Summary:
The second variable "SHELL" simply tells make explicitly which shell to use, instead of allowing it to default to "/bin/sh", which may or may not be Bash.

However, simply defining the second variable by itself causes make to throw an error concerning a circular definition, as it would be attempting to use the "shell" command while simultaneously trying to set which shell to use. Thus, the first variable "BASH_EXISTS" is defined such that make already knows about "/path/to/bash" before trying to use it to set "SHELL".

A more technically correct solution would be to edit the makefile itself to make it compatible with non-bash shells (see the original Issue discussion for details). However, as it seems very few of the people working on this project were building with non-bash shells, I figured this solution would be good enough.
Closes https://github.com/facebook/rocksdb/pull/1631

Differential Revision: D4295689

Pulled By: yiwu-arbug

fbshipit-source-id: e4f9532

Summary:
Add C API for CompactRangeOptions.
Closes https://github.com/facebook/rocksdb/pull/1596

Differential Revision: D4252339

Pulled By: yiwu-arbug

fbshipit-source-id: f768f93

Summary:
made db_stress capable of adding range deletions to its db and verifying their correctness. i'll make db_crashtest.py use this option later once the collapsing optimization (https://github.com/facebook/rocksdb/pull/1614) is committed because currently it slows down the test too much.
Closes https://github.com/facebook/rocksdb/pull/1625

Differential Revision: D4293939

Pulled By: ajkr

fbshipit-source-id: d3beb3a

Summary: Closes https://github.com/facebook/rocksdb/pull/1592

Differential Revision: D4246260

Pulled By: ajkr

fbshipit-source-id: ce03fa2

Summary:
IsTrivialMove returns true if no input file overlaps with output_level+1 with more than max_compaction_bytes_ bytes.
Closes https://github.com/facebook/rocksdb/pull/1619

Differential Revision: D4278338

Pulled By: yiwu-arbug

fbshipit-source-id: 994c001

Summary: Closes https://github.com/facebook/rocksdb/pull/1630

Differential Revision: D4293200

Pulled By: IslamAbdelRahman

fbshipit-source-id: 9c81f85

Summary: Closes https://github.com/facebook/rocksdb/pull/1629

Differential Revision: D4293183

Pulled By: IslamAbdelRahman

fbshipit-source-id: 759ea92

Summary:
When enabled, this option replaces range tombstones with a sequence of
point tombstones covering the same range. This can be used to A/B test perf of
range tombstones vs sequential point tombstones, and help us find the cross-over
point, i.e., the size of the range above which range tombstones outperform point
tombstones.
Closes https://github.com/facebook/rocksdb/pull/1594

Differential Revision: D4246312

Pulled By: ajkr

fbshipit-source-id: 3b00b23

Summary:
Fix error on mac/windows build since they don't recognize `uint`.
Closes https://github.com/facebook/rocksdb/pull/1624

Differential Revision: D4287139

Pulled By: yiwu-arbug

fbshipit-source-id: b7cc88f

Summary:
Add EventListener::OnExternalFileIngested() to allow user to subscribe to external file ingestion events
Closes https://github.com/facebook/rocksdb/pull/1623

Differential Revision: D4285844

Pulled By: IslamAbdelRahman

fbshipit-source-id: 0b95a88

Summary:
This is an implementation of non-exclusive locks for pessimistic transactions. It is relatively simple and does not prevent starvation (ie. it's possible that request for exclusive access will never be granted if there are always threads holding shared access). It is done by changing `KeyLockInfo` to hold an set a transaction ids, instead of just one, and adding a flag specifying whether this lock is currently held with exclusive access or not.

Some implementation notes:
- Some lock diagnostic functions had to be updated to return a set of transaction ids for a given lock, eg. `GetWaitingTxn` and `GetLockStatusData`.
- Deadlock detection is a bit more complicated since a transaction can now wait on multiple other transactions. A BFS is done in this case, and deadlock detection depth is now just a limit on the number of transactions we visit.
- Expirable transactions do not work efficiently with shared locks at the moment, but that's okay for now.
Closes https://github.com/facebook/rocksdb/pull/1573

Differential Revision: D4239097

Pulled By: lth

fbshipit-source-id: da7c074

Summary:
I hit the land button too fast and didn't include the line.
Closes https://github.com/facebook/rocksdb/pull/1622

Differential Revision: D4281316

Pulled By: yiwu-arbug

fbshipit-source-id: c7b38e0

Summary:
These changes are included in the new branch-cut.
Closes https://github.com/facebook/rocksdb/pull/1621

Differential Revision: D4281015

Pulled By: yiwu-arbug

fbshipit-source-id: d88858b

Summary:
Embarassingly enough, the first time I tried to use my new feature in logdevice it crashed with this assertion failure:

  db/pinned_iterators_manager.h:30: void rocksdb::PinnedIteratorsManager::StartPinning(): Assertion `pinning_enabled == false' failed

The issue was that `pinned_iters_mgr_.StartPinning()` was called but `pinned_iters_mgr_.ReleasePinnedData()` wasn't.
Closes https://github.com/facebook/rocksdb/pull/1611

Differential Revision: D4265622

Pulled By: al13n321

fbshipit-source-id: 747b10f

Summary:
Allow user to explicitly specify that the generated file by SstFileWriter will be ingested in a specific CF.
This allow us to persist the CF id in the generated file
Closes https://github.com/facebook/rocksdb/pull/1615

Differential Revision: D4270422

Pulled By: IslamAbdelRahman

fbshipit-source-id: 7fb954e

Summary:
Made delete_obsolete_files_period_micros option dynamic. It can be updating using DB::SetDBOptions().
Closes https://github.com/facebook/rocksdb/pull/1595

Differential Revision: D4246569

Pulled By: tonek

fbshipit-source-id: d23f560

Summary:
override is missing for FilterV2
Closes https://github.com/facebook/rocksdb/pull/1606

Differential Revision: D4263832

Pulled By: IslamAbdelRahman

fbshipit-source-id: d8b337a

Summary:
Add memtable_insert_with_hint_prefix_size option to db_bench
Closes https://github.com/facebook/rocksdb/pull/1604

Differential Revision: D4260549

Pulled By: yiwu-arbug

fbshipit-source-id: cee5ef7

Summary:
Reduce number of comparisons in heap by caching which child node in the first level is smallest (left_child or right_child)
So next time we can compare directly against the smallest child

I see that the total number of calls to comparator drops significantly when using this optimization

Before caching (~2mil key comparison for iterating the DB)
```
$ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq" --db="/dev/shm/heap_opt" --use_existing_db --disable_auto_compactions --cache_size=1000000000  --perf_level=2
readseq      :       0.338 micros/op 2959201 ops/sec;  327.4 MB/s user_key_comparison_count = 2000008
```
After caching (~1mil key comparison for iterating the DB)
```
$ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq" --db="/dev/shm/heap_opt" --use_existing_db --disable_auto_compactions --cache_size=1000000000 --perf_level=2
readseq      :       0.309 micros/op 3236801 ops/sec;  358.1 MB/s user_key_comparison_count = 1000011
```

It also improves
Closes https://github.com/facebook/rocksdb/pull/1600

Differential Revision: D4256027

Pulled By: IslamAbdelRahman

fbshipit-source-id: 76fcc66

Summary:
Travis fail because it uses clang 3.6 which don't recognize
`__attribute__((__no_sanitize__("undefined")))`
Closes https://github.com/facebook/rocksdb/pull/1601

Differential Revision: D4257175

Pulled By: IslamAbdelRahman

fbshipit-source-id: fb4d1ab

Summary:
Now that we have userspace persisted cache, we don't need flashcache anymore.
Closes https://github.com/facebook/rocksdb/pull/1588

Differential Revision: D4245114

Pulled By: igorcanadi

fbshipit-source-id: e2c1c72

Summary:
Multi-write thread may update the status of the parallel_group in
WriteThread::CompleteParallelWorker if the status of Writer is not ok!
When copy write status to the paralle_group, the write thread just hold the
mutex of the the writer processed by itself. it is useless. The thread
should held the the leader of the parallel_group instead.
Closes https://github.com/facebook/rocksdb/pull/1598

Differential Revision: D4252335

Pulled By: siying

fbshipit-source-id: 3864cf7

Summary:
This adds the ability for compaction filter to say "drop this key-value, and also drop everything up to key x". This will cause the compaction to seek input iterator to x, without reading the data. This can make compaction much faster when large consecutive chunks of data are filtered out. See the changes in include/rocksdb/compaction_filter.h for the new API.

Along the way this diff also adds ability for compaction filter changing merge operands, similar to how it can change values; we're not going to use this feature, it just seemed easier and cleaner to implement it than to document that it's not implemented :)

The diff is not as big as it may seem, about half of the lines are a test.
Closes https://github.com/facebook/rocksdb/pull/1599

Differential Revision: D4252092

Pulled By: al13n321

fbshipit-source-id: 41e1e48

Summary: Closes https://github.com/facebook/rocksdb/pull/1587

Differential Revision: D4245923

Pulled By: yiwu-arbug

fbshipit-source-id: 6ee7291

Summary:
Add C API to set base_backgroud_compactions
Closes https://github.com/facebook/rocksdb/pull/1571

Differential Revision: D4245709

Pulled By: yiwu-arbug

fbshipit-source-id: 792c6b8

Summary: Closes https://github.com/facebook/rocksdb/pull/1591

Differential Revision: D4246019

Pulled By: ajkr

fbshipit-source-id: 0c4aa37

Summary:
…rong owner

 mysql_mtr_filter script needs proper oncall
Closes https://github.com/facebook/rocksdb/pull/1586

Differential Revision: D4245150

Pulled By: anirbanr-fb

fbshipit-source-id: fd8577c

Summary: Closes https://github.com/facebook/rocksdb/pull/1578

Differential Revision: D4241171

Pulled By: ajkr

fbshipit-source-id: ce5fd83

Summary:
In dynamic leveled compaction, when calculating read bytes, output level bytes may be wronglyl calculated as input level inputs. Fix it.
Closes https://github.com/facebook/rocksdb/pull/1475

Differential Revision: D4148412

Pulled By: siying

fbshipit-source-id: f2f475a

Summary:
Make conversion explicit, implicit conversion breaks the build
Closes https://github.com/facebook/rocksdb/pull/1589

Differential Revision: D4245158

Pulled By: IslamAbdelRahman

fbshipit-source-id: aaec00d

Summary:
"make analyze" complains the assignment is not useful. Remove it.
Closes https://github.com/facebook/rocksdb/pull/1581

Differential Revision: D4241697

Pulled By: siying

fbshipit-source-id: 178f67a

Summary:
AddTombstones() needs to be before t->Get(), oops :'(
Closes https://github.com/facebook/rocksdb/pull/1576

Differential Revision: D4241041

Pulled By: ajkr

fbshipit-source-id: 781ceea

Summary:
https://github.com/facebook/rocksdb/commit/99c052a34f93d119b75eccdcd489ecd581d48ee9 fixes integer overflow in GetL0ThresholdSpeedupCompaction() by checking if int become -ve.
UBSAN will complain about that since this is still an overflow, we can fix the issue by simply using int64_t
Closes https://github.com/facebook/rocksdb/pull/1582

Differential Revision: D4241525

Pulled By: IslamAbdelRahman

fbshipit-source-id: b3ae21f

Summary:
disable UBSAN for functions with intentional left shift on -ve number / overflow

These functions are
rocksdb:: Hash
FixedLengthColBufEncoder::Append
FaultInjectionTest:: Key
Closes https://github.com/facebook/rocksdb/pull/1577

Differential Revision: D4240801

Pulled By: IslamAbdelRahman

fbshipit-source-id: 3e1caf6

Summary:
Fix CompactionJob::Install division by zero
Closes https://github.com/facebook/rocksdb/pull/1580

Differential Revision: D4240794

Pulled By: IslamAbdelRahman

fbshipit-source-id: 7286721

Summary:
Having -ve value for max_write_buffer_number does not make sense and cause us to do a left shift on a -ve value number
Closes https://github.com/facebook/rocksdb/pull/1579

Differential Revision: D4240798

Pulled By: IslamAbdelRahman

fbshipit-source-id: bd6267e

Summary:
Fix division by zero in compaction_job.cc
Closes https://github.com/facebook/rocksdb/pull/1575

Differential Revision: D4240818

Pulled By: IslamAbdelRahman

fbshipit-source-id: a8bc757

Summary:
Both the single deletion and the value are included in compaction outputs, so no need to update the stat for the value's deletion yet, otherwise it'd be double-counted.
Closes https://github.com/facebook/rocksdb/pull/1574

Differential Revision: D4241181

Pulled By: ajkr

fbshipit-source-id: c9aaa15

Summary:
- "rocksdb.compaction.key.drop.range_del" - number of keys dropped during compaction due to a range tombstone covering them
- "rocksdb.compaction.range_del.drop.obsolete" - number of range tombstones dropped due to compaction to bottom level and no snapshot saving them
- s/CompactionIteratorStats/CompactionIterationStats/g since this class is no longer specific to CompactionIterator -- it's also updated for range tombstone iteration during compaction
- Move the above class into a separate .h file to avoid circular dependency.
Closes https://github.com/facebook/rocksdb/pull/1520

Differential Revision: D4187179

Pulled By: ajkr

fbshipit-source-id: 10c2103

Summary:
In one deployment we saw high latencies (presumably from slow iterator operations) and a lot of CPU time reported by perf with this stack:

```
  rocksdb::MergingIterator::Next
  rocksdb::DBIter::FindNextUserEntryInternal
  rocksdb::DBIter::Seek
```

I think what's happening is:
1. we create a snapshot iterator,
2. we do lots of Put()s for the same key x; this creates lots of entries in memtable,
3. we seek the iterator to a key slightly smaller than x,
4. the seek walks over lots of entries in memtable for key x, skipping them because of high sequence numbers.

CC IslamAbdelRahman
Closes https://github.com/facebook/rocksdb/pull/1413

Differential Revision: D4083879

Pulled By: IslamAbdelRahman

fbshipit-source-id: a83ddae