You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db/db_impl/db_impl_readonly.cc

335 lines
11 KiB

// 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).
#include "db/db_impl/db_impl_readonly.h"
#include "db/arena_wrapped_db_iter.h"
#include "db/db_impl/compacted_db_impl.h"
#include "db/db_impl/db_impl.h"
#include "db/db_iter.h"
#include "db/merge_context.h"
#include "logging/logging.h"
#include "monitoring/perf_context_imp.h"
#include "util/cast_util.h"
namespace ROCKSDB_NAMESPACE {
DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
const std::string& dbname)
Make backups openable as read-only DBs (#8142) Summary: A current limitation of backups is that you don't know the exact database state of when the backup was taken. With this new feature, you can at least inspect the backup's DB state without restoring it by opening it as a read-only DB. Rather than add something like OpenAsReadOnlyDB to the BackupEngine API, which would inhibit opening stackable DB implementations read-only (if/when their APIs support it), we instead provide a DB name and Env that can be used to open as a read-only DB. Possible follow-up work: * Add a version of GetBackupInfo for a single backup. * Let CreateNewBackup return the BackupID of the newly-created backup. Implementation details: Refactored ChrootFileSystem to split off new base class RemapFileSystem, which allows more general remapping of files. We use this base class to implement BackupEngineImpl::RemapSharedFileSystem. To minimize API impact, I decided to just add these fields `name_for_open` and `env_for_open` to those set by GetBackupInfo when include_file_details=true. Creating the RemapSharedFileSystem adds a bit to the memory consumption, perhaps unnecessarily in some cases, but this has been mitigated by (a) only initialize the RemapSharedFileSystem lazily when GetBackupInfo with include_file_details=true is called, and (b) using the existing `shared_ptr<FileInfo>` objects to hold most of the mapping data. To enhance API safety, RemapSharedFileSystem is wrapped by new ReadOnlyFileSystem which rejects any attempts to write. This uncovered a couple of places in which DB::OpenForReadOnly would write to the filesystem, so I fixed these. Added a release note because this affects logging. Additional minor refactoring in backupable_db.cc to support the new functionality. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8142 Test Plan: new test (run with ASAN and UBSAN), added to stress test and ran it for a while with amplified backup_one_in Reviewed By: ajkr Differential Revision: D27535408 Pulled By: pdillinger fbshipit-source-id: 04666d310aa0261ef6b2385c43ca793ce1dfd148
4 years ago
: DBImpl(db_options, dbname, /*seq_per_batch*/ false,
/*batch_per_txn*/ true, /*read_only*/ true) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"Opening the db in read only mode");
LogFlush(immutable_db_options_.info_log);
}
DBImplReadOnly::~DBImplReadOnly() {}
// Implementations of the DB interface
Status DBImplReadOnly::Get(const ReadOptions& read_options,
ColumnFamilyHandle* column_family, const Slice& key,
PinnableSlice* pinnable_val) {
return Get(read_options, column_family, key, pinnable_val,
/*timestamp*/ nullptr);
}
Status DBImplReadOnly::Get(const ReadOptions& read_options,
ColumnFamilyHandle* column_family, const Slice& key,
PinnableSlice* pinnable_val,
std::string* timestamp) {
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2 years ago
if (read_options.io_activity != Env::IOActivity::kUnknown) {
return Status::InvalidArgument(
"Cannot call Get with `ReadOptions::io_activity` != "
"`Env::IOActivity::kUnknown`");
}
assert(pinnable_val != nullptr);
// TODO: stopwatch DB_GET needed?, perf timer needed?
PERF_TIMER_GUARD(get_snapshot_time);
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
assert(column_family);
if (read_options.timestamp) {
const Status s = FailIfTsMismatchCf(
column_family, *(read_options.timestamp), /*ts_for_read=*/true);
if (!s.ok()) {
return s;
}
} else {
const Status s = FailIfCfHasTs(column_family);
if (!s.ok()) {
return s;
}
}
// Clear the timestamps for returning results so that we can distinguish
// between tombstone or key that has never been written
if (timestamp) {
timestamp->clear();
}
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
const Comparator* ucmp = column_family->GetComparator();
assert(ucmp);
std::string* ts = ucmp->timestamp_size() > 0 ? timestamp : nullptr;
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
Status s;
SequenceNumber snapshot = versions_->LastSequence();
GetWithTimestampReadCallback read_cb(snapshot);
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
auto cfd = cfh->cfd();
if (tracer_) {
InstrumentedMutexLock lock(&trace_mutex_);
if (tracer_) {
tracer_->Get(column_family, key);
}
}
SuperVersion* super_version = cfd->GetSuperVersion();
MergeContext merge_context;
Use only "local" range tombstones during Get (#4449) Summary: Previously, range tombstones were accumulated from every level, which was necessary if a range tombstone in a higher level covered a key in a lower level. However, RangeDelAggregator::AddTombstones's complexity is based on the number of tombstones that are currently stored in it, which is wasteful in the Get case, where we only need to know the highest sequence number of range tombstones that cover the key from higher levels, and compute the highest covering sequence number at the current level. This change introduces this optimization, and removes the use of RangeDelAggregator from the Get path. In the benchmark results, the following command was used to initialize the database: ``` ./db_bench -db=/dev/shm/5k-rts -use_existing_db=false -benchmarks=filluniquerandom -write_buffer_size=1048576 -compression_type=lz4 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 -value_size=112 -key_size=16 -block_size=4096 -level_compaction_dynamic_level_bytes=true -num=5000000 -max_background_jobs=12 -benchmark_write_rate_limit=20971520 -range_tombstone_width=100 -writes_per_range_tombstone=100 -max_num_range_tombstones=50000 -bloom_bits=8 ``` ...and the following command was used to measure read throughput: ``` ./db_bench -db=/dev/shm/5k-rts/ -use_existing_db=true -benchmarks=readrandom -disable_auto_compactions=true -num=5000000 -reads=100000 -threads=32 ``` The filluniquerandom command was only run once, and the resulting database was used to measure read performance before and after the PR. Both binaries were compiled with `DEBUG_LEVEL=0`. Readrandom results before PR: ``` readrandom : 4.544 micros/op 220090 ops/sec; 16.9 MB/s (63103 of 100000 found) ``` Readrandom results after PR: ``` readrandom : 11.147 micros/op 89707 ops/sec; 6.9 MB/s (63103 of 100000 found) ``` So it's actually slower right now, but this PR paves the way for future optimizations (see #4493). ---- Pull Request resolved: https://github.com/facebook/rocksdb/pull/4449 Differential Revision: D10370575 Pulled By: abhimadan fbshipit-source-id: 9a2e152be1ef36969055c0e9eb4beb0d96c11f4d
6 years ago
SequenceNumber max_covering_tombstone_seq = 0;
LookupKey lkey(key, snapshot, read_options.timestamp);
PERF_TIMER_STOP(get_snapshot_time);
Add support for wide-column point lookups (#10540) Summary: The patch adds a new API `GetEntity` that can be used to perform wide-column point lookups. It also extends the `Get` code path and the `MemTable` / `MemTableList` and `Version` / `GetContext` logic accordingly so that wide-column entities can be served from both memtables and SSTs. If the result of a lookup is a wide-column entity (`kTypeWideColumnEntity`), it is passed to the application in deserialized form; if it is a plain old key-value (`kTypeValue`), it is presented as a wide-column entity with a single default (anonymous) column. (In contrast, regular `Get` returns plain old key-values as-is, and returns the value of the default column for wide-column entities, see https://github.com/facebook/rocksdb/issues/10483 .) The result of `GetEntity` is a self-contained `PinnableWideColumns` object. `PinnableWideColumns` contains a `PinnableSlice`, which either stores the underlying data in its own buffer or holds on to a cache handle. It also contains a `WideColumns` instance, which indexes the contents of the `PinnableSlice`, so applications can access the values of columns efficiently. There are several pieces of functionality which are currently not supported for wide-column entities: there is currently no `MultiGetEntity` or wide-column iterator; also, `Merge` and `GetMergeOperands` are not supported, and there is no `GetEntity` implementation for read-only and secondary instances. We plan to implement these in future PRs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10540 Test Plan: `make check` Reviewed By: akankshamahajan15 Differential Revision: D38847474 Pulled By: ltamasi fbshipit-source-id: 42311a34ccdfe88b3775e847a5e2a5296e002b5b
2 years ago
if (super_version->mem->Get(lkey, pinnable_val->GetSelf(),
/*columns=*/nullptr, ts, &s, &merge_context,
&max_covering_tombstone_seq, read_options,
false /* immutable_memtable */, &read_cb)) {
pinnable_val->PinSelf();
RecordTick(stats_, MEMTABLE_HIT);
} else {
PERF_TIMER_GUARD(get_from_output_files_time);
Fix PinSelf() read-after-free in DB::GetMergeOperands() (#9507) Summary: **Context:** Running the new test `DBMergeOperandTest.MergeOperandReadAfterFreeBug` prior to this fix surfaces the read-after-free bug of PinSef() as below: ``` READ of size 8 at 0x60400002529d thread T0 https://github.com/facebook/rocksdb/issues/5 0x7f199a in rocksdb::PinnableSlice::PinSelf(rocksdb::Slice const&) include/rocksdb/slice.h:171 https://github.com/facebook/rocksdb/issues/6 0x7f199a in rocksdb::DBImpl::GetImpl(rocksdb::ReadOptions const&, rocksdb::Slice const&, rocksdb::DBImpl::GetImplOptions&) db/db_impl/db_impl.cc:1919 https://github.com/facebook/rocksdb/issues/7 0x540d63 in rocksdb::DBImpl::GetMergeOperands(rocksdb::ReadOptions const&, rocksdb::ColumnFamilyHandle*, rocksdb::Slice const&, rocksdb::PinnableSlice*, rocksdb::GetMergeOperandsOptions*, int*) db/db_impl/db_impl.h:203 freed by thread T0 here: https://github.com/facebook/rocksdb/issues/3 0x1191399 in rocksdb::cache_entry_roles_detail::RegisteredDeleter<rocksdb::Block, (rocksdb::CacheEntryRole)0>::Delete(rocksdb::Slice const&, void*) cache/cache_entry_roles.h:99 https://github.com/facebook/rocksdb/issues/4 0x719348 in rocksdb::LRUHandle::Free() cache/lru_cache.h:205 https://github.com/facebook/rocksdb/issues/5 0x71047f in rocksdb::LRUCacheShard::Release(rocksdb::Cache::Handle*, bool) cache/lru_cache.cc:547 https://github.com/facebook/rocksdb/issues/6 0xa78f0a in rocksdb::Cleanable::DoCleanup() include/rocksdb/cleanable.h:60 https://github.com/facebook/rocksdb/issues/7 0xa78f0a in rocksdb::Cleanable::Reset() include/rocksdb/cleanable.h:38 https://github.com/facebook/rocksdb/issues/8 0xa78f0a in rocksdb::PinnedIteratorsManager::ReleasePinnedData() db/pinned_iterators_manager.h:71 https://github.com/facebook/rocksdb/issues/9 0xd0c21b in rocksdb::PinnedIteratorsManager::~PinnedIteratorsManager() db/pinned_iterators_manager.h:24 https://github.com/facebook/rocksdb/issues/10 0xd0c21b in rocksdb::Version::Get(rocksdb::ReadOptions const&, rocksdb::LookupKey const&, rocksdb::PinnableSlice*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*, rocksdb::Status*, rocksdb::MergeContext*, unsigned long*, bool*, bool*, unsigned long*, rocksdb::ReadCallback*, bool*, bool) db/pinned_iterators_manager.h:22 https://github.com/facebook/rocksdb/issues/11 0x7f0fdf in rocksdb::DBImpl::GetImpl(rocksdb::ReadOptions const&, rocksdb::Slice const&, rocksdb::DBImpl::GetImplOptions&) db/db_impl/db_impl.cc:1886 https://github.com/facebook/rocksdb/issues/12 0x540d63 in rocksdb::DBImpl::GetMergeOperands(rocksdb::ReadOptions const&, rocksdb::ColumnFamilyHandle*, rocksdb::Slice const&, rocksdb::PinnableSlice*, rocksdb::GetMergeOperandsOptions*, int*) db/db_impl/db_impl.h:203 previously allocated by thread T0 here: https://github.com/facebook/rocksdb/issues/1 0x1239896 in rocksdb::AllocateBlock(unsigned long, **rocksdb::MemoryAllocator*)** memory/memory_allocator.h:35 https://github.com/facebook/rocksdb/issues/2 0x1239896 in rocksdb::BlockFetcher::CopyBufferToHeapBuf() table/block_fetcher.cc:171 https://github.com/facebook/rocksdb/issues/3 0x1239896 in rocksdb::BlockFetcher::GetBlockContents() table/block_fetcher.cc:206 https://github.com/facebook/rocksdb/issues/4 0x122eae5 in rocksdb::BlockFetcher::ReadBlockContents() table/block_fetcher.cc:325 https://github.com/facebook/rocksdb/issues/5 0x11b1f45 in rocksdb::Status rocksdb::BlockBasedTable::MaybeReadBlockAndLoadToCache<rocksdb::Block>(rocksdb::FilePrefetchBuffer*, rocksdb::ReadOptions const&, rocksdb::BlockHandle const&, rocksdb::UncompressionDict const&, bool, rocksdb::CachableEntry<rocksdb::Block>*, rocksdb::BlockType, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, rocksdb::BlockContents*) const table/block_based/block_based_table_reader.cc:1503 ``` Here is the analysis: - We have [PinnedIteratorsManager](https://github.com/facebook/rocksdb/blob/6.28.fb/db/version_set.cc#L1980) with `Cleanable` capability in our `Version::Get()` path. It's responsible for managing the life-time of pinned iterator and invoking registered cleanup functions during its own destruction. - For example in case above, the merge operands's clean-up gets associated with this manger in [GetContext::push_operand](https://github.com/facebook/rocksdb/blob/6.28.fb/table/get_context.cc#L405). During PinnedIteratorsManager's [destruction](https://github.com/facebook/rocksdb/blob/6.28.fb/db/pinned_iterators_manager.h#L67), the release function associated with those merge operand data is invoked. **And that's what we see in "freed by thread T955 here" in ASAN.** - Bug 🐛: `PinnedIteratorsManager` is local to `Version::Get()` while the data of merge operands need to outlive `Version::Get` and stay till they get [PinSelf()](https://github.com/facebook/rocksdb/blob/6.28.fb/db/db_impl/db_impl.cc#L1905), **which is the read-after-free in ASAN.** - This bug is likely to be an overlook of `PinnedIteratorsManager` when developing the API `DB::GetMergeOperands` cuz the current logic works fine with the existing case of getting the *merged value* where the operands do not need to live that long. - This bug was not surfaced much (even in its unit test) due to the release function associated with the merge operands (which are actually blocks put in cache as you can see in `BlockBasedTable::MaybeReadBlockAndLoadToCache` **in "previously allocated by" in ASAN report**) is a cache entry deleter. The deleter will call `Cache::Release()` which, for LRU cache, won't immediately deallocate the block based on LRU policy [unless the cache is full or being instructed to force erase](https://github.com/facebook/rocksdb/blob/6.28.fb/cache/lru_cache.cc#L521-L531) - `DBMergeOperandTest.MergeOperandReadAfterFreeBug` makes the cache extremely small to force cache full. **Summary:** - Fix the bug by align `PinnedIteratorsManager`'s lifetime with the merge operands Pull Request resolved: https://github.com/facebook/rocksdb/pull/9507 Test Plan: - New test `DBMergeOperandTest.MergeOperandReadAfterFreeBug` - db bench on read path - Setup (LSM tree with several levels, cache the whole db to avoid read IO, warm cache with readseq to avoid read IO): `TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="fillrandom,readseq -num=1000000 -cache_size=100000000 -write_buffer_size=10000 -statistics=1 -max_bytes_for_level_base=10000 -level0_file_num_compaction_trigger=1``TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="readrandom" -num=1000000 -cache_size=100000000 ` - Actual command run (run 20-run for 20 times and then average the 20-run's average micros/op) - `for j in {1..20}; do (for i in {1..20}; do rm -rf /dev/shm/rocksdb/ && TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="fillrandom,readseq,readrandom" -num=1000000 -cache_size=100000000 -write_buffer_size=10000 -statistics=1 -max_bytes_for_level_base=10000 -level0_file_num_compaction_trigger=1 | egrep 'readrandom'; done > rr_output_pre.txt && (awk '{sum+=$3; sum_sqrt+=$3^2}END{print sum/20, sqrt(sum_sqrt/20-(sum/20)^2)}' rr_output_pre.txt) >> rr_output_pre_2.txt); done` - **Result: Pre-change: 3.79193 micros/op; Post-change: 3.79528 micros/op (+0.09%)** (pre-change)sorted avg micros/op of each 20-run | std of micros/op of each 20-run | (post-change) sorted avg micros/op of each 20-run | std of micros/op of each 20-run -- | -- | -- | -- 3.58355 | 0.265209 | 3.48715 | 0.382076 3.58845 | 0.519927 | 3.5832 | 0.382726 3.66415 | 0.452097 | 3.677 | 0.563831 3.68495 | 0.430897 | 3.68405 | 0.495355 3.70295 | 0.482893 | 3.68465 | 0.431438 3.719 | 0.463806 | 3.71945 | 0.457157 3.7393 | 0.453423 | 3.72795 | 0.538604 3.7806 | 0.527613 | 3.75075 | 0.444509 3.7817 | 0.426704 | 3.7683 | 0.468065 3.809 | 0.381033 | 3.8086 | 0.557378 3.80985 | 0.466011 | 3.81805 | 0.524833 3.8165 | 0.500351 | 3.83405 | 0.529339 3.8479 | 0.430326 | 3.86285 | 0.44831 3.85125 | 0.434108 | 3.8717 | 0.544098 3.8556 | 0.524602 | 3.895 | 0.411679 3.8656 | 0.476383 | 3.90965 | 0.566636 3.8911 | 0.488477 | 3.92735 | 0.608038 3.898 | 0.493978 | 3.9439 | 0.524511 3.97235 | 0.515008 | 3.9623 | 0.477416 3.9768 | 0.519993 | 3.98965 | 0.521481 - CI Reviewed By: ajkr Differential Revision: D34030519 Pulled By: hx235 fbshipit-source-id: a99ac585c11704c5ed93af033cb29ba0a7b16ae8
3 years ago
PinnedIteratorsManager pinned_iters_mgr;
super_version->current->Get(
Add support for wide-column point lookups (#10540) Summary: The patch adds a new API `GetEntity` that can be used to perform wide-column point lookups. It also extends the `Get` code path and the `MemTable` / `MemTableList` and `Version` / `GetContext` logic accordingly so that wide-column entities can be served from both memtables and SSTs. If the result of a lookup is a wide-column entity (`kTypeWideColumnEntity`), it is passed to the application in deserialized form; if it is a plain old key-value (`kTypeValue`), it is presented as a wide-column entity with a single default (anonymous) column. (In contrast, regular `Get` returns plain old key-values as-is, and returns the value of the default column for wide-column entities, see https://github.com/facebook/rocksdb/issues/10483 .) The result of `GetEntity` is a self-contained `PinnableWideColumns` object. `PinnableWideColumns` contains a `PinnableSlice`, which either stores the underlying data in its own buffer or holds on to a cache handle. It also contains a `WideColumns` instance, which indexes the contents of the `PinnableSlice`, so applications can access the values of columns efficiently. There are several pieces of functionality which are currently not supported for wide-column entities: there is currently no `MultiGetEntity` or wide-column iterator; also, `Merge` and `GetMergeOperands` are not supported, and there is no `GetEntity` implementation for read-only and secondary instances. We plan to implement these in future PRs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10540 Test Plan: `make check` Reviewed By: akankshamahajan15 Differential Revision: D38847474 Pulled By: ltamasi fbshipit-source-id: 42311a34ccdfe88b3775e847a5e2a5296e002b5b
2 years ago
read_options, lkey, pinnable_val, /*columns=*/nullptr, ts, &s,
&merge_context, &max_covering_tombstone_seq, &pinned_iters_mgr,
/*value_found*/ nullptr,
/*key_exists*/ nullptr, /*seq*/ nullptr, &read_cb,
/*is_blob*/ nullptr,
/*do_merge*/ true);
RecordTick(stats_, MEMTABLE_MISS);
}
RecordTick(stats_, NUMBER_KEYS_READ);
size_t size = pinnable_val->size();
RecordTick(stats_, BYTES_READ, size);
RecordInHistogram(stats_, BYTES_PER_READ, size);
PERF_COUNTER_ADD(get_read_bytes, size);
return s;
}
Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
ColumnFamilyHandle* column_family) {
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2 years ago
if (read_options.io_activity != Env::IOActivity::kUnknown) {
return NewErrorIterator(Status::InvalidArgument(
"Cannot call NewIterator with `ReadOptions::io_activity` != "
"`Env::IOActivity::kUnknown`"));
}
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
assert(column_family);
if (read_options.timestamp) {
const Status s = FailIfTsMismatchCf(
column_family, *(read_options.timestamp), /*ts_for_read=*/true);
if (!s.ok()) {
return NewErrorIterator(s);
}
} else {
const Status s = FailIfCfHasTs(column_family);
if (!s.ok()) {
return NewErrorIterator(s);
}
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
}
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
auto cfd = cfh->cfd();
SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
SequenceNumber latest_snapshot = versions_->LastSequence();
SequenceNumber read_seq =
read_options.snapshot != nullptr
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
->number_
: latest_snapshot;
ReadCallback* read_callback = nullptr; // No read callback provided.
auto db_iter = NewArenaWrappedDbIterator(
env_, read_options, *cfd->ioptions(), super_version->mutable_cf_options,
super_version->current, read_seq,
super_version->mutable_cf_options.max_sequential_skip_in_iterations,
super_version->version_number, read_callback);
auto internal_iter = NewInternalIterator(
db_iter->GetReadOptions(), cfd, super_version, db_iter->GetArena(),
Skip swaths of range tombstone covered keys in merging iterator (2022 edition) (#10449) Summary: Delete range logic is moved from `DBIter` to `MergingIterator`, and `MergingIterator` will seek to the end of a range deletion if possible instead of scanning through each key and check with `RangeDelAggregator`. With the invariant that a key in level L (consider memtable as the first level, each immutable and L0 as a separate level) has a larger sequence number than all keys in any level >L, a range tombstone `[start, end)` from level L covers all keys in its range in any level >L. This property motivates optimizations in iterator: - in `Seek(target)`, if level L has a range tombstone `[start, end)` that covers `target.UserKey`, then for all levels > L, we can do Seek() on `end` instead of `target` to skip some range tombstone covered keys. - in `Next()/Prev()`, if the current key is covered by a range tombstone `[start, end)` from level L, we can do `Seek` to `end` for all levels > L. This PR implements the above optimizations in `MergingIterator`. As all range tombstone covered keys are now skipped in `MergingIterator`, the range tombstone logic is removed from `DBIter`. The idea in this PR is similar to https://github.com/facebook/rocksdb/issues/7317, but this PR leaves `InternalIterator` interface mostly unchanged. **Credit**: the cascading seek optimization and the sentinel key (discussed below) are inspired by [Pebble](https://github.com/cockroachdb/pebble/blob/master/merging_iter.go) and suggested by ajkr in https://github.com/facebook/rocksdb/issues/7317. The two optimizations are mostly implemented in `SeekImpl()/SeekForPrevImpl()` and `IsNextDeleted()/IsPrevDeleted()` in `merging_iterator.cc`. See comments for each method for more detail. One notable change is that the minHeap/maxHeap used by `MergingIterator` now contains range tombstone end keys besides point key iterators. This helps to reduce the number of key comparisons. For example, for a range tombstone `[start, end)`, a `start` and an `end` `HeapItem` are inserted into the heap. When a `HeapItem` for range tombstone start key is popped from the minHeap, we know this range tombstone becomes "active" in the sense that, before the range tombstone's end key is popped from the minHeap, all the keys popped from this heap is covered by the range tombstone's internal key range `[start, end)`. Another major change, *delete range sentinel key*, is made to `LevelIterator`. Before this PR, when all point keys in an SST file are iterated through in `MergingIterator`, a level iterator would advance to the next SST file in its level. In the case when an SST file has a range tombstone that covers keys beyond the SST file's last point key, advancing to the next SST file would lose this range tombstone. Consequently, `MergingIterator` could return keys that should have been deleted by some range tombstone. We prevent this by pretending that file boundaries in each SST file are sentinel keys. A `LevelIterator` now only advance the file iterator once the sentinel key is processed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10449 Test Plan: - Added many unit tests in db_range_del_test - Stress test: `./db_stress --readpercent=5 --prefixpercent=19 --writepercent=20 -delpercent=10 --iterpercent=44 --delrangepercent=2` - Additional iterator stress test is added to verify against iterators against expected state: https://github.com/facebook/rocksdb/issues/10538. This is based on ajkr's previous attempt https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913. ``` python3 ./tools/db_crashtest.py blackbox --simple --write_buffer_size=524288 --target_file_size_base=524288 --max_bytes_for_level_base=2097152 --compression_type=none --max_background_compactions=8 --value_size_mult=33 --max_key=5000000 --interval=10 --duration=7200 --delrangepercent=3 --delpercent=9 --iterpercent=25 --writepercent=60 --readpercent=3 --prefixpercent=0 --num_iterations=1000 --range_deletion_width=100 --verify_iterator_with_expected_state_one_in=1 ``` - Performance benchmark: I used a similar setup as in the blog [post](http://rocksdb.org/blog/2018/11/21/delete-range.html) that introduced DeleteRange, "a database with 5 million data keys, and 10000 range tombstones (ignoring those dropped during compaction) that were written in regular intervals after 4.5 million data keys were written". As expected, the performance with this PR depends on the range tombstone width. ``` # Setup: TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=fillrandom --writes=4500000 --num=5000000 TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=overwrite --writes=500000 --num=5000000 --use_existing_db=true --writes_per_range_tombstone=50 # Scan entire DB TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=readseq[-X5] --use_existing_db=true --num=5000000 --disable_auto_compactions=true # Short range scan (10 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=100000 --seek_nexts=10 --disable_auto_compactions=true # Long range scan(1000 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=2500 --seek_nexts=1000 --disable_auto_compactions=true ``` Avg over of 10 runs (some slower tests had fews runs): For the first column (tombstone), 0 means no range tombstone, 100-10000 means width of the 10k range tombstones, and 1 means there is a single range tombstone in the entire DB (width is 1000). The 1 tombstone case is to test regression when there's very few range tombstones in the DB, as no range tombstone is likely to take a different code path than with range tombstones. - Scan entire DB | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2525600 (± 43564) |2486917 (± 33698) |-1.53% | | 100 |1853835 (± 24736) |2073884 (± 32176) |+11.87% | | 1000 |422415 (± 7466) |1115801 (± 22781) |+164.15% | | 10000 |22384 (± 227) |227919 (± 6647) |+918.22% | | 1 range tombstone |2176540 (± 39050) |2434954 (± 24563) |+11.87% | - Short range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |35398 (± 533) |35338 (± 569) |-0.17% | | 100 |28276 (± 664) |31684 (± 331) |+12.05% | | 1000 |7637 (± 77) |25422 (± 277) |+232.88% | | 10000 |1367 |28667 |+1997.07% | | 1 range tombstone |32618 (± 581) |32748 (± 506) |+0.4% | - Long range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2262 (± 33) |2353 (± 20) |+4.02% | | 100 |1696 (± 26) |1926 (± 18) |+13.56% | | 1000 |410 (± 6) |1255 (± 29) |+206.1% | | 10000 |25 |414 |+1556.0% | | 1 range tombstone |1957 (± 30) |2185 (± 44) |+11.65% | - Microbench does not show significant regression: https://gist.github.com/cbi42/59f280f85a59b678e7e5d8561e693b61 Reviewed By: ajkr Differential Revision: D38450331 Pulled By: cbi42 fbshipit-source-id: b5ef12e8d8c289ed2e163ccdf277f5039b511fca
2 years ago
read_seq, /* allow_unprepared_value */ true, db_iter);
db_iter->SetIterUnderDBIter(internal_iter);
return db_iter;
}
Status DBImplReadOnly::NewIterators(
const ReadOptions& read_options,
const std::vector<ColumnFamilyHandle*>& column_families,
std::vector<Iterator*>* iterators) {
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
if (read_options.timestamp) {
for (auto* cf : column_families) {
assert(cf);
const Status s = FailIfTsMismatchCf(cf, *(read_options.timestamp),
/*ts_for_read=*/true);
if (!s.ok()) {
return s;
}
}
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
} else {
for (auto* cf : column_families) {
assert(cf);
const Status s = FailIfCfHasTs(cf);
if (!s.ok()) {
return s;
Revise APIs related to user-defined timestamp (#8946) Summary: ajkr reminded me that we have a rule of not including per-kv related data in `WriteOptions`. Namely, `WriteOptions` should not include information about "what-to-write", but should just include information about "how-to-write". According to this rule, `WriteOptions::timestamp` (experimental) is clearly a violation. Therefore, this PR removes `WriteOptions::timestamp` for compliance. After the removal, we need to pass timestamp info via another set of APIs. This PR proposes a set of overloaded functions `Put(write_opts, key, value, ts)`, `Delete(write_opts, key, ts)`, and `SingleDelete(write_opts, key, ts)`. Planned to add `Write(write_opts, batch, ts)`, but its complexity made me reconsider doing it in another PR (maybe). For better checking and returning error early, we also add a new set of APIs to `WriteBatch` that take extra `timestamp` information when writing to `WriteBatch`es. These set of APIs in `WriteBatchWithIndex` are currently not supported, and are on our TODO list. Removed `WriteBatch::AssignTimestamps()` and renamed `WriteBatch::AssignTimestamp()` to `WriteBatch::UpdateTimestamps()` since this method require that all keys have space for timestamps allocated already and multiple timestamps can be updated. The constructor of `WriteBatch` now takes a fourth argument `default_cf_ts_sz` which is the timestamp size of the default column family. This will be used to allocate space when calling APIs that do not specify a column family handle. Also, updated `DB::Get()`, `DB::MultiGet()`, `DB::NewIterator()`, `DB::NewIterators()` methods, replacing some assertions about timestamp to returning Status code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8946 Test Plan: make check ./db_bench -benchmarks=fillseq,fillrandom,readrandom,readseq,deleterandom -user_timestamp_size=8 ./db_stress --user_timestamp_size=8 -nooverwritepercent=0 -test_secondary=0 -secondary_catch_up_one_in=0 -continuous_verification_interval=0 Make sure there is no perf regression by running the following ``` ./db_bench_opt -db=/dev/shm/rocksdb -use_existing_db=0 -level0_stop_writes_trigger=256 -level0_slowdown_writes_trigger=256 -level0_file_num_compaction_trigger=256 -disable_wal=1 -duration=10 -benchmarks=fillrandom ``` Before this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.831 micros/op 546235 ops/sec; 60.4 MB/s ``` After this PR ``` DB path: [/dev/shm/rocksdb] fillrandom : 1.820 micros/op 549404 ops/sec; 60.8 MB/s ``` Reviewed By: ltamasi Differential Revision: D33721359 Pulled By: riversand963 fbshipit-source-id: c131561534272c120ffb80711d42748d21badf09
3 years ago
}
}
}
ReadCallback* read_callback = nullptr; // No read callback provided.
if (iterators == nullptr) {
return Status::InvalidArgument("iterators not allowed to be nullptr");
}
iterators->clear();
iterators->reserve(column_families.size());
SequenceNumber latest_snapshot = versions_->LastSequence();
SequenceNumber read_seq =
read_options.snapshot != nullptr
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
->number_
: latest_snapshot;
for (auto cfh : column_families) {
auto* cfd = static_cast_with_check<ColumnFamilyHandleImpl>(cfh)->cfd();
auto* sv = cfd->GetSuperVersion()->Ref();
auto* db_iter = NewArenaWrappedDbIterator(
env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
sv->current, read_seq,
sv->mutable_cf_options.max_sequential_skip_in_iterations,
sv->version_number, read_callback);
auto* internal_iter = NewInternalIterator(
Skip swaths of range tombstone covered keys in merging iterator (2022 edition) (#10449) Summary: Delete range logic is moved from `DBIter` to `MergingIterator`, and `MergingIterator` will seek to the end of a range deletion if possible instead of scanning through each key and check with `RangeDelAggregator`. With the invariant that a key in level L (consider memtable as the first level, each immutable and L0 as a separate level) has a larger sequence number than all keys in any level >L, a range tombstone `[start, end)` from level L covers all keys in its range in any level >L. This property motivates optimizations in iterator: - in `Seek(target)`, if level L has a range tombstone `[start, end)` that covers `target.UserKey`, then for all levels > L, we can do Seek() on `end` instead of `target` to skip some range tombstone covered keys. - in `Next()/Prev()`, if the current key is covered by a range tombstone `[start, end)` from level L, we can do `Seek` to `end` for all levels > L. This PR implements the above optimizations in `MergingIterator`. As all range tombstone covered keys are now skipped in `MergingIterator`, the range tombstone logic is removed from `DBIter`. The idea in this PR is similar to https://github.com/facebook/rocksdb/issues/7317, but this PR leaves `InternalIterator` interface mostly unchanged. **Credit**: the cascading seek optimization and the sentinel key (discussed below) are inspired by [Pebble](https://github.com/cockroachdb/pebble/blob/master/merging_iter.go) and suggested by ajkr in https://github.com/facebook/rocksdb/issues/7317. The two optimizations are mostly implemented in `SeekImpl()/SeekForPrevImpl()` and `IsNextDeleted()/IsPrevDeleted()` in `merging_iterator.cc`. See comments for each method for more detail. One notable change is that the minHeap/maxHeap used by `MergingIterator` now contains range tombstone end keys besides point key iterators. This helps to reduce the number of key comparisons. For example, for a range tombstone `[start, end)`, a `start` and an `end` `HeapItem` are inserted into the heap. When a `HeapItem` for range tombstone start key is popped from the minHeap, we know this range tombstone becomes "active" in the sense that, before the range tombstone's end key is popped from the minHeap, all the keys popped from this heap is covered by the range tombstone's internal key range `[start, end)`. Another major change, *delete range sentinel key*, is made to `LevelIterator`. Before this PR, when all point keys in an SST file are iterated through in `MergingIterator`, a level iterator would advance to the next SST file in its level. In the case when an SST file has a range tombstone that covers keys beyond the SST file's last point key, advancing to the next SST file would lose this range tombstone. Consequently, `MergingIterator` could return keys that should have been deleted by some range tombstone. We prevent this by pretending that file boundaries in each SST file are sentinel keys. A `LevelIterator` now only advance the file iterator once the sentinel key is processed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10449 Test Plan: - Added many unit tests in db_range_del_test - Stress test: `./db_stress --readpercent=5 --prefixpercent=19 --writepercent=20 -delpercent=10 --iterpercent=44 --delrangepercent=2` - Additional iterator stress test is added to verify against iterators against expected state: https://github.com/facebook/rocksdb/issues/10538. This is based on ajkr's previous attempt https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913. ``` python3 ./tools/db_crashtest.py blackbox --simple --write_buffer_size=524288 --target_file_size_base=524288 --max_bytes_for_level_base=2097152 --compression_type=none --max_background_compactions=8 --value_size_mult=33 --max_key=5000000 --interval=10 --duration=7200 --delrangepercent=3 --delpercent=9 --iterpercent=25 --writepercent=60 --readpercent=3 --prefixpercent=0 --num_iterations=1000 --range_deletion_width=100 --verify_iterator_with_expected_state_one_in=1 ``` - Performance benchmark: I used a similar setup as in the blog [post](http://rocksdb.org/blog/2018/11/21/delete-range.html) that introduced DeleteRange, "a database with 5 million data keys, and 10000 range tombstones (ignoring those dropped during compaction) that were written in regular intervals after 4.5 million data keys were written". As expected, the performance with this PR depends on the range tombstone width. ``` # Setup: TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=fillrandom --writes=4500000 --num=5000000 TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=overwrite --writes=500000 --num=5000000 --use_existing_db=true --writes_per_range_tombstone=50 # Scan entire DB TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=readseq[-X5] --use_existing_db=true --num=5000000 --disable_auto_compactions=true # Short range scan (10 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=100000 --seek_nexts=10 --disable_auto_compactions=true # Long range scan(1000 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=2500 --seek_nexts=1000 --disable_auto_compactions=true ``` Avg over of 10 runs (some slower tests had fews runs): For the first column (tombstone), 0 means no range tombstone, 100-10000 means width of the 10k range tombstones, and 1 means there is a single range tombstone in the entire DB (width is 1000). The 1 tombstone case is to test regression when there's very few range tombstones in the DB, as no range tombstone is likely to take a different code path than with range tombstones. - Scan entire DB | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2525600 (± 43564) |2486917 (± 33698) |-1.53% | | 100 |1853835 (± 24736) |2073884 (± 32176) |+11.87% | | 1000 |422415 (± 7466) |1115801 (± 22781) |+164.15% | | 10000 |22384 (± 227) |227919 (± 6647) |+918.22% | | 1 range tombstone |2176540 (± 39050) |2434954 (± 24563) |+11.87% | - Short range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |35398 (± 533) |35338 (± 569) |-0.17% | | 100 |28276 (± 664) |31684 (± 331) |+12.05% | | 1000 |7637 (± 77) |25422 (± 277) |+232.88% | | 10000 |1367 |28667 |+1997.07% | | 1 range tombstone |32618 (± 581) |32748 (± 506) |+0.4% | - Long range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2262 (± 33) |2353 (± 20) |+4.02% | | 100 |1696 (± 26) |1926 (± 18) |+13.56% | | 1000 |410 (± 6) |1255 (± 29) |+206.1% | | 10000 |25 |414 |+1556.0% | | 1 range tombstone |1957 (± 30) |2185 (± 44) |+11.65% | - Microbench does not show significant regression: https://gist.github.com/cbi42/59f280f85a59b678e7e5d8561e693b61 Reviewed By: ajkr Differential Revision: D38450331 Pulled By: cbi42 fbshipit-source-id: b5ef12e8d8c289ed2e163ccdf277f5039b511fca
2 years ago
db_iter->GetReadOptions(), cfd, sv, db_iter->GetArena(), read_seq,
/* allow_unprepared_value */ true, db_iter);
db_iter->SetIterUnderDBIter(internal_iter);
iterators->push_back(db_iter);
}
return Status::OK();
}
namespace {
Make backups openable as read-only DBs (#8142) Summary: A current limitation of backups is that you don't know the exact database state of when the backup was taken. With this new feature, you can at least inspect the backup's DB state without restoring it by opening it as a read-only DB. Rather than add something like OpenAsReadOnlyDB to the BackupEngine API, which would inhibit opening stackable DB implementations read-only (if/when their APIs support it), we instead provide a DB name and Env that can be used to open as a read-only DB. Possible follow-up work: * Add a version of GetBackupInfo for a single backup. * Let CreateNewBackup return the BackupID of the newly-created backup. Implementation details: Refactored ChrootFileSystem to split off new base class RemapFileSystem, which allows more general remapping of files. We use this base class to implement BackupEngineImpl::RemapSharedFileSystem. To minimize API impact, I decided to just add these fields `name_for_open` and `env_for_open` to those set by GetBackupInfo when include_file_details=true. Creating the RemapSharedFileSystem adds a bit to the memory consumption, perhaps unnecessarily in some cases, but this has been mitigated by (a) only initialize the RemapSharedFileSystem lazily when GetBackupInfo with include_file_details=true is called, and (b) using the existing `shared_ptr<FileInfo>` objects to hold most of the mapping data. To enhance API safety, RemapSharedFileSystem is wrapped by new ReadOnlyFileSystem which rejects any attempts to write. This uncovered a couple of places in which DB::OpenForReadOnly would write to the filesystem, so I fixed these. Added a release note because this affects logging. Additional minor refactoring in backupable_db.cc to support the new functionality. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8142 Test Plan: new test (run with ASAN and UBSAN), added to stress test and ran it for a while with amplified backup_one_in Reviewed By: ajkr Differential Revision: D27535408 Pulled By: pdillinger fbshipit-source-id: 04666d310aa0261ef6b2385c43ca793ce1dfd148
4 years ago
// Return OK if dbname exists in the file system or create it if
// create_if_missing
Status OpenForReadOnlyCheckExistence(const DBOptions& db_options,
const std::string& dbname) {
Status s;
if (!db_options.create_if_missing) {
// Attempt to read "CURRENT" file
const std::shared_ptr<FileSystem>& fs = db_options.env->GetFileSystem();
std::string manifest_path;
uint64_t manifest_file_number;
s = VersionSet::GetCurrentManifestPath(dbname, fs.get(), &manifest_path,
&manifest_file_number);
Make backups openable as read-only DBs (#8142) Summary: A current limitation of backups is that you don't know the exact database state of when the backup was taken. With this new feature, you can at least inspect the backup's DB state without restoring it by opening it as a read-only DB. Rather than add something like OpenAsReadOnlyDB to the BackupEngine API, which would inhibit opening stackable DB implementations read-only (if/when their APIs support it), we instead provide a DB name and Env that can be used to open as a read-only DB. Possible follow-up work: * Add a version of GetBackupInfo for a single backup. * Let CreateNewBackup return the BackupID of the newly-created backup. Implementation details: Refactored ChrootFileSystem to split off new base class RemapFileSystem, which allows more general remapping of files. We use this base class to implement BackupEngineImpl::RemapSharedFileSystem. To minimize API impact, I decided to just add these fields `name_for_open` and `env_for_open` to those set by GetBackupInfo when include_file_details=true. Creating the RemapSharedFileSystem adds a bit to the memory consumption, perhaps unnecessarily in some cases, but this has been mitigated by (a) only initialize the RemapSharedFileSystem lazily when GetBackupInfo with include_file_details=true is called, and (b) using the existing `shared_ptr<FileInfo>` objects to hold most of the mapping data. To enhance API safety, RemapSharedFileSystem is wrapped by new ReadOnlyFileSystem which rejects any attempts to write. This uncovered a couple of places in which DB::OpenForReadOnly would write to the filesystem, so I fixed these. Added a release note because this affects logging. Additional minor refactoring in backupable_db.cc to support the new functionality. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8142 Test Plan: new test (run with ASAN and UBSAN), added to stress test and ran it for a while with amplified backup_one_in Reviewed By: ajkr Differential Revision: D27535408 Pulled By: pdillinger fbshipit-source-id: 04666d310aa0261ef6b2385c43ca793ce1dfd148
4 years ago
} else {
// Historic behavior that doesn't necessarily make sense
s = db_options.env->CreateDirIfMissing(dbname);
}
return s;
}
} // namespace
Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
DB** dbptr, bool /*error_if_wal_file_exists*/) {
Status s = OpenForReadOnlyCheckExistence(options, dbname);
if (!s.ok()) {
return s;
}
*dbptr = nullptr;
// Try to first open DB as fully compacted DB
s = CompactedDBImpl::Open(options, dbname, dbptr);
if (s.ok()) {
return s;
}
DBOptions db_options(options);
ColumnFamilyOptions cf_options(options);
std::vector<ColumnFamilyDescriptor> column_families;
column_families.push_back(
ColumnFamilyDescriptor(kDefaultColumnFamilyName, cf_options));
std::vector<ColumnFamilyHandle*> handles;
s = DBImplReadOnly::OpenForReadOnlyWithoutCheck(
db_options, dbname, column_families, &handles, dbptr);
if (s.ok()) {
assert(handles.size() == 1);
// i can delete the handle since DBImpl is always holding a
// reference to default column family
delete handles[0];
}
return s;
}
Status DB::OpenForReadOnly(
const DBOptions& db_options, const std::string& dbname,
const std::vector<ColumnFamilyDescriptor>& column_families,
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
bool error_if_wal_file_exists) {
// If dbname does not exist in the file system, should not do anything
Status s = OpenForReadOnlyCheckExistence(db_options, dbname);
if (!s.ok()) {
return s;
}
return DBImplReadOnly::OpenForReadOnlyWithoutCheck(
db_options, dbname, column_families, handles, dbptr,
error_if_wal_file_exists);
}
Status DBImplReadOnly::OpenForReadOnlyWithoutCheck(
const DBOptions& db_options, const std::string& dbname,
const std::vector<ColumnFamilyDescriptor>& column_families,
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
bool error_if_wal_file_exists) {
*dbptr = nullptr;
handles->clear();
SuperVersionContext sv_context(/* create_superversion */ true);
DBImplReadOnly* impl = new DBImplReadOnly(db_options, dbname);
impl->mutex_.Lock();
Status s = impl->Recover(column_families, true /* read only */,
error_if_wal_file_exists);
if (s.ok()) {
// set column family handles
for (auto cf : column_families) {
auto cfd =
impl->versions_->GetColumnFamilySet()->GetColumnFamily(cf.name);
if (cfd == nullptr) {
s = Status::InvalidArgument("Column family not found", cf.name);
break;
}
handles->push_back(new ColumnFamilyHandleImpl(cfd, impl, &impl->mutex_));
}
}
if (s.ok()) {
for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
sv_context.NewSuperVersion();
cfd->InstallSuperVersion(&sv_context, &impl->mutex_);
}
}
impl->mutex_.Unlock();
sv_context.Clean();
if (s.ok()) {
*dbptr = impl;
for (auto* h : *handles) {
impl->NewThreadStatusCfInfo(
static_cast_with_check<ColumnFamilyHandleImpl>(h)->cfd());
}
} else {
for (auto h : *handles) {
delete h;
}
handles->clear();
delete impl;
}
return s;
}
} // namespace ROCKSDB_NAMESPACE