- 02 11月, 2022 1 次提交
-
-
由 akankshamahajan 提交于
Summary: Fix memory corruption error in scans if async_io is enabled. Memory corruption happened if data is overlapping between two buffers. If there is IOError while reading the data, it leads to empty buffer and other buffer already in progress of async read goes again for reading causing the error. Fix: Added check to abort IO in second buffer if curr_ got empty. This PR also fixes db_stress failures which happened when buffers are not aligned. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10890 Test Plan: - Ran make crash_test -j32 with async_io enabled. - Ran benchmarks to make sure there is no regression. Reviewed By: anand1976 Differential Revision: D40881731 Pulled By: akankshamahajan15 fbshipit-source-id: 39fcf2134c7b1bbb08415ede3e1ef261ac2dbc58
-
- 01 11月, 2022 5 次提交
-
-
由 Yanqin Jin 提交于
Summary: This PR implements the originally disabled `Merge()` APIs when user-defined timestamp is enabled. Simplest usage: ```cpp // assume string append merge op is used with '.' as delimiter. // ts1 < ts2 db->Put(WriteOptions(), "key", ts1, "v0"); db->Merge(WriteOptions(), "key", ts2, "1"); ReadOptions ro; ro.timestamp = &ts2; db->Get(ro, "key", &value); ASSERT_EQ("v0.1", value); ``` Some code comments are added for clarity. Note: support for timestamp in `DB::GetMergeOperands()` will be done in a follow-up PR. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10819 Test Plan: make check Reviewed By: ltamasi Differential Revision: D40603195 Pulled By: riversand963 fbshipit-source-id: f96d6f183258f3392d80377025529f7660503013
-
由 Denis Hananein 提交于
Summary: I've tried to compile the main branch, but there are two minor things which are make CE. I'm not sure about the second one (`num_empty_non_l0_level`), probably there is should be additional assert. ``` -c ../cache/clock_cache.cc [build] ../cache/clock_cache.cc:855:15: error: variable 'i' set but not used [-Werror,-Wunused-but-set-variable] [build] for (size_t i = 0; &array_[current] != h; i++) { [build] ^ ``` ``` [build] ../db/version_set.cc:3665:7: error: variable 'num_empty_non_l0_level' set but not used [-Werror,-Wunused-but-set-variable] [build] int num_empty_non_l0_level = 0; [build] ^ [build] 1 error generated. ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/10907 Reviewed By: jay-zhuang Differential Revision: D40866667 Pulled By: ajkr fbshipit-source-id: 963b7bd56859d0b3b2779cd36fad229425cb7b17
-
由 Hui Xiao 提交于
Summary: **Context/Summary:** https://github.com/facebook/rocksdb/pull/10777 mistakenly added a history entry under 7.8 release but the PR is not included in 7.8. This mistake was due to rebase and merge didn't realize it was a conflict when "## Unreleased" was changed to "## 7.8.0 (10/22/2022)". Pull Request resolved: https://github.com/facebook/rocksdb/pull/10898 Test Plan: Make check Reviewed By: akankshamahajan15 Differential Revision: D40861001 Pulled By: hx235 fbshipit-source-id: b2310c95490f6ebb90834a210c965a74c9560b51
-
由 Levi Tamasi 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10900 Reviewed By: akankshamahajan15 Differential Revision: D40825886 Pulled By: ltamasi fbshipit-source-id: e60f74aa8a622c3c71e1fee420fd586728fb2b7b
-
由 sdong 提交于
Summary: When there is a column family that doesn't get any traffic, its stats are still dumped when options.options.stats_dump_period_sec triggers. This sometimes spam the information logs. With this change, we skip the printing if there is not change, until 8 periods. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10891 Test Plan: Manually test the behavior with hacked db_bench setups. Reviewed By: jay-zhuang Differential Revision: D40777183 fbshipit-source-id: ef0b9a793e4f6282df099b464f01d1fb4c5a2cab
-
- 29 10月, 2022 6 次提交
-
-
由 Yanqin Jin 提交于
Summary: Currently, a memtable's stats `num_deletes_` is incremented only if the entry is a regular delete (kTypeDeletion). We need to fix it by accounting for kTypeSingleDeletion and kTypeDeletionWithTimestamp. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10886 Test Plan: make check Reviewed By: ltamasi Differential Revision: D40740754 Pulled By: riversand963 fbshipit-source-id: 7bde62cd6df136585bc5bfb1c426c7a8276c08e1
-
由 Jay Zhuang 提交于
Summary: The for loop is marked as unreachable code because it will never call the increment. Switch it to `if`. ``` \table\merging_iterator.cc(823): error C2220: the following warning is treated as an error \table\merging_iterator.cc(823): warning C4702: unreachable code \table\merging_iterator.cc(1030): error C2220: the following warning is treated as an error \table\merging_iterator.cc(1030): warning C4702: unreachable code ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/10897 Reviewed By: cbi42 Differential Revision: D40811790 Pulled By: jay-zhuang fbshipit-source-id: fe8fd3e7cf3d6f710360c402b79763854d5120df
-
由 Yanqin Jin 提交于
Summary: The motivation and benefit of current behavior of passing `LockInfo&&` as argument to AcquireLocked() and AcquireWithTimeout() is not clear to me. Furthermore, in AcquireWithTimeout(), we access members of `LockInfo&&` after it is passed to AcquireLocked() as rvalue ref. In addition, we may call `AcquireLocked()` with `std::move(lock_info)` multiple times. This leads to linter warning of use-after-move. If future implementation of AcquireLocked() does something like moving-construct a new `LockedInfo` using the passed-in `LockInfo&&`, then the caller cannot use it because `LockInfo` has a member of type `autovector`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10874 Test Plan: make check Reviewed By: ltamasi Differential Revision: D40704210 Pulled By: riversand963 fbshipit-source-id: 20091df65b4fc63b072bcec9809efc49955d6d35
-
由 Hui Xiao 提交于
Summary: **Context/Summary:** Run the following to format ``` find ./examples -iname *.h -o -iname *.cc | xargs clang-format -i find ./memory -iname *.h -o -iname *.cc | xargs clang-format -i find ./memtable -iname *.h -o -iname *.cc | xargs clang-format -i ``` **Test** - Manual inspection to ensure changes are cosmetic only - CI Pull Request resolved: https://github.com/facebook/rocksdb/pull/10893 Reviewed By: jay-zhuang Differential Revision: D40779187 Pulled By: hx235 fbshipit-source-id: 529cbb0f0fbd698d95817e8c42fe3ce32254d9b0
-
由 Levi Tamasi 提交于
Summary: The PR fixes the handling of `Merge`s in `GetEntity`. Note that `Merge` is not yet supported for wide-column entities written using `PutEntity`; this change is about returning correct (i.e. consistent with `Get`) results in cases like when the base value is a plain old key-value written using `Put` or when there is no real base value because we hit either a tombstone or the beginning of history. Implementation-wise, the patch introduces a new wrapper around the existing `MergeHelper::TimedFullMerge` that can store the merge result in either a string (for the purposes of `Get`) or a `PinnableWideColumns` instance (for `GetEntity`). Pull Request resolved: https://github.com/facebook/rocksdb/pull/10894 Test Plan: `make check` Reviewed By: riversand963 Differential Revision: D40782708 Pulled By: ltamasi fbshipit-source-id: 3d700d56b2ef81f02ba1e2d93f6481bf13abcc90
-
由 Jay Zhuang 提交于
Summary: * Upgrade CircleCI orb from 2.4 to 5.0 * Setup vs2022 build * Use image build-in vs2019 and vs2022 * Remove vs2017 * Remove CMAKE_CXX_STANDARD=20 Pull Request resolved: https://github.com/facebook/rocksdb/pull/10090 Reviewed By: ajkr Differential Revision: D40787942 Pulled By: jay-zhuang fbshipit-source-id: cc74c02a9f28dd784a0ba5502c4bfc9ff1a26d3e
-
- 28 10月, 2022 4 次提交
-
-
由 anand76 提交于
Summary: This option allows a custom cleanup command line for a non-Posix file system to be used by db_crashtest.py to cleanup between runs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10883 Test Plan: Run the whitebox crash test Reviewed By: pdillinger Differential Revision: D40726424 Pulled By: anand1976 fbshipit-source-id: b827f6b583ff78f9ca75ced2d96f7e58f5200432
-
由 Levi Tamasi 提交于
Summary: It's unsafe to call `malloc_usable_size` with an address not returned by a function from the `malloc` family (see https://github.com/facebook/rocksdb/issues/10798). The patch switches from using `new[]` / `delete[]` for `LRUHandle` to `malloc` / `free`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10884 Test Plan: `make check` Reviewed By: pdillinger Differential Revision: D40738089 Pulled By: ltamasi fbshipit-source-id: ac5583f88125fee49c314639be6b6df85937fbee
-
由 Changyu Bi 提交于
Summary: Right now in MergingIterator, for each range tombstone start and end key, we pop one end from heap and push the other end into the heap. This involves extra downheap and upheap cost. In the likely cases when a range tombstone iterator emits relatively adjacent keys, these keys should have similar order within all keys in the heap. This can happen when there is a burst of consecutive range tombstones, and most of the keys covered by them are dropped already. This PR uses `replace_top()` when inserting new range tombstone keys, which is more efficient in these common cases. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10877 Test Plan: - existing UT - ran all flavors of stress test through sandcastle - benchmark: ``` # Set up: --writes_per_range_tombstone=1 means one point write and one delete range TEST_TMPDIR=/tmp/rocksdb-rangedel-test-all-tombstone ./db_bench --benchmarks=fillseq,levelstats --writes_per_range_tombstone=1 --max_num_range_tombstones=1000000 --range_tombstone_width=2 --num=100000000 --writes=800000 --max_bytes_for_level_base=4194304 --disable_auto_compactions --write_buffer_size=33554432 --key_size=64 Level Files Size(MB) -------------------- 0 8 152 1 0 0 2 0 0 3 0 0 4 0 0 5 0 0 6 0 0 # Benchmark TEST_TMPDIR=/tmp/rocksdb-rangedel-test-all-tombstone/ ./db_bench --benchmarks=readseq[-W1][-X5],levelstats --use_existing_db=true --cache_size=3221225472 --num=100000000 --reads=1000000 --disable_auto_compactions=true --avoid_flush_during_recovery=true # Pre PR readseq [AVG 5 runs] : 1432116 (± 59664) ops/sec; 224.0 (± 9.3) MB/sec readseq [MEDIAN 5 runs] : 1454886 ops/sec; 227.5 MB/sec # Post PR readseq [AVG 5 runs] : 1944425 (± 29521) ops/sec; 304.1 (± 4.6) MB/sec readseq [MEDIAN 5 runs] : 1959430 ops/sec; 306.5 MB/sec ``` Reviewed By: ajkr Differential Revision: D40710936 Pulled By: cbi42 fbshipit-source-id: cb782fb9cdcd26c0c3eb9443215a4ef4d2f79022
-
由 sdong 提交于
Summary: Add some extra information in outputs of "sst_dump --command=raw" to help debug some issues. Right now, encoded block handle is printed out. It is more useful to directly print out offset and size. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10873 Test Plan: Manually run it against a file and check the output. Reviewed By: anand1976 Differential Revision: D40742289 fbshipit-source-id: 04d7de26e7f27e1595a7cc3ac1c1082e4e835b93
-
- 27 10月, 2022 7 次提交
-
-
由 anand76 提交于
Summary: The call to `folly::coro::collectAllRange()` should move the input `mget_tasks`. But just in case, assert and clear the std::vector before reusing. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10845 Reviewed By: akankshamahajan15 Differential Revision: D40611719 Pulled By: anand1976 fbshipit-source-id: 0f32b387cf5a2894b13389016c020b01ab479b5e
-
由 Peter Dillinger 提交于
Summary: If windows.h is not included in a particular way, it can conflict with other code including it. I don't know all the details, but having just one standard place where we include windows.h in header files seems best and seems to fix the internal issue we hit. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10885 Test Plan: CI and internal validation Reviewed By: anand1976 Differential Revision: D40738945 Pulled By: pdillinger fbshipit-source-id: 88f635e895b1c7b810baad159e6dbb8351344cac
-
由 Alan Paxton 提交于
RocksJava API - fix Transaction.multiGet() size limit, remove bogus EnsureLocalCapacity() calls (#10674) Summary: Resolves see https://github.com/facebook/rocksdb/issues/9006 Fixes 2 related issues with JNI local references in the RocksJava API. 1. Some instances of RocksJava API JNI code appear to have misunderstood the reason for `JNIEnv->EnsureLocalCapacity()` and are carrying out bogus checks which happen to fail with some larger parameter values (many column families in a single call, very long key names or values). Remove these checks and add some regression tests for the previous failures. 2. The helper for Transaction multiGet operations (`multiGet()`, `multiGetForUpdate()`,...) is limited in the number of keys it can `get()` for because it requires a corresponding number of live local references. Refactor the helper slightly, copying out the key contents within a loop so that the references don't have to exist at the same time. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10674 Reviewed By: ajkr Differential Revision: D40515361 Pulled By: jay-zhuang fbshipit-source-id: f1be0126181a698b3ad27c0945a39c54d950aa25
-
由 Qiaolin Yu 提交于
Summary: Currently, the name of `block_cache_trace_analyzer_tool` in `CMakeLists.txt` is somewhat confusing. ## Makefile The same thing in Makefile is called `block_cache_trace_analyzer`. ```c++ block_cache_trace_analyzer: $(OBJ_DIR)/tools/block_cache_analyzer/block_cache_trace_analyzer_tool.o $(ANALYZE_OBJECTS) $(TOOLS_LIBRARY) $(LIBRARY) $(AM_LINK) ``` ## RocksDB Wiki Also, in the [Block-cache-analysis-and-simulation-tools](https://github.com/facebook/rocksdb/wiki/Block-cache-analysis-and-simulation-tools#quick-start) of RocksDB Wiki, it is called `block_cache_trace_analyzer` too. <img width="955" alt="Screen Shot 2022-10-13 at 20 07 09" src="https://user-images.githubusercontent.com/90088090/195591912-00b539b4-7f8c-4117-bf72-ac4eb51100d1.png"> Therefore, I think maybe it's better to rename `block_cache_trace_analyzer_tool` to `block_cache_trace_analyzer` in `CMakeLists.txt`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10814 Reviewed By: ajkr Differential Revision: D40348522 Pulled By: jay-zhuang fbshipit-source-id: f3d69d5880b27cdb8c8fe71df56fa3dbe1dc32fb
-
由 Jay Zhuang 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10882 Reviewed By: riversand963 Differential Revision: D40724867 Pulled By: jay-zhuang fbshipit-source-id: 7f387724f8cd07d8d2b90566a515a4e9078d21f1
-
由 Peter Dillinger 提交于
Summary: Complements https://github.com/facebook/rocksdb/issues/10867 with some manual edits to avoid weird formatting or to avoid massive reformatting third party code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10870 Test Plan: `make check` etc Reviewed By: riversand963 Differential Revision: D40686526 Pulled By: pdillinger fbshipit-source-id: 6af988fe4b0a8ae4a5992ec2c3c37fe67584226e
-
由 Peter Dillinger 提交于
Summary: This is purely the result of running `clang-format -i` on files, except some files have been excluded for manual intervention in a separate PR Pull Request resolved: https://github.com/facebook/rocksdb/pull/10867 Test Plan: `make check`, `make check-headers`, `make format` Reviewed By: jay-zhuang Differential Revision: D40682086 Pulled By: pdillinger fbshipit-source-id: 8673d978553ab99b516da7fb63ba0b82523337f8
-
- 26 10月, 2022 9 次提交
-
-
由 Brendan MacDonell 提交于
Summary: While PR#9749 nominally added support for XXH3 in the Java API, it did not update the `toCppChecksumType` method. As a result, setting the checksum type to XXH3 actually set it to CRC32c instead. This commit adds the missing entry to portal.h, and also updates the tests so that they verify the options passed to RocksDB, instead of simply checking that the getter returns the value set by the setter. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10862 Reviewed By: pdillinger Differential Revision: D40665031 Pulled By: ajkr fbshipit-source-id: 2834419b3361a4bac47db3b858951fb451b5bdc8
-
由 Levi Tamasi 提交于
Summary: The patch adjusts the generation of values in batched ops stress tests so that the digits 0..9 are appended (instead of prepended) to the values written. This has the advantage of aligning the encoding of the "value base" into the value string across non-batched, batched, and CF consistency stress tests. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10872 Test Plan: Tested using some black box stress test runs. Reviewed By: riversand963 Differential Revision: D40692847 Pulled By: ltamasi fbshipit-source-id: 26bf8adff2944cbe416665f09c3bab89d80416b3
-
由 sdong 提交于
Summary: Some lines of .h and .cc files are not properly fomatted. Clear them up with clang format. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10868 Test Plan: Watch existing CI to pass Reviewed By: ajkr Differential Revision: D40683485 fbshipit-source-id: 491fbb78b2cdcb948164f306829909ad816d5d0b
-
由 Yanqin Jin 提交于
Summary: This PR is the result of running the following command ``` find ./utilities/transactions/ -name '*.cc' -o -name '*.h' -o -name '*.c' -o -name '*.hpp' -o -name '*.cpp' | xargs clang-format -i ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/10871 Test Plan: make check Reviewed By: cbi42 Differential Revision: D40686871 Pulled By: riversand963 fbshipit-source-id: 613738d667ec8f8e13cce4802e0e166d6be52211
-
由 Yanqin Jin 提交于
Summary: Run clang-format on some files in db/db_impl/ directory ``` clang-format -i <file> ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/10869 Test Plan: make check Reviewed By: ltamasi Differential Revision: D40685390 Pulled By: riversand963 fbshipit-source-id: 64449ccb21b0d61c5142eb2bcbff828acb45c154
-
由 anand76 提交于
Summary: Run clang-format on files under the `table` directory. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10852 Reviewed By: ajkr Differential Revision: D40650732 Pulled By: anand1976 fbshipit-source-id: 2023a958e37fd6274040c5181130284600c9e0ef
-
由 Changyu Bi 提交于
Summary: FragmentedRangeTombstoneList has a member variable `seq_set_` that contains the sequence numbers of all range tombstones in a set. The set is constructed in `FragmentTombstones()` and is used only in `FragmentedRangeTombstoneList::ContainsRange()` which only happens during compaction. This PR moves the initialization of `seq_set_` to `FragmentedRangeTombstoneList::ContainsRange()`. This should speed up `FragmentTombstones()` when the range tombstone list is used for read/scan requests. Microbench shows the speed improvement to be ~45%. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10848 Test Plan: - Existing tests and stress test: `python3 tools/db_crashtest.py whitebox --simple --verify_iterator_with_expected_state_one_in=5`. - Microbench: update `range_del_aggregator_bench` to benchmark speed of `FragmentTombstones()`: ``` ./range_del_aggregator_bench --num_range_tombstones=1000 --tombstone_start_upper_bound=50000000 --num_runs=10000 --tombstone_width_mean=200 --should_deletes_per_run=100 --use_compaction_range_del_aggregator=true Before this PR: ========================= Fragment Tombstones: 270.286 us AddTombstones: 1.28933 us ShouldDelete (first): 0.525528 us ShouldDelete (rest): 0.0797519 us After this PR: time to fragment tombstones is pushed to AddTombstones() which only happen during compaction. ========================= Fragment Tombstones: 149.879 us AddTombstones: 102.131 us ShouldDelete (first): 0.565871 us ShouldDelete (rest): 0.0729444 us ``` - db_bench: this should improve speed for fragmenting range tombstones for mutable memtable: ``` ./db_bench --benchmarks=readwhilewriting --writes_per_range_tombstone=100 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=250000 --disable_auto_compactions --max_num_range_tombstones=100000 --finish_after_writes --write_buffer_size=1073741824 --threads=25 Before this PR: readwhilewriting : 18.301 micros/op 1310445 ops/sec 4.769 seconds 6250000 operations; 28.1 MB/s (41001 of 250000 found) After this PR: readwhilewriting : 16.943 micros/op 1439376 ops/sec 4.342 seconds 6250000 operations; 23.8 MB/s (28977 of 250000 found) ``` Reviewed By: ajkr Differential Revision: D40646227 Pulled By: cbi42 fbshipit-source-id: ea471667edb258f67d01cfd828588e80a89e4083
-
由 Hui Xiao 提交于
Fix FIFO causing overlapping seqnos in L0 files due to overlapped seqnos between ingested files and memtable's (#10777) Summary: **Context:** Same as https://github.com/facebook/rocksdb/pull/5958#issue-511150930 but apply the fix to FIFO Compaction case Repro: ``` COERCE_CONTEXT_SWICH=1 make -j56 db_stress ./db_stress --acquire_snapshot_one_in=0 --adaptive_readahead=0 --allow_data_in_errors=True --async_io=1 --avoid_flush_during_recovery=0 --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 --batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=18 --bottommost_compression_type=disable --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_size=8388608 --cache_type=lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=1 --charge_table_reader=1 --checkpoint_one_in=0 --checksum_type=kCRC32c --clear_column_family_one_in=0 --column_families=1 --compact_files_one_in=0 --compact_range_one_in=1000 --compaction_pri=3 --open_files=-1 --compaction_style=2 --fifo_allow_compaction=1 --compaction_ttl=0 --compression_max_dict_buffer_bytes=8388607 --compression_max_dict_bytes=16384 --compression_parallel_threads=1 --compression_type=zlib --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --data_block_index_type=0 --db=/dev/shm/rocksdb_test0/rocksdb_crashtest_whitebox --db_write_buffer_size=8388608 --delpercent=4 --delrangepercent=1 --destroy_db_initially=1 --detect_filter_construct_corruption=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --fail_if_options_file_error=1 --file_checksum_impl=none --flush_one_in=1000 --format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=0 --get_property_one_in=0 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=15 --index_type=3 --ingest_external_file_one_in=100 --initial_auto_readahead_size=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --log2_keys_per_lock=10 --long_running_snapshots=0 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000 --max_key_len=3 --max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=1048576 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=4194304 --memtable_prefix_bloom_size_ratio=0.5 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --memtablerep=skip_list --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --num_levels=1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=32 --open_write_fault_one_in=0 --ops_per_thread=200000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=1 --pause_background_one_in=0 --periodic_compaction_seconds=0 --prefix_size=8 --prefixpercent=5 --prepopulate_block_cache=0 --progress_reports=0 --read_fault_one_in=0 --readahead_size=16384 --readpercent=45 --recycle_log_file_num=1 --reopen=20 --ribbon_starting_level=999 --snapshot_hold_ops=1000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --top_level_index_pinning=3 --unpartitioned_pinning=0 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=1 --use_merge=0 --use_multiget=1 --user_timestamp_size=0 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=0 --verify_db_one_in=1000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=zstd --write_buffer_size=524288 --write_dbid_to_manifest=0 --writepercent=35 put or merge error: Corruption: force_consistency_checks(DEBUG): VersionBuilder: L0 file https://github.com/facebook/rocksdb/issues/479 with seqno 23711 29070 vs. file https://github.com/facebook/rocksdb/issues/482 with seqno 27138 29049 ``` **Summary:** FIFO only does intra-L0 compaction in the following four cases. For other cases, FIFO drops data instead of compacting on data, which is irrelevant to the overlapping seqno issue we are solving. - [FIFOCompactionPicker::PickSizeCompaction](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L155) when `total size < compaction_options_fifo.max_table_files_size` and `compaction_options_fifo.allow_compaction == true` - For this path, we simply reuse the fix in `FindIntraL0Compaction` https://github.com/facebook/rocksdb/pull/5958/files#diff-c261f77d6dd2134333c4a955c311cf4a196a08d3c2bb6ce24fd6801407877c89R56 - This path was not stress-tested at all. Therefore we covered `fifo.allow_compaction` in stress test to surface the overlapping seqno issue we are fixing here. - [FIFOCompactionPicker::PickCompactionToWarm](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L313) when `compaction_options_fifo.age_for_warm > 0` - For this path, we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and skip files of largest seqno greater than `earliest_mem_seqno` - This path was not stress-tested at all. However covering `age_for_warm` option worths a separate PR to deal with db stress compatibility. Therefore we manually tested this path for this PR - [FIFOCompactionPicker::CompactRange](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker_fifo.cc#L365) that ends up picking one of the above two compactions - [CompactionPicker::CompactFiles](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.cc#L378) - Since `SanitizeCompactionInputFiles()` will be called [before](https://github.com/facebook/rocksdb/blob/7.6.fb/db/compaction/compaction_picker.h#L111-L113) `CompactionPicker::CompactFiles` , we simply replicate the idea in https://github.com/facebook/rocksdb/pull/5958#issue-511150930 in `SanitizeCompactionInputFiles()`. To simplify implementation, we return `Stats::Abort()` on encountering seqno-overlapped file when doing compaction to L0 instead of skipping the file and proceed with the compaction. Some additional clean-up included in this PR: - Renamed `earliest_memtable_seqno` to `earliest_mem_seqno` for consistent naming - Added comment about `earliest_memtable_seqno` in related APIs - Made parameter `earliest_memtable_seqno` constant and required Pull Request resolved: https://github.com/facebook/rocksdb/pull/10777 Test Plan: - make check - New unit test `TEST_P(DBCompactionTestFIFOCheckConsistencyWithParam, FlushAfterIntraL0CompactionWithIngestedFile)`corresponding to the above 4 cases, which will fail accordingly without the fix - Regular CI stress run on this PR + stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761 and on FIFO compaction only Reviewed By: ajkr Differential Revision: D40090485 Pulled By: hx235 fbshipit-source-id: 52624186952ee7109117788741aeeac86b624a4f
-
由 sdong 提交于
Summary: Run format check for .h and .cc files to clean the format Pull Request resolved: https://github.com/facebook/rocksdb/pull/10851 Test Plan: Watch CI tests to pass Reviewed By: ajkr Differential Revision: D40649723 fbshipit-source-id: 62d32cead0b3b8e6540e86d25451bd72642109eb
-
- 25 10月, 2022 8 次提交
-
-
由 changyubi 提交于
Summary: Ran find . -iname '*.h' -o -iname '*.cc' | xargs clang-format -i under monitoring/. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10857 Test Plan: existing CI. Reviewed By: siying Differential Revision: D40652600 Pulled By: cbi42 fbshipit-source-id: 2af2467c33995b093e07b7512b8c32ed4144968e
-
由 changyubi 提交于
Summary: Ran `find . -iname '*.h' -o -iname '*.cc' | xargs clang-format -i` under test_util/. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10855 Test Plan: existing CI. Reviewed By: siying Differential Revision: D40652583 Pulled By: cbi42 fbshipit-source-id: ed0fbcfe17b6f9ec217a64b80d6d43dfbf1cc34e
-
由 akankshamahajan 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10860 Test Plan: CircleCI jobs Reviewed By: anand1976 Differential Revision: D40656236 Pulled By: akankshamahajan15 fbshipit-source-id: 557600db5c2e0ab9b400655336c467307f7136de
-
由 akankshamahajan 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10861 Test Plan: CircleCI jobs Reviewed By: siying Differential Revision: D40654198 Pulled By: akankshamahajan15 fbshipit-source-id: 787be2575578b3aa3bd985509f96fdb9e02f7ad7
-
由 akankshamahajan 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10859 Test Plan: CircleCI jobs Reviewed By: anand1976 Differential Revision: D40653839 Pulled By: akankshamahajan15 fbshipit-source-id: ce75205ee34ee3896a77a807d5c556886de78b01
-
由 akankshamahajan 提交于
Summary: Fix error ``` rocksdb/system_clock.h:30:11: error: '~SystemClock' overrides a destructor but is not marked 'override' [-Werror,-Wsuggest-destructor-override] virtual ~SystemClock() {} ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/10858 Test Plan: Ran internally Reviewed By: siying Differential Revision: D40652374 Pulled By: akankshamahajan15 fbshipit-source-id: 5dda8ca03ea57d709442c87e23e5fe097d7db672
-
由 sdong 提交于
Summary: Run "clang-format" against files under port to make it happy. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10849 Test Plan: Watch existing CI to pass. Reviewed By: anand1976 Differential Revision: D40645839 fbshipit-source-id: 582b4215503223795cf6234af90cc4e8e4eba773
-
由 Levi Tamasi 提交于
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/10853 Test Plan: `make check` Reviewed By: siying Differential Revision: D40651315 Pulled By: ltamasi fbshipit-source-id: 8b270ff4777a06464be86e376c2a680427866a46
-