|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
|
|
|
|
#pragma once
|
|
|
|
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <stdint.h>
|
|
|
|
|
|
|
|
#include <memory>
|
|
|
|
#include <string>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "rocksdb/slice.h"
|
|
|
|
#include "rocksdb/slice_transform.h"
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
#include "table/block_based/filter_block_reader_common.h"
|
Hide FilterBits{Builder,Reader} from public API (#9592)
Summary:
We don't have any evidence of people using these to build custom
filters. The recommended way of customizing filter handling is to
defer to various built-in policies based on FilterBuildingContext
(e.g. to build Monkey filtering policy). With old API, we have
evidence of people modifying keys going into filter, but most cases
of that can be handled with prefix_extractor.
Having FilterBitsBuilder+Reader in the public API is an ogoing
hinderance to code evolution (e.g. recent new Finish and
MaybePostVerify), and so this change removes them from the public API
for 7.0. Maybe they will come back in some form later, but lacking
evidence of them providing value in the public API, we want to take back
more freedom to evolve these.
With this moved to internal-only, there is no rush to clean up the
complex Finish signatures, or add memory allocator support, but doing so
is much easier with them out of public API, for example to use
CacheAllocationPtr without exposing it in the public API.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9592
Test Plan: cosmetic changes only
Reviewed By: hx235
Differential Revision: D34315470
Pulled By: pdillinger
fbshipit-source-id: 03e03bb66a72c73df2c464d2dbbbae906dd8f99b
3 years ago
|
|
|
#include "table/block_based/filter_policy_internal.h"
|
|
|
|
#include "table/block_based/parsed_full_filter_block.h"
|
|
|
|
#include "util/hash.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
class FilterPolicy;
|
|
|
|
class FilterBitsBuilder;
|
|
|
|
class FilterBitsReader;
|
|
|
|
|
|
|
|
// A FullFilterBlockBuilder is used to construct a full filter for a
|
|
|
|
// particular Table. It generates a single string which is stored as
|
|
|
|
// a special block in the Table.
|
|
|
|
// The format of full filter block is:
|
|
|
|
// +----------------------------------------------------------------+
|
|
|
|
// | full filter for all keys in sst file |
|
|
|
|
// +----------------------------------------------------------------+
|
|
|
|
// The full filter can be very large. At the end of it, we put
|
|
|
|
// num_probes: how many hash functions are used in bloom filter
|
|
|
|
//
|
|
|
|
class FullFilterBlockBuilder : public FilterBlockBuilder {
|
|
|
|
public:
|
|
|
|
explicit FullFilterBlockBuilder(const SliceTransform* prefix_extractor,
|
|
|
|
bool whole_key_filtering,
|
|
|
|
FilterBitsBuilder* filter_bits_builder);
|
|
|
|
// No copying allowed
|
|
|
|
FullFilterBlockBuilder(const FullFilterBlockBuilder&) = delete;
|
|
|
|
void operator=(const FullFilterBlockBuilder&) = delete;
|
|
|
|
|
|
|
|
// bits_builder is created in filter_policy, it should be passed in here
|
|
|
|
// directly. and be deleted here
|
|
|
|
~FullFilterBlockBuilder() {}
|
|
|
|
|
|
|
|
virtual bool IsBlockBased() override { return false; }
|
|
|
|
virtual void StartBlock(uint64_t /*block_offset*/) override {}
|
|
|
|
virtual void Add(const Slice& key_without_ts) override;
|
|
|
|
virtual bool IsEmpty() const override { return !any_added_; }
|
|
|
|
virtual size_t EstimateEntriesAdded() override;
|
|
|
|
virtual Slice Finish(
|
|
|
|
const BlockHandle& tmp, Status* status,
|
|
|
|
std::unique_ptr<const char[]>* filter_data = nullptr) override;
|
|
|
|
using FilterBlockBuilder::Finish;
|
|
|
|
|
Account Bloom/Ribbon filter construction memory in global memory limit (#9073)
Summary:
Note: This PR is the 4th part of a bigger PR stack (https://github.com/facebook/rocksdb/pull/9073) and will rebase/merge only after the first three PRs (https://github.com/facebook/rocksdb/pull/9070, https://github.com/facebook/rocksdb/pull/9071, https://github.com/facebook/rocksdb/pull/9130) merge.
**Context:**
Similar to https://github.com/facebook/rocksdb/pull/8428, this PR is to track memory usage during (new) Bloom Filter (i.e,FastLocalBloom) and Ribbon Filter (i.e, Ribbon128) construction, moving toward the goal of [single global memory limit using block cache capacity](https://github.com/facebook/rocksdb/wiki/Projects-Being-Developed#improving-memory-efficiency). It also constrains the size of the banding portion of Ribbon Filter during construction by falling back to Bloom Filter if that banding is, at some point, larger than the available space in the cache under `LRUCacheOptions::strict_capacity_limit=true`.
The option to turn on this feature is `BlockBasedTableOptions::reserve_table_builder_memory = true` which by default is set to `false`. We [decided](https://github.com/facebook/rocksdb/pull/9073#discussion_r741548409) not to have separate option for separate memory user in table building therefore their memory accounting are all bundled under one general option.
**Summary:**
- Reserved/released cache for creation/destruction of three main memory users with the passed-in `FilterBuildingContext::cache_res_mgr` during filter construction:
- hash entries (i.e`hash_entries`.size(), we bucket-charge hash entries during insertion for performance),
- banding (Ribbon Filter only, `bytes_coeff_rows` +`bytes_result_rows` + `bytes_backtrack`),
- final filter (i.e, `mutable_buf`'s size).
- Implementation details: in order to use `CacheReservationManager::CacheReservationHandle` to account final filter's memory, we have to store the `CacheReservationManager` object and `CacheReservationHandle` for final filter in `XXPH3BitsFilterBuilder` as well as explicitly delete the filter bits builder when done with the final filter in block based table.
- Added option fo run `filter_bench` with this memory reservation feature
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9073
Test Plan:
- Added new tests in `db_bloom_filter_test` to verify filter construction peak cache reservation under combination of `BlockBasedTable::Rep::FilterType` (e.g, `kFullFilter`, `kPartitionedFilter`), `BloomFilterPolicy::Mode`(e.g, `kFastLocalBloom`, `kStandard128Ribbon`, `kDeprecatedBlock`) and `BlockBasedTableOptions::reserve_table_builder_memory`
- To address the concern for slow test: tests with memory reservation under `kFullFilter` + `kStandard128Ribbon` and `kPartitionedFilter` take around **3000 - 6000 ms** and others take around **1500 - 2000 ms**, in total adding **20000 - 25000 ms** to the test suit running locally
- Added new test in `bloom_test` to verify Ribbon Filter fallback on large banding in FullFilter
- Added test in `filter_bench` to verify that this feature does not significantly slow down Bloom/Ribbon Filter construction speed. Local result averaged over **20** run as below:
- FastLocalBloom
- baseline `./filter_bench -impl=2 -quick -runs 20 | grep 'Build avg'`:
- **Build avg ns/key: 29.56295** (DEBUG_LEVEL=1), **29.98153** (DEBUG_LEVEL=0)
- new feature (expected to be similar as above)`./filter_bench -impl=2 -quick -runs 20 -reserve_table_builder_memory=true | grep 'Build avg'`:
- **Build avg ns/key: 30.99046** (DEBUG_LEVEL=1), **30.48867** (DEBUG_LEVEL=0)
- new feature of RibbonFilter with fallback (expected to be similar as above) `./filter_bench -impl=2 -quick -runs 20 -reserve_table_builder_memory=true -strict_capacity_limit=true | grep 'Build avg'` :
- **Build avg ns/key: 31.146975** (DEBUG_LEVEL=1), **30.08165** (DEBUG_LEVEL=0)
- Ribbon128
- baseline `./filter_bench -impl=3 -quick -runs 20 | grep 'Build avg'`:
- **Build avg ns/key: 129.17585** (DEBUG_LEVEL=1), **130.5225** (DEBUG_LEVEL=0)
- new feature (expected to be similar as above) `./filter_bench -impl=3 -quick -runs 20 -reserve_table_builder_memory=true | grep 'Build avg' `:
- **Build avg ns/key: 131.61645** (DEBUG_LEVEL=1), **132.98075** (DEBUG_LEVEL=0)
- new feature of RibbonFilter with fallback (expected to be a lot faster than above due to fallback) `./filter_bench -impl=3 -quick -runs 20 -reserve_table_builder_memory=true -strict_capacity_limit=true | grep 'Build avg'` :
- **Build avg ns/key: 52.032965** (DEBUG_LEVEL=1), **52.597825** (DEBUG_LEVEL=0)
- And the warning message of `"Cache reservation for Ribbon filter banding failed due to cache full"` is indeed logged to console.
Reviewed By: pdillinger
Differential Revision: D31991348
Pulled By: hx235
fbshipit-source-id: 9336b2c60f44d530063da518ceaf56dac5f9df8e
3 years ago
|
|
|
virtual void ResetFilterBitsBuilder() override {
|
|
|
|
filter_bits_builder_.reset();
|
|
|
|
}
|
|
|
|
|
Detect (new) Bloom/Ribbon Filter construction corruption (#9342)
Summary:
Note: rebase on and merge after https://github.com/facebook/rocksdb/pull/9349, https://github.com/facebook/rocksdb/pull/9345, (optional) https://github.com/facebook/rocksdb/pull/9393
**Context:**
(Quoted from pdillinger) Layers of information during new Bloom/Ribbon Filter construction in building block-based tables includes the following:
a) set of keys to add to filter
b) set of hashes to add to filter (64-bit hash applied to each key)
c) set of Bloom indices to set in filter, with duplicates
d) set of Bloom indices to set in filter, deduplicated
e) final filter and its checksum
This PR aims to detect corruption (e.g, unexpected hardware/software corruption on data structures residing in the memory for a long time) from b) to e) and leave a) as future works for application level.
- b)'s corruption is detected by verifying the xor checksum of the hash entries calculated as the entries accumulate before being added to the filter. (i.e, `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()`)
- c) - e)'s corruption is detected by verifying the hash entries indeed exists in the constructed filter by re-querying these hash entries in the filter (i.e, `FilterBitsBuilder::MaybePostVerify()`) after computing the block checksum (except for PartitionFilter, which is done right after each `FilterBitsBuilder::Finish` for impl simplicity - see code comment for more). For this stage of detection, we assume hash entries are not corrupted after checking on b) since the time interval from b) to c) is relatively short IMO.
Option to enable this feature of detection is `BlockBasedTableOptions::detect_filter_construct_corruption` which is false by default.
**Summary:**
- Implemented new functions `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()` and `FilterBitsBuilder::MaybePostVerify()`
- Ensured hash entries, final filter and banding and their [cache reservation ](https://github.com/facebook/rocksdb/issues/9073) are released properly despite corruption
- See [Filter.construction.artifacts.release.point.pdf ](https://github.com/facebook/rocksdb/files/7923487/Design.Filter.construction.artifacts.release.point.pdf) for high-level design
- Bundled and refactored hash entries's related artifact in XXPH3FilterBitsBuilder into `HashEntriesInfo` for better control on lifetime of these artifact during `SwapEntires`, `ResetEntries`
- Ensured RocksDB block-based table builder calls `FilterBitsBuilder::MaybePostVerify()` after constructing the filter by `FilterBitsBuilder::Finish()`
- When encountering such filter construction corruption, stop writing the filter content to files and mark such a block-based table building non-ok by storing the corruption status in the builder.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9342
Test Plan:
- Added new unit test `DBFilterConstructionCorruptionTestWithParam.DetectCorruption`
- Included this new feature in `DBFilterConstructionReserveMemoryTestWithParam.ReserveMemory` as this feature heavily touch ReserveMemory's impl
- For fallback case, I run `./filter_bench -impl=3 -detect_filter_construct_corruption=true -reserve_table_builder_memory=true -strict_capacity_limit=true -quick -runs 10 | grep 'Build avg'` to make sure nothing break.
- Added to `filter_bench`: increased filter construction time by **30%**, mostly by `MaybePostVerify()`
- FastLocalBloom
- Before change: `./filter_bench -impl=2 -quick -runs 10 | grep 'Build avg'`: **28.86643s**
- After change:
- `./filter_bench -impl=2 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless): **27.6644s (-4% perf improvement might be due to now we don't drop bloom hash entry in `AddAllEntries` along iteration but in bulk later, same with the bypassing-MaybePostVerify case below)**
- `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (expect acceptable increase): **34.41159s (+20%)**
- `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (by-passing MaybePostVerify, expect minor increase): **27.13431s (-6%)**
- Standard128Ribbon
- Before change: `./filter_bench -impl=3 -quick -runs 10 | grep 'Build avg'`: **122.5384s**
- After change:
- `./filter_bench -impl=3 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless - verified by removing MaybePostVerify under this case and found only +-1ns difference): **124.3588s (+2%)**
- `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(expect acceptable increase): **159.4946s (+30%)**
- `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(by-passing MaybePostVerify, expect minor increase) : **125.258s (+2%)**
- Added to `db_stress`: `make crash_test`, `./db_stress --detect_filter_construct_corruption=true`
- Manually smoke-tested: manually corrupted the filter construction in some db level tests with basic PUT and background flush. As expected, the error did get returned to users in subsequent PUT and Flush status.
Reviewed By: pdillinger
Differential Revision: D33746928
Pulled By: hx235
fbshipit-source-id: cb056426be5a7debc1cd16f23bc250f36a08ca57
3 years ago
|
|
|
virtual Status MaybePostVerifyFilter(const Slice& filter_content) override {
|
|
|
|
return filter_bits_builder_->MaybePostVerify(filter_content);
|
|
|
|
}
|
|
|
|
|
|
|
|
protected:
|
|
|
|
virtual void AddKey(const Slice& key);
|
|
|
|
std::unique_ptr<FilterBitsBuilder> filter_bits_builder_;
|
|
|
|
virtual void Reset();
|
|
|
|
void AddPrefix(const Slice& key);
|
|
|
|
const SliceTransform* prefix_extractor() { return prefix_extractor_; }
|
Fix a bug for SeekForPrev with partitioned filter and prefix (#8137)
Summary:
According to https://github.com/facebook/rocksdb/issues/5907, each filter partition "should include the bloom of the prefix of the last
key in the previous partition" so that SeekForPrev() in prefix mode can return correct result.
The prefix of the last key in the previous partition does not necessarily have the same prefix
as the first key in the current partition. Regardless of the first key in current partition, the
prefix of the last key in the previous partition should be added. The existing code, however,
does not follow this. Furthermore, there is another issue: when finishing current filter partition,
`FullFilterBlockBuilder::AddPrefix()` is called for the first key in next filter partition, which effectively
overwrites `last_prefix_str_` prematurely. Consequently, when the filter block builder proceeds
to the next partition, `last_prefix_str_` will be the prefix of its first key, leaving no way of adding
the bloom of the prefix of the last key of the previous partition.
Prefix extractor is FixedLength.2.
```
[ filter part 1 ] [ filter part 2 ]
abc d
```
When SeekForPrev("abcd"), checking the filter partition will land on filter part 2 because "abcd" > "abc"
but smaller than "d".
If the filter in filter part 2 happens to return false for the test for "ab", then SeekForPrev("abcd") will build
incorrect iterator tree in non-total-order mode.
Also fix a unit test which starts to fail following this PR. `InDomain` should not fail due to assertion
error when checking on an arbitrary key.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8137
Test Plan:
```
make check
```
Without this fix, the following command will fail pretty soon.
```
./db_stress --acquire_snapshot_one_in=10000 --avoid_flush_during_recovery=0 \
--avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 \
--batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=17 \
--bottommost_compression_type=disable --cache_index_and_filter_blocks=1 --cache_size=1048576 \
--checkpoint_one_in=0 --checksum_type=kxxHash64 --clear_column_family_one_in=0 \
--compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_ttl=0 \
--compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 \
--compression_parallel_threads=1 --compression_type=zstd --compression_zstd_max_train_bytes=0 \
--continuous_verification_interval=0 --db=/dev/shm/rocksdb/rocksdb_crashtest_whitebox \
--db_write_buffer_size=8388608 --delpercent=5 --delrangepercent=0 --destroy_db_initially=0 --enable_blob_files=0 \
--enable_compaction_filter=0 --enable_pipelined_write=1 --file_checksum_impl=big --flush_one_in=1000000 \
--format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 \
--get_sorted_wal_files_one_in=0 --index_block_restart_interval=4 --index_type=2 --ingest_external_file_one_in=0 \
--iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True \
--log2_keys_per_lock=10 --long_running_snapshots=1 --mark_for_compaction_one_file_in=0 \
--max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000000 --max_key_len=3 \
--max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=16777216 --max_write_buffer_number=3 \
--max_write_buffer_size_to_maintain=8388608 --memtablerep=skip_list --mmap_read=1 --mock_direct_io=False \
--nooverwritepercent=0 --open_files=500000 --ops_per_thread=20000000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=1 --partition_pinning=0 --pause_background_one_in=1000000 \
--periodic_compaction_seconds=0 --prefixpercent=5 --progress_reports=0 --read_fault_one_in=0 --read_only=0 \
--readpercent=45 --recycle_log_file_num=0 --reopen=20 --secondary_catch_up_one_in=0 \
--snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 \
--sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=False \
--target_file_size_base=2097152 --target_file_size_multiplier=2 --test_batches_snapshots=0 --test_cf_consistency=0 \
--top_level_index_pinning=0 --unpartitioned_pinning=1 --use_blob_db=0 --use_block_based_filter=0 \
--use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 \
--use_multiget=0 --use_ribbon_filter=0 --use_txn=0 --user_timestamp_size=8 --verify_checksum=1 \
--verify_checksum_one_in=1000000 --verify_db_one_in=100000 --write_buffer_size=4194304 \
--write_dbid_to_manifest=1 --writepercent=35
```
Reviewed By: pdillinger
Differential Revision: D27553054
Pulled By: riversand963
fbshipit-source-id: 60e391e4a2d8d98a9a3172ec5d6176b90ec3de98
4 years ago
|
|
|
const std::string& last_prefix_str() const { return last_prefix_str_; }
|
|
|
|
|
|
|
|
private:
|
|
|
|
// important: all of these might point to invalid addresses
|
|
|
|
// at the time of destruction of this filter block. destructor
|
|
|
|
// should NOT dereference them.
|
|
|
|
const SliceTransform* prefix_extractor_;
|
|
|
|
bool whole_key_filtering_;
|
|
|
|
bool last_whole_key_recorded_;
|
|
|
|
std::string last_whole_key_str_;
|
|
|
|
bool last_prefix_recorded_;
|
|
|
|
std::string last_prefix_str_;
|
Fix a bug for SeekForPrev with partitioned filter and prefix (#8137)
Summary:
According to https://github.com/facebook/rocksdb/issues/5907, each filter partition "should include the bloom of the prefix of the last
key in the previous partition" so that SeekForPrev() in prefix mode can return correct result.
The prefix of the last key in the previous partition does not necessarily have the same prefix
as the first key in the current partition. Regardless of the first key in current partition, the
prefix of the last key in the previous partition should be added. The existing code, however,
does not follow this. Furthermore, there is another issue: when finishing current filter partition,
`FullFilterBlockBuilder::AddPrefix()` is called for the first key in next filter partition, which effectively
overwrites `last_prefix_str_` prematurely. Consequently, when the filter block builder proceeds
to the next partition, `last_prefix_str_` will be the prefix of its first key, leaving no way of adding
the bloom of the prefix of the last key of the previous partition.
Prefix extractor is FixedLength.2.
```
[ filter part 1 ] [ filter part 2 ]
abc d
```
When SeekForPrev("abcd"), checking the filter partition will land on filter part 2 because "abcd" > "abc"
but smaller than "d".
If the filter in filter part 2 happens to return false for the test for "ab", then SeekForPrev("abcd") will build
incorrect iterator tree in non-total-order mode.
Also fix a unit test which starts to fail following this PR. `InDomain` should not fail due to assertion
error when checking on an arbitrary key.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8137
Test Plan:
```
make check
```
Without this fix, the following command will fail pretty soon.
```
./db_stress --acquire_snapshot_one_in=10000 --avoid_flush_during_recovery=0 \
--avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=0 \
--batch_protection_bytes_per_key=0 --block_size=16384 --bloom_bits=17 \
--bottommost_compression_type=disable --cache_index_and_filter_blocks=1 --cache_size=1048576 \
--checkpoint_one_in=0 --checksum_type=kxxHash64 --clear_column_family_one_in=0 \
--compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_ttl=0 \
--compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 \
--compression_parallel_threads=1 --compression_type=zstd --compression_zstd_max_train_bytes=0 \
--continuous_verification_interval=0 --db=/dev/shm/rocksdb/rocksdb_crashtest_whitebox \
--db_write_buffer_size=8388608 --delpercent=5 --delrangepercent=0 --destroy_db_initially=0 --enable_blob_files=0 \
--enable_compaction_filter=0 --enable_pipelined_write=1 --file_checksum_impl=big --flush_one_in=1000000 \
--format_version=5 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 \
--get_sorted_wal_files_one_in=0 --index_block_restart_interval=4 --index_type=2 --ingest_external_file_one_in=0 \
--iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True \
--log2_keys_per_lock=10 --long_running_snapshots=1 --mark_for_compaction_one_file_in=0 \
--max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=100000000 --max_key_len=3 \
--max_manifest_file_size=1073741824 --max_write_batch_group_size_bytes=16777216 --max_write_buffer_number=3 \
--max_write_buffer_size_to_maintain=8388608 --memtablerep=skip_list --mmap_read=1 --mock_direct_io=False \
--nooverwritepercent=0 --open_files=500000 --ops_per_thread=20000000 --optimize_filters_for_memory=0 --paranoid_file_checks=1 --partition_filters=1 --partition_pinning=0 --pause_background_one_in=1000000 \
--periodic_compaction_seconds=0 --prefixpercent=5 --progress_reports=0 --read_fault_one_in=0 --read_only=0 \
--readpercent=45 --recycle_log_file_num=0 --reopen=20 --secondary_catch_up_one_in=0 \
--snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=104857600 \
--sst_file_manager_bytes_per_truncate=0 --subcompactions=2 --sync=0 --sync_fault_injection=False \
--target_file_size_base=2097152 --target_file_size_multiplier=2 --test_batches_snapshots=0 --test_cf_consistency=0 \
--top_level_index_pinning=0 --unpartitioned_pinning=1 --use_blob_db=0 --use_block_based_filter=0 \
--use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_merge=0 \
--use_multiget=0 --use_ribbon_filter=0 --use_txn=0 --user_timestamp_size=8 --verify_checksum=1 \
--verify_checksum_one_in=1000000 --verify_db_one_in=100000 --write_buffer_size=4194304 \
--write_dbid_to_manifest=1 --writepercent=35
```
Reviewed By: pdillinger
Differential Revision: D27553054
Pulled By: riversand963
fbshipit-source-id: 60e391e4a2d8d98a9a3172ec5d6176b90ec3de98
4 years ago
|
|
|
// Whether prefix_extractor_->InDomain(last_whole_key_) is true.
|
|
|
|
// Used in partitioned filters so that the last prefix from the previous
|
|
|
|
// filter partition will be added to the current partition if
|
|
|
|
// last_key_in_domain_ is true, regardless of the current key.
|
|
|
|
bool last_key_in_domain_;
|
|
|
|
bool any_added_;
|
|
|
|
std::unique_ptr<const char[]> filter_data_;
|
|
|
|
};
|
|
|
|
|
|
|
|
// A FilterBlockReader is used to parse filter from SST table.
|
|
|
|
// KeyMayMatch and PrefixMayMatch would trigger filter checking
|
|
|
|
class FullFilterBlockReader
|
|
|
|
: public FilterBlockReaderCommon<ParsedFullFilterBlock> {
|
|
|
|
public:
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
FullFilterBlockReader(const BlockBasedTable* t,
|
|
|
|
CachableEntry<ParsedFullFilterBlock>&& filter_block);
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
|
|
|
|
static std::unique_ptr<FilterBlockReader> Create(
|
|
|
|
const BlockBasedTable* table, const ReadOptions& ro,
|
|
|
|
FilePrefetchBuffer* prefetch_buffer, bool use_cache, bool prefetch,
|
|
|
|
bool pin, BlockCacheLookupContext* lookup_context);
|
|
|
|
|
|
|
|
bool IsBlockBased() override { return false; }
|
|
|
|
|
|
|
|
bool KeyMayMatch(const Slice& key, const SliceTransform* prefix_extractor,
|
|
|
|
uint64_t block_offset, const bool no_io,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
const Slice* const const_ikey_ptr, GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context) override;
|
|
|
|
|
|
|
|
bool PrefixMayMatch(const Slice& prefix,
|
|
|
|
const SliceTransform* prefix_extractor,
|
|
|
|
uint64_t block_offset, const bool no_io,
|
|
|
|
const Slice* const const_ikey_ptr,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context) override;
|
|
|
|
|
|
|
|
void KeysMayMatch(MultiGetRange* range,
|
|
|
|
const SliceTransform* prefix_extractor,
|
|
|
|
uint64_t block_offset, const bool no_io,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
BlockCacheLookupContext* lookup_context) override;
|
|
|
|
|
|
|
|
void PrefixesMayMatch(MultiGetRange* range,
|
|
|
|
const SliceTransform* prefix_extractor,
|
|
|
|
uint64_t block_offset, const bool no_io,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
BlockCacheLookupContext* lookup_context) override;
|
|
|
|
size_t ApproximateMemoryUsage() const override;
|
|
|
|
bool RangeMayExist(const Slice* iterate_upper_bound, const Slice& user_key,
|
|
|
|
const SliceTransform* prefix_extractor,
|
|
|
|
const Comparator* comparator,
|
|
|
|
const Slice* const const_ikey_ptr, bool* filter_checked,
|
Fix iterator reading filter block despite read_tier == kBlockCacheTier (#6562)
Summary:
We're seeing iterators with `ReadOptions::read_tier == kBlockCacheTier` sometimes doing file reads. Stack trace:
```
rocksdb::RandomAccessFileReader::Read(unsigned long, unsigned long, rocksdb::Slice*, char*, bool) const
rocksdb::BlockFetcher::ReadBlockContents()
rocksdb::Status rocksdb::BlockBasedTable::MaybeReadBlockAndLoadToCache<rocksdb::ParsedFullFilterBlock>(rocksdb::FilePrefetchBuffer*, rocksdb::ReadOptions const&, rocksdb::BlockHandle const&, rocksdb::UncompressionDict const&, rocksdb::CachableEntry<rocksdb::ParsedFullFilterBlock>*, rocksdb::BlockType, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, rocksdb::BlockContents*) const
rocksdb::Status rocksdb::BlockBasedTable::RetrieveBlock<rocksdb::ParsedFullFilterBlock>(rocksdb::FilePrefetchBuffer*, rocksdb::ReadOptions const&, rocksdb::BlockHandle const&, rocksdb::UncompressionDict const&, rocksdb::CachableEntry<rocksdb::ParsedFullFilterBlock>*, rocksdb::BlockType, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, bool, bool) const
rocksdb::FilterBlockReaderCommon<rocksdb::ParsedFullFilterBlock>::ReadFilterBlock(rocksdb::BlockBasedTable const*, rocksdb::FilePrefetchBuffer*, rocksdb::ReadOptions const&, bool, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, rocksdb::CachableEntry<rocksdb::ParsedFullFilterBlock>*)
rocksdb::FilterBlockReaderCommon<rocksdb::ParsedFullFilterBlock>::GetOrReadFilterBlock(bool, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, rocksdb::CachableEntry<rocksdb::ParsedFullFilterBlock>*) const
rocksdb::FullFilterBlockReader::MayMatch(rocksdb::Slice const&, bool, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*) const
rocksdb::FullFilterBlockReader::RangeMayExist(rocksdb::Slice const*, rocksdb::Slice const&, rocksdb::SliceTransform const*, rocksdb::Comparator const*, rocksdb::Slice const*, bool*, bool, rocksdb::BlockCacheLookupContext*)
rocksdb::BlockBasedTable::PrefixMayMatch(rocksdb::Slice const&, rocksdb::ReadOptions const&, rocksdb::SliceTransform const*, bool, rocksdb::BlockCacheLookupContext*) const
rocksdb::BlockBasedTableIterator<rocksdb::DataBlockIter, rocksdb::Slice>::SeekImpl(rocksdb::Slice const*)
rocksdb::ForwardIterator::SeekInternal(rocksdb::Slice const&, bool)
rocksdb::DBIter::Seek(rocksdb::Slice const&)
```
`BlockBasedTableIterator::CheckPrefixMayMatch` was missing a check for `kBlockCacheTier`. This PR adds it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6562
Test Plan: deployed it to a logdevice test cluster and looked at logdevice's IO tracing.
Reviewed By: siying
Differential Revision: D20529368
Pulled By: al13n321
fbshipit-source-id: 65bf33964b1951464415c900336635fb20919611
5 years ago
|
|
|
bool need_upper_bound_check, bool no_io,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
BlockCacheLookupContext* lookup_context) override;
|
|
|
|
|
|
|
|
private:
|
|
|
|
bool MayMatch(const Slice& entry, bool no_io, GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context) const;
|
|
|
|
void MayMatch(MultiGetRange* range, bool no_io,
|
|
|
|
const SliceTransform* prefix_extractor,
|
Move the filter readers out of the block cache (#5504)
Summary:
Currently, when the block cache is used for the filter block, it is not
really the block itself that is stored in the cache but a FilterBlockReader
object. Since this object is not pure data (it has, for instance, pointers that
might dangle, including in one case a back pointer to the TableReader), it's not
really sharable. To avoid the issues around this, the current code erases the
cache entries when the TableReader is closed (which, BTW, is not sufficient
since a concurrent TableReader might have picked up the object in the meantime).
Instead of doing this, the patch moves the FilterBlockReader out of the cache
altogether, and decouples the filter reader object from the filter block.
In particular, instead of the TableReader owning, or caching/pinning the
FilterBlockReader (based on the customer's settings), with the change the
TableReader unconditionally owns the FilterBlockReader, which in turn
owns/caches/pins the filter block. This change also enables us to reuse the code
paths historically used for data blocks for filters as well.
Note:
Eviction statistics for filter blocks are temporarily broken. We plan to fix this in a
separate phase.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5504
Test Plan: make asan_check
Differential Revision: D16036974
Pulled By: ltamasi
fbshipit-source-id: 770f543c5fb4ed126fd1e04bfd3809cf4ff9c091
5 years ago
|
|
|
BlockCacheLookupContext* lookup_context) const;
|
|
|
|
bool IsFilterCompatible(const Slice* iterate_upper_bound, const Slice& prefix,
|
|
|
|
const Comparator* comparator) const;
|
|
|
|
|
|
|
|
private:
|
|
|
|
bool full_length_enabled_;
|
|
|
|
size_t prefix_extractor_full_length_;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|