Summary:
Part of the procedures to handle manifest IO error is to disable file deletion in case some files in limbo state get deleted prematurely. This is not ideal because: 1) not all the VersionEdits whose commit encounter such an error contain updates for files, disabling file deletion sometimes are not necessary. 2) `EnableFileDeletion` has a force mode that could make other threads accidentally disrupt this procedure in recovery. 3) Disabling file deletion as a whole is also not as efficient as more precisely tracking impacted files from being prematurely deleted. This PR replaces this mechanism with tracking such files and quarantine them from being deleted in `ErrorHandler`.
These are the types of files being actively tracked in quarantine in this PR:
1) new table files and blob files from a background job
2) old manifest file whose immediately following new manifest file's CURRENT file creation gets into unclear state. Current handling is not sufficient to make sure the old manifest file is kept in case it's needed.
Note that WAL logs are not part of the quarantine because `min_log_number_to_keep` is a safe mechanism and it's only updated after successful manifest commits so it can prevent this premature deletion issue from happening.
We track these files' file numbers because they share the same file number space.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12030
Test Plan: Modified existing unit tests
Reviewed By: ajkr
Differential Revision: D51036774
Pulled By: jowlyzhang
fbshipit-source-id: 84ef26271fbbc888ef70da5c40fe843bd7038716
Summary:
A race condition between recovery and backup can happen with error messages like this:
```Failure in BackupEngine::CreateNewBackup with: IO error: No such file or directory: While opening a file for sequentially reading: /dev/shm/rocksdb_test/rocksdb_crashtest_whitebox/002653.log: No such file or directory```
PR https://github.com/facebook/rocksdb/issues/6949 introduced disabling file deletion during error handling of manifest IO errors. Aformentioned race condition is caused by this chain of event:
[Backup engine] disable file deletion
[Recovery] disable file deletion <= this is optional for the race condition, it may or may not get called
[Backup engine] get list of file to copy/link
[Recovery] force enable file deletion
.... some files refered by backup engine get deleted
[Backup engine] copy/link file <= error no file found
This PR fixes this with:
1) Recovery thread is currently forcing enabling file deletion as long as file deletion is disabled. Regardless of whether the previous error handling is for manifest IO error and that disabled it in the first place. This means it could incorrectly enabling file deletions intended by other threads like backup threads, file snapshotting threads. This PR does this check explicitly before making the call.
2) `disable_delete_obsolete_files_` is designed as a counter to allow different threads to enable and disable file deletion separately. The recovery thread currently does a force enable file deletion, because `ErrorHandler::SetBGError()` can be called multiple times by different threads when they receive a manifest IO error(details per PR https://github.com/facebook/rocksdb/issues/6949), resulting in `DBImpl::DisableFileDeletions` to be called multiple times too. Making a force enable file deletion call that resets the counter `disable_delete_obsolete_files_` to zero is a workaround for this. However, as it shows in the race condition, it can incorrectly suppress other threads like a backup thread's intention to keep the file deletion disabled. <strike>This PR adds a `std::atomic<int> disable_file_deletion_count_` to the error handler to track the needed counter decrease more precisely</strike>. This PR tracks and caps file deletion enabling/disabling in error handler.
3) for recovery, the section to find obsolete files and purge them was moved to be done after the attempt to enable file deletion. The actual finding and purging is more likely to happen if file deletion was previously disabled and get re-enabled now. An internal function `DBImpl::EnableFileDeletionsWithLock` was added to support change 2) and 3). Some useful logging was explicitly added to keep those log messages around.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11955
Test Plan: existing unit tests
Reviewed By: anand1976
Differential Revision: D50290592
Pulled By: jowlyzhang
fbshipit-source-id: 73aa8331ca4d636955a5b0324b1e104a26e00c9b
Summary:
cbi42 pointed out a race condition in which `recovery_io_error_` and `recovery_error_` could be updated inconsistently due to releasing the DB mutex in `EventHelpers::NotifyOnBackgroundError()`. There doesn't seem to be a point to having two status objects, so this PR consolidates them.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11937
Reviewed By: cbi42
Differential Revision: D50105793
Pulled By: ajkr
fbshipit-source-id: 3de95baccfa44351a49a5c2aa0986c9bc81baa8f
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: 49da91ec09/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: 49da91ec09/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
Summary:
Ran `find ./db/ -type f | xargs clang-format -i`. Excluded minor changes it tried to make on db/db_impl/. Everything else it changed was directly under db/ directory. Included minor manual touchups mentioned in PR commit history.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10910
Reviewed By: riversand963
Differential Revision: D40880683
Pulled By: ajkr
fbshipit-source-id: cfe26cda05b3fb9a72e3cb82c286e21d8c5c4174
Summary:
## Problem Summary
RocksDB will acquire the global mutex of db instance for every time when user calls `Write`. When RocksDB schedules a lot of compaction jobs, it will compete the mutex with write thread and it will hurt the write performance.
## Problem Solution:
I want to use log_write_mutex to replace the global mutex in most case so that we do not acquire it in write-thread unless there is a write-stall event or a write-buffer-full event occur.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7516
Test Plan:
1. make check
2. CI
3. COMPILE_WITH_TSAN=1 make db_stress
make crash_test
make crash_test_with_multiops_wp_txn
make crash_test_with_multiops_wc_txn
make crash_test_with_atomic_flush
Reviewed By: siying
Differential Revision: D36908702
Pulled By: riversand963
fbshipit-source-id: 59b13881f4f5c0a58fd3ca79128a396d9cd98efe
Summary:
Fix and enhance the background error recovery logic to handle the
following situations -
1. Background read errors during flush/compaction (previously was
resulting in unrecoverable state)
2. Fix auto recovery failure on read/write errors during atomic flush.
It was failing due to a bug in setting the resuming_from_bg_err variable
in AtomicFlushMemTablesToOutputFiles.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9679
Test Plan: Add new unit tests in error_handler_fs_test
Reviewed By: riversand963
Differential Revision: D34770097
Pulled By: anand1976
fbshipit-source-id: 136da973a28d684b9c74bdf668519b0cbbbe1742
Summary:
Add statistics and info log for error handler: counters for bg error, bg io error, bg retryable io error, auto resume, auto resume total retry, and auto resume sucess; Histogram for auto resume retry count in each recovery call.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8050
Test Plan: make check and add test to error_handler_fs_test
Reviewed By: anand1976
Differential Revision: D26990565
Pulled By: zhichao-cao
fbshipit-source-id: 49f71e8ea4e9db8b189943976404205b56ab883f
Summary:
This change eliminates the need for a lot of the PermitUncheckedError calls on return from ErrorHandler methods. The calls are no longer needed as the status is returned as a reference rather than a copy. Additionally, this means that the originating status (recovery_error_, bg_error_) is not cleared implicitly as a result of calling one of these methods.
For this class, I do not know if the proper behavior should be to call PermitUncheckedError in the destructor or if the checked state should be cleared when the status is cleared. I did tests both ways. Without the code in the destructor, the status will need to be cleared in at least some of the places where it is set to OK. When running tests, I found no instances where this class was destructed with a non-OK, non-checked Status.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7539
Reviewed By: anand1976
Differential Revision: D25340565
Pulled By: pdillinger
fbshipit-source-id: 1730c035c81a475875ea745226112030ec25136c
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
Summary:
This test uses database functionality and required more extensive work to get it to pass than the other tests. The DB functionality required for this test now passes the check.
When it was unclear what the proper behavior was for unchecked status codes, a TODO was added.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7283
Reviewed By: akankshamahajan15
Differential Revision: D23251497
Pulled By: ajkr
fbshipit-source-id: 52b79629bdafa0a58de8ead1d1d66f141b331523
Summary:
In current codebase, in write path, if Retryable IO Error happens, SetBGError is called. The retryable IO Error is converted to hard error and DB is in read only mode. User or application needs to resume it. In this PR, if Retryable IO Error happens in one DB, SetBGError will create a new thread to call Resume (auto resume). otpions.max_bgerror_resume_count controls if auto resume is enabled or not (if max_bgerror_resume_count<=0, auto resume will not be enabled). options.bgerror_resume_retry_interval controls the time interval to call Resume again if the previous resume fails due to the Retryable IO Error. If non-retryable error happens during resume, auto resume will terminate.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6765
Test Plan: Added the unit test cases in error_handler_fs_test and pass make asan_check
Reviewed By: anand1976
Differential Revision: D21916789
Pulled By: zhichao-cao
fbshipit-source-id: acb8b5e5dc3167adfa9425a5b7fc104f6b95cb0b
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
Summary:
When dynamically linking two binaries together, different builds of RocksDB from two sources might cause errors. To provide a tool for user to solve the problem, the RocksDB namespace is changed to a flag which can be overridden in build time.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6433
Test Plan: Build release, all and jtest. Try to build with ROCKSDB_NAMESPACE with another flag.
Differential Revision: D19977691
fbshipit-source-id: aa7f2d0972e1c31d75339ac48478f34f6cfcfb3e
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
Summary:
Currently, if RocksDB encounters errors during a write operation (user requested or BG operations), it sets DBImpl::bg_error_ and fails subsequent writes. This PR allows the DB to be resumed for certain classes of errors. It consists of 3 parts -
1. Introduce Status::Severity in rocksdb::Status to indicate whether a given error can be recovered from or not
2. Refactor the error handling code so that setting bg_error_ and deciding on severity is in one place
3. Provide an API for the user to clear the error and resume the DB instance
This whole change is broken up into multiple PRs. Initially, we only allow clearing the error for Status::NoSpace() errors during background flush/compaction. Subsequent PRs will expand this to include more errors and foreground operations such as Put(), and implement a polling mechanism for out-of-space errors.
Closes https://github.com/facebook/rocksdb/pull/3997
Differential Revision: D8653831
Pulled By: anand1976
fbshipit-source-id: 6dc835c76122443a7668497c0226b4f072bc6afd
Yu Zhang