rocksdb/db/repair_test.cc

391 lines
13 KiB
C++
Raw Normal View History

// Copyright (c) 2016-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).
#ifndef ROCKSDB_LITE
#include <algorithm>
#include <string>
#include <vector>
#include "db/db_impl/db_impl.h"
#include "db/db_test_util.h"
#include "file/file_util.h"
#include "rocksdb/comparator.h"
#include "rocksdb/db.h"
#include "rocksdb/transaction_log.h"
#include "util/string_util.h"
namespace ROCKSDB_NAMESPACE {
#ifndef ROCKSDB_LITE
class RepairTest : public DBTestBase {
public:
RepairTest() : DBTestBase("/repair_test", /*env_do_fsync=*/true) {}
Status GetFirstSstPath(std::string* first_sst_path) {
assert(first_sst_path != nullptr);
first_sst_path->clear();
uint64_t manifest_size;
std::vector<std::string> files;
Status s = db_->GetLiveFiles(files, &manifest_size);
if (s.ok()) {
auto sst_iter =
std::find_if(files.begin(), files.end(), [](const std::string& file) {
uint64_t number;
FileType type;
bool ok = ParseFileName(file, &number, &type);
return ok && type == kTableFile;
});
*first_sst_path = sst_iter == files.end() ? "" : dbname_ + *sst_iter;
}
return s;
}
};
TEST_F(RepairTest, LostManifest) {
// Add a couple SST files, delete the manifest, and verify RepairDB() saves
// the day.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
// Need to get path before Close() deletes db_, but delete it after Close() to
// ensure Close() didn't change the manifest.
std::string manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(manifest_path));
ASSERT_OK(env_->DeleteFile(manifest_path));
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
ASSERT_EQ(Get("key"), "val");
ASSERT_EQ(Get("key2"), "val2");
}
TEST_F(RepairTest, CorruptManifest) {
// Manifest is in an invalid format. Expect a full recovery.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
// Need to get path before Close() deletes db_, but overwrite it after Close()
// to ensure Close() didn't change the manifest.
std::string manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(manifest_path));
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 22:47:08 +00:00
Create a CustomEnv class; Add WinFileSystem; Make LegacyFileSystemWrapper private (#7703) Summary: This PR does the following: -> Creates a WinFileSystem class. This class is the Windows equivalent of the PosixFileSystem and will be used on Windows systems. -> Introduces a CustomEnv class. A CustomEnv is an Env that takes a FileSystem as constructor argument. I believe there will only ever be two implementations of this class (PosixEnv and WinEnv). There is still a CustomEnvWrapper class that takes an Env and a FileSystem and wraps the Env calls with the input Env but uses the FileSystem for the FileSystem calls -> Eliminates the public uses of the LegacyFileSystemWrapper. With this change in place, there are effectively the following patterns of Env: - "Base Env classes" (PosixEnv, WinEnv). These classes implement the core Env functions (e.g. Threads) and have a hard-coded input FileSystem. These classes inherit from CompositeEnv, implement the core Env functions (threads) and delegate the FileSystem-like calls to the input file system. - Wrapped Composite Env classes (MemEnv). These classes take in an Env and a FileSystem. The core env functions are re-directed to the wrapped env. The file system calls are redirected to the input file system - Legacy Wrapped Env classes. These classes take in an Env input (but no FileSystem). The core env functions are re-directed to the wrapped env. A "Legacy File System" is created using this env and the file system calls directed to the env itself. With these changes in place, the PosixEnv becomes a singleton -- there is only ever one created. Any other use of the PosixEnv is via another wrapped env. This cleans up some of the issues with the env construction and destruction. Additionally, there were places in the code that required had an Env when they required a FileSystem. Many of these places would wrap the Env with a LegacyFileSystemWrapper instead of using the env->GetFileSystem(). These places were changed, thereby removing layers of additional redirection (LegacyFileSystem --> Env --> Env::FileSystem). Pull Request resolved: https://github.com/facebook/rocksdb/pull/7703 Reviewed By: zhichao-cao Differential Revision: D25762190 Pulled By: anand1976 fbshipit-source-id: 1a088e97fc916f28ac69c149cd1dcad0ab31704b
2021-01-06 18:48:24 +00:00
ASSERT_OK(CreateFile(env_->GetFileSystem(), manifest_path, "blah",
false /* use_fsync */));
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
ASSERT_EQ(Get("key"), "val");
ASSERT_EQ(Get("key2"), "val2");
}
TEST_F(RepairTest, IncompleteManifest) {
// In this case, the manifest is valid but does not reference all of the SST
// files. Expect a full recovery.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
std::string orig_manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
CopyFile(orig_manifest_path, orig_manifest_path + ".tmp");
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
// Need to get path before Close() deletes db_, but overwrite it after Close()
// to ensure Close() didn't change the manifest.
std::string new_manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(new_manifest_path));
// Replace the manifest with one that is only aware of the first SST file.
CopyFile(orig_manifest_path + ".tmp", new_manifest_path);
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
ASSERT_EQ(Get("key"), "val");
ASSERT_EQ(Get("key2"), "val2");
}
TEST_F(RepairTest, PostRepairSstFileNumbering) {
// Verify after a DB is repaired, new files will be assigned higher numbers
// than old files.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
uint64_t pre_repair_file_num = dbfull()->TEST_Current_Next_FileNo();
Close();
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
uint64_t post_repair_file_num = dbfull()->TEST_Current_Next_FileNo();
ASSERT_GE(post_repair_file_num, pre_repair_file_num);
}
TEST_F(RepairTest, LostSst) {
// Delete one of the SST files but preserve the manifest that refers to it,
// then verify the DB is still usable for the intact SST.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
std::string sst_path;
ASSERT_OK(GetFirstSstPath(&sst_path));
ASSERT_FALSE(sst_path.empty());
ASSERT_OK(env_->DeleteFile(sst_path));
Close();
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
// Exactly one of the key-value pairs should be in the DB now.
ASSERT_TRUE((Get("key") == "val") != (Get("key2") == "val2"));
}
TEST_F(RepairTest, CorruptSst) {
// Corrupt one of the SST files but preserve the manifest that refers to it,
// then verify the DB is still usable for the intact SST.
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
ASSERT_OK(Put("key2", "val2"));
ASSERT_OK(Flush());
std::string sst_path;
ASSERT_OK(GetFirstSstPath(&sst_path));
ASSERT_FALSE(sst_path.empty());
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 22:47:08 +00:00
Create a CustomEnv class; Add WinFileSystem; Make LegacyFileSystemWrapper private (#7703) Summary: This PR does the following: -> Creates a WinFileSystem class. This class is the Windows equivalent of the PosixFileSystem and will be used on Windows systems. -> Introduces a CustomEnv class. A CustomEnv is an Env that takes a FileSystem as constructor argument. I believe there will only ever be two implementations of this class (PosixEnv and WinEnv). There is still a CustomEnvWrapper class that takes an Env and a FileSystem and wraps the Env calls with the input Env but uses the FileSystem for the FileSystem calls -> Eliminates the public uses of the LegacyFileSystemWrapper. With this change in place, there are effectively the following patterns of Env: - "Base Env classes" (PosixEnv, WinEnv). These classes implement the core Env functions (e.g. Threads) and have a hard-coded input FileSystem. These classes inherit from CompositeEnv, implement the core Env functions (threads) and delegate the FileSystem-like calls to the input file system. - Wrapped Composite Env classes (MemEnv). These classes take in an Env and a FileSystem. The core env functions are re-directed to the wrapped env. The file system calls are redirected to the input file system - Legacy Wrapped Env classes. These classes take in an Env input (but no FileSystem). The core env functions are re-directed to the wrapped env. A "Legacy File System" is created using this env and the file system calls directed to the env itself. With these changes in place, the PosixEnv becomes a singleton -- there is only ever one created. Any other use of the PosixEnv is via another wrapped env. This cleans up some of the issues with the env construction and destruction. Additionally, there were places in the code that required had an Env when they required a FileSystem. Many of these places would wrap the Env with a LegacyFileSystemWrapper instead of using the env->GetFileSystem(). These places were changed, thereby removing layers of additional redirection (LegacyFileSystem --> Env --> Env::FileSystem). Pull Request resolved: https://github.com/facebook/rocksdb/pull/7703 Reviewed By: zhichao-cao Differential Revision: D25762190 Pulled By: anand1976 fbshipit-source-id: 1a088e97fc916f28ac69c149cd1dcad0ab31704b
2021-01-06 18:48:24 +00:00
ASSERT_OK(CreateFile(env_->GetFileSystem(), sst_path, "blah",
false /* use_fsync */));
Close();
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
// Exactly one of the key-value pairs should be in the DB now.
ASSERT_TRUE((Get("key") == "val") != (Get("key2") == "val2"));
}
TEST_F(RepairTest, UnflushedSst) {
// This test case invokes repair while some data is unflushed, then verifies
// that data is in the db.
ASSERT_OK(Put("key", "val"));
VectorLogPtr wal_files;
ASSERT_OK(dbfull()->GetSortedWalFiles(wal_files));
ASSERT_EQ(wal_files.size(), 1);
{
uint64_t total_ssts_size;
std::unordered_map<std::string, uint64_t> sst_files;
ASSERT_OK(GetAllDataFiles(kTableFile, &sst_files, &total_ssts_size));
ASSERT_EQ(total_ssts_size, 0);
}
// Need to get path before Close() deletes db_, but delete it after Close() to
// ensure Close() didn't change the manifest.
std::string manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(manifest_path));
ASSERT_OK(env_->DeleteFile(manifest_path));
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
Reopen(CurrentOptions());
ASSERT_OK(dbfull()->GetSortedWalFiles(wal_files));
ASSERT_EQ(wal_files.size(), 0);
{
uint64_t total_ssts_size;
std::unordered_map<std::string, uint64_t> sst_files;
ASSERT_OK(GetAllDataFiles(kTableFile, &sst_files, &total_ssts_size));
ASSERT_GT(total_ssts_size, 0);
}
ASSERT_EQ(Get("key"), "val");
}
TEST_F(RepairTest, SeparateWalDir) {
do {
Options options = CurrentOptions();
DestroyAndReopen(options);
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Put("foo", "bar"));
VectorLogPtr wal_files;
ASSERT_OK(dbfull()->GetSortedWalFiles(wal_files));
ASSERT_EQ(wal_files.size(), 1);
{
uint64_t total_ssts_size;
std::unordered_map<std::string, uint64_t> sst_files;
ASSERT_OK(GetAllDataFiles(kTableFile, &sst_files, &total_ssts_size));
ASSERT_EQ(total_ssts_size, 0);
}
std::string manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(manifest_path));
ASSERT_OK(env_->DeleteFile(manifest_path));
ASSERT_OK(RepairDB(dbname_, options));
// make sure that all WALs are converted to SSTables.
options.wal_dir = "";
Reopen(options);
ASSERT_OK(dbfull()->GetSortedWalFiles(wal_files));
ASSERT_EQ(wal_files.size(), 0);
{
uint64_t total_ssts_size;
std::unordered_map<std::string, uint64_t> sst_files;
ASSERT_OK(GetAllDataFiles(kTableFile, &sst_files, &total_ssts_size));
ASSERT_GT(total_ssts_size, 0);
}
ASSERT_EQ(Get("key"), "val");
ASSERT_EQ(Get("foo"), "bar");
} while(ChangeWalOptions());
}
TEST_F(RepairTest, RepairMultipleColumnFamilies) {
// Verify repair logic associates SST files with their original column
// families.
const int kNumCfs = 3;
const int kEntriesPerCf = 2;
DestroyAndReopen(CurrentOptions());
CreateAndReopenWithCF({"pikachu1", "pikachu2"}, CurrentOptions());
for (int i = 0; i < kNumCfs; ++i) {
for (int j = 0; j < kEntriesPerCf; ++j) {
ASSERT_OK(Put(i, "key" + ToString(j), "val" + ToString(j)));
if (j == kEntriesPerCf - 1 && i == kNumCfs - 1) {
// Leave one unflushed so we can verify WAL entries are properly
// associated with column families.
continue;
}
ASSERT_OK(Flush(i));
}
}
// Need to get path before Close() deletes db_, but delete it after Close() to
// ensure Close() doesn't re-create the manifest.
std::string manifest_path =
DescriptorFileName(dbname_, dbfull()->TEST_Current_Manifest_FileNo());
Close();
ASSERT_OK(env_->FileExists(manifest_path));
ASSERT_OK(env_->DeleteFile(manifest_path));
ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
ReopenWithColumnFamilies({"default", "pikachu1", "pikachu2"},
CurrentOptions());
for (int i = 0; i < kNumCfs; ++i) {
for (int j = 0; j < kEntriesPerCf; ++j) {
ASSERT_EQ(Get(i, "key" + ToString(j)), "val" + ToString(j));
}
}
}
TEST_F(RepairTest, RepairColumnFamilyOptions) {
// Verify repair logic uses correct ColumnFamilyOptions when repairing a
// database with different options for column families.
const int kNumCfs = 2;
const int kEntriesPerCf = 2;
Options opts(CurrentOptions()), rev_opts(CurrentOptions());
opts.comparator = BytewiseComparator();
rev_opts.comparator = ReverseBytewiseComparator();
DestroyAndReopen(opts);
CreateColumnFamilies({"reverse"}, rev_opts);
ReopenWithColumnFamilies({"default", "reverse"},
std::vector<Options>{opts, rev_opts});
for (int i = 0; i < kNumCfs; ++i) {
for (int j = 0; j < kEntriesPerCf; ++j) {
ASSERT_OK(Put(i, "key" + ToString(j), "val" + ToString(j)));
if (i == kNumCfs - 1 && j == kEntriesPerCf - 1) {
// Leave one unflushed so we can verify RepairDB's flush logic
continue;
}
ASSERT_OK(Flush(i));
}
}
Close();
// RepairDB() records the comparator in the manifest, and DB::Open would fail
// if a different comparator were used.
ASSERT_OK(RepairDB(dbname_, opts, {{"default", opts}, {"reverse", rev_opts}},
opts /* unknown_cf_opts */));
ASSERT_OK(TryReopenWithColumnFamilies({"default", "reverse"},
std::vector<Options>{opts, rev_opts}));
for (int i = 0; i < kNumCfs; ++i) {
for (int j = 0; j < kEntriesPerCf; ++j) {
ASSERT_EQ(Get(i, "key" + ToString(j)), "val" + ToString(j));
}
}
// Examine table properties to verify RepairDB() used the right options when
// converting WAL->SST
TablePropertiesCollection fname_to_props;
ASSERT_OK(db_->GetPropertiesOfAllTables(handles_[1], &fname_to_props));
ASSERT_EQ(fname_to_props.size(), 2U);
for (const auto& fname_and_props : fname_to_props) {
std::string comparator_name (
InternalKeyComparator(rev_opts.comparator).Name());
comparator_name = comparator_name.substr(comparator_name.find(':') + 1);
ASSERT_EQ(comparator_name,
fname_and_props.second->comparator_name);
}
Close();
// Also check comparator when it's provided via "unknown" CF options
ASSERT_OK(RepairDB(dbname_, opts, {{"default", opts}},
rev_opts /* unknown_cf_opts */));
ASSERT_OK(TryReopenWithColumnFamilies({"default", "reverse"},
std::vector<Options>{opts, rev_opts}));
for (int i = 0; i < kNumCfs; ++i) {
for (int j = 0; j < kEntriesPerCf; ++j) {
ASSERT_EQ(Get(i, "key" + ToString(j)), "val" + ToString(j));
}
}
}
TEST_F(RepairTest, DbNameContainsTrailingSlash) {
{
bool tmp;
if (env_->AreFilesSame("", "", &tmp).IsNotSupported()) {
fprintf(stderr,
"skipping RepairTest.DbNameContainsTrailingSlash due to "
"unsupported Env::AreFilesSame\n");
return;
}
}
ASSERT_OK(Put("key", "val"));
ASSERT_OK(Flush());
Close();
ASSERT_OK(RepairDB(dbname_ + "/", CurrentOptions()));
Reopen(CurrentOptions());
ASSERT_EQ(Get("key"), "val");
}
#endif // ROCKSDB_LITE
} // namespace ROCKSDB_NAMESPACE
int main(int argc, char** argv) {
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}
#else
#include <stdio.h>
int main(int /*argc*/, char** /*argv*/) {
fprintf(stderr, "SKIPPED as RepairDB is not supported in ROCKSDB_LITE\n");
return 0;
}
#endif // ROCKSDB_LITE