rocksdb/utilities/debug.cc

123 lines
4.5 KiB
C++
Raw Normal View History

// 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 "rocksdb/utilities/debug.h"
#include "db/db_impl/db_impl.h"
#include "rocksdb/utilities/options_type.h"
namespace ROCKSDB_NAMESPACE {
static std::unordered_map<std::string, ValueType> value_type_string_map = {
{"TypeDeletion", ValueType::kTypeDeletion},
{"TypeValue", ValueType::kTypeValue},
{"TypeMerge", ValueType::kTypeMerge},
{"TypeLogData", ValueType::kTypeLogData},
{"TypeColumnFamilyDeletion", ValueType::kTypeColumnFamilyDeletion},
{"TypeColumnFamilyValue", ValueType::kTypeColumnFamilyValue},
{"TypeColumnFamilyMerge", ValueType::kTypeColumnFamilyMerge},
{"TypeSingleDeletion", ValueType::kTypeSingleDeletion},
{"TypeColumnFamilySingleDeletion",
ValueType::kTypeColumnFamilySingleDeletion},
{"TypeBeginPrepareXID", ValueType::kTypeBeginPrepareXID},
{"TypeEndPrepareXID", ValueType::kTypeEndPrepareXID},
{"TypeCommitXID", ValueType::kTypeCommitXID},
{"TypeRollbackXID", ValueType::kTypeRollbackXID},
{"TypeNoop", ValueType::kTypeNoop},
{"TypeColumnFamilyRangeDeletion",
ValueType::kTypeColumnFamilyRangeDeletion},
{"TypeRangeDeletion", ValueType::kTypeRangeDeletion},
{"TypeColumnFamilyBlobIndex", ValueType::kTypeColumnFamilyBlobIndex},
{"TypeBlobIndex", ValueType::kTypeBlobIndex},
{"TypeBeginPersistedPrepareXID", ValueType::kTypeBeginPersistedPrepareXID},
{"TypeBeginUnprepareXID", ValueType::kTypeBeginUnprepareXID},
{"TypeDeletionWithTimestamp", ValueType::kTypeDeletionWithTimestamp},
{"TypeCommitXIDAndTimestamp", ValueType::kTypeCommitXIDAndTimestamp},
{"TypeWideColumnEntity", ValueType::kTypeWideColumnEntity},
{"TypeColumnFamilyWideColumnEntity",
Add initial support for TimedPut API (#12419) Summary: This PR adds support for `TimedPut` API. We introduced a new type `kTypeValuePreferredSeqno` for entries added to the DB via the `TimedPut` API. The life cycle of such an entry on the write/flush/compaction paths are: 1) It is initially added to memtable as: `<user_key, seq, kTypeValuePreferredSeqno>: {value, write_unix_time}` 2) When it's flushed to L0 sst files, it's converted to: `<user_key, seq, kTypeValuePreferredSeqno>: {value, preferred_seqno}` when we have easy access to the seqno to time mapping. 3) During compaction, if certain conditions are met, we swap in the `preferred_seqno` and the entry will become: `<user_key, preferred_seqno, kTypeValue>: value`. This step helps fast track these entries to the cold tier if they are eligible after the sequence number swap. On the read path: A `kTypeValuePreferredSeqno` entry acts the same as a `kTypeValue` entry, the unix_write_time/preferred seqno part packed in value is completely ignored. Needed follow ups: 1) The seqno to time mapping accessible in flush needs to be extended to cover the `write_unix_time` for possible `kTypeValuePreferredSeqno` entries. This also means we need to track these `write_unix_time` in memtable. 2) Compaction filter support for the new `kTypeValuePreferredSeqno` type for feature parity with other `kTypeValue` and equivalent types. 3) Stress test coverage for the feature Pull Request resolved: https://github.com/facebook/rocksdb/pull/12419 Test Plan: Added unit tests Reviewed By: pdillinger Differential Revision: D54920296 Pulled By: jowlyzhang fbshipit-source-id: c8b43f7a7c465e569141770e93c748371ff1da9e
2024-03-14 22:44:55 +00:00
ValueType::kTypeColumnFamilyWideColumnEntity},
{"TypeValuePreferredSeqno", ValueType::kTypeValuePreferredSeqno},
{"TypeColumnFamilyValuePreferredSeqno",
ValueType::kTypeColumnFamilyValuePreferredSeqno},
};
std::string KeyVersion::GetTypeName() const {
std::string type_name;
if (SerializeEnum<ValueType>(value_type_string_map,
static_cast<ValueType>(type), &type_name)) {
return type_name;
} else {
return "Invalid";
}
}
Status GetAllKeyVersions(DB* db, Slice begin_key, Slice end_key,
size_t max_num_ikeys,
std::vector<KeyVersion>* key_versions) {
if (nullptr == db) {
return Status::InvalidArgument("db cannot be null.");
}
return GetAllKeyVersions(db, db->DefaultColumnFamily(), begin_key, end_key,
max_num_ikeys, key_versions);
}
Status GetAllKeyVersions(DB* db, ColumnFamilyHandle* cfh, Slice begin_key,
Slice end_key, size_t max_num_ikeys,
std::vector<KeyVersion>* key_versions) {
if (nullptr == db) {
return Status::InvalidArgument("db cannot be null.");
}
if (nullptr == cfh) {
return Status::InvalidArgument("Column family handle cannot be null.");
}
if (nullptr == key_versions) {
return Status::InvalidArgument("key_versions cannot be null.");
}
key_versions->clear();
DBImpl* idb = static_cast<DBImpl*>(db->GetRootDB());
auto icmp = InternalKeyComparator(idb->GetOptions(cfh).comparator);
ReadOptions read_options;
Arena arena;
ScopedArenaPtr<InternalIterator> iter(
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
2022-09-02 16:51:19 +00:00
idb->NewInternalIterator(read_options, &arena, kMaxSequenceNumber, cfh));
if (!begin_key.empty()) {
InternalKey ikey;
ikey.SetMinPossibleForUserKey(begin_key);
iter->Seek(ikey.Encode());
} else {
iter->SeekToFirst();
}
size_t num_keys = 0;
for (; iter->Valid(); iter->Next()) {
ParsedInternalKey ikey;
Status pik_status =
ParseInternalKey(iter->key(), &ikey, true /* log_err_key */); // TODO
if (!pik_status.ok()) {
return pik_status;
}
if (!end_key.empty() &&
icmp.user_comparator()->Compare(ikey.user_key, end_key) > 0) {
break;
}
key_versions->emplace_back(ikey.user_key.ToString() /* _user_key */,
iter->value().ToString() /* _value */,
ikey.sequence /* _sequence */,
static_cast<int>(ikey.type) /* _type */);
if (++num_keys >= max_num_ikeys) {
break;
}
}
return Status::OK();
}
} // namespace ROCKSDB_NAMESPACE