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
Summary: As title. Exposed a Count function that returns the number of updates in a batch. Could be handy for replication sequence number check.
Test Plan: make check;
Reviewers: emayanke, sheki, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11523
Summary:
With the Makefile now updated to correctly update all .o files, this
should fix the issues recompiling stringappend_test. This should also fix the
"segmentation-fault" that we were getting earlier. Now, stringappend_test should
be clean, and I have added it back to the unit-tests. Also made some minor updates
to the tests themselves.
Test Plan:
1. make clean; make stringappend_test -j 32 (will test it by itself)
2. make clean; make all check -j 32 (to run all unit tests)
3. make clean; make release (test in release mode)
4. valgrind ./stringappend_test (valgrind tests)
Reviewers: haobo, jpaton, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11505
Summary:
The old Makefile did not remove ALL .o and .d files, but rather only
those that happened to be in the root folder and one-level deep. This was causing
issues when recompiling files in deeper folders. This fix now causes make clean
to find ALL .o and .d files via a unix "find" command, and then remove them.
Test Plan:
make clean;
make all -j 32;
Reviewers: haobo, jpaton, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11493
Summary: [start_time, end_time) is waht I'm following for the buckets and the whole time-range. Also cleaned up some code in db_ttl.* Not correcting the spacing/indenting convention for util/ldb_cmd.cc in this diff.
Test Plan: python ldb_test.py, make ttl_test, Run mcrocksdb-backup tool, Run the ldb tool on 2 mcrocksdb production backups form sigmafio033.prn1
Reviewers: vamsi, haobo
Reviewed By: vamsi
Differential Revision: https://reviews.facebook.net/D11433
Summary:
Scan and Dump commands in ldb use iterator. We need to also print timestamp for ttl databases for debugging. For this I create a TtlIterator class pointer in these functions and assign it the value of Iterator pointer which actually points to t TtlIterator object, and access the new function ValueWithTS which can return TS also. Buckets feature for dump command: gives a count of different key-values in the specified time-range distributed across the time-range partitioned according to bucket-size. start_time and end_time are specified in unixtimestamp and bucket in seconds on the user-commandline
Have commented out 3 ines from ldb_test.py so that the test does not break right now. It breaks because timestamp is also printed now and I have to look at wildcards in python to compare properly.
Test Plan: python tools/ldb_test.py
Reviewers: vamsi, dhruba, haobo, sheki
Reviewed By: vamsi
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11403
Summary: As title, now that db_stress supports --map_read properly
Test Plan: make crash_test
Reviewers: vamsi, emayanke, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11391
Summary: as title, use initialize list so that lines fit in 80 chars.
Test Plan: make check;
Reviewers: sheki, dhruba
Differential Revision: https://reviews.facebook.net/D11385
Summary: as title, also removed an incorrect assertion
Test Plan: make check; db_stress --mmap_read=1; db_stress --mmap_read=0
Reviewers: dhruba, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11367
Summary:
Zlib_{Compress,Uncompress} did not handle very small input buffers properly. In addition, they did not call inflate/deflate until Z_STREAM_END was returned; it was possible for them to exit when only Z_OK had returned.
This diff also fixes a bunch of lint errors.
Test Plan: Run make check
Reviewers: dhruba, sheki, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11301
Summary: This diff added an option to control the incremenal sync frequency. db_bench has a new flag bytes_per_sync for easy tuning exercise.
Test Plan: make check; db_bench
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11295
Summary:
simplify the printing code in db_bench
use TickersMap and HistogramsNameMap introduced in previous diffs.
Test Plan: ./db_bench --statistics=1 and see if all the statistics are printed
Reviewers: haobo, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11355
Summary:
Merge multiple multiple memtables in memory before writing it
out to a file in L0.
There is a new config parameter min_write_buffer_number_to_merge
that specifies the number of write buffers that should be merged
together to a single file in storage. The system will not flush
wrte buffers to storage unless at least these many buffers have
accumulated in memory.
The default value of this new parameter is 1, which means that
a write buffer will be immediately flushed to disk as soon it is
ready.
Test Plan: make check
Differential Revision: https://reviews.facebook.net/D11241
Summary:
Rocksdb allos specifying the number of files in L0 that triggers
compactions. Expose this api as a command line parameter for
running db_stress.
Test Plan: Run test
Reviewers: sheki, emayanke
Reviewed By: emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11343
Summary: Add a histogram to track WriteBlock times
Test Plan: db_bench and print
Reviewers: haobo, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11319
Summary:
I'm concerned about a random seg-fault that sometimes occurs when
running stringappend_test. I will investigate further. First, I am removing
stringappend_test from the regular release tests, and making some clean-ups
to the code.
Test Plan:
1. make stringappend_test
2. ./stringappend_test
Reviewers: haobo, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11313
Summary:
Use a bit set to keep track of which random number is generated.
Currently only supports single-threaded. All our perf tests are run with threads=1
Copied over bitset implementation from common/datastructures
Test Plan: printed the generated keys, and verified all keys were present.
Reviewers: MarkCallaghan, haobo, dhruba
Reviewed By: MarkCallaghan
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11247
Summary: This hopefully gives the right semantics to compaction filter. Will write a small wiki to explain the ideas.
Test Plan: make check; db_stress
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11121
Summary: Table is setup for compaction using Table::SetupForCompaction. So read block calls can be differentiated b/w Gets/Compaction. Use this and measure times.
Test Plan: db_bench --statistics=1
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, MarkCallaghan
Differential Revision: https://reviews.facebook.net/D11217
Summary:
During compaction, we sync the output files after they are fully written out. This causes unnecessary blocking of the compaction thread and burstiness of the write traffic.
This diff simply asks the OS to sync data incrementally as they are written, on the background. The hope is that, at the final sync, most of the data are already on disk and we would block less on the sync call. Thus, each compaction runs faster and we could use fewer number of compaction threads to saturate IO.
In addition, the write traffic will be smoothed out, hopefully reducing the IO P99 latency too.
Some quick tests show 10~20% improvement in per thread compaction throughput. Combined with posix advice on compaction read, just 5 threads are enough to almost saturate the udb flash bandwidth for 800 bytes write only benchmark.
What's more promising is that, with saturated IO, iostat shows average wait time is actually smoother and much smaller.
For the write only test 800bytes test:
Before the change: await occillate between 10ms and 3ms
After the change: await ranges 1-3ms
Will test against read-modify-write workload too, see if high read latency P99 could be resolved.
Will introduce a parameter to control the sync interval in a follow up diff after cleaning up EnvOptions.
Test Plan: make check; db_bench; db_stress
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11115
Summary:
Preliminary! Introduced the --use_multiget=1 and --keys_per_multiget=n
flags for db_bench. Also updated and tested the ReadRandom() method
to include an option to use multiget. By default,
keys_per_multiget=100.
Preliminary tests imply that multiget is at least 1.25x faster per
key than regular get.
Will continue adding Multiget for ReadMissing, ReadHot,
RandomWithVerify, ReadRandomWriteRandom; soon. Will also think
about ways to better verify benchmarks.
Test Plan:
1. make db_bench
2. ./db_bench --benchmarks=fillrandom
3. ./db_bench --benchmarks=readrandom --use_existing_db=1
--use_multiget=1 --threads=4 --keys_per_multiget=100
4. ./db_bench --benchmarks=readrandom --use_existing_db=1
--threads=4
5. Verify ops/sec (and 1000000 of 1000000 keys found)
Reviewers: haobo, MarkCallaghan, dhruba
Reviewed By: MarkCallaghan
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11127
Summary:
This diff simplifies EnvOptions by treating it as POD, similar to Options.
- virtual functions are removed and member fields are accessed directly.
- StorageOptions is removed.
- Options.allow_readahead and Options.allow_readahead_compactions are deprecated.
- Unused global variables are removed: useOsBuffer, useFsReadAhead, useMmapRead, useMmapWrite
Test Plan: make check; db_stress
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11175
Summary:
Completed the implementation for the Redis API for Lists.
The Redis API uses rocksdb as a backend to persistently
store maps from key->list. It supports basic operations
for appending, inserting, pushing, popping, and accessing
a list, given its key.
Test Plan:
- Compile with: make redis_test
- Test with: ./redis_test
- Run all unit tests (for all rocksdb) with: make all check
- To use an interactive REDIS client use: ./redis_test -m
- To clean the database before use: ./redis_test -m -d
Reviewers: haobo, dhruba, zshao
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D10833
Summary:
The code was such that if multi-threaded-compactions as well
as seek compaction are enabled then it submits multiple
compaction request for the same range of keys. This causes
extraneous sst-files to accumulate at various levels.
Test Plan:
I am not able to write a very good unit test for this one
but can easily reproduce this bug with 'dbstress' with the
following options.
batch=1;maxk=100000000;ops=100000000;ro=0;fm=2;bpl=10485760;of=500000; wbn=3; mbc=20; mb=2097152; wbs=4194304; dds=1; sync=0; t=32; bs=16384; cs=1048576; of=500000; ./db_stress --disable_seek_compaction=0 --mmap_read=0 --threads=$t --block_size=$bs --cache_size=$cs --open_files=$of --verify_checksum=1 --db=/data/mysql/leveldb/dbstress.dir --sync=$sync --disable_wal=1 --disable_data_sync=$dds --write_buffer_size=$wbs --target_file_size_base=$mb --target_file_size_multiplier=$fm --max_write_buffer_number=$wbn --max_background_compactions=$mbc --max_bytes_for_level_base=$bpl --reopen=$ro --ops_per_thread=$ops --max_key=$maxk --test_batches_snapshots=$batch
Reviewers: leveldb, emayanke
Reviewed By: emayanke
Differential Revision: https://reviews.facebook.net/D11055
Summary: Added logic to make another WriteBatch with Timestamps during the Write function execution in TTL class. Also expanded the ttl_test to test for it. Have done nothing for Merge for now.
Test Plan: make ttl_test;./ttl_test
Reviewers: haobo, vamsi, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D10827
Summary: the assert was wrong in D11145. Broke build
Test Plan: make db_bench run it
Reviewers: dhruba, haobo, emayanke
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11187
Summary:
The current code prints the name of the InternalKeyComparator
in the log file. We would also like to print the name of the
user-specified comparator for easier debugging.
Test Plan: make check
Reviewers: sheki
Reviewed By: sheki
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11181
Summary: Provide a map of histograms and ticker vs strings. Fb303 libraries can use this to provide the mapping. We will not have to duplicate the code during release.
Test Plan: db_bench with statistics=1
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11145
Summary:
Without this files could be written out to a level greater than the maximum level possible and is the source of the segfaults that wormhole awas getting. The sequence of steps that was followed:
1. WriteLevel0Table was called when memtable was to be flushed for a file.
2. PickLevelForMemTableOutput was called to determine the level to which this file should be pushed.
3. PickLevelForMemTableOutput returned a wrong result because max_mem_compaction_level was equal to 2 even when num_levels was equal to 0.
The fix to re-initialize max_mem_compaction_level based on num_levels passed seems correct.
Test Plan: make all check; Also made a dummy file to mimic the wormhole-file behaviour which was causing the segfaults and found that the same segfault occurs without this change and not with this.
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11157
Summary: These extra options caught some bugs. Will be run via Jenkins now with the crash_test
Test Plan: ./make crashtest
Reviewers: dhruba, vamsi
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D11151
Summary:
I think the check for "error" that I added had caused
false alarm. Fixed that.
Test Plan:
Revert Plan: OK
Task ID: #
Reviewers: emayanke, dhruba
Reviewed By: emayanke
Differential Revision: https://reviews.facebook.net/D11139
Summary: Added a target to Makefile called 'tags' that runs ctags and cscope on all *.cc and *.h file
Test Plan:
Run 'make tags'. Then start vim and do
:set tags=./tags
:cs add cscope.out
These commands should give you no error messages. You should then be able to access cscope db and ctags as normal in vim.
Reviewers: dhruba
Differential Revision: https://reviews.facebook.net/D11103
Summary:
Implemented the MultiGet operator which takes in a list of keys
and returns their associated values. Currently uses std::vector as its
container data structure. Otherwise, it works identically to "Get".
Test Plan:
1. make db_test ; compile it
2. ./db_test ; test it
3. make all check ; regress / run all tests
4. make release ; (optional) compile with release settings
Reviewers: haobo, MarkCallaghan, dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D10875
Summary: Added the 'score' column to the compaction stats output, which shows the level total size devided by level target size. Could be useful when monitoring compaction decisions...
Test Plan: make check; db_bench
Reviewers: dhruba
CC: leveldb, MarkCallaghan
Differential Revision: https://reviews.facebook.net/D11025
Summary:
This diff adds an option to specify whether PTHREAD_MUTEX_ADAPTIVE_NP will be enabled for the rocksdb single big kernel lock. db_bench also have this option now.
Quickly tested 8 thread cpu bound 100 byte random read.
No fast mutex: ~750k/s ops
With fast mutex: ~880k/s ops
Test Plan: make check; db_bench; db_stress
Reviewers: dhruba
CC: MarkCallaghan, leveldb
Differential Revision: https://reviews.facebook.net/D11031
Dhruba Borthakur