summary:
We use `db_stress.cc` intensively to test and verify the behavior of RocksDB. Sometimes we need to add new tests for recently added features. Original `StressTest` class provides many general functionality that can be leveraged by other tests. Therefore, in this refactoring PR, I try to identify the general operations as well as operations that future tests most likely want to customize. Future tests can inherit `StressTest` and overriding the virtual functions to test custom logic.
Closes https://github.com/facebook/rocksdb/pull/3902
Differential Revision: D8284607
Pulled By: riversand963
fbshipit-source-id: 019302d04665a2b18334b6d05d04a477168c8ea4
Summary:
This adds some rules in the tools/advisor/advisor/rules.ini (refer this for more information) file and corresponding python parser scripts for parsing the rules file and the rocksdb LOG and OPTIONS files. This is WIP for adding rules depending on ODS. The starting point of the script is the rocksdb/tools/advisor/advisor/rule_parser.py file.
Closes https://github.com/facebook/rocksdb/pull/3934
Reviewed By: maysamyabandeh
Differential Revision: D8304059
Pulled By: poojam23
fbshipit-source-id: 47f2a50f04d46d40e225dd1cbf58ba490f79e239
Summary:
PR https://github.com/facebook/rocksdb/pull/3838 made some changes that triggers lint warnings.
Run `make format` to fix formatting as suggested by siying .
Also piggyback two changes:
1) fix singleton destruction order for windows and posix env
2) fix two clang warnings
Closes https://github.com/facebook/rocksdb/pull/3954
Differential Revision: D8272041
Pulled By: miasantreble
fbshipit-source-id: 7c4fd12bd17aac13534520de0c733328aa3c6c9f
Summary:
format_version=3 changes the format of SST index. This is however not being tested currently since tests only work with the default format_version which is currently 2. The patch extends the most related tests to also test for format_version=3.
Closes https://github.com/facebook/rocksdb/pull/3942
Differential Revision: D8238413
Pulled By: maysamyabandeh
fbshipit-source-id: 915725f55753dd8e9188e802bf471c23645ad035
Summary:
Windows does not have LD_PRELOAD mechanism to override all memory allocation functions and ZSTD makes use of C-tuntime calloc. During flushes and compactions default system allocator fragments and the system slows down considerably.
For builds with jemalloc we employ an advanced ZSTD context creation API that re-directs memory allocation to jemalloc. To reduce the cost of context creation on each block we cache ZSTD context within the block based table builder while a new SST file is being built, this will help all platform builds including those w/o jemalloc. This avoids system allocator fragmentation and improves the performance.
The change does not address random reads and currently on Windows reads with ZSTD regress as compared with SNAPPY compression.
Closes https://github.com/facebook/rocksdb/pull/3838
Differential Revision: D8229794
Pulled By: miasantreble
fbshipit-source-id: 719b622ab7bf4109819bc44f45ec66f0dd3ee80d
Summary:
We need to keep the DB directory around since the direct IO check in "db_crashtest.py" relies on it existing. This PR fixes an issue where it was removed after each stress test run during the second half of whitebox crash testing.
Closes https://github.com/facebook/rocksdb/pull/3946
Differential Revision: D8247998
Pulled By: ajkr
fbshipit-source-id: 4e7cffbdab9b40df125e7842d0d59916e76261d3
Summary:
Previously `db_stress` attempted to configure direct I/O dynamically in `SetOptions()` which had multiple problems (ummm must've never been tested):
- It's a DB option so SetDBOptions should've been called instead
- It's not a dynamic option so even SetDBOptions would fail
- It required enabling SyncPoint to mask O_DIRECT since it had no way to detect whether the DB directory was in tmpfs or not. This required locking that consumed ~80% of db_stress CPU.
In this PR I delete the broken dynamic config and instead configure it statically, only enabling it if the DB directory truly supports O_DIRECT.
Closes https://github.com/facebook/rocksdb/pull/3939
Differential Revision: D8238120
Pulled By: ajkr
fbshipit-source-id: 60bb2deebe6c9b54a3f788079261715b4a229279
Summary:
Small format error below causes build to fail. I believe that this :
```
fprintf(stderr, "num reads to do %lu\n", reads_);
```
Can be changed to this:
```
fprintf(stderr, "num reads to do %" PRIu64 "\n", reads_);
```
Successful build
```
CC utilities/blob_db/blob_dump_tool.o
AR librocksdb_debug.a
ar: creating archive librocksdb_debug.a
/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/ranlib: file: librocksdb_debug.a(rocks_lua_compaction_filter.o) has no symbols
CC tools/db_bench.o
CC tools/db_bench_tool.o
tools/db_bench_tool.cc:4532:46: error: format specifies type 'unsigned long' but the argument has type 'int64_t' (aka 'long long') [-Werror,-Wformat]
fprintf(stderr, "num reads to do %lu\n", reads_);
~~~ ^~~~~~
%lld
1 error generated.
make: *** [tools/db_bench_tool.o] Error 1
```
```
$ cd rocksdb
$ make all
$ g++ --version
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 9.1.0 (clang-902.0.39.1)
Target: x86_64-apple-darwin17.5.0
Thread model: posix
InstalledDir: /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin
```
Closes https://github.com/facebook/rocksdb/pull/3909
Differential Revision: D8215710
Pulled By: siying
fbshipit-source-id: 15e49fb02a818fec846e9f9b2a50e372b6b67751
Summary:
Implement midpoint insertion strategy where new blocks will be insert to the middle of LRU list, then move the head on the first hit in cache.
Closes https://github.com/facebook/rocksdb/pull/3877
Differential Revision: D8100895
Pulled By: yiwu-arbug
fbshipit-source-id: f4bd83cb8be469e5d02072cfc8bd66011391f3da
Summary:
Catch up with Posix features
NewWritableRWFile must fail when file does not exists
Implement Env::Truncate()
Adjust Env options optimization functions
Implement MemoryMappedBuffer on Windows.
Closes https://github.com/facebook/rocksdb/pull/3857
Differential Revision: D8053610
Pulled By: ajkr
fbshipit-source-id: ccd0d46c29648a9f6f496873bc1c9d6c5547487e
Summary:
I repro'd some of the "unexpected value" failures showing up in our CI lately and they always happened on keys that have a mix of single deletes and merge operands. The `SingleDelete()` API comment mentions it's incompatible with `Merge()`, so this PR prevents `db_stress` from mixing them.
Closes https://github.com/facebook/rocksdb/pull/3878
Differential Revision: D8097346
Pulled By: ajkr
fbshipit-source-id: 357a48c6a31156f4f8db3ce565638ad924c437a1
Summary:
Currently it is not possible to change bloom filter config without restart the db, which is causing a lot of operational complexity for users.
This PR aims to make it possible to dynamically change bloom filter config.
Closes https://github.com/facebook/rocksdb/pull/3601
Differential Revision: D7253114
Pulled By: miasantreble
fbshipit-source-id: f22595437d3e0b86c95918c484502de2ceca120c
Summary:
In the past, the default value of max_manifest_file_size is uint64_t::MAX,
allowing a long running RocksDB process to grow its MANIFEST file to take up
the entire disk, as reported in [issue 3851](https://github.com/facebook/rocksdb/issues/3851). It is reasonable and common to provide a default non-max value for this option. Therefore, I set the value to 1GB.
siying miasantreble Please let me know whether this looks good to you. Thanks!
Closes https://github.com/facebook/rocksdb/pull/3867
Differential Revision: D8051524
Pulled By: riversand963
fbshipit-source-id: 50251f0804b1fa933a19a30d19d261ea8b9d2b72
Summary:
I noticed, while debugging an unrelated issue, that db_stress is failing to build on mac, leading to a failed `make all`.
```
$ make db_stress -j4
...
tools/db_stress.cc:862:69: error: cannot initialize a parameter of type 'uint64_t *' (aka 'unsigned long long *') with an rvalue of type 'size_t *' (aka 'unsigned long *')
status = FLAGS_env->GetFileSize(FLAGS_expected_values_path, &size);
^~~~~
./include/rocksdb/env.h:277:66: note: passing argument to parameter 'file_size' here
virtual Status GetFileSize(const std::string& fname, uint64_t* file_size) = 0;
^
1 error generated.
make: *** [tools/db_stress.o] Error 1
make: *** Waiting for unfinished jobs....
```
Closes https://github.com/facebook/rocksdb/pull/3839
Differential Revision: D7979236
Pulled By: sagar0
fbshipit-source-id: 0615e7bb5405bade71e4203803bf723720422d62
Summary:
Previously `DBOptions::use_direct_io_for_flush_and_compaction=true` combined with `DBOptions::use_direct_reads=false` could cause RocksDB to simultaneously read from two file descriptors for the same file, where background reads used direct I/O and foreground reads used buffered I/O. Our measurements found this mixed-mode I/O negatively impacted foreground read perf, compared to when only buffered I/O was used.
This PR makes the mixed-mode I/O situation impossible by repurposing `DBOptions::use_direct_io_for_flush_and_compaction` to only apply to background writes, and `DBOptions::use_direct_reads` to apply to all reads. There is no risk of direct background direct writes happening simultaneously with buffered reads since we never read from and write to the same file simultaneously.
Closes https://github.com/facebook/rocksdb/pull/3829
Differential Revision: D7915443
Pulled By: ajkr
fbshipit-source-id: 78bcbf276449b7e7766ab6b0db246f789fb1b279
Summary:
- Any options unknown to `db_crashtest.py` are now passed directly to `db_stress`. This way, we won't need to update `db_crashtest.py` every time `db_stress` gets a new option.
- Remove `db_crashtest.py` redundant arguments where the value is the same as `db_stress`'s default
- Remove `db_crashtest.py` redundant arguments where the value is the same in a previously applied options map. For example, default_params are always applied before whitebox_default_params, so if they require the same value for an argument, that value only needs to be provided in default_params.
- Made the simple option maps applied in addition to the regular option maps. Previously they were exclusive which led to lots of duplication
Closes https://github.com/facebook/rocksdb/pull/3809
Differential Revision: D7885779
Pulled By: ajkr
fbshipit-source-id: 3a3243b55724d6d5bff36e939b582b9b62c538a8
Summary:
In case `--expected_values_path` is unset, we allocate a buffer internally to hold the expected DB state. This PR makes sure it is freed.
Closes https://github.com/facebook/rocksdb/pull/3804
Differential Revision: D7874694
Pulled By: ajkr
fbshipit-source-id: a8f7655e009507c4e639ceebfc3525d69c856e3b
Summary:
Returning bytes_read causes the caller to call GetLastError()
to report failure but the lasterror may be overwritten by then
so we lose the error code.
Fix up CMake file to include xpress source code only when needed.
Fix warning for the uninitialized var.
Closes https://github.com/facebook/rocksdb/pull/3795
Differential Revision: D7832935
Pulled By: anand1976
fbshipit-source-id: 4be21affb9b85d361b96244f4ef459f492b7cb2b
Summary:
- Original commit: a4fb1f8c04
- Revert commit (we reverted as a quick fix to get crash tests passing): 6afe22db2e
This PR includes the contents of the original commit plus two bug fixes, which are:
- In whitebox crash test, only set `--expected_values_path` for `db_stress` runs in the first half of the crash test's duration. In the second half, a fresh DB is created for each `db_stress` run, so we cannot maintain expected state across `db_stress` runs.
- Made `Exists()` return true for `UNKNOWN_SENTINEL` values. I previously had an assert in `Exists()` that value was not `UNKNOWN_SENTINEL`. But it is possible for post-crash-recovery expected values to be `UNKNOWN_SENTINEL` (i.e., if the crash happens in the middle of an update), in which case this assertion would be tripped. The effect of returning true in this case is there may be cases where a `SingleDelete` deletes no data. But if we had returned false, the effect would be calling `SingleDelete` on a key with multiple older versions, which is not supported.
Closes https://github.com/facebook/rocksdb/pull/3793
Differential Revision: D7811671
Pulled By: ajkr
fbshipit-source-id: 67e0295bfb1695ff9674837f2e05bb29c50efc30
Summary:
crash-recovery verification is failing in the whitebox testing, which may or may not be a valid correctness issue -- need more time to investigate. In the meantime, reverting so we don't mask other failures.
Closes https://github.com/facebook/rocksdb/pull/3786
Differential Revision: D7794516
Pulled By: ajkr
fbshipit-source-id: 28ccdfdb9ec9b3b0fb08c15cbf9d2e282201ff33
Summary:
- When options file is provided to db_stress, take supported options from the file instead of from flags
- Call `BuildOptionsTable` after `Open` so it can use `options_` once it has been populated either from flags or from file
- Allow options filename to be passed via `db_crashtest.py`
Closes https://github.com/facebook/rocksdb/pull/3768
Differential Revision: D7755331
Pulled By: ajkr
fbshipit-source-id: 5205cc5deb0d74d677b9832174153812bab9a60a
Summary:
Previously, our `db_stress` tool held the expected state of the DB in-memory, so after crash-recovery, there was no way to verify data correctness. This PR adds an option, `--expected_values_file`, which specifies a file holding the expected values.
In black-box testing, the `db_stress` process can be killed arbitrarily, so updates to the `--expected_values_file` must be atomic. We achieve this by `mmap`ing the file and relying on `std::atomic<uint32_t>` for atomicity. Actually this doesn't provide a total guarantee on what we want as `std::atomic<uint32_t>` could, in theory, be translated into multiple stores surrounded by a mutex. We can verify our assumption by looking at `std::atomic::is_always_lock_free`.
For the `mmap`'d file, we didn't have an existing way to expose its contents as a raw memory buffer. This PR adds it in the `Env::NewMemoryMappedFileBuffer` function, and `MemoryMappedFileBuffer` class.
`db_crashtest.py` is updated to use an expected values file for black-box testing. On the first iteration (when the DB is created), an empty file is provided as `db_stress` will populate it when it runs. On subsequent iterations, that same filename is provided so `db_stress` can check the data is as expected on startup.
Closes https://github.com/facebook/rocksdb/pull/3629
Differential Revision: D7463144
Pulled By: ajkr
fbshipit-source-id: c8f3e82c93e045a90055e2468316be155633bd8b
Summary:
Background activities like compaction can negatively affect
latency of higher-priority tasks like request processing. To avoid this,
rocksdb already lowers the IO priority of background threads on Linux
systems. While this takes care of typical IO-bound systems, it does not
help much when CPU (temporarily) becomes the bottleneck. This is
especially likely when using more expensive compression settings.
This patch adds an API to allow for lowering the CPU priority of
background threads, modeled on the IO priority API. Benchmarks (see
below) show significant latency and throughput improvements when CPU
bound. As a result, workloads with some CPU usage bursts should benefit
from lower latencies at a given utilization, or should be able to push
utilization higher at a given request latency target.
A useful side effect is that compaction CPU usage is now easily visible
in common tools, allowing for an easier estimation of the contribution
of compaction vs. request processing threads.
As with IO priority, the implementation is limited to Linux, degrading
to a no-op on other systems.
Closes https://github.com/facebook/rocksdb/pull/3763
Differential Revision: D7740096
Pulled By: gwicke
fbshipit-source-id: e5d32373e8dc403a7b0c2227023f9ce4f22b413c
Summary:
db_stress was already capable running transactions by setting use_txn. Running it under stress showed a couple of problems fixed in this patch.
- The uncommitted transaction must be either rolled back or commit after recovery.
- Current implementation of WritePrepared transaction cannot handle cf drop before crash. Clarified that in the comments and added safety checks. When running with use_txn, clear_column_family_one_in must be set to 0.
Closes https://github.com/facebook/rocksdb/pull/3733
Differential Revision: D7654419
Pulled By: maysamyabandeh
fbshipit-source-id: a024bad80a9dc99677398c00d29ff17d4436b7f3
Summary:
fix a bug in `db_stress` where an int array was incorrectly deallocated using delete instead of delete[]
Closes https://github.com/facebook/rocksdb/pull/3725
Differential Revision: D7634749
Pulled By: miasantreble
fbshipit-source-id: 489b776f5f4c03de1824edac5495787ec19cc910
Summary:
this PR fixes a few failed contbuild:
1. ASAN memory leak in Block::NewIterator (table/block.cc:429). the proper destruction of first_level_iter_ and second_level_iter_ of two_level_iterator.cc is missing from the code after the refactoring in https://github.com/facebook/rocksdb/pull/3406
2. various unused param errors introduced by https://github.com/facebook/rocksdb/pull/3662
3. updated comment for `ForceReleaseCachedEntry` to emphasize the use of `force_erase` flag.
Closes https://github.com/facebook/rocksdb/pull/3718
Reviewed By: maysamyabandeh
Differential Revision: D7621192
Pulled By: miasantreble
fbshipit-source-id: 476c94264083a0730ded957c29de7807e4f5b146
