Summary:
RocksDB secondary can replay both MANIFEST and WAL now.
On the one hand, the memory usage by memtables will grow after replaying WAL for sometime. On the other hand, replaying the MANIFEST can bring the database persistent data to a more recent point in time, giving us the opportunity to discard some memtables containing out-dated data.
This PR coordinates the MANIFEST and WAL replay, using the updates from MANIFEST replay to update the active memtable and immutable memtable list of each column family.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5305
Differential Revision: D15386512
Pulled By: riversand963
fbshipit-source-id: a3ea6fc415f8382d8cf624f52a71ebdcffa3e355
Summary:
Previously if iterator upper/lower bound presents, `DBIter` will check the bound for every key. This patch turns the check into per-file or per-data block check when applicable, by checking against either file largest/smallest key or block index key.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5111
Differential Revision: D15330061
Pulled By: siying
fbshipit-source-id: 8a653fe3cd50d94d81eb2d13b087326c58ee2024
Summary:
In the current db_bench trace replay, the replay process strictly follows the timestamp to issue the queries. In some cases, user does not care about the time. Therefore, fast forward is needed for users to speed up the replay process.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5273
Differential Revision: D15389232
Pulled By: zhichao-cao
fbshipit-source-id: 735d629b9d2a167b05af3e4fa0ddf9d5d0be1806
Summary:
They are kind of flaky at the moment. Will re-enable it when flakiness is fixed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5315
Differential Revision: D15382744
Pulled By: maysamyabandeh
fbshipit-source-id: 8b2f9d81a4bb34bfd51481727a682d5cd063c5e3
Summary:
RangeDelAggregator::StripeRep::Invalidate() clears up several vectors. If we know there isn't anything to there, we can safe these small CPUs. Profiling shows that it sometimes take non-negligible amount of CPU. Worth a small optimization.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5312
Differential Revision: D15380511
Pulled By: siying
fbshipit-source-id: 53c5f34c33b4cb1e743643c6086ac56d0b84ec2e
Summary:
If DB is opened with `avoid_unnecessary_blocking_io` being true, then `~ColumnFamilyHandleImpl` enqueues a purge request and schedules a background thread to perform the deletion. Without test sync point, whether the SST file is purged or not at a later point in time is not deterministic. If the SST does not exist, it will cause an assertion failure.
How to reproduce:
```
$git checkout 6492430eaf
$make -j20 deletefile_test
$gtest-parallel --repeat 1000 --worker 16 ./deletefile_test --gtest_filter=DeleteFileTest.BackgroundPurgeCFDropTest
```
The test may fail a few times.
With changes made in this PR, repeat the above commands, and the test should not fail.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5310
Differential Revision: D15361136
Pulled By: riversand963
fbshipit-source-id: c4308d5f8da83472c893bf7f8ceed347fbfa850f
Summary:
In options_helper.cc various functions take a const unordered_map of
string -> TypeInfo for options handling. These functions pass by-value
the (const) maps, resulting in unnecessary copies.
Change to pass by reference.
This results in a noticable reduction in the amount of time spent
parsing options - in my case a set of unit tests using RocksDB which
call SetOptions() to modify options see a ~25% runtime reduction.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5295
Differential Revision: D15296334
Pulled By: riversand963
fbshipit-source-id: 4d4be3db635264943607911b296dda27fd7ce1a7
Summary:
This is a workaround for the issue described in #5169.
It has been tested on a database with very large values, but not dedicated test has been added to the code base.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5213
Differential Revision: D15243116
Pulled By: siying
fbshipit-source-id: e0c226a6cd71a60924dcd7ce7af74abcb4054484
Summary:
The recent improvement in https://github.com/facebook/rocksdb/pull/3661 could cause a deadlock: When writing recoverable state, we also commit its sequence number to commit table, which could result into evicting existing commit entry, which could result into advancing max_evicted_seq_, which would need to get snapshots from database, which requires obtaining db mutex. The patch releases db_mutex before calling the callback in WriteRecoverableState to avoid the potential deadlock. It also improves the stress tests to let the issue be manifested in the tests.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5306
Differential Revision: D15341458
Pulled By: maysamyabandeh
fbshipit-source-id: 05dcbed7e21b789fd1e5fd5ee8eea08077162323
Summary:
After cherry-pick a bug fix to 6.2.fb branch, update the HISTORY.md file to reflect this change.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5309
Differential Revision: D15358002
Pulled By: riversand963
fbshipit-source-id: 5a60510ec6dd444ce5ffaefc69b2e4c38914a921
Summary:
The test was not using separate MemTablePostProcessInfo per memetable insert thread and thus tsan was complaining about data race.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5308
Differential Revision: D15356420
Pulled By: maysamyabandeh
fbshipit-source-id: 46c2f2d19fb02c3c775b587aa09ca9c0dae6ed04
Summary:
This PR has two fixes for crash test failures -
1. Fix a bug in TestMultiGet() in db_stress that was passing list of key to MultiGet() in the wrong order, thus ensuring that actual values don't match expected values
2. Remove an incorrect assertion in FilePickerMultiGet::GetNextFileInLevelWithKeys() that checks that files in a level are in sorted order. This is not true with MultiGet(), especially if there are duplicate keys and we may have to go back one file for the next key. Furthermore, this assertion makes more sense when a new version is created, rather than at lookup time
Test -
asan_crash and ubsan_crash tests
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5301
Differential Revision: D15337383
Pulled By: anand1976
fbshipit-source-id: 35092cb15bbc1700e5e823cbe07bfa62f1e9e6c6
Summary:
Performing unordered writes in rocksdb when unordered_write option is set to true. When enabled the writes to memtable are done without joining any write thread. This offers much higher write throughput since the upcoming writes would not have to wait for the slowest memtable write to finish. The tradeoff is that the writes visible to a snapshot might change over time. If the application cannot tolerate that, it should implement its own mechanisms to work around that. Using TransactionDB with WRITE_PREPARED write policy is one way to achieve that. Doing so increases the max throughput by 2.2x without however compromising the snapshot guarantees.
The patch is prepared based on an original by siying
Existing unit tests are extended to include unordered_write option.
Benchmark Results:
```
TEST_TMPDIR=/dev/shm/ ./db_bench_unordered --benchmarks=fillrandom --threads=32 --num=10000000 -max_write_buffer_number=16 --max_background_jobs=64 --batch_size=8 --writes=3000000 -level0_file_num_compaction_trigger=99999 --level0_slowdown_writes_trigger=99999 --level0_stop_writes_trigger=99999 -enable_pipelined_write=false -disable_auto_compactions --unordered_write=1
```
With WAL
- Vanilla RocksDB: 78.6 MB/s
- WRITER_PREPARED with unordered_write: 177.8 MB/s (2.2x)
- unordered_write: 368.9 MB/s (4.7x with relaxed snapshot guarantees)
Without WAL
- Vanilla RocksDB: 111.3 MB/s
- WRITER_PREPARED with unordered_write: 259.3 MB/s MB/s (2.3x)
- unordered_write: 645.6 MB/s (5.8x with relaxed snapshot guarantees)
- WRITER_PREPARED with unordered_write disable concurrency control: 185.3 MB/s MB/s (2.35x)
Limitations:
- The feature is not yet extended to `max_successive_merges` > 0. The feature is also incompatible with `enable_pipelined_write` = true as well as with `allow_concurrent_memtable_write` = false.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5218
Differential Revision: D15219029
Pulled By: maysamyabandeh
fbshipit-source-id: 38f2abc4af8780148c6128acdba2b3227bc81759
Summary:
Previous code may call `~ColumnFamilyData` in `DBImpl::AtomicFlushMemTablesToOutputFiles` if the column family is dropped or `cfd->IsFlushPending() == false`. In `~ColumnFamilyData`, the db mutex is released briefly and re-acquired. This can cause correctness issue. The reason is as follows.
Assume there are more bg flush threads. After bg_flush_thr1 releases the db mutex, bg_flush_thr2 can grab it and pop an element from the flush queue. This will cause bg_flush_thr2 to accidentally pick some memtables which should have been picked by bg_flush_thr1. To make the matter worse, bg_flush_thr2 can clear `flush_requested_` flag for the memtable list, causing a subsequent call to `MemTableList::IsFlushPending()` by bg_flush_thr1 to return false, which is wrong.
The fix is to delay `ColumnFamilyData::Unref` and `~ColumnFamilyData` for column families not selected for flush until `AtomicFlushMemTablesToOutputFiles` returns. Furthermore, a bg flush thread should not clear `MemTableList::flush_requested_` in `MemTableList::PickMemtablesToFlush` unless atomic flush is not used **or** the memtable list does not have unpicked memtables.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5294
Differential Revision: D15295297
Pulled By: riversand963
fbshipit-source-id: 03b101205ca22c242647cbf488bcf0ed80b2ecbd
Summary:
https://github.com/facebook/rocksdb/pull/5256 broke it: `block_iter_.user_key()` may not be valid even if `block_iter_points_to_real_block_` is true. E.g. if there was an IO error or Status::Incomplete.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5291
Differential Revision: D15273324
Pulled By: al13n321
fbshipit-source-id: 442e5b09f9884a58f92a6ac1ca93af719c219886
Summary:
CachableEntry is used in a variety of contexts: it may refer to a cached
object (i.e. an object in the block cache), an owned object, or an
unowned object; also, in some cases (most notably with iterators), the
responsibility of managing the pointed-to object gets handed off to
another object. Each of the above scenarios have different implications
for the lifecycle of the referenced object. For the most part, the patch
does not change the lifecycle of managed objects; however, it makes
these relationships explicit, and it also enables us to eliminate some
hacks and accident-prone code around releasing cache handles and
deleting/cleaning up objects. (The only places where the patch changes
how an objects are managed are the partitions of partitioned indexes and
filters.)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5252
Differential Revision: D15101358
Pulled By: ltamasi
fbshipit-source-id: 9eb59e9ae5a7230e3345789762d0ba1f189485be
Summary:
There were no C bindings for lowering thread pool priority. This adds those.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5285
Differential Revision: D15290050
Pulled By: siying
fbshipit-source-id: b2ed94d0c39d27434ace2204829a242b53d0d67a
Summary:
When reseek happens in merging iterator, reseeking a child iterator can be avoided if:
(1) the iterator represents imutable data
(2) reseek() to a larger key than the current key
(3) the current key of the child iterator is larger than the seek key
because it is guaranteed that the result will fall into the same position.
This optimization will be useful for use cases where users keep seeking to keys nearby in ascending order.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5286
Differential Revision: D15283635
Pulled By: siying
fbshipit-source-id: 35f79ffd5ce3609146faa8cd55f2bfd733502f83
Summary:
This PR fixes a couple of bugs in FilePickerMultiGet that were causing db_stress test failures. The failures were caused by -
1. Improper handling of a key that matches the user key portion of an L0 file's largest key. In this case, the curr_index_in_curr_level file index in L0 for that key was getting incremented, but batch_iter_ was not advanced. By design, all keys in a batch are supposed to be checked against an L0 file before advancing to the next L0 file. Not advancing to the next key in the batch was causing a double increment of curr_index_in_curr_level due to the same key being processed again
2. Improper handling of a key that matches the user key portion of the largest key in the last file of L1 and higher. This was resulting in a premature end to the processing of the batch for that level when the next key in the batch is a duplicate. Typically, the keys in MultiGet will not be duplicates, but its good to handle that case correctly
Test -
asan_crash
make check
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5292
Differential Revision: D15282530
Pulled By: anand1976
fbshipit-source-id: d1a6a86e0af273169c3632db22a44d79c66a581f
Summary:
Right now, DBIter::Next() always checks whether an entry is for the same user key as the previous entry to see whether the key should be hidden to the user. However, if previous entry's sequence number is 0, the check is not needed because 0 is the oldest possible sequence number.
We could extend it from seqnum 0 case to simply prev_seqno >= current_seqno. However, it is less robust with bug or unexpected situations, while the gain is relatively low. We can always extend it later when needed.
In a readseq benchmark with full formed LSM-tree, number of key comparisons called is reduced from 2.981 to 2.165. readseq against a fully compacted DB, no key comparison is called. Performance in this benchmark didn't show obvious improvement, which is expected because key comparisons only takes small percentage of CPU. But it may show up to be more effective if users have an expensive customized comparator.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5244
Differential Revision: D15067257
Pulled By: siying
fbshipit-source-id: b7e1ef3ec4fa928cba509683d2b3246e35d270d9
Summary:
Previously in PR https://github.com/facebook/rocksdb/pull/5161 we have added the capability to do WAL tailing in `OpenAsSecondary`, in this PR we extend such feature to `TryCatchUpWithPrimary` which is useful for an secondary RocksDB instance to retrieve and apply the latest updates and refresh log readers if needed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5282
Differential Revision: D15261011
Pulled By: miasantreble
fbshipit-source-id: a15c94471e8c3b3b1f7f47c3135db1126e936949
Summary:
Right now there is a potential race condition where two threads are created to iterate through the DB (https://gist.github.com/miasantreble/88f5798a397ee7cb8e7baff9db2d9e85). The problem is that in `BlockBasedTable::NewIndexIterator`, if both threads failed to find index_reader from block cache, they will call `CreateIndexReader->UpdateIndexType()` which creates a race to update `index_type` in the shared rep_ object. By checking the code, we realize the index type is always populated by `PrefetchIndexAndFilterBlocks` during the table `Open` call, so there is no need to update index type every time during iterator creation. This PR attempts to fix the race condition by removing the unnecessary call to `UpdateIndexType`
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5288
Differential Revision: D15252509
Pulled By: miasantreble
fbshipit-source-id: 6e3258652121d5c76d267f7ac457e15c5e84756e
Summary:
Disable it for now until we can get stress tests to pass consistently.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5284
Differential Revision: D15230727
Pulled By: anand1976
fbshipit-source-id: 239baacdb3c4cd4fb7c4447f7582b9042501d752
Summary:
Part of compaction cpu goes to processing snapshot list, the larger the list the bigger the overhead. Although the lifetime of most of the snapshots is much shorter than the lifetime of compactions, the compaction conservatively operates on the list of snapshots that it initially obtained. This patch allows the snapshot list to be updated via a callback if the compaction is taking long. This should let the compaction to continue more efficiently with much smaller snapshot list.
For simplicity, to avoid the feature is disabled in two cases: i) When more than one sub-compaction are sharing the same snapshot list, ii) when Range Delete is used in which the range delete aggregator has its own copy of snapshot list.
This fixes the reverted https://github.com/facebook/rocksdb/pull/5099 issue with range deletes.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5278
Differential Revision: D15203291
Pulled By: maysamyabandeh
fbshipit-source-id: fa645611e606aa222c7ce53176dc5bb6f259c258
Summary:
This PR fixes three memory issues found by ASAN
* in db_stress, the key vector for MultiGet is created using `emplace_back` which could potentially invalidates references to the underlying storage (vector<string>) due to auto resizing. Fix by calling reserve in advance.
* Similar issue in construction of GetContext autovector in version_set.cc
* In multiget_context.h use T[] specialization for unique_ptr that holds a char array
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5279
Differential Revision: D15202893
Pulled By: miasantreble
fbshipit-source-id: 14cc2cda0ed64d29f2a1e264a6bfdaa4294ee75d
Summary:
This allows debug releases of RocksJava to be build with the Docker release targets.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5274
Differential Revision: D15185067
Pulled By: sagar0
fbshipit-source-id: f3988e472f281f5844d9a07098344a827b1e7eb1
Summary:
The new option will pick a batch size randomly in the range 1-64. It will then space the keys in the batch by random intervals.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5264
Differential Revision: D15175522
Pulled By: anand1976
fbshipit-source-id: c16baa69d0f1ff4cf53c55c813ddd82c8aeb58fc
Summary:
Right now `OptimizeLevelStyleCompaction` may set compression type to Snappy even when Snappy is not supported, this may cause errors like "no snappy compression support"
Fixes https://github.com/facebook/rocksdb/issues/4283
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4325
Differential Revision: D15125542
Pulled By: miasantreble
fbshipit-source-id: 70890b73ababe16752721555dbd290633c2aafac
Summary:
Right now, when Seek() is called again, RocksDB always does a binary search against the files and index blocks, even if they end up with the same file/block. Improve it as following:
1. in LevelIterator, reseek first try to check the boundary of the current file. If it falls into the same file, skip the binary search to find the file
2. in block based table iterator, reseek skip to reseek the iterator block if the seek key is larger than the current key and lower than the index key (boundary of the current block and the next block).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5256
Differential Revision: D15105072
Pulled By: siying
fbshipit-source-id: 39634bdb4a881082451fa39cecd7ecf12160bf80
Summary:
Sometimes, users might make mistake of not releasing snapshots before closing the DB. This is undocumented use of RocksDB and the behavior is unknown. We return DB::Close() to provide a way to check it for the users. Aborted() will be returned to users when they call DB::Close().
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5272
Differential Revision: D15159713
Pulled By: siying
fbshipit-source-id: 39369def612398d9f239d83d396b5a28e5af65cd
Summary:
Our daily stress tests are failing after this feature. Reverting temporarily until we figure the reason for test failures.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5269
Differential Revision: D15151285
Pulled By: maysamyabandeh
fbshipit-source-id: e4002b99690a97df30d4b4b58bf0f61e9591bc6e
Summary:
At least one of the meta-block loading functions (`ReadRangeDelBlock`)
uses the same block reading function (`NewDataBlockIterator`) as data
block reads, which means it uses the dictionary handle. However, the
dictionary handle was uninitialized while reading meta-blocks, causing
readers to receive an error. This situation was only noticed when
`cache_index_and_filter_blocks=true`.
This PR initializes the handle to null while reading meta-blocks to
prevent the error. It also adds support to `db_stress` /
`db_crashtest.py` for `cache_index_and_filter_blocks`.
Fixes#5263.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5267
Differential Revision: D15149264
Pulled By: maysamyabandeh
fbshipit-source-id: 991d38a306c62db5976778bfb050fa3cd4a0671b
Summary:
Since currently pipelined write allows one thread to perform memtable writes
while another thread is traversing the `flush_scheduler_`, it will cause an
assertion failure in `FlushScheduler::Clear`. To unblock crash recoery tests,
we temporarily disable pipelined write when atomic flush is enabled.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5266
Differential Revision: D15142285
Pulled By: riversand963
fbshipit-source-id: a0c20fe4ac543e08feaed602414f982054df7831
Summary:
With atomic flush, RocksDB background flush will flush memtables of a column family up to the largest memtable id in the immutable memtable list. This can introduce a bug in the following scenario. A user thread inserts into a column family until the memtable is full and triggers a flush. This will add the column family to flush_scheduler_. Then the user thread writes another record to the column family. In the PreprocessWrite function, the user thread picks the column family from flush_scheduler_ and schedules a flush request. The flush request gaurantees to flush all the memtables up to the current largest memtable ID of the immutable memtable list. Then the user thread writes new data to the newly-created active memtable. After the write returns, the user thread closes the db. This can cause assertion failure when the background flush thread tries to install superversion for the column family. The solution is to not install flush results if the db has already set `shutting_down_` to true.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5254
Differential Revision: D15124149
Pulled By: riversand963
fbshipit-source-id: 0a667a41339dedb5a18bcb01b0bf11c275c04df0
Summary:
Improve the iterators performance when the user explicitly sets the readahead size via `ReadOptions.readahead_size`.
1. Stop creating new table readers when the user explicitly sets readahead size.
2. Make use of an internal buffer based on `FilePrefetchBuffer` instead of using `ReadaheadRandomAccessFileReader`, to handle the user readahead requests (for both buffered and direct io cases).
3. Add `readahead_size` to db_bench.
**Benchmarks:**
https://gist.github.com/sagar0/53693edc320a18abeaeca94ca32f5737
For 1 MB readahead, Buffered IO performance improves by 28% and Direct IO performance improves by 50%.
For 512KB readahead, Buffered IO performance improves by 30% and Direct IO performance improves by 67%.
**Test Plan:**
Updated `DBIteratorTest.ReadAhead` test to make sure that:
- no new table readers are created for iterators on setting ReadOptions.readahead_size
- At least "readahead" number of bytes are actually getting read on each iterator read.
TODO later:
- Use similar logic for compactions as well.
- This ties in nicely with #4052 and paves the way for removing ReadaheadRandomAcessFile later.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5246
Differential Revision: D15107946
Pulled By: sagar0
fbshipit-source-id: 2c1149729ca7d779e4e8b7710ba6f4e8cbfd3bea
Summary:
The newly added test CompactionJobTest.SnapshotRefresh sets the snapshot refresh period to 0 to stress the feature. This results into large number of refresh events, which in turn results into an UBSAN failure when a bitwise shift operand goes beyond the uint64_t size.
The patch fixes that by simplifying the shift logic to be done only by 2 bits after each refresh. Furthermore it verifies that the shift operation does not result in decreasing the refresh period.
Testing:
COMPILE_WITH_UBSAN=1 make -j32 compaction_job_test
./compaction_job_test --gtest_filter=CompactionJobTest.SnapshotRefresh
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5257
Differential Revision: D15106463
Pulled By: maysamyabandeh
fbshipit-source-id: f2718898ea7ba4fa9f7e87b70cf98fe647c0de80
Summary:
Part of compaction cpu goes to processing snapshot list, the larger the list the bigger the overhead. Although the lifetime of most of the snapshots is much shorter than the lifetime of compactions, the compaction conservatively operates on the list of snapshots that it initially obtained. This patch allows the snapshot list to be updated via a callback if the compaction is taking long. This should let the compaction to continue more efficiently with much smaller snapshot list.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5099
Differential Revision: D15086710
Pulled By: maysamyabandeh
fbshipit-source-id: 7649f56c3b6b2fb334962048150142a3bf9c1a12
Summary:
- By providing the "env" field in any text-based options (i.e., string, map, or file), we can use `NewCustomObject` to deserialize the text value into an actual `Env` object.
- Currently factory functions for `Env` registered with object registry should only return pointer to static `Env` objects. That's because `DBOptions::env` is a raw pointer so we cannot easily delegate cleanup.
- Note I did not add `env` to `db_option_type_info`. It wasn't needed for (de)serialization, and I believe we don't want to do verification on `env`, even by checking name. That's because the user should be able to copy their DB from Linux to Windows, change envs, and not see an option verification error.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5237
Differential Revision: D15056360
Pulled By: siying
fbshipit-source-id: 4b5f0b83297a5058f8949ec955dbf27d98d73d7e
Yanqin Jin