rocksdb/db/db_impl_debug.cc
Siying Dong d59549298f Skip deleted WALs during recovery
Summary:
This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic.

Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction)

This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2.
Closes https://github.com/facebook/rocksdb/pull/3765

Differential Revision: D7747618

Pulled By: siying

fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-03 15:43:09 -07:00

233 lines
6.7 KiB
C++

// 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#ifndef NDEBUG
#include "db/db_impl.h"
#include "monitoring/thread_status_updater.h"
namespace rocksdb {
uint64_t DBImpl::TEST_GetLevel0TotalSize() {
InstrumentedMutexLock l(&mutex_);
return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
}
void DBImpl::TEST_SwitchWAL() {
WriteContext write_context;
InstrumentedMutexLock l(&mutex_);
SwitchWAL(&write_context);
}
int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
ColumnFamilyHandle* column_family) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
cfd = cfh->cfd();
}
InstrumentedMutexLock l(&mutex_);
return cfd->current()->storage_info()->MaxNextLevelOverlappingBytes();
}
void DBImpl::TEST_GetFilesMetaData(
ColumnFamilyHandle* column_family,
std::vector<std::vector<FileMetaData>>* metadata) {
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
auto cfd = cfh->cfd();
InstrumentedMutexLock l(&mutex_);
metadata->resize(NumberLevels());
for (int level = 0; level < NumberLevels(); level++) {
const std::vector<FileMetaData*>& files =
cfd->current()->storage_info()->LevelFiles(level);
(*metadata)[level].clear();
for (const auto& f : files) {
(*metadata)[level].push_back(*f);
}
}
}
uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
return versions_->manifest_file_number();
}
uint64_t DBImpl::TEST_Current_Next_FileNo() {
return versions_->current_next_file_number();
}
Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
const Slice* end,
ColumnFamilyHandle* column_family,
bool disallow_trivial_move) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
cfd = cfh->cfd();
}
int output_level =
(cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
? level
: level + 1;
return RunManualCompaction(cfd, level, output_level, 0, 0, begin, end, true,
disallow_trivial_move);
}
Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
WriteContext write_context;
InstrumentedMutexLock l(&mutex_);
if (cfd == nullptr) {
cfd = default_cf_handle_->cfd();
}
return SwitchMemtable(cfd, &write_context);
}
Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
FlushOptions fo;
fo.wait = wait;
ColumnFamilyData* cfd;
if (cfh == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfhi = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh);
cfd = cfhi->cfd();
}
return FlushMemTable(cfd, fo, FlushReason::kTest);
}
Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
ColumnFamilyData* cfd;
if (column_family == nullptr) {
cfd = default_cf_handle_->cfd();
} else {
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
cfd = cfh->cfd();
}
return WaitForFlushMemTable(cfd);
}
Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
// Wait until the compaction completes
// TODO: a bug here. This function actually does not necessarily
// wait for compact. It actually waits for scheduled compaction
// OR flush to finish.
InstrumentedMutexLock l(&mutex_);
while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
bg_flush_scheduled_ ||
(wait_unscheduled && unscheduled_compactions_)) &&
bg_error_.ok()) {
bg_cv_.Wait();
}
return bg_error_;
}
void DBImpl::TEST_LockMutex() {
mutex_.Lock();
}
void DBImpl::TEST_UnlockMutex() {
mutex_.Unlock();
}
void* DBImpl::TEST_BeginWrite() {
auto w = new WriteThread::Writer();
write_thread_.EnterUnbatched(w, &mutex_);
return reinterpret_cast<void*>(w);
}
void DBImpl::TEST_EndWrite(void* w) {
auto writer = reinterpret_cast<WriteThread::Writer*>(w);
write_thread_.ExitUnbatched(writer);
delete writer;
}
size_t DBImpl::TEST_LogsToFreeSize() {
InstrumentedMutexLock l(&mutex_);
return logs_to_free_.size();
}
uint64_t DBImpl::TEST_LogfileNumber() {
InstrumentedMutexLock l(&mutex_);
return logfile_number_;
}
Status DBImpl::TEST_GetAllImmutableCFOptions(
std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map) {
std::vector<std::string> cf_names;
std::vector<const ImmutableCFOptions*> iopts;
{
InstrumentedMutexLock l(&mutex_);
for (auto cfd : *versions_->GetColumnFamilySet()) {
cf_names.push_back(cfd->GetName());
iopts.push_back(cfd->ioptions());
}
}
iopts_map->clear();
for (size_t i = 0; i < cf_names.size(); ++i) {
iopts_map->insert({cf_names[i], iopts[i]});
}
return Status::OK();
}
uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
return logs_with_prep_tracker_.FindMinLogContainingOutstandingPrep();
}
size_t DBImpl::TEST_PreparedSectionCompletedSize() {
return logs_with_prep_tracker_.TEST_PreparedSectionCompletedSize();
}
size_t DBImpl::TEST_LogsWithPrepSize() {
return logs_with_prep_tracker_.TEST_LogsWithPrepSize();
}
uint64_t DBImpl::TEST_FindMinPrepLogReferencedByMemTable() {
autovector<MemTable*> empty_list;
return FindMinPrepLogReferencedByMemTable(versions_.get(), nullptr,
empty_list);
}
Status DBImpl::TEST_GetLatestMutableCFOptions(
ColumnFamilyHandle* column_family, MutableCFOptions* mutable_cf_options) {
InstrumentedMutexLock l(&mutex_);
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
*mutable_cf_options = *cfh->cfd()->GetLatestMutableCFOptions();
return Status::OK();
}
int DBImpl::TEST_BGCompactionsAllowed() const {
InstrumentedMutexLock l(&mutex_);
return GetBGJobLimits().max_compactions;
}
int DBImpl::TEST_BGFlushesAllowed() const {
InstrumentedMutexLock l(&mutex_);
return GetBGJobLimits().max_flushes;
}
SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
if (last_seq_same_as_publish_seq_) {
return versions_->LastSequence();
} else {
return versions_->LastAllocatedSequence();
}
}
} // namespace rocksdb
#endif // NDEBUG