2018-05-31 17:42:44 +00:00
|
|
|
// 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
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
|
|
|
|
#include "utilities/transactions/write_prepared_txn_db.h"
|
|
|
|
#include "utilities/transactions/write_unprepared_txn.h"
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
2018-06-27 19:05:29 +00:00
|
|
|
class WriteUnpreparedTxn;
|
|
|
|
|
2018-05-31 17:42:44 +00:00
|
|
|
class WriteUnpreparedTxnDB : public WritePreparedTxnDB {
|
2018-06-27 19:05:29 +00:00
|
|
|
public:
|
2018-05-31 17:42:44 +00:00
|
|
|
using WritePreparedTxnDB::WritePreparedTxnDB;
|
|
|
|
|
2018-07-07 00:17:36 +00:00
|
|
|
Status Initialize(const std::vector<size_t>& compaction_enabled_cf_indices,
|
|
|
|
const std::vector<ColumnFamilyHandle*>& handles) override;
|
|
|
|
|
|
|
|
Transaction* BeginTransaction(const WriteOptions& write_options,
|
|
|
|
const TransactionOptions& txn_options,
|
2018-05-31 17:42:44 +00:00
|
|
|
Transaction* old_txn) override;
|
2018-06-27 19:05:29 +00:00
|
|
|
|
|
|
|
// Struct to hold ownership of snapshot and read callback for cleanup.
|
|
|
|
struct IteratorState;
|
|
|
|
|
|
|
|
using WritePreparedTxnDB::NewIterator;
|
|
|
|
Iterator* NewIterator(const ReadOptions& options,
|
|
|
|
ColumnFamilyHandle* column_family,
|
|
|
|
WriteUnpreparedTxn* txn);
|
2018-07-07 00:17:36 +00:00
|
|
|
|
|
|
|
private:
|
|
|
|
Status RollbackRecoveredTransaction(const DBImpl::RecoveredTransaction* rtxn);
|
2018-05-31 17:42:44 +00:00
|
|
|
};
|
|
|
|
|
2018-07-24 07:09:18 +00:00
|
|
|
class WriteUnpreparedCommitEntryPreReleaseCallback : public PreReleaseCallback {
|
|
|
|
// TODO(lth): Reduce code duplication with
|
|
|
|
// WritePreparedCommitEntryPreReleaseCallback
|
|
|
|
public:
|
|
|
|
// includes_data indicates that the commit also writes non-empty
|
|
|
|
// CommitTimeWriteBatch to memtable, which needs to be committed separately.
|
|
|
|
WriteUnpreparedCommitEntryPreReleaseCallback(
|
|
|
|
WritePreparedTxnDB* db, DBImpl* db_impl,
|
|
|
|
const std::map<SequenceNumber, size_t>& unprep_seqs,
|
|
|
|
size_t data_batch_cnt = 0, bool publish_seq = true)
|
|
|
|
: db_(db),
|
|
|
|
db_impl_(db_impl),
|
|
|
|
unprep_seqs_(unprep_seqs),
|
|
|
|
data_batch_cnt_(data_batch_cnt),
|
|
|
|
includes_data_(data_batch_cnt_ > 0),
|
|
|
|
publish_seq_(publish_seq) {
|
|
|
|
assert(unprep_seqs.size() > 0);
|
|
|
|
}
|
|
|
|
|
2019-04-02 22:14:41 +00:00
|
|
|
virtual Status Callback(SequenceNumber commit_seq,
|
|
|
|
bool is_mem_disabled __attribute__((__unused__)),
|
|
|
|
uint64_t) override {
|
2018-07-24 07:09:18 +00:00
|
|
|
const uint64_t last_commit_seq = LIKELY(data_batch_cnt_ <= 1)
|
|
|
|
? commit_seq
|
|
|
|
: commit_seq + data_batch_cnt_ - 1;
|
|
|
|
// Recall that unprep_seqs maps (un)prepared_seq => prepare_batch_cnt.
|
|
|
|
for (const auto& s : unprep_seqs_) {
|
|
|
|
for (size_t i = 0; i < s.second; i++) {
|
|
|
|
db_->AddCommitted(s.first + i, last_commit_seq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (includes_data_) {
|
|
|
|
assert(data_batch_cnt_);
|
|
|
|
// Commit the data that is accompanied with the commit request
|
|
|
|
for (size_t i = 0; i < data_batch_cnt_; i++) {
|
|
|
|
// For commit seq of each batch use the commit seq of the last batch.
|
|
|
|
// This would make debugging easier by having all the batches having
|
|
|
|
// the same sequence number.
|
|
|
|
db_->AddCommitted(commit_seq + i, last_commit_seq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (db_impl_->immutable_db_options().two_write_queues && publish_seq_) {
|
|
|
|
assert(is_mem_disabled); // implies the 2nd queue
|
|
|
|
// Publish the sequence number. We can do that here assuming the callback
|
|
|
|
// is invoked only from one write queue, which would guarantee that the
|
|
|
|
// publish sequence numbers will be in order, i.e., once a seq is
|
|
|
|
// published all the seq prior to that are also publishable.
|
|
|
|
db_impl_->SetLastPublishedSequence(last_commit_seq);
|
|
|
|
}
|
|
|
|
// else SequenceNumber that is updated as part of the write already does the
|
|
|
|
// publishing
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
WritePreparedTxnDB* db_;
|
|
|
|
DBImpl* db_impl_;
|
|
|
|
const std::map<SequenceNumber, size_t>& unprep_seqs_;
|
|
|
|
size_t data_batch_cnt_;
|
|
|
|
// Either because it is commit without prepare or it has a
|
|
|
|
// CommitTimeWriteBatch
|
|
|
|
bool includes_data_;
|
|
|
|
// Should the callback also publishes the commit seq number
|
|
|
|
bool publish_seq_;
|
|
|
|
};
|
|
|
|
|
WritePrepared: fix two versions in compaction see different status for released snapshots (#4890)
Summary:
Fix how CompactionIterator::findEarliestVisibleSnapshots handles released snapshot. It fixing the two scenarios:
Scenario 1:
key1 has two values v1 and v2. There're two snapshots s1 and s2 taken after v1 and v2 are committed. Right after compaction output v2, s1 is released. Now findEarliestVisibleSnapshot may see s1 being released, and return the next snapshot, which is s2. That's larger than v2's earliest visible snapshot, which was s1.
The fix: the only place we check against last snapshot and current key snapshot is when we decide whether to compact out a value if it is hidden by a later value. In the check if we see current snapshot is even larger than last snapshot, we know last snapshot is released, and we are safe to compact out current key.
Scenario 2:
key1 has two values v1 and v2. there are two snapshots s1 and s2 taken after v1 and v2 are committed. During compaction before we process the key, s1 is released. When compaction process v2, snapshot checker may return kSnapshotReleased, and the earliest visible snapshot for v2 become s2. When compaction process v1, snapshot checker may return kIsInSnapshot (for WritePrepared transaction, it could be because v1 is still in commit cache). The result will become inconsistent here.
The fix: remember the set of released snapshots ever reported by snapshot checker, and ignore them when finding result for findEarliestVisibleSnapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4890
Differential Revision: D13705538
Pulled By: maysamyabandeh
fbshipit-source-id: e577f0d9ee1ff5a6035f26859e56902ecc85a5a4
2019-01-19 01:20:13 +00:00
|
|
|
class WriteUnpreparedRollbackPreReleaseCallback : public PreReleaseCallback {
|
|
|
|
// TODO(lth): Reduce code duplication with
|
|
|
|
// WritePreparedCommitEntryPreReleaseCallback
|
|
|
|
public:
|
|
|
|
WriteUnpreparedRollbackPreReleaseCallback(
|
|
|
|
WritePreparedTxnDB* db, DBImpl* db_impl,
|
|
|
|
const std::map<SequenceNumber, size_t>& unprep_seqs,
|
|
|
|
SequenceNumber rollback_seq)
|
|
|
|
: db_(db),
|
|
|
|
db_impl_(db_impl),
|
|
|
|
unprep_seqs_(unprep_seqs),
|
|
|
|
rollback_seq_(rollback_seq) {
|
|
|
|
assert(unprep_seqs.size() > 0);
|
|
|
|
assert(db_impl_->immutable_db_options().two_write_queues);
|
|
|
|
}
|
|
|
|
|
2019-04-02 22:14:41 +00:00
|
|
|
virtual Status Callback(SequenceNumber commit_seq,
|
|
|
|
bool is_mem_disabled __attribute__((__unused__)),
|
|
|
|
uint64_t) override {
|
WritePrepared: fix two versions in compaction see different status for released snapshots (#4890)
Summary:
Fix how CompactionIterator::findEarliestVisibleSnapshots handles released snapshot. It fixing the two scenarios:
Scenario 1:
key1 has two values v1 and v2. There're two snapshots s1 and s2 taken after v1 and v2 are committed. Right after compaction output v2, s1 is released. Now findEarliestVisibleSnapshot may see s1 being released, and return the next snapshot, which is s2. That's larger than v2's earliest visible snapshot, which was s1.
The fix: the only place we check against last snapshot and current key snapshot is when we decide whether to compact out a value if it is hidden by a later value. In the check if we see current snapshot is even larger than last snapshot, we know last snapshot is released, and we are safe to compact out current key.
Scenario 2:
key1 has two values v1 and v2. there are two snapshots s1 and s2 taken after v1 and v2 are committed. During compaction before we process the key, s1 is released. When compaction process v2, snapshot checker may return kSnapshotReleased, and the earliest visible snapshot for v2 become s2. When compaction process v1, snapshot checker may return kIsInSnapshot (for WritePrepared transaction, it could be because v1 is still in commit cache). The result will become inconsistent here.
The fix: remember the set of released snapshots ever reported by snapshot checker, and ignore them when finding result for findEarliestVisibleSnapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4890
Differential Revision: D13705538
Pulled By: maysamyabandeh
fbshipit-source-id: e577f0d9ee1ff5a6035f26859e56902ecc85a5a4
2019-01-19 01:20:13 +00:00
|
|
|
assert(is_mem_disabled); // implies the 2nd queue
|
|
|
|
const uint64_t last_commit_seq = commit_seq;
|
|
|
|
db_->AddCommitted(rollback_seq_, last_commit_seq);
|
|
|
|
// Recall that unprep_seqs maps (un)prepared_seq => prepare_batch_cnt.
|
|
|
|
for (const auto& s : unprep_seqs_) {
|
|
|
|
for (size_t i = 0; i < s.second; i++) {
|
|
|
|
db_->AddCommitted(s.first + i, last_commit_seq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
db_impl_->SetLastPublishedSequence(last_commit_seq);
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
WritePreparedTxnDB* db_;
|
|
|
|
DBImpl* db_impl_;
|
|
|
|
const std::map<SequenceNumber, size_t>& unprep_seqs_;
|
|
|
|
SequenceNumber rollback_seq_;
|
|
|
|
};
|
|
|
|
|
2018-07-24 07:09:18 +00:00
|
|
|
struct KeySetBuilder : public WriteBatch::Handler {
|
|
|
|
WriteUnpreparedTxn* txn_;
|
|
|
|
bool rollback_merge_operands_;
|
|
|
|
|
|
|
|
KeySetBuilder(WriteUnpreparedTxn* txn, bool rollback_merge_operands)
|
|
|
|
: txn_(txn), rollback_merge_operands_(rollback_merge_operands) {}
|
|
|
|
|
|
|
|
Status PutCF(uint32_t cf, const Slice& key, const Slice& val) override;
|
|
|
|
|
|
|
|
Status DeleteCF(uint32_t cf, const Slice& key) override;
|
|
|
|
|
|
|
|
Status SingleDeleteCF(uint32_t cf, const Slice& key) override;
|
|
|
|
|
|
|
|
Status MergeCF(uint32_t cf, const Slice& key, const Slice& val) override;
|
|
|
|
|
|
|
|
// Recovered batches do not contain 2PC markers.
|
|
|
|
Status MarkNoop(bool) override { return Status::InvalidArgument(); }
|
|
|
|
Status MarkBeginPrepare(bool) override { return Status::InvalidArgument(); }
|
|
|
|
Status MarkEndPrepare(const Slice&) override {
|
|
|
|
return Status::InvalidArgument();
|
|
|
|
}
|
|
|
|
Status MarkCommit(const Slice&) override { return Status::InvalidArgument(); }
|
|
|
|
Status MarkRollback(const Slice&) override {
|
|
|
|
return Status::InvalidArgument();
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2018-05-31 17:42:44 +00:00
|
|
|
} // namespace rocksdb
|
|
|
|
#endif // ROCKSDB_LITE
|