mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +00:00
c268628c25
Summary: In the current implementation, any retryable IO error happens during Flush is mapped to a hard error. In this case, DB is stopped and write is stalled unless the background error is cleaned. In this PR, if WAL is DISABLED, the retryable IO error during FLush is mapped to a soft error. Such that, the memtable can continue receive the writes. At the same time, if auto resume is triggered, SwtichMemtable will not be called during Flush when resuming the DB to avoid to many small memtables. Testing cases are added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7310 Test Plan: adding new unit test, pass make check. Reviewed By: anand1976 Differential Revision: D23710892 Pulled By: zhichao-cao fbshipit-source-id: bc4ca50d11c6b23b60d2c0cb171d86d542b038e9
120 lines
3.9 KiB
C++
120 lines
3.9 KiB
C++
// Copyright (c) 2018-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
#pragma once
|
|
|
|
#include "monitoring/instrumented_mutex.h"
|
|
#include "options/db_options.h"
|
|
#include "rocksdb/io_status.h"
|
|
#include "rocksdb/listener.h"
|
|
#include "rocksdb/status.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class DBImpl;
|
|
|
|
// This structure is used to store the DB recovery context. The context is
|
|
// the information that related to the recover actions. For example, it contains
|
|
// FlushReason, which tells the flush job why this flush is called.
|
|
struct DBRecoverContext {
|
|
FlushReason flush_reason;
|
|
|
|
DBRecoverContext() : flush_reason(FlushReason::kErrorRecovery) {}
|
|
|
|
DBRecoverContext(FlushReason reason) : flush_reason(reason) {}
|
|
};
|
|
|
|
class ErrorHandler {
|
|
public:
|
|
ErrorHandler(DBImpl* db, const ImmutableDBOptions& db_options,
|
|
InstrumentedMutex* db_mutex)
|
|
: db_(db),
|
|
db_options_(db_options),
|
|
bg_error_(Status::OK()),
|
|
recovery_error_(Status::OK()),
|
|
recovery_io_error_(IOStatus::OK()),
|
|
cv_(db_mutex),
|
|
end_recovery_(false),
|
|
recovery_thread_(nullptr),
|
|
db_mutex_(db_mutex),
|
|
auto_recovery_(false),
|
|
recovery_in_prog_(false),
|
|
soft_error_no_bg_work_(false) {}
|
|
~ErrorHandler() {
|
|
bg_error_.PermitUncheckedError();
|
|
recovery_error_.PermitUncheckedError();
|
|
recovery_io_error_.PermitUncheckedError();
|
|
}
|
|
|
|
void EnableAutoRecovery() { auto_recovery_ = true; }
|
|
|
|
Status::Severity GetErrorSeverity(BackgroundErrorReason reason,
|
|
Status::Code code,
|
|
Status::SubCode subcode);
|
|
|
|
Status SetBGError(const Status& bg_err, BackgroundErrorReason reason);
|
|
|
|
Status SetBGError(const IOStatus& bg_io_err, BackgroundErrorReason reason);
|
|
|
|
Status GetBGError() { return bg_error_; }
|
|
|
|
Status GetRecoveryError() { return recovery_error_; }
|
|
|
|
Status ClearBGError();
|
|
|
|
bool IsDBStopped() {
|
|
return !bg_error_.ok() &&
|
|
bg_error_.severity() >= Status::Severity::kHardError;
|
|
}
|
|
|
|
bool IsBGWorkStopped() {
|
|
return !bg_error_.ok() &&
|
|
(bg_error_.severity() >= Status::Severity::kHardError ||
|
|
!auto_recovery_ || soft_error_no_bg_work_);
|
|
}
|
|
|
|
bool IsSoftErrorNoBGWork() { return soft_error_no_bg_work_; }
|
|
|
|
bool IsRecoveryInProgress() { return recovery_in_prog_; }
|
|
|
|
Status RecoverFromBGError(bool is_manual = false);
|
|
void CancelErrorRecovery();
|
|
|
|
void EndAutoRecovery();
|
|
|
|
private:
|
|
DBImpl* db_;
|
|
const ImmutableDBOptions& db_options_;
|
|
Status bg_error_;
|
|
// A separate Status variable used to record any errors during the
|
|
// recovery process from hard errors
|
|
Status recovery_error_;
|
|
// A separate IO Status variable used to record any IO errors during
|
|
// the recovery process. At the same time, recovery_error_ is also set.
|
|
IOStatus recovery_io_error_;
|
|
// The condition variable used with db_mutex during auto resume for time
|
|
// wait.
|
|
InstrumentedCondVar cv_;
|
|
bool end_recovery_;
|
|
std::unique_ptr<port::Thread> recovery_thread_;
|
|
|
|
InstrumentedMutex* db_mutex_;
|
|
// A flag indicating whether automatic recovery from errors is enabled
|
|
bool auto_recovery_;
|
|
bool recovery_in_prog_;
|
|
// A flag to indicate that for the soft error, we should not allow any
|
|
// backrgound work execpt the work is from recovery.
|
|
bool soft_error_no_bg_work_;
|
|
|
|
// Used to store the context for recover, such as flush reason.
|
|
DBRecoverContext recover_context_;
|
|
|
|
Status OverrideNoSpaceError(Status bg_error, bool* auto_recovery);
|
|
void RecoverFromNoSpace();
|
|
Status StartRecoverFromRetryableBGIOError(IOStatus io_error);
|
|
void RecoverFromRetryableBGIOError();
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|