Summary:
Currently, whenever DB Verification fails we bail out by calling `exit(1)`. This is kind of bad since it causes unclean shutdown and spew of error log messages like:
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
05:03:27 pthread lock: Invalid argument
This diff adds a new parameter that is set to true when verification fails. It can then use the parameter to bail out safely.
Test Plan: Casued artificail failure. Verified that exit was clean.
Reviewers: dhruba, haobo, ljin
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18243
Summary:
The file tree structure in Version is prebuilt and the range of each file is known.
On the Get() code path, we do binary search in FindFile() by comparing
target key with each file's largest key and also check the range for each L0 file.
With some pre-calculated knowledge, each key comparision that has been done can serve
as a hint to narrow down further searches:
(1) If a key falls within a L0 file's range, we can safely skip the next
file if its range does not overlap with the current one.
(2) If a key falls within a file's range in level L0 - Ln-1, we should only
need to binary search in the next level for files that overlap with the current one.
(1) will be able to skip some files depending one the key distribution.
(2) can greatly reduce the range of binary search, especially for bottom
levels, given that one file most likely only overlaps with N files from
the level below (where N is max_bytes_for_level_multiplier). So on level
L, we will only look at ~N files instead of N^L files.
Some inital results: measured with 500M key DB, when write is light (10k/s = 1.2M/s), this
improves QPS ~7% on top of blocked bloom. When write is heavier (80k/s =
9.6M/s), it gives us ~13% improvement.
Test Plan: make all check
Reviewers: haobo, igor, dhruba, sdong, yhchiang
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17205
Summary: Compiling for iOS has by default turned on -Wmissing-prototypes, which causes rocksdb to fail compiling. This diff turns on -Wmissing-prototypes in our compile options and cleans up all functions with missing prototypes.
Test Plan: compiles
Reviewers: dhruba, haobo, ljin, sdong
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17649
Summary: When opening DB in read-only mode, client can choose to only specify a subset of column families ("default" column family can't be omitted, though)
Test Plan: added a unit test in column_family_test
Reviewers: haobo, sdong, ljin, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17565
Summary: We switched to prefix_seek method of seeking. This means that anytime we check Valid(), we also need to check starts_with(prefix)
Test Plan: ran db_stress
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16953
Summary: We're trying to deprecate prefix iterators, so no need to test them in db_stress
Test Plan: ran it
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16917
Summary:
this should fix the hash_skip_list issue, but I still see seqno
assertion failure in the last run. Will continue investigating and
address that in a different diff
Test Plan: make whitebox_crash_test
Reviewers: igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16851
Summary:
Hash skip list has issues, causing db_stress to fail badly.
For now, switching back to skip_list by default before we figure out root cause.
Test Plan: db_stress is happy(ier)
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16845
Summary:
*) fixed the comment
*) constant 1 was not casted to 64-bit, which (I think) might cause overflow if we shift it too much
*) default prefix size to be 7, like it was before
Test Plan: compiled
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16827
Summary: as title
Test Plan: running python tools/db_crashtest.py
Reviewers: igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16803
Summary: Fix the db_stress test, let is run with HashSkipList for real
Test Plan:
python tools/db_crashtest.py
python tools/db_crashtest2.py
Reviewers: igor, haobo
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16773
Summary:
I had this diff for a while to test column families implementation. Last night, I ran it sucessfully for 10 hours with the command:
time ./db_stress --threads=30 --ops_per_thread=200000000 --max_key=5000 --column_families=20 --clear_column_family_one_in=3000000 --verify_before_write=1 --reopen=50 --max_background_compactions=10 --max_background_flushes=10 --db=/tmp/db_stress
It is ready to be committed :)
Test Plan: Ran it for 10 hours
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16797
Summary:
(1) Fix SanitizeOptions() to also check HashLinkList. The current
dynamic case just happens to work because the 2 classes have the same
layout.
(2) Do not delete SliceTransform object in HashSkipListFactory and
HashLinkListFactory destructor. Reason: SanitizeOptions() enforces
prefix_extractor and SliceTransform to be the same object when
Hash**Factory is used. This makes the behavior strange: when
Hash**Factory is used, prefix_extractor will be released by RocksDB. If
other memtable factory is used, prefix_extractor should be released by
user.
Test Plan: db_bench && make asan_check
Reviewers: haobo, igor, sdong
Reviewed By: igor
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D16587
Summary: By removing some includes form options.h and reply on forward declaration, we can more easily reason the dependencies.
Test Plan: make all check
Reviewers: kailiu, haobo, igor, dhruba
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15411
Summary:
It looks like we might have some trouble when building the new release with 4.8, since fbcode is using glibc2.17-fb by default and we are using glibc2.17. It was reported by Benjamin Renard in our internal group.
This diff moves our fbcode build to use glibc2.17-fb by default. I got some linker errors when compiling, complaining that `google::SetUsageMessage()` was undefined. After deleting all offending lines, the compile was successful and everything works.
Test Plan:
Compiled
Ran ./db_bench ./db_stress ./db_repl_stress
Reviewers: kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15405
Summary: I'm separating code-cleanup part of https://reviews.facebook.net/D14517. This will make D14517 easier to understand and this diff easier to review.
Test Plan: make check
Reviewers: haobo, kailiu, sdong, dhruba, tnovak
Reviewed By: tnovak
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15099
Summary:
Let's get rid of TransformRep and it's children. We have confirmed that HashSkipListRep works better with multifeed, so there is no benefit to keeping this around.
This diff is mostly just deleting references to obsoleted functions. I also have a diff for fbcode that we'll need to push when we switch to new release.
I had to expose HashSkipListRepFactory in the client header files because db_impl.cc needs access to GetTransform() function for SanitizeOptions.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14397
Summary:
These bugs were caught by ASAN crash test.
1. The first one, in table/filter_block.cc is very nasty. We first reference entries_ and store the reference to Slice prev. Then, we call entries_.append(), which can change the reference. The Slice prev now points to junk.
2. The second one is a bug in a test, so it's not very serious. Once we set read_opts.prefix, we never clear it, so some other function might still reference it.
Test Plan: asan crash test now runs more than 5 mins. Before, it failed immediately. I will run the full one, but the full one takes quite some time (5 hours)
Reviewers: dhruba, haobo, kailiu
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14223
Summary: This diff invoves some more complicated issues in the posix environment.
Test Plan: works under mac os. will need to verify dev box.
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14061
Summary: This diff leverage the existing block cache and extend it to cache index/filter block.
Test Plan:
Added new tests in db_test and table_test
The correctness is checked by:
1. make check
2. make valgrind_check
Performance is test by:
1. 10 times of build_tools/regression_build_test.sh on two versions of rocksdb before/after the code change. Test results suggests no significant difference between them. For the two key operatons `overwrite` and `readrandom`, the average iops are both 20k and ~260k, with very small variance).
2. db_stress.
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb, haobo, xjin
Differential Revision: https://reviews.facebook.net/D13167
Summary:
Rocksdb can now support a uncompressed block cache, or a compressed
block cache or both. Lookups first look for a block in the
uncompressed cache, if it is not found only then it is looked up
in the compressed cache. If it is found in the compressed cache,
then it is uncompressed and inserted into the uncompressed cache.
It is possible that the same block resides in the compressed cache
as well as the uncompressed cache at the same time. Both caches
have their own individual LRU policy.
Test Plan: Unit test case attached.
Reviewers: kailiu, sdong, haobo, leveldb
Reviewed By: haobo
CC: xjin, haobo
Differential Revision: https://reviews.facebook.net/D12675
Summary: Converted db_stress, db_repl_stress and db_bench to use gflags
Test Plan: I tested by printing out all the flags from old and new versions. Tried defaults, + various combinations with "interesting flags". Also, tested by running db_crashtest.py and db_crashtest2.py.
Reviewers: emayanke, dhruba, haobo, kailiu, sdong
Reviewed By: emayanke
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D13581
Summary:
Change namespace from leveldb to rocksdb. This allows a single
application to link in open-source leveldb code as well as
rocksdb code into the same process.
Test Plan: compile rocksdb
Reviewers: emayanke
Reviewed By: emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D13287
Summary: Will use iterators to verify keys in the db for half of its keys and Gets for the other half.
Test Plan: ./db_stress --max_key=1000 --ops_per_thread=100
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D13227
Summary: Using an iterator instead of the Get method, each thread goes through a portion of the database and verifies values by comparing to the shared state.
Test Plan:
./db_stress --db=/tmp/tmppp --max_key=10000 --ops_per_thread=10000
To test some basic cases, the following lines can be added (each set in turn) to the verifyDb method with the following expected results:
// Should abort with "Unexpected value found"
shared.Delete(start);
// Should abort with "Value not found"
WriteOptions write_opts;
db_->Delete(write_opts, Key(start));
// Should succeed
WriteOptions write_opts;
shared.Delete(start);
db_->Delete(write_opts, Key(start));
// Should abort with "Value not found"
WriteOptions write_opts;
db_->Delete(write_opts, Key(start + (end-start)/2));
// Should abort with "Value not found"
db_->Delete(write_opts, Key(end-1));
// Should abort with "Unexpected value"
shared.Delete(end-1);
// Should abort with "Unexpected value"
shared.Delete(start + (end-start)/2);
// Should abort with "Value not found"
db_->Delete(write_opts, Key(start));
shared.Delete(start);
db_->Delete(write_opts, Key(end-1));
db_->Delete(write_opts, Key(end-2));
To test the out of range abort, change the key in the for loop to Key(i+1), so that the key defined by the index i is now outside of the supposed range of the database.
Reviewers: emayanke
Reviewed By: emayanke
CC: dhruba, xjin
Differential Revision: https://reviews.facebook.net/D13071
Summary:
Added MultiIterate() which does a seek and some Next/Prev
calls. Iterator status is checked only, no data integrity check
Test Plan:
make db_stress
./db_stress --iterpercent=<nonzero value> --readpercent=, etc.
Reviewers: emayanke, dhruba, xjin
Reviewed By: emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D12915
Summary:
Added a new field called max_size_amplification_ratio in the
CompactionOptionsUniversal structure. This determines the maximum
percentage overhead of space amplification.
The size amplification is defined to be the ratio between the size of
the oldest file to the sum of the sizes of all other files. If the
size amplification exceeds the specified value, then min_merge_width
and max_merge_width are ignored and a full compaction of all files is done.
A value of 10 means that the size a database that stores 100 bytes
of user data could occupy 110 bytes of physical storage.
Test Plan: Unit test DBTest.UniversalCompactionSpaceAmplification added.
Reviewers: haobo, emayanke, xjin
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D12825
Summary: Replace include/leveldb with include/rocksdb.
Test Plan:
make clean; make check
make clean; make release
Differential Revision: https://reviews.facebook.net/D12489
Summary:
This patch adds three new MemTableRep's: UnsortedRep, PrefixHashRep, and VectorRep.
UnsortedRep stores keys in an std::unordered_map of std::sets. When an iterator is requested, it dumps the keys into an std::set and iterates over that.
VectorRep stores keys in an std::vector. When an iterator is requested, it creates a copy of the vector and sorts it using std::sort. The iterator accesses that new vector.
PrefixHashRep stores keys in an unordered_map mapping prefixes to ordered sets.
I also added one API change. I added a function MemTableRep::MarkImmutable. This function is called when the rep is added to the immutable list. It doesn't do anything yet, but it seems like that could be useful. In particular, for the vectorrep, it means we could elide the extra copy and just sort in place. The only reason I haven't done that yet is because the use of the ArenaAllocator complicates things (I can elaborate on this if needed).
Test Plan:
make -j32 check
./db_stress --memtablerep=vector
./db_stress --memtablerep=unsorted
./db_stress --memtablerep=prefixhash --prefix_size=10
Reviewers: dhruba, haobo, emayanke
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D12117
Test Plan:
- make all check;
- make release;
- make stringappend_test; ./stringappend_test
Reviewers: haobo, emayanke
Reviewed By: haobo
CC: leveldb, kailiu
Differential Revision: https://reviews.facebook.net/D12381
Summary:
Updated db_bench and utilities/merge_operators.h to allow for dynamic benchmarking
of merge operators in db_bench. Added a new test (--benchmarks=mergerandom), which performs
a bunch of random Merge() operations over random keys. Also added a "--merge_operator=" flag
so that the tester can easily benchmark different merge operators. Currently supports
the PutOperator and UInt64Add operator. Support for stringappend or list append may come later.
Test Plan:
1. make db_bench
2. Test the PutOperator (simulating Put) as follows:
./db_bench --benchmarks=fillrandom,readrandom,updaterandom,readrandom,mergerandom,readrandom --merge_operator=put
--threads=2
3. Test the UInt64AddOperator (simulating numeric addition) similarly:
./db_bench --value_size=8 --benchmarks=fillrandom,readrandom,updaterandom,readrandom,mergerandom,readrandom
--merge_operator=uint64add --threads=2
Reviewers: haobo, dhruba, zshao, MarkCallaghan
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11535
Summary:
Minor fix to current codes, including: coding style, output format,
comments. No major logic change. There are only 2 real changes, please see my inline comments.
Test Plan: make all check
Reviewers: haobo, dhruba, emayanke
Differential Revision: https://reviews.facebook.net/D12297
Summary: rocksdb replicaiton will need this when writing value+TS from master to slave 'as is'
Test Plan: make
Reviewers: dhruba, vamsi, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11919
Summary: Removed KeyMayExistImpl because KeyMayExist demanded Get like semantics now. Removed no_io from memtable and imm because we need the proper value now and shouldn't just stop when we see Merge in memtable. Added checks to block_cache. Updated documentation and unit-test
Test Plan: make all check;db_stress for 1 hour
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11853
Summary:
Introduced KeyMayExist checking during writebatch-delete and removed from Outer Delete API because it uses writebatch-delete.
Added code to skip getting Table from disk if not already present in table_cache.
Some renaming of variables.
Introduced KeyMayExistImpl which allows checking since specified sequence number in GetImpl useful to check partially written writebatch.
Changed KeyMayExist to not be pure virtual and provided a default implementation.
Expanded unit-tests in db_test to check appropriately.
Ran db_stress for 1 hour with ./db_stress --max_key=100000 --ops_per_thread=10000000 --delpercent=50 --filter_deletes=1 --statistics=1.
Test Plan: db_stress;make check
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D11745
Summary:
Wrote a new function in db_impl.c-CheckKeyMayExist that calls Get but with a new parameter turned on which makes Get return false only if bloom filters can guarantee that key is not in database. Delete calls this function and if the option- deletes_use_filter is turned on and CheckKeyMayExist returns false, the delete will be dropped saving:
1. Put of delete type
2. Space in the db,and
3. Compaction time
Test Plan:
make all check;
will run db_stress and db_bench and enhance unit-test once the basic design gets approved
Reviewers: dhruba, haobo, vamsi
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11607
Summary: db_stress should alos print complete statistics like db_bench. Needed this when I wanted to measure number of delete-IOs dropped due to CheckKeyMayExist to be introduced to rocksdb codebase later- to make deltes in rocksdb faster
Test Plan: make db_stress;./db_stress --max_key=100 --ops_per_thread=1000 --statistics=1
Reviewers: sheki, dhruba, vamsi, haobo
Reviewed By: dhruba
Differential Revision: https://reviews.facebook.net/D11655
Summary:
There is a new option called hybrid_mode which, when switched on,
causes HBase style compactions. Files from L0 are
compacted back into L0. This meat of this compaction algorithm
is in PickCompactionHybrid().
All files reside in L0. That means all files have overlapping
keys. Each file has a time-bound, i.e. each file contains a
range of keys that were inserted around the same time. The
start-seqno and the end-seqno refers to the timeframe when
these keys were inserted. Files that have contiguous seqno
are compacted together into a larger file. All files are
ordered from most recent to the oldest.
The current compaction algorithm starts to look for
candidate files starting from the most recent file. It continues to
add more files to the same compaction run as long as the
sum of the files chosen till now is smaller than the next
candidate file size. This logic needs to be debated
and validated.
The above logic should reduce write amplification to a
large extent... will publish numbers shortly.
Test Plan: dbstress runs for 6 hours with no data corruption (tested so far).
Differential Revision: https://reviews.facebook.net/D11289
Summary:
There is a new option called hybrid_mode which, when switched on,
causes HBase style compactions. Files from L0 are
compacted back into L0. This meat of this compaction algorithm
is in PickCompactionHybrid().
All files reside in L0. That means all files have overlapping
keys. Each file has a time-bound, i.e. each file contains a
range of keys that were inserted around the same time. The
start-seqno and the end-seqno refers to the timeframe when
these keys were inserted. Files that have contiguous seqno
are compacted together into a larger file. All files are
ordered from most recent to the oldest.
The current compaction algorithm starts to look for
candidate files starting from the most recent file. It continues to
add more files to the same compaction run as long as the
sum of the files chosen till now is smaller than the next
candidate file size. This logic needs to be debated
and validated.
The above logic should reduce write amplification to a
large extent... will publish numbers shortly.
Test Plan: dbstress runs for 6 hours with no data corruption (tested so far).
Differential Revision: https://reviews.facebook.net/D11289
Igor Canadi