Commit Graph

705 Commits

Author SHA1 Message Date
Yi Wu
5e9e5a4702 Blob DB: Fix race condition between flush and write
Summary:
A race condition will happen when:
* a user thread writes a value, but it hits the write stop condition because there are too many un-flushed memtables, while holding blob_db_impl.write_mutex_.
* Flush is triggered and call flush begin listener and try to acquire blob_db_impl.write_mutex_.

Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3149

Differential Revision: D6279805

Pulled By: yiwu-arbug

fbshipit-source-id: 0e3c58afb78795ebe3360a2c69e05651e3908c40
2017-11-08 19:42:22 -08:00
Yi Wu
ca75f0a64a Blob DB: Fix release build
Summary:
`compression` shadow the method name in `BlobFile`. Rename it.
Closes https://github.com/facebook/rocksdb/pull/3148

Differential Revision: D6274498

Pulled By: yiwu-arbug

fbshipit-source-id: 7d293596530998b23b6b8a8940f983f9b6343a98
2017-11-08 13:14:20 -08:00
Yi Wu
4f9f124347 Blob DB: use compression in file header instead of global options
Summary:
To fix the issue of failing to decompress existing value after reopen DB with a different compression settings.
Closes https://github.com/facebook/rocksdb/pull/3142

Differential Revision: D6267260

Pulled By: yiwu-arbug

fbshipit-source-id: c7cf7f3e33b0cd25520abf4771cdf9180cc02a5f
2017-11-07 17:42:17 -08:00
Manuel Ung
e03377c7fd Add lock wait time as a perf context counter
Summary:
Adds two new counters:

`key_lock_wait_count` counts how many times a lock was blocked by another transaction and had to wait, instead of being granted the lock immediately.
`key_lock_wait_time` counts the time spent acquiring locks.
Closes https://github.com/facebook/rocksdb/pull/3107

Differential Revision: D6217332

Pulled By: lth

fbshipit-source-id: 55d4f46da5550c333e523263422fd61d6a46deb9
2017-11-06 10:57:19 -08:00
Yi Wu
be410dede8 Fix PinnableSlice move assignment
Summary:
After move assignment, we need to re-initialized the moved PinnableSlice.

Also update blob_db_impl.cc to not reuse the moved PinnableSlice since it is supposed to be in an undefined state after move.
Closes https://github.com/facebook/rocksdb/pull/3127

Differential Revision: D6238585

Pulled By: yiwu-arbug

fbshipit-source-id: bd99f2e37406c4f7de160c7dee6a2e8126bc224e
2017-11-03 18:13:21 -07:00
Yi Wu
2581c0a5a1 Blob DB: Fix BlobDBTest::SnapshotAndGarbageCollection asan failure
Summary:
Fix unreleased snapshot at the end of the test.
Closes https://github.com/facebook/rocksdb/pull/3126

Differential Revision: D6232867

Pulled By: yiwu-arbug

fbshipit-source-id: 651ca3144fc573ea2ab0ab20f0a752fb4a101d26
2017-11-03 10:26:59 -07:00
Yi Wu
62578d80c1 Blob DB: Add compaction filter to remove expired blob index entries
Summary:
After adding expiration to blob index in #3066, we are now able to add a compaction filter to cleanup expired blob index entries.
Closes https://github.com/facebook/rocksdb/pull/3090

Differential Revision: D6183812

Pulled By: yiwu-arbug

fbshipit-source-id: 9cb03267a9702975290e758c9c176a2c03530b83
2017-11-02 17:27:38 -07:00
Yi Wu
7bfa88037e Blob DB: fix snapshot handling
Summary:
Blob db will keep blob file if data in the file is visible to an active snapshot. Before this patch it checks whether there is an active snapshot has sequence number greater than the earliest sequence in the file. This is problematic since we take snapshot on every read, if it keep having reads, old blob files will not be cleanup. Change to check if there is an active snapshot falls in the range of [earliest_sequence, obsolete_sequence) where obsolete sequence is
1. if data is relocated to another file by garbage collection, it is the latest sequence at the time garbage collection finish
2. otherwise, it is the latest sequence of the file
Closes https://github.com/facebook/rocksdb/pull/3087

Differential Revision: D6182519

Pulled By: yiwu-arbug

fbshipit-source-id: cdf4c35281f782eb2a9ad6a87b6727bbdff27a45
2017-11-02 15:58:27 -07:00
Yi Wu
f662f8f0b6 Blob DB: option to enable garbage collection
Summary:
Add an option to enable/disable auto garbage collection, where we keep counting how many keys have been evicted by either deletion or compaction and decide whether to garbage collect a blob file.

Default disable auto garbage collection for now since the whole logic is not fully tested and we plan to make major change to it.
Closes https://github.com/facebook/rocksdb/pull/3117

Differential Revision: D6224756

Pulled By: yiwu-arbug

fbshipit-source-id: cdf53bdccec96a4580a2b3a342110ad9e8864dfe
2017-11-02 15:58:27 -07:00
Yi Wu
167ba599ec Blob DB: Fix flaky BlobDBTest::GCExpiredKeyWhileOverwriting test
Summary:
The test intent to wait until key being overwritten until proceed with garbage collection. It failed to wait for `PutUntil` finally finish. Fixing it.
Closes https://github.com/facebook/rocksdb/pull/3116

Differential Revision: D6222833

Pulled By: yiwu-arbug

fbshipit-source-id: fa9b57a772b92a66cf250b44e7975c43f62f45c5
2017-11-02 13:27:34 -07:00
Sagar Vemuri
25ac1697b4 Blob DB: Evict oldest blob file when close to blob db size limit
Summary:
Evict oldest blob file and put it in obsolete_files list when close to blob db size limit. The file will be delete when the `DeleteObsoleteFiles` background job runs next time.
For now I set `kEvictOldestFileAtSize` constant, which controls when to evict the oldest file, at 90%. It could be tweaked or made into an option if really needed; I didn't want to expose it as an option pre-maturely as there are already too many :) .
Closes https://github.com/facebook/rocksdb/pull/3094

Differential Revision: D6187340

Pulled By: sagar0

fbshipit-source-id: 687f8262101b9301bf964b94025a2fe9d8573421
2017-11-02 12:11:21 -07:00
Maysam Yabandeh
60d83df23d WritePrepared Txn: Move DB class to its own file
Summary:
Move  WritePreparedTxnDB from pessimistic_transaction_db.h to its own header, write_prepared_txn_db.h
Closes https://github.com/facebook/rocksdb/pull/3114

Differential Revision: D6220987

Pulled By: maysamyabandeh

fbshipit-source-id: 18893fb4fdc6b809fe117dabb544080f9b4a301b
2017-11-02 11:14:30 -07:00
Maysam Yabandeh
02693f64fc WritePrepared Txn: ValidateSnapshot
Summary:
Implements ValidateSnapshot for WritePrepared txns and also adds a unit test to clarify the contract of this function.
Closes https://github.com/facebook/rocksdb/pull/3101

Differential Revision: D6199405

Pulled By: maysamyabandeh

fbshipit-source-id: ace509934c307ea5d26f4bbac5f836d7c80fd240
2017-11-01 19:11:09 -07:00
Maysam Yabandeh
17731a43a6 WritePrepared Txn: Optimize for recoverable state
Summary:
GetCommitTimeWriteBatch is currently used to store some state as part of commit in 2PC. In MyRocks it is specifically used to store some data that would be needed only during recovery. So it is not need to be stored in memtable right after each commit.
This patch enables an optimization to write the GetCommitTimeWriteBatch only to the WAL. The batch will be written to memtable during recovery when the WAL is replayed. To cover the case when WAL is deleted after memtable flush, the batch is also buffered and written to memtable right before each memtable flush.
Closes https://github.com/facebook/rocksdb/pull/3071

Differential Revision: D6148023

Pulled By: maysamyabandeh

fbshipit-source-id: 2d09bae5565abe2017c0327421010d5c0d55eaa7
2017-11-01 17:26:46 -07:00
Maysam Yabandeh
c1cf94c787 WritePrepared Txn: sort indexes before batch collapse
Summary:
The collapse of duplicate keys in write batch needs to sort the indexes of duplicate keys since it only checks the index in the batch with the head of the list of duplicate keys.
Closes https://github.com/facebook/rocksdb/pull/3093

Differential Revision: D6186800

Pulled By: maysamyabandeh

fbshipit-source-id: abc9ae8c2f1840445a5584f925cf86ecc6f37154
2017-11-01 08:56:57 -07:00
Yi Wu
f6082d1944 Blob DB: cleanup unused options
Summary:
* cleanup num_concurrent_simple_blobs. We don't do concurrent writes (by taking write_mutex_) so it doesn't make sense to have multiple non TTL files open. We can revisit later when we want to improve writes.
* cleanup eviction callback. we don't have plan to use it now.
* rename s/open_simple_blob_files_/open_non_ttl_file_/ and s/open_blob_files_/open_ttl_files_/ to avoid confusion.
Closes https://github.com/facebook/rocksdb/pull/3088

Differential Revision: D6182598

Pulled By: yiwu-arbug

fbshipit-source-id: 99e6f5e01fa66d31309cdb06ce48502464bac6ad
2017-10-31 16:42:08 -07:00
Sagar Vemuri
f5078dde2d Blob DB: Initialize all fields in Blob Header, Footer and Record structs
Summary:
Fixing un-itializations caught by valgrind.
Closes https://github.com/facebook/rocksdb/pull/3103

Differential Revision: D6200195

Pulled By: sagar0

fbshipit-source-id: bf35a3fb03eb1d308e4c5ce30dee1e345d7b03b3
2017-10-31 16:42:08 -07:00
Yi Wu
3ebb7ba7b9 Blob DB: update blob file format
Summary:
Changing blob file format and some code cleanup around the change. The change with blob log format are:
* Remove timestamp field in blob file header, blob file footer and blob records. The field is not being use and often confuse with expiration field.
* Blob file header now come with column family id, which always equal to default column family id. It leaves room for future support of column family.
* Compression field in blob file header now is a standalone byte (instead of compact encode with flags field)
* Blob file footer now come with its own crc.
* Key length now being uint64_t instead of uint32_t
* Blob CRC now checksum both key and value (instead of value only).
* Some reordering of the fields.

The list of cleanups:
* Better inline comments in blob_log_format.h
* rename ttlrange_t and snrange_t to ExpirationRange and SequenceRange respectively.
* simplify blob_db::Reader
* Move crc checking logic to inside blob_log_format.cc
Closes https://github.com/facebook/rocksdb/pull/3081

Differential Revision: D6171304

Pulled By: yiwu-arbug

fbshipit-source-id: e4373e0d39264441b7e2fbd0caba93ddd99ea2af
2017-10-27 13:27:12 -07:00
Yi Wu
5a2a6483dc Blob DB: Inline small values in base DB
Summary:
Adding the `min_blob_size` option to allow storing small values in base db (in LSM tree) together with the key. The goal is to improve performance for small values, while taking advantage of blob db's low write amplification for large values.

Also adding expiration timestamp to blob index. It will be useful to evict stale blob indexes in base db by adding a compaction filter. I'll work on the compaction filter in future patches.

See blob_index.h for the new blob index format. There are 4 cases when writing a new key:
* small value w/o TTL: put in base db as normal value (i.e. ValueType::kTypeValue)
* small value w/ TTL: put (type, expiration, value) to base db.
* large value w/o TTL: write value to blob log and put (type, file, offset, size, compression) to base db.
* large value w/TTL: write value to blob log and put (type, expiration, file, offset, size, compression) to base db.
Closes https://github.com/facebook/rocksdb/pull/3066

Differential Revision: D6142115

Pulled By: yiwu-arbug

fbshipit-source-id: 9526e76e19f0839310a3f5f2a43772a4ad182cd0
2017-10-26 12:30:54 -07:00
Sagar Vemuri
96e3a600ba Return write error on reaching blob dir size limit
Summary:
I found that we continue accepting writes even when the blob db goes beyond the configured blob directory size limit. Now, we return an error for writes on reaching `blob_dir_size` limit and if `is_fifo` is set to false. (We cannot just drop any file when `is_fifo` is true.)

Deleting the oldest file when `is_fifo` is true will be handled in a later PR.
Closes https://github.com/facebook/rocksdb/pull/3060

Differential Revision: D6136156

Pulled By: sagar0

fbshipit-source-id: 2f11cb3f2eedfa94524fbfa2613dd64bfad7a23c
2017-10-25 16:30:37 -07:00
zach shipko
386a57e6ef Fix build on OpenBSD
Summary:
A few simple changes to allow RocksDB to be built on OpenBSD. Let me know if any further changes are needed.
Closes https://github.com/facebook/rocksdb/pull/3061

Differential Revision: D6138800

Pulled By: ajkr

fbshipit-source-id: a13a17b5dc051e6518bd56a8c5efd1d24dd81b0c
2017-10-24 13:27:38 -07:00
Yi Wu
66a2c44ef4 Add DB::Properties::kEstimateOldestKeyTime
Summary:
With FIFO compaction we would like to get the oldest data time for monitoring. The problem is we don't have timestamp for each key in the DB. As an approximation, we expose the earliest of sst file "creation_time" property.

My plan is to override the property with a more accurate value with blob db, where we actually have timestamp.
Closes https://github.com/facebook/rocksdb/pull/2842

Differential Revision: D5770600

Pulled By: yiwu-arbug

fbshipit-source-id: 03833c8f10bbfbee62f8ea5c0d03c0cafb5d853a
2017-10-23 15:27:27 -07:00
Dmitri Smirnov
d2a65c59e1 Fix unused var warnings in Release mode
Summary:
MSVC does not support unused attribute at this time. A separate assignment line fixes the issue probably by being counted as usage for MSVC and it no longer complains about unused var.
Closes https://github.com/facebook/rocksdb/pull/3048

Differential Revision: D6126272

Pulled By: maysamyabandeh

fbshipit-source-id: 4907865db45fd75a39a15725c0695aaa17509c1f
2017-10-23 14:27:04 -07:00
Maysam Yabandeh
63822eb761 Enable two write queues for transactions
Summary:
Enable concurrent_prepare flag for WritePrepared transactions and extend the existing transaction tests with this config.
Closes https://github.com/facebook/rocksdb/pull/3046

Differential Revision: D6106534

Pulled By: maysamyabandeh

fbshipit-source-id: 88c8d21d45bc492beb0a131caea84a2ac5e7d38c
2017-10-23 14:27:04 -07:00
Dmitri Smirnov
ebab2e2d42 Enable MSVC W4 with a few exceptions. Fix warnings and bugs
Summary: Closes https://github.com/facebook/rocksdb/pull/3018

Differential Revision: D6079011

Pulled By: yiwu-arbug

fbshipit-source-id: 988a721e7e7617967859dba71d660fc69f4dff57
2017-10-19 10:57:12 -07:00
Maysam Yabandeh
7e38238981 WritePrepared Txn: Disable GC during recovery
Summary:
Disables GC during recovery of a WritePrepared txn db to avoid GCing uncommitted key values.
Closes https://github.com/facebook/rocksdb/pull/2980

Differential Revision: D6000191

Pulled By: maysamyabandeh

fbshipit-source-id: fc4d522c643d24ebf043f811fe4ecd0dd0294675
2017-10-18 09:11:50 -07:00
Yi Wu
eaaef91178 Blob DB: Store blob index as kTypeBlobIndex in base db
Summary:
Blob db insert blob index to base db as kTypeBlobIndex type, to tell apart values written by plain rocksdb or blob db. This is to make it possible to migrate from existing rocksdb to blob db.

Also with the patch blob db garbage collection get away from OptimisticTransaction. Instead it use a custom write callback to achieve similar behavior as OptimisticTransaction. This is because we need to pass the is_blob_index flag to DBImpl::Get but OptimisticTransaction don't support it.
Closes https://github.com/facebook/rocksdb/pull/3000

Differential Revision: D6050044

Pulled By: yiwu-arbug

fbshipit-source-id: 61dc72ab9977625e75f78cd968e7d8a3976e3632
2017-10-17 17:28:11 -07:00
Yi Wu
0552029b5c Blob DB: not writing sequence number as blob record footer
Summary:
Previously each time we write a blob we write blog_record_header + key + value + blob_record_footer to blob log. The footer only contains a sequence and a crc for the sequence number. The sequence number was used in garbage collection to verify the value is recent. After #2703 we moved to use optimistic transaction and no longer use sequence number from the footer. Remove the footer altogether.

There's another usage of sequence number and we are keeping it: Each blob log file keep track of sequence number range of keys in it, and use it to check if it is reference by a snapshot, before being deleted.
Closes https://github.com/facebook/rocksdb/pull/3005

Differential Revision: D6057585

Pulled By: yiwu-arbug

fbshipit-source-id: d6da53c457a316e9723f359a1b47facfc3ffe090
2017-10-17 12:13:08 -07:00
Yi Wu
10ba50e9eb Blob DB: Move BlobFile definition to a separate file
Summary:
simply move BlobFile definition from blob_db_impl.h to blob_file.h.
Closes https://github.com/facebook/rocksdb/pull/3002

Differential Revision: D6050143

Pulled By: yiwu-arbug

fbshipit-source-id: a8fb6e094fe39bdeace6279569834bc65aa64a34
2017-10-13 14:42:26 -07:00
Zhongyi Xie
e2548366e1 add GetLiveFiles and GetLiveFilesMetaData for BlobDB
Summary: Closes https://github.com/facebook/rocksdb/pull/2976

Differential Revision: D5994759

Pulled By: miasantreble

fbshipit-source-id: 985c31dccb957cb970c302f813cd07a1e8cb6438
2017-10-09 19:56:04 -07:00
Yi Wu
8c392a31d7 WritePrepared Txn: Iterator
Summary:
On iterator create, take a snapshot, create a ReadCallback and pass the ReadCallback to the underlying DBIter to check if key is committed.
Closes https://github.com/facebook/rocksdb/pull/2981

Differential Revision: D6001471

Pulled By: yiwu-arbug

fbshipit-source-id: 3565c4cdaf25370ba47008b0e0cb65b31dfe79fe
2017-10-09 17:15:28 -07:00
Yi Wu
17c6325e8a WritePrepare Txn: Cancel flush/compaction before destruction
Summary:
On WritePreparedTxnDB destruct there could be running compaction/flush holding a SnapshotChecker, which holds a pointer back to WritePreparedTxnDB. Make sure those jobs finished before destructing WritePreparedTxnDB.

This is caught by TransactionTest::SeqAdvanceTest.
Closes https://github.com/facebook/rocksdb/pull/2982

Differential Revision: D6002957

Pulled By: yiwu-arbug

fbshipit-source-id: f1e70390c9798d1bd7959f5c8e2a1c14100773c3
2017-10-06 20:55:53 -07:00
Maysam Yabandeh
ec6c5383d0 WritePrepared Txn: end-to-end tests
Summary:
Enable WritePrepared policy for existing transaction tests.
Closes https://github.com/facebook/rocksdb/pull/2972

Differential Revision: D5993614

Pulled By: maysamyabandeh

fbshipit-source-id: d1eb53e2920c4e2a56434bb001231c98426f3509
2017-10-06 14:26:45 -07:00
Sagar Vemuri
da29eba43b Enable WAL for blob index
Summary:
Enabled WAL, during GC, for blob index which is stored on regular RocksDB.
Closes https://github.com/facebook/rocksdb/pull/2975

Differential Revision: D5997384

Pulled By: sagar0

fbshipit-source-id: b76c1487d8b5be0e36c55e8d77ffe3d37d63d85b
2017-10-06 10:59:31 -07:00
Yi Wu
d1b74b0c82 WritePrepared Txn: Compaction/Flush
Summary:
Update Compaction/Flush to support WritePreparedTxnDB: Add SnapshotChecker which is a proxy to query WritePreparedTxnDB::IsInSnapshot. Pass SnapshotChecker to DBImpl on WritePreparedTxnDB open. CompactionIterator use it to check if a key has been committed and if it is visible to a snapshot. In CompactionIterator:
* check if key has been committed. If not, output uncommitted keys AS-IS.
* use SnapshotChecker to check if key is visible to a snapshot when in need.
* do not output key with seq = 0 if the key is not committed.
Closes https://github.com/facebook/rocksdb/pull/2926

Differential Revision: D5902907

Pulled By: yiwu-arbug

fbshipit-source-id: 945e037fdf0aa652dc5ba0ad879461040baa0320
2017-10-06 10:41:53 -07:00
Yi Wu
cc20ec3689 WritePrepared Txn: Test sequence number 0 is visible
Summary:
Compaction will output keys with sequence number 0, if it is visible to
earliest snapshot. Adding a test to make sure IsInSnapshot() report sequence number 0 is
visible to any snapshot.
Closes https://github.com/facebook/rocksdb/pull/2974

Differential Revision: D5990665

Pulled By: yiwu-arbug

fbshipit-source-id: ef50ebc777ff8ca688771f3ab598c7a609b0b65e
2017-10-05 16:26:44 -07:00
Maysam Yabandeh
4e3c3d8c6a WritePrepared Txn: duplicate keys
Summary:
With WriteCommitted, when the write batch has duplicate keys, the txn db simply inserts them to the db with different seq numbers and let the db ignore/merge the duplicate values at the read time. With WritePrepared all the entries of the batch are inserted with the same seq number which prevents us from benefiting from this simple solution.

This patch applies a hackish solution to unblock the end-to-end testing. The hack is to be replaced with a proper solution soon. The patch simply detects the duplicate key insertions, and mark the previous one as obsolete. Then before writing to the db it rewrites the batch eliminating the obsolete keys. This would incur a memcpy cost. Furthermore handing duplicate merge would require to do FullMerge instead of simply ignoring the previous value, which is not handled by this patch.
Closes https://github.com/facebook/rocksdb/pull/2969

Differential Revision: D5976337

Pulled By: maysamyabandeh

fbshipit-source-id: 114e65b66f137d8454ff2d1d782b8c05da95f989
2017-10-05 07:41:02 -07:00
Maysam Yabandeh
283d60761e fix valgrind leak report in unit test
Summary:
I cannot locally reproduce the valgrind leak report but based on my code inspection not deleting txn1 might be the reason.
```
==197848== 2,990 (544 direct, 2,446 indirect) bytes in 1 blocks are definitely lost in loss record 15 of 16
==197848==    at 0x4C2D06F: operator new(unsigned long) (in /usr/local/fbcode/gcc-5-glibc-2.23/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==197848==    by 0x7D5B31: rocksdb::WritePreparedTxnDB::BeginTransaction(rocksdb::WriteOptions const&, rocksdb::TransactionOptions const&, rocksdb::Transaction*) (pessimistic_transaction_db.cc:173)
==197848==    by 0x7D80C1: rocksdb::PessimisticTransactionDB::Initialize(std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&) (pessimistic_transaction_db.cc:115)
==197848==    by 0x7DC42F: rocksdb::WritePreparedTxnDB::Initialize(std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&) (pessimistic_transaction_db.cc:151)
==197848==    by 0x7D8CA0: rocksdb::TransactionDB::WrapDB(rocksdb::DB*, rocksdb::TransactionDBOptions const&, std::vector<unsigned long, std::allocator<unsigned long> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> > const&, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:275)
==197848==    by 0x7D9F26: rocksdb::TransactionDB::Open(rocksdb::DBOptions const&, rocksdb::TransactionDBOptions const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::vector<rocksdb::ColumnFamilyDescriptor, std::allocator<rocksdb::ColumnFamilyDescriptor> > const&, std::vector<rocksdb::ColumnFamilyHandle*, std::allocator<rocksdb::ColumnFamilyHandle*> >*, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:227)
==197848==    by 0x7DB349: rocksdb::TransactionDB::Open(rocksdb::Options const&, rocksdb::TransactionDBOptions const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, rocksdb::TransactionDB**) (pessimistic_transaction_db.cc:198)
==197848==    by 0x52ABD2: rocksdb::TransactionTest::ReOpenNoDelete() (transaction_test.h:87)
==197848==    by 0x51F7B8: rocksdb::WritePreparedTransactionTest_BasicRecoveryTest_Test::TestBody() (write_prepared_transaction_test.cc:843)
==197848==    by 0x857557: HandleSehExceptionsInMethodIfSupported<testing::Test, void> (gtest-all.cc:3824)
==197848==    by 0x857557: void testing::internal::HandleExceptionsInMethodIfSupported<testing::Test, void>(testing::Test*, void (testing::Test::*)(), char const*) (gtest-all.cc:3860)
==197848==    by 0x84E7EB: testing::Test::Run() [clone .part.485] (gtest-all.cc:3897)
==197848==    by 0x84E9BC: Run (gtest-all.cc:3888)
==197848==    by 0x84E9BC: testing::TestInfo::Run() [clone .part.486] (gtest-all.cc:4072)
```
Closes https://github.com/facebook/rocksdb/pull/2963

Differential Revision: D5968856

Pulled By: maysamyabandeh

fbshipit-source-id: 2ac512bbcad37dc8eeeffe4f363978913354180c
2017-10-03 14:58:07 -07:00
Maysam Yabandeh
d27258d3a6 WritePrepared Txn: Rollback
Summary:
Implement the rollback of WritePrepared txns. For each modified value, it reads the value before the txn and write it back. This would cancel out the effect of transaction. It also remove the rolled back txn from prepared heap.
Closes https://github.com/facebook/rocksdb/pull/2946

Differential Revision: D5937575

Pulled By: maysamyabandeh

fbshipit-source-id: a6d3c47f44db3729f44b287a80f97d08dc4e888d
2017-10-02 19:59:27 -07:00
Sagar Vemuri
bb38cd03a9 Limit number of merge operands in Cassandra merge operator
Summary:
Now that RocksDB supports conditional merging during point lookups (introduced in #2923), Cassandra value merge operator can be updated to pass in a limit. The limit needs to be passed in from the Cassandra code.
Closes https://github.com/facebook/rocksdb/pull/2947

Differential Revision: D5938454

Pulled By: sagar0

fbshipit-source-id: d64a72d53170d8cf202b53bd648475c3952f7d7f
2017-10-02 16:11:40 -07:00
Andrew Kryczka
5df172da2f fix deletion-triggered compaction in table builder
Summary:
It was broken when `NotifyCollectTableCollectorsOnFinish` was introduced. That function called `Finish` on each of the `TablePropertiesCollector`s, and `CompactOnDeletionCollector::Finish()` was resetting all its internal state. Then, when we checked whether compaction is necessary, the flag had already been cleared.

Fixed above issue by avoiding resetting internal state during `Finish()`. Multiple calls to `Finish()` are allowed, but callers cannot invoke `AddUserKey()` on the collector after any finishes.
Closes https://github.com/facebook/rocksdb/pull/2936

Differential Revision: D5918659

Pulled By: ajkr

fbshipit-source-id: 4f05e9d80e50ee762ba1e611d8d22620029dca6b
2017-09-28 18:17:30 -07:00
Maysam Yabandeh
385049baf2 WritePrepared Txn: Recovery
Summary:
Recover txns from the WAL. Also added some unit tests.
Closes https://github.com/facebook/rocksdb/pull/2901

Differential Revision: D5859596

Pulled By: maysamyabandeh

fbshipit-source-id: 6424967b231388093b4effffe0a3b1b7ec8caeb0
2017-09-28 16:56:45 -07:00
Quinn Jarrell
6a541afcc4 Make bytes_per_sync and wal_bytes_per_sync mutable
Summary:
SUMMARY
Moves the bytes_per_sync and wal_bytes_per_sync options from immutableoptions to mutable options. Also if wal_bytes_per_sync is changed, the wal file and memtables are flushed.
TEST PLAN
ran make check
all passed

Two new tests SetBytesPerSync, SetWalBytesPerSync check that after issuing setoptions with a new value for the var, the db options have the new value.
Closes https://github.com/facebook/rocksdb/pull/2893

Reviewed By: yiwu-arbug

Differential Revision: D5845814

Pulled By: TheRushingWookie

fbshipit-source-id: 93b52d779ce623691b546679dcd984a06d2ad1bd
2017-09-27 17:49:45 -07:00
Yi Wu
ec48e5c77f Add TransactionDB::SingleDelete()
Summary:
Looks like the API is simply missing. Adding it.
Closes https://github.com/facebook/rocksdb/pull/2937

Differential Revision: D5919955

Pulled By: yiwu-arbug

fbshipit-source-id: 6e2e9c96c29882b0bb4113d1f8efb72bffc57878
2017-09-27 10:27:26 -07:00
Yi Wu
be97dbb15c Fix WritePreparedTransactionTest::SeqAdvanceTest ASAN failure
Summary: Closes https://github.com/facebook/rocksdb/pull/2922

Differential Revision: D5895310

Pulled By: yiwu-arbug

fbshipit-source-id: 52c635a25d22478ec1eca49b6817551202babac2
2017-09-22 15:26:42 -07:00
Yi Wu
1480e6f7cf Fix TransactionTest::SeqAdvanceTest ASAN failure
Summary:
The test didn't delete txn before creating a new one.
Closes https://github.com/facebook/rocksdb/pull/2913

Differential Revision: D5880236

Pulled By: yiwu-arbug

fbshipit-source-id: 7a4fcaada3d86332292754502cd8f4341143bf4f
2017-09-21 09:56:54 -07:00
Pengchao Wang
e4234fbdcf collecting kValue type tombstone
Summary:
In our testing cluster, we found large amount tombstone has been promoted to kValue type from kMerge after reaching the top level of compaction. Since we used to only collecting tombstone in merge operator, those tombstones can never be collected.

This PR addresses the issue by adding a GC step in compaction filter, which is only for kValue type records. Since those record already reached the top of compaction (no earlier data exists) we can safely remove them in compaction filter without worrying old data appears.

This PR also removes an old optimization in cassandra merge operator for single merge operands.  We need to do GC even on a single operand, so the optimation does not make sense anymore.
Closes https://github.com/facebook/rocksdb/pull/2855

Reviewed By: sagar0

Differential Revision: D5806445

Pulled By: wpc

fbshipit-source-id: 6eb25629d4ce917eb5e8b489f64a6aa78c7d270b
2017-09-18 16:27:12 -07:00
Maysam Yabandeh
60beefd6e0 WritePrepared Txn: Advance seq one per batch
Summary:
By default the seq number in DB is increased once per written key. WritePrepared txns requires the seq to be increased once per the entire batch so that the seq would be used as the prepare timestamp by which the transaction is identified. Also we need to increase seq for the commit marker since it would give a unique id to the commit timestamp of transactions.

Two unit tests are added to verify our understanding of how the seq should be increased. The recovery path requires much more work and is left to another patch.
Closes https://github.com/facebook/rocksdb/pull/2885

Differential Revision: D5837843

Pulled By: maysamyabandeh

fbshipit-source-id: a08960b93d727e1cf438c254d0c2636fb133cc1c
2017-09-18 14:45:08 -07:00
Yi Wu
9a970c81af Fix WriteBatchWithIndex::GetFromBatchAndDB not allowing StackableDB
Summary: Closes https://github.com/facebook/rocksdb/pull/2881

Differential Revision: D5829682

Pulled By: yiwu-arbug

fbshipit-source-id: abb8fa14b58cea7c416282f9be19e8b1a7961c6e
2017-09-13 17:26:35 -07:00
Maysam Yabandeh
09713a64b3 WritePrepared Txn: Lock-free CommitMap
Summary:
We had two proposals for lock-free commit maps. This patch implements the latter one that was simpler. We can later experiment with both proposals.

In this impl each entry is an std::atomic of uint64_t, which are accessed via memory_order_acquire/release. In x86_64 arch this is compiled to simple reads and writes from memory.
Closes https://github.com/facebook/rocksdb/pull/2861

Differential Revision: D5800724

Pulled By: maysamyabandeh

fbshipit-source-id: 41abae9a4a5df050a8eb696c43de11c2770afdda
2017-09-13 12:12:11 -07:00