Summary:
The first key is used to defer reading the data block until this file gets to the top of merging iterator's heap. For short range scans, most files never make it to the top of the heap, so this change can reduce read amplification by a lot sometimes.
Consider the following workload. There are a few data streams (we'll be calling them "logs"), each stream consisting of a sequence of blobs (we'll be calling them "records"). Each record is identified by log ID and a sequence number within the log. RocksDB key is concatenation of log ID and sequence number (big endian). Reads are mostly relatively short range scans, each within a single log. Writes are mostly sequential for each log, but writes to different logs are randomly interleaved. Compactions are disabled; instead, when we accumulate a few tens of sst files, we create a new column family and start writing to it.
So, a typical sst file consists of a few ranges of blocks, each range corresponding to one log ID (we use FlushBlockPolicy to cut blocks at log boundaries). A typical read would go like this. First, iterator Seek() reads one block from each sst file. Then a series of Next()s move through one sst file (since writes to each log are mostly sequential) until the subiterator reaches the end of this log in this sst file; then Next() switches to the next sst file and reads sequentially from that, and so on. Often a range scan will only return records from a small number of blocks in small number of sst files; in this case, the cost of initial Seek() reading one block from each file may be bigger than the cost of reading the actually useful blocks.
Neither iterate_upper_bound nor bloom filters can prevent reading one block from each file in Seek(). But this PR can: if the index contains first key from each block, we don't have to read the block until this block actually makes it to the top of merging iterator's heap, so for short range scans we won't read any blocks from most of the sst files.
This PR does the deferred block loading inside value() call. This is not ideal: there's no good way to report an IO error from inside value(). As discussed with siying offline, it would probably be better to change InternalIterator's interface to explicitly fetch deferred value and get status. I'll do it in a separate PR.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5289
Differential Revision: D15256423
Pulled By: al13n321
fbshipit-source-id: 750e4c39ce88e8d41662f701cf6275d9388ba46a
Summary:
Given that index value is a BlockHandle, which is basically an <offset, size> pair we can apply delta encoding on the values. The first value at each index restart interval encoded the full BlockHandle but the rest encode only the size. Refer to IndexBlockIter::DecodeCurrentValue for the detail of the encoding. This reduces the index size which helps using the block cache more efficiently. The feature is enabled with using format_version 4.
The feature comes with a bit of cpu overhead which should be paid back by the higher cache hits due to smaller index block size.
Results with sysbench read-only using 4k blocks and using 16 index restart interval:
Format 2:
19585 rocksdb read-only range=100
Format 3:
19569 rocksdb read-only range=100
Format 4:
19352 rocksdb read-only range=100
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3983
Differential Revision: D8361343
Pulled By: maysamyabandeh
fbshipit-source-id: f882ee082322acac32b0072e2bdbb0b5f854e651
Summary:
Before this PR, Iterator/InternalIterator may simultaneously have non-ok status() and Valid() = true. That state means that the last operation failed, but the iterator is nevertheless positioned on some unspecified record. Likely intended uses of that are:
* If some sst files are corrupted, a normal iterator can be used to read the data from files that are not corrupted.
* When using read_tier = kBlockCacheTier, read the data that's in block cache, skipping over the data that is not.
However, this behavior wasn't documented well (and until recently the wiki on github had misleading incorrect information). In the code there's a lot of confusion about the relationship between status() and Valid(), and about whether Seek()/SeekToLast()/etc reset the status or not. There were a number of bugs caused by this confusion, both inside rocksdb and in the code that uses rocksdb (including ours).
This PR changes the convention to:
* If status() is not ok, Valid() always returns false.
* Any seek operation resets status. (Before the PR, it depended on iterator type and on particular error.)
This does sacrifice the two use cases listed above, but siying said it's ok.
Overview of the changes:
* A commit that adds missing status checks in MergingIterator. This fixes a bug that actually affects us, and we need it fixed. `DBIteratorTest.NonBlockingIterationBugRepro` explains the scenario.
* Changes to lots of iterator types to make all of them conform to the new convention. Some bug fixes along the way. By far the biggest changes are in DBIter, which is a big messy piece of code; I tried to make it less big and messy but mostly failed.
* A stress-test for DBIter, to gain some confidence that I didn't break it. It does a few million random operations on the iterator, while occasionally modifying the underlying data (like ForwardIterator does) and occasionally returning non-ok status from internal iterator.
To find the iterator types that needed changes I searched for "public .*Iterator" in the code. Here's an overview of all 27 iterator types:
Iterators that didn't need changes:
* status() is always ok(), or Valid() is always false: MemTableIterator, ModelIter, TestIterator, KVIter (2 classes with this name anonymous namespaces), LoggingForwardVectorIterator, VectorIterator, MockTableIterator, EmptyIterator, EmptyInternalIterator.
* Thin wrappers that always pass through Valid() and status(): ArenaWrappedDBIter, TtlIterator, InternalIteratorFromIterator.
Iterators with changes (see inline comments for details):
* DBIter - an overhaul:
- It used to silently skip corrupted keys (`FindParseableKey()`), which seems dangerous. This PR makes it just stop immediately after encountering a corrupted key, just like it would for other kinds of corruption. Let me know if there was actually some deeper meaning in this behavior and I should put it back.
- It had a few code paths silently discarding subiterator's status. The stress test caught a few.
- The backwards iteration code path was expecting the internal iterator's set of keys to be immutable. It's probably always true in practice at the moment, since ForwardIterator doesn't support backwards iteration, but this PR fixes it anyway. See added DBIteratorTest.ReverseToForwardBug for an example.
- Some parts of backwards iteration code path even did things like `assert(iter_->Valid())` after a seek, which is never a safe assumption.
- It used to not reset status on seek for some types of errors.
- Some simplifications and better comments.
- Some things got more complicated from the added error handling. I'm open to ideas for how to make it nicer.
* MergingIterator - check status after every operation on every subiterator, and in some places assert that valid subiterators have ok status.
* ForwardIterator - changed to the new convention, also slightly simplified.
* ForwardLevelIterator - fixed some bugs and simplified.
* LevelIterator - simplified.
* TwoLevelIterator - changed to the new convention. Also fixed a bug that would make SeekForPrev() sometimes silently ignore errors from first_level_iter_.
* BlockBasedTableIterator - minor changes.
* BlockIter - replaced `SetStatus()` with `Invalidate()` to make sure non-ok BlockIter is always invalid.
* PlainTableIterator - some seeks used to not reset status.
* CuckooTableIterator - tiny code cleanup.
* ManagedIterator - fixed some bugs.
* BaseDeltaIterator - changed to the new convention and fixed a bug.
* BlobDBIterator - seeks used to not reset status.
* KeyConvertingIterator - some small change.
Closes https://github.com/facebook/rocksdb/pull/3810
Differential Revision: D7888019
Pulled By: al13n321
fbshipit-source-id: 4aaf6d3421c545d16722a815b2fa2e7912bc851d
Summary:
this PR fixes a few failed contbuild:
1. ASAN memory leak in Block::NewIterator (table/block.cc:429). the proper destruction of first_level_iter_ and second_level_iter_ of two_level_iterator.cc is missing from the code after the refactoring in https://github.com/facebook/rocksdb/pull/3406
2. various unused param errors introduced by https://github.com/facebook/rocksdb/pull/3662
3. updated comment for `ForceReleaseCachedEntry` to emphasize the use of `force_erase` flag.
Closes https://github.com/facebook/rocksdb/pull/3718
Reviewed By: maysamyabandeh
Differential Revision: D7621192
Pulled By: miasantreble
fbshipit-source-id: 476c94264083a0730ded957c29de7807e4f5b146
Summary:
Use a customzied BlockBasedTableIterator and LevelIterator to replace current implementations leveraging two-level-iterator. Hope the customized logic will make code easier to understand. As a side effect, BlockBasedTableIterator reduces the allocation for the data block iterator object, and avoid the virtual function call to it, because we can directly reference BlockIter, a final class. Similarly, LevelIterator reduces virtual function call to the dummy iterator iterating the file metadata. It also enabled further optimization.
The upper bound check is also moved from index block to data block. This implementation fits this iterator better. After the change, forwared iterator is slightly optimized to ensure we trim those iterators.
The two-level-iterator now is only used by partitioned index, so it is simplified.
Closes https://github.com/facebook/rocksdb/pull/3406
Differential Revision: D6809041
Pulled By: siying
fbshipit-source-id: 7da3b9b1d3c8e9d9405302c15920af1fcaf50ffa
Summary:
Now if we have iterate_upper_bound set, we continue read until get a key >= upper_bound. For a lot of cases that neighboring data blocks have a user key gap between them, our index key will be a user key in the middle to get a shorter size. For example, if we have blocks:
[a b c d][f g h]
Then the index key for the first block will be 'e'.
then if upper bound is any key between 'd' and 'e', for example, d1, d2, ..., d99999999999, we don't have to read the second block and also know that we have done our iteration by reaching the last key that smaller the upper bound already.
This diff can reduce RA in most cases.
Closes https://github.com/facebook/rocksdb/pull/2239
Differential Revision: D4990693
Pulled By: lightmark
fbshipit-source-id: ab30ea2e3c6edf3fddd5efed3c34fcf7739827ff
Summary:
Add new Iterator API, `SeekForPrev`: find the last key that <= target key
support prefix_extractor
support prefix_same_as_start
support upper_bound
not supported in iterators without Prev()
Also add tests in db_iter_test and db_iterator_test
Pass all tests
Cheers!
Test Plan: make all check -j64
Reviewers: andrewkr, yiwu, IslamAbdelRahman, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D64149
Summary:
This diff include these simple change
- Rename ReleasePinnedIterators to ReleasePinnedData
- Rename PinIteratorIfNeeded to PinIterator
- Use std::vector directly in PinnedIteratorsManager instead of std::unique_ptr<std::vector>
- Generalize PinnedIteratorsManager by adding PinPtr which can pin any pointer
Test Plan: existing tests
Reviewers: sdong, yiwu, andrewkr
Reviewed By: andrewkr
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D61305
Summary:
While trying to reuse PinData() / ReleasePinnedData() .. to optimize away some memcpys I realized that there is a significant overhead for using PinData() / ReleasePinnedData if they were called many times.
This diff refactor the pinning logic by introducing PinnedIteratorsManager a centralized component that will be created once and will be notified whenever we need to Pin an Iterator. This implementation have much less overhead than the original implementation
Test Plan:
make check -j64
COMPILE_WITH_ASAN=1 make check -j64
Reviewers: yhchiang, sdong, andrewkr
Reviewed By: andrewkr
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D56493
Summary:
This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted
ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted
Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted
Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed.
Benchmark results (using https://phabricator.fb.com/P20083553)
```
// $ du -h /home/tec/local/normal.4K.Snappy/db10077
// 6.1G /home/tec/local/normal.4K.Snappy/db10077
// $ du -h /home/tec/local/zero.8K.LZ4/db10077
// 6.4G /home/tec/local/zero.8K.LZ4/db10077
// Benchmarks for shard db10077
// _build/opt/rocks/benchmark/rocks_copy_benchmark \
// --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \
// --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077"
// First run
// ============================================================================
// rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s
// ============================================================================
// BM_StringCopy 1.73s 576.97m
// BM_StringPiece 103.74% 1.67s 598.55m
// ============================================================================
// Match rate : 1000000 / 1000000
// Second run
// ============================================================================
// rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s
// ============================================================================
// BM_StringCopy 611.99ms 1.63
// BM_StringPiece 203.76% 300.35ms 3.33
// ============================================================================
// Match rate : 1000000 / 1000000
```
Test Plan: Unit tests
Reviewers: sdong, igor, anthony, yhchiang, rven
Reviewed By: rven
Subscribers: dhruba, lovro, adsharma
Differential Revision: https://reviews.facebook.net/D48999
Summary:
Separate a new class InternalIterator from class Iterator, when the look-up is done internally, which also means they operate on key with sequence ID and type.
This change will enable potential future optimizations but for now InternalIterator's functions are still the same as Iterator's.
At the same time, separate the cleanup function to a separate class and let both of InternalIterator and Iterator inherit from it.
Test Plan: Run all existing tests.
Reviewers: igor, yhchiang, anthony, kradhakrishnan, IslamAbdelRahman, rven
Reviewed By: rven
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D48549
Summary: Try to allocate LevelFileIteratorState and LevelFileNumIterator from DB iterator's arena, instead of calling malloc and free.
Test Plan: valgrind check
Reviewers: rven, yhchiang, anthony, kradhakrishnan, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D40929
Summary:
When using latest clang (3.6 or 3.7/trunck) rocksdb is failing with many errors. Almost all of them are missing override errors. This diff adds missing override keyword. No manual changes.
Prerequisites: bear and clang 3.5 build with extra tools
```lang=bash
% USE_CLANG=1 bear make all # generate a compilation database http://clang.llvm.org/docs/JSONCompilationDatabase.html
% clang-modernize -p . -include . -add-override
% make format
```
Test Plan:
Make sure all tests are passing.
```lang=bash
% #Use default fb code clang.
% make check
```
Verify less error and no missing override errors.
```lang=bash
% # Have trunk clang present in path.
% ROCKSDB_NO_FBCODE=1 CC=clang CXX=clang++ make
```
Reviewers: igor, kradhakrishnan, rven, meyering, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D34077
Summary:
When reading from kBlockCacheTier, ForwardIterator's internal child iterators
may end up in the incomplete state (read was unable to complete without doing
disk I/O). `ForwardIterator::status()` will correctly report that; however, the
iterator may be stuck in that state until all sub-iterators are rebuilt:
* `NeedToSeekImmutable()` may return false even if some sub-iterators are
incomplete
* one of the child iterators may be an empty iterator without any state other
that the kIncomplete status (created using `NewErrorIterator()`); seeking on
any such iterator has no effect -- we need to construct it again
Akin to rebuilding iterators after a superversion bump, this diff makes forward
iterator reset all incomplete child iterators when `Seek()` or `Next()` are
called.
Test Plan: TEST_TMPDIR=/dev/shm/rocksdbtest ROCKSDB_TESTS=TailingIterator ./db_test
Reviewers: igor, sdong, ljin
Reviewed By: ljin
Subscribers: lovro, march, leveldb
Differential Revision: https://reviews.facebook.net/D22575
Summary:
In this patch, try to allocate the whole iterator tree starting from DBIter from an arena
1. ArenaWrappedDBIter is created when serves as the entry point of an iterator tree, with an arena in it.
2. Add an option to create iterator from arena for following iterators: DBIter, MergingIterator, MemtableIterator, all mem table's iterators, all table reader's iterators and two level iterator.
3. MergeIteratorBuilder is created to incrementally build the tree of internal iterators. It is passed to mem table list and version set and add iterators to it.
Limitations:
(1) Only DB::NewIterator() without tailing uses the arena. Other cases, including readonly DB and compactions are still from malloc
(2) Two level iterator itself is allocated in arena, but not iterators inside it.
Test Plan: make all check
Reviewers: ljin, haobo
Reviewed By: haobo
Subscribers: leveldb, dhruba, yhchiang, igor
Differential Revision: https://reviews.facebook.net/D18513
Summary:
As a follow-up diff for https://reviews.facebook.net/D17805, add
optimization to check PrefixMayMatch on Seek()
Test Plan: make all check
Reviewers: igor, haobo, sdong, yhchiang, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17853
Summary: In PlainTable, use one single byte to represent 8 bytes of internal bytes, if seqID = 0 and it is value type (which should be common for bottom most files). It is to save 7 bytes for uncompressed cases.
Test Plan: make all check
Reviewers: haobo, dhruba, kailiu
Reviewed By: haobo
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D15489
Summary:
This fixes#3130525. Dhruba's suggestion and Tnovak's implementation :)
The issue was with SkipEmptyDataBlocksForward(), but I also changed SkipEmptyDataBlocksBackward(). Is that OK?
Test Plan: Run the logdevice test
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D13911
Summary: This patch makes Table and TableBuilder a abstract class and make all the implementation of the current table into BlockedBasedTable and BlockedBasedTable Builder.
Test Plan: Make db_test.cc to work with block based table. Add a new test simple_table_db_test.cc where a different simple table format is implemented.
Reviewers: dhruba, haobo, kailiu, emayanke, vamsi
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D13521
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:
Current posix advice implementation ties up the access pattern hint with the creation of a file.
It is not possible to apply different advice for different access (random get vs compaction read),
without keeping two open files for the same table. This patch extended the RandomeAccessFile interface
to accept new access hint at anytime. Particularly, we are able to set different access hint on the same
table file based on when/how the file is used.
Two options are added to set the access hint, after the file is first opened and after the file is being
compacted.
Test Plan: make check; db_stress; db_bench
Reviewers: dhruba
Reviewed By: dhruba
CC: MarkCallaghan, leveldb
Differential Revision: https://reviews.facebook.net/D10905
Summary:
- don't see a point exposing table.h to the public.
- fixed make clean to remove also *.d files.
Test Plan: make check; db_stress
Reviewers: dhruba, heyongqiang
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D10479
Summary:
This patch allows an application to specify whether to use bufferedio,
reads-via-mmaps and writes-via-mmaps per database. Earlier, there
was a global static variable that was used to configure this functionality.
The default setting remains the same (and is backward compatible):
1. use bufferedio
2. do not use mmaps for reads
3. use mmap for writes
4. use readaheads for reads needed for compaction
I also added a parameter to db_bench to be able to explicitly specify
whether to do readaheads for compactions or not.
Test Plan: make check
Reviewers: sheki, heyongqiang, MarkCallaghan
Reviewed By: sheki
CC: leveldb
Differential Revision: https://reviews.facebook.net/D9429
- Replace raw slice comparison with a call to user comparator.
Added test for custom comparators.
- Fix end of namespace comments.
- Fixed bug in picking inputs for a level-0 compaction.
When finding overlapping files, the covered range may expand
as files are added to the input set. We now correctly expand
the range when this happens instead of continuing to use the
old range. For example, suppose L0 contains files with the
following ranges:
F1: a .. d
F2: c .. g
F3: f .. j
and the initial compaction target is F3. We used to search
for range f..j which yielded {F2,F3}. However we now expand
the range as soon as another file is added. In this case,
when F2 is added, we expand the range to c..j and restart the
search. That picks up file F1 as well.
This change fixes a bug related to deleted keys showing up
incorrectly after a compaction as described in Issue 44.
(Sync with upstream @25072954)
