rocksdb/db/error_handler.h

128 lines
4.3 KiB
C
Raw Normal View History

// 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 {
Auto recovery from out of space errors (#4164) Summary: This commit implements automatic recovery from a Status::NoSpace() error during background operations such as write callback, flush and compaction. The broad design is as follows - 1. Compaction errors are treated as soft errors and don't put the database in read-only mode. A compaction is delayed until enough free disk space is available to accomodate the compaction outputs, which is estimated based on the input size. This means that users can continue to write, and we rely on the WriteController to delay or stop writes if the compaction debt becomes too high due to persistent low disk space condition 2. Errors during write callback and flush are treated as hard errors, i.e the database is put in read-only mode and goes back to read-write only fater certain recovery actions are taken. 3. Both types of recovery rely on the SstFileManagerImpl to poll for sufficient disk space. We assume that there is a 1-1 mapping between an SFM and the underlying OS storage container. For cases where multiple DBs are hosted on a single storage container, the user is expected to allocate a single SFM instance and use the same one for all the DBs. If no SFM is specified by the user, DBImpl::Open() will allocate one, but this will be one per DB and each DB will recover independently. The recovery implemented by SFM is as follows - a) On the first occurance of an out of space error during compaction, subsequent compactions will be delayed until the disk free space check indicates enough available space. The required space is computed as the sum of input sizes. b) The free space check requirement will be removed once the amount of free space is greater than the size reserved by in progress compactions when the first error occured c) If the out of space error is a hard error, a background thread in SFM will poll for sufficient headroom before triggering the recovery of the database and putting it in write-only mode. The headroom is calculated as the sum of the write_buffer_size of all the DB instances associated with the SFM 4. EventListener callbacks will be called at the start and completion of automatic recovery. Users can disable the auto recov ery in the start callback, and later initiate it manually by calling DB::Resume() Todo: 1. More extensive testing 2. Add disk full condition to db_stress (follow-on PR) Pull Request resolved: https://github.com/facebook/rocksdb/pull/4164 Differential Revision: D9846378 Pulled By: anand1976 fbshipit-source-id: 80ea875dbd7f00205e19c82215ff6e37da10da4a
2018-09-15 20:36:19 +00:00
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;
Only flush after recovery for retryable IOError (#11880) Summary: https://github.com/facebook/rocksdb/issues/11872 causes a unit test to start failing with the error message below. The cause is that the additional call to `FlushAllColumnFamilies()` in `DBImpl::ResumeImpl()` can run while DB is closing. More detailed explanation: there are two places where we call `ResumeImpl()`: 1. in `ErrorHandler::RecoverFromBGError`, for manual resume or recovery from errors like OutOfSpace through sst file manager, and 2. in `Errorhandler::RecoverFromRetryableBGIOError`, for error recovery from errors like flush failure due to retryable IOError. This is tracked by `ErrorHandler::recovery_thread_`. Here is how DB close waits for error recovery: https://github.com/facebook/rocksdb/blob/49da91ec097b4efcd8a8e4dc1b287e9f81eb4093/db/db_impl/db_impl.cc#L540-L543 `CancelErrorRecovery()` waits until `recovery_thread_` finishes and `IsRecoveryInProgress()` checks the `recovery_in_prog_` flag. The additional call to `FlushAllColumnFamilies()` in `ResumeImpl()` happens after it clears bg error and the `recovery_in_prog_` flag: https://github.com/facebook/rocksdb/blob/49da91ec097b4efcd8a8e4dc1b287e9f81eb4093/db/db_impl/db_impl.cc#L436-L463. So if `ResumeImpl()` is called in `RecoverFromBGError()`, we can have a thread running `FlushAllColumnFamilies()` while DB is closing and thought that recovery is done. The fix is to only do the additional call to `FlushAllColumnFamilies()` when doing error recovery through `Errorhandler::RecoverFromRetryableBGIOError` by setting flags in `DBRecoverContext`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11880 Test Plan: `gtest-parallel --repeat=100 --workers=4 ./error_handler_fs_test --gtest_filter="*AutoRecoverFlushError*"` reproduces the error pretty reliably. ```[==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from DBErrorHandlingFSTest [ RUN ] DBErrorHandlingFSTest.AutoRecoverFlushError error_handler_fs_test: db/column_family.cc:1618: rocksdb::ColumnFamilySet::~ColumnFamilySet(): Assertion `last_ref' failed. Received signal 6 (Aborted) ... https://github.com/facebook/rocksdb/issues/10 0x00007fac4409efd6 in __GI___assert_fail (assertion=0x7fac452c0afa "last_ref", file=0x7fac452c9fb5 "db/column_family.cc", line=1618, function=0x7fac452cb950 "rocksdb::ColumnFamilySet::~ColumnFamilySet()") at assert.c:101 101 in assert.c https://github.com/facebook/rocksdb/issues/11 0x00007fac44b5324f in rocksdb::ColumnFamilySet::~ColumnFamilySet (this=0x7b5400000000) at db/column_family.cc:1618 1618 assert(last_ref); https://github.com/facebook/rocksdb/issues/12 0x00007fac44e0f047 in std::default_delete<rocksdb::ColumnFamilySet>::operator() (this=0x7b5800000940, __ptr=0x7b5400000000) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85 85 delete __ptr; https://github.com/facebook/rocksdb/issues/13 std::__uniq_ptr_impl<rocksdb::ColumnFamilySet, std::default_delete<rocksdb::ColumnFamilySet> >::reset (this=0x7b5800000940, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:182 182 _M_deleter()(__old_p); https://github.com/facebook/rocksdb/issues/14 std::unique_ptr<rocksdb::ColumnFamilySet, std::default_delete<rocksdb::ColumnFamilySet> >::reset (this=0x7b5800000940, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:456 456 _M_t.reset(std::move(__p)); https://github.com/facebook/rocksdb/issues/15 rocksdb::VersionSet::~VersionSet (this=this@entry=0x7b5800000900) at db/version_set.cc:5081 5081 column_family_set_.reset(); https://github.com/facebook/rocksdb/issues/16 0x00007fac44e0f97a in rocksdb::VersionSet::~VersionSet (this=0x7b5800000900) at db/version_set.cc:5078 5078 VersionSet::~VersionSet() { https://github.com/facebook/rocksdb/issues/17 0x00007fac44bf0b2f in std::default_delete<rocksdb::VersionSet>::operator() (this=0x7b8c00000068, __ptr=0x7b5800000900) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85 85 delete __ptr; https://github.com/facebook/rocksdb/issues/18 std::__uniq_ptr_impl<rocksdb::VersionSet, std::default_delete<rocksdb::VersionSet> >::reset (this=0x7b8c00000068, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:182 182 _M_deleter()(__old_p); https://github.com/facebook/rocksdb/issues/19 std::unique_ptr<rocksdb::VersionSet, std::default_delete<rocksdb::VersionSet> >::reset (this=0x7b8c00000068, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:456 456 _M_t.reset(std::move(__p)); https://github.com/facebook/rocksdb/issues/20 rocksdb::DBImpl::CloseHelper (this=this@entry=0x7b8c00000000) at db/db_impl/db_impl.cc:676 676 versions_.reset(); https://github.com/facebook/rocksdb/issues/21 0x00007fac44bf1346 in rocksdb::DBImpl::CloseImpl (this=0x7b8c00000000) at db/db_impl/db_impl.cc:720 720 Status DBImpl::CloseImpl() { return CloseHelper(); } https://github.com/facebook/rocksdb/issues/22 rocksdb::DBImpl::~DBImpl (this=this@entry=0x7b8c00000000) at db/db_impl/db_impl.cc:738 738 closing_status_ = CloseImpl(); https://github.com/facebook/rocksdb/issues/23 0x00007fac44bf2bba in rocksdb::DBImpl::~DBImpl (this=0x7b8c00000000) at db/db_impl/db_impl.cc:722 722 DBImpl::~DBImpl() { https://github.com/facebook/rocksdb/issues/24 0x00007fac455444d4 in rocksdb::DBTestBase::Close (this=this@entry=0x7b6c00000000) at db/db_test_util.cc:678 678 delete db_; https://github.com/facebook/rocksdb/issues/25 0x00007fac455455fb in rocksdb::DBTestBase::TryReopen (this=this@entry=0x7b6c00000000, options=...) at db/db_test_util.cc:707 707 Close(); https://github.com/facebook/rocksdb/issues/26 0x00007fac45543459 in rocksdb::DBTestBase::Reopen (this=0x7ffed74b79a0, options=...) at db/db_test_util.cc:670 670 ASSERT_OK(TryReopen(options)); https://github.com/facebook/rocksdb/issues/27 0x00000000004f2522 in rocksdb::DBErrorHandlingFSTest_AutoRecoverFlushError_Test::TestBody (this=this@entry=0x7b6c00000000) at db/error_handler_fs_test.cc:1224 1224 Reopen(options); ``` Reviewed By: jowlyzhang Differential Revision: D49579701 Pulled By: cbi42 fbshipit-source-id: 3fc8325e6dde7e7faa8bcad95060cb4e26eda638
2023-09-25 16:34:39 +00:00
bool flush_after_recovery;
Only flush after recovery for retryable IOError (#11880) Summary: https://github.com/facebook/rocksdb/issues/11872 causes a unit test to start failing with the error message below. The cause is that the additional call to `FlushAllColumnFamilies()` in `DBImpl::ResumeImpl()` can run while DB is closing. More detailed explanation: there are two places where we call `ResumeImpl()`: 1. in `ErrorHandler::RecoverFromBGError`, for manual resume or recovery from errors like OutOfSpace through sst file manager, and 2. in `Errorhandler::RecoverFromRetryableBGIOError`, for error recovery from errors like flush failure due to retryable IOError. This is tracked by `ErrorHandler::recovery_thread_`. Here is how DB close waits for error recovery: https://github.com/facebook/rocksdb/blob/49da91ec097b4efcd8a8e4dc1b287e9f81eb4093/db/db_impl/db_impl.cc#L540-L543 `CancelErrorRecovery()` waits until `recovery_thread_` finishes and `IsRecoveryInProgress()` checks the `recovery_in_prog_` flag. The additional call to `FlushAllColumnFamilies()` in `ResumeImpl()` happens after it clears bg error and the `recovery_in_prog_` flag: https://github.com/facebook/rocksdb/blob/49da91ec097b4efcd8a8e4dc1b287e9f81eb4093/db/db_impl/db_impl.cc#L436-L463. So if `ResumeImpl()` is called in `RecoverFromBGError()`, we can have a thread running `FlushAllColumnFamilies()` while DB is closing and thought that recovery is done. The fix is to only do the additional call to `FlushAllColumnFamilies()` when doing error recovery through `Errorhandler::RecoverFromRetryableBGIOError` by setting flags in `DBRecoverContext`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11880 Test Plan: `gtest-parallel --repeat=100 --workers=4 ./error_handler_fs_test --gtest_filter="*AutoRecoverFlushError*"` reproduces the error pretty reliably. ```[==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from DBErrorHandlingFSTest [ RUN ] DBErrorHandlingFSTest.AutoRecoverFlushError error_handler_fs_test: db/column_family.cc:1618: rocksdb::ColumnFamilySet::~ColumnFamilySet(): Assertion `last_ref' failed. Received signal 6 (Aborted) ... https://github.com/facebook/rocksdb/issues/10 0x00007fac4409efd6 in __GI___assert_fail (assertion=0x7fac452c0afa "last_ref", file=0x7fac452c9fb5 "db/column_family.cc", line=1618, function=0x7fac452cb950 "rocksdb::ColumnFamilySet::~ColumnFamilySet()") at assert.c:101 101 in assert.c https://github.com/facebook/rocksdb/issues/11 0x00007fac44b5324f in rocksdb::ColumnFamilySet::~ColumnFamilySet (this=0x7b5400000000) at db/column_family.cc:1618 1618 assert(last_ref); https://github.com/facebook/rocksdb/issues/12 0x00007fac44e0f047 in std::default_delete<rocksdb::ColumnFamilySet>::operator() (this=0x7b5800000940, __ptr=0x7b5400000000) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85 85 delete __ptr; https://github.com/facebook/rocksdb/issues/13 std::__uniq_ptr_impl<rocksdb::ColumnFamilySet, std::default_delete<rocksdb::ColumnFamilySet> >::reset (this=0x7b5800000940, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:182 182 _M_deleter()(__old_p); https://github.com/facebook/rocksdb/issues/14 std::unique_ptr<rocksdb::ColumnFamilySet, std::default_delete<rocksdb::ColumnFamilySet> >::reset (this=0x7b5800000940, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:456 456 _M_t.reset(std::move(__p)); https://github.com/facebook/rocksdb/issues/15 rocksdb::VersionSet::~VersionSet (this=this@entry=0x7b5800000900) at db/version_set.cc:5081 5081 column_family_set_.reset(); https://github.com/facebook/rocksdb/issues/16 0x00007fac44e0f97a in rocksdb::VersionSet::~VersionSet (this=0x7b5800000900) at db/version_set.cc:5078 5078 VersionSet::~VersionSet() { https://github.com/facebook/rocksdb/issues/17 0x00007fac44bf0b2f in std::default_delete<rocksdb::VersionSet>::operator() (this=0x7b8c00000068, __ptr=0x7b5800000900) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:85 85 delete __ptr; https://github.com/facebook/rocksdb/issues/18 std::__uniq_ptr_impl<rocksdb::VersionSet, std::default_delete<rocksdb::VersionSet> >::reset (this=0x7b8c00000068, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:182 182 _M_deleter()(__old_p); https://github.com/facebook/rocksdb/issues/19 std::unique_ptr<rocksdb::VersionSet, std::default_delete<rocksdb::VersionSet> >::reset (this=0x7b8c00000068, __p=0x0) at /usr/bin/../lib/gcc/x86_64-linux-gnu/11/../../../../include/c++/11/bits/unique_ptr.h:456 456 _M_t.reset(std::move(__p)); https://github.com/facebook/rocksdb/issues/20 rocksdb::DBImpl::CloseHelper (this=this@entry=0x7b8c00000000) at db/db_impl/db_impl.cc:676 676 versions_.reset(); https://github.com/facebook/rocksdb/issues/21 0x00007fac44bf1346 in rocksdb::DBImpl::CloseImpl (this=0x7b8c00000000) at db/db_impl/db_impl.cc:720 720 Status DBImpl::CloseImpl() { return CloseHelper(); } https://github.com/facebook/rocksdb/issues/22 rocksdb::DBImpl::~DBImpl (this=this@entry=0x7b8c00000000) at db/db_impl/db_impl.cc:738 738 closing_status_ = CloseImpl(); https://github.com/facebook/rocksdb/issues/23 0x00007fac44bf2bba in rocksdb::DBImpl::~DBImpl (this=0x7b8c00000000) at db/db_impl/db_impl.cc:722 722 DBImpl::~DBImpl() { https://github.com/facebook/rocksdb/issues/24 0x00007fac455444d4 in rocksdb::DBTestBase::Close (this=this@entry=0x7b6c00000000) at db/db_test_util.cc:678 678 delete db_; https://github.com/facebook/rocksdb/issues/25 0x00007fac455455fb in rocksdb::DBTestBase::TryReopen (this=this@entry=0x7b6c00000000, options=...) at db/db_test_util.cc:707 707 Close(); https://github.com/facebook/rocksdb/issues/26 0x00007fac45543459 in rocksdb::DBTestBase::Reopen (this=0x7ffed74b79a0, options=...) at db/db_test_util.cc:670 670 ASSERT_OK(TryReopen(options)); https://github.com/facebook/rocksdb/issues/27 0x00000000004f2522 in rocksdb::DBErrorHandlingFSTest_AutoRecoverFlushError_Test::TestBody (this=this@entry=0x7b6c00000000) at db/error_handler_fs_test.cc:1224 1224 Reopen(options); ``` Reviewed By: jowlyzhang Differential Revision: D49579701 Pulled By: cbi42 fbshipit-source-id: 3fc8325e6dde7e7faa8bcad95060cb4e26eda638
2023-09-25 16:34:39 +00:00
DBRecoverContext()
: flush_reason(FlushReason::kErrorRecovery),
flush_after_recovery(false) {}
DBRecoverContext(FlushReason reason)
: flush_reason(reason), flush_after_recovery(false) {}
};
class ErrorHandler {
public:
ErrorHandler(DBImpl* db, const ImmutableDBOptions& db_options,
InstrumentedMutex* db_mutex)
: db_(db),
db_options_(db_options),
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),
is_db_stopped_(false),
bg_error_stats_(db_options.statistics) {
// Clear the checked flag for uninitialized errors
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);
const Status& SetBGError(const Status& bg_err, BackgroundErrorReason reason);
Status GetBGError() const { return bg_error_; }
Status GetRecoveryError() const { return recovery_error_; }
Status ClearBGError();
bool IsDBStopped() { return is_db_stopped_.load(std::memory_order_acquire); }
bool IsBGWorkStopped() {
assert(db_mutex_);
db_mutex_->AssertHeld();
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
// background work except 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_;
std::atomic<bool> is_db_stopped_;
// The pointer of DB statistics.
std::shared_ptr<Statistics> bg_error_stats_;
const Status& HandleKnownErrors(const Status& bg_err,
BackgroundErrorReason reason);
Status OverrideNoSpaceError(const Status& bg_error, bool* auto_recovery);
void RecoverFromNoSpace();
const Status& StartRecoverFromRetryableBGIOError(const IOStatus& io_error);
void RecoverFromRetryableBGIOError();
// First, if it is in recovery and the recovery_error is ok. Set the
// recovery_error_ to bg_err. Second, if the severity is higher than the
// current bg_error_, overwrite it.
void CheckAndSetRecoveryAndBGError(const Status& bg_err);
};
} // namespace ROCKSDB_NAMESPACE