rocksdb/file/file_util.cc

190 lines
6.3 KiB
C++
Raw Normal View History

// 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).
//
#include "file/file_util.h"
#include <string>
#include <algorithm>
#include "file/random_access_file_reader.h"
#include "file/sequence_file_reader.h"
#include "file/sst_file_manager_impl.h"
#include "file/writable_file_writer.h"
#include "rocksdb/env.h"
namespace ROCKSDB_NAMESPACE {
// Utility function to copy a file up to a specified length
IOStatus CopyFile(FileSystem* fs, const std::string& source,
const std::string& destination, uint64_t size,
bool use_fsync) {
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
const FileOptions soptions;
IOStatus io_s;
std::unique_ptr<SequentialFileReader> src_reader;
std::unique_ptr<WritableFileWriter> dest_writer;
{
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
std::unique_ptr<FSSequentialFile> srcfile;
io_s = fs->NewSequentialFile(source, soptions, &srcfile, nullptr);
if (!io_s.ok()) {
return io_s;
}
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
std::unique_ptr<FSWritableFile> destfile;
io_s = fs->NewWritableFile(destination, soptions, &destfile, nullptr);
if (!io_s.ok()) {
return io_s;
}
if (size == 0) {
// default argument means copy everything
io_s = fs->GetFileSize(source, IOOptions(), &size, nullptr);
if (!io_s.ok()) {
return io_s;
}
}
src_reader.reset(new SequentialFileReader(std::move(srcfile), source));
dest_writer.reset(
new WritableFileWriter(std::move(destfile), destination, soptions));
}
char buffer[4096];
Slice slice;
while (size > 0) {
size_t bytes_to_read = std::min(sizeof(buffer), static_cast<size_t>(size));
io_s = status_to_io_status(src_reader->Read(bytes_to_read, &slice, buffer));
if (!io_s.ok()) {
return io_s;
}
if (slice.size() == 0) {
return IOStatus::Corruption("file too small");
}
io_s = dest_writer->Append(slice);
if (!io_s.ok()) {
return io_s;
}
size -= slice.size();
}
return dest_writer->Sync(use_fsync);
}
// Utility function to create a file with the provided contents
IOStatus CreateFile(FileSystem* fs, const std::string& destination,
const std::string& contents, bool use_fsync) {
const EnvOptions soptions;
IOStatus io_s;
std::unique_ptr<WritableFileWriter> dest_writer;
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
std::unique_ptr<FSWritableFile> destfile;
io_s = fs->NewWritableFile(destination, soptions, &destfile, nullptr);
if (!io_s.ok()) {
return io_s;
}
dest_writer.reset(
new WritableFileWriter(std::move(destfile), destination, soptions));
io_s = dest_writer->Append(Slice(contents));
if (!io_s.ok()) {
return io_s;
}
return dest_writer->Sync(use_fsync);
}
Status DeleteDBFile(const ImmutableDBOptions* db_options,
const std::string& fname, const std::string& dir_to_sync,
const bool force_bg, const bool force_fg) {
#ifndef ROCKSDB_LITE
SstFileManagerImpl* sfm =
static_cast<SstFileManagerImpl*>(db_options->sst_file_manager.get());
if (sfm && !force_fg) {
return sfm->ScheduleFileDeletion(fname, dir_to_sync, force_bg);
} else {
return db_options->env->DeleteFile(fname);
}
#else
(void)dir_to_sync;
(void)force_bg;
(void)force_fg;
// SstFileManager is not supported in ROCKSDB_LITE
// Delete file immediately
return db_options->env->DeleteFile(fname);
#endif
}
bool IsWalDirSameAsDBPath(const ImmutableDBOptions* db_options) {
bool same = false;
assert(!db_options->db_paths.empty());
Status s = db_options->env->AreFilesSame(db_options->wal_dir,
db_options->db_paths[0].path, &same);
if (s.IsNotSupported()) {
same = db_options->wal_dir == db_options->db_paths[0].path;
}
return same;
}
Ingest SST files with checksum information (#6891) Summary: Application can ingest SST files with file checksum information, such that during ingestion, DB is able to check data integrity and identify of the SST file. The PR introduces generate_and_verify_file_checksum to IngestExternalFileOption to control if the ingested checksum information should be verified with the generated checksum. 1. If generate_and_verify_file_checksum options is *FALSE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enables the SST file checksum and the checksum function name matches the checksum function name in DB, we trust the ingested checksum, store it in Manifest. If the checksum function name does not match, we treat that as an error and fail the IngestExternalFile() call. 2. If generate_and_verify_file_checksum options is *TRUE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enable the SST file checksum, we will use the checksum generator from DB to calculate the checksum for each ingested SST files after they are copied or moved. Then, compare the checksum results with the ingested checksum information: _A)_ if the checksum function name does not match, _verification always report true_ and we store the DB generated checksum information in Manifest. _B)_ if the checksum function name mach, and checksum match, ingestion continues and stores the checksum information in the Manifest. Otherwise, terminate file ingestion and report file corruption. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6891 Test Plan: added unit test, pass make asan_check Reviewed By: pdillinger Differential Revision: D21935988 Pulled By: zhichao-cao fbshipit-source-id: 7b55f486632db467e76d72602218d0658aa7f6ed
2020-06-11 21:25:01 +00:00
IOStatus GenerateOneFileChecksum(FileSystem* fs, const std::string& file_path,
FileChecksumGenFactory* checksum_factory,
std::string* file_checksum,
std::string* file_checksum_func_name,
size_t verify_checksums_readahead_size,
bool allow_mmap_reads) {
if (checksum_factory == nullptr) {
return IOStatus::InvalidArgument("Checksum factory is invalid");
}
assert(file_checksum != nullptr);
assert(file_checksum_func_name != nullptr);
FileChecksumGenContext gen_context;
std::unique_ptr<FileChecksumGenerator> checksum_generator =
checksum_factory->CreateFileChecksumGenerator(gen_context);
uint64_t size;
IOStatus io_s;
std::unique_ptr<RandomAccessFileReader> reader;
{
std::unique_ptr<FSRandomAccessFile> r_file;
io_s = fs->NewRandomAccessFile(file_path, FileOptions(), &r_file, nullptr);
if (!io_s.ok()) {
return io_s;
}
io_s = fs->GetFileSize(file_path, IOOptions(), &size, nullptr);
if (!io_s.ok()) {
return io_s;
}
reader.reset(new RandomAccessFileReader(std::move(r_file), file_path));
}
// Found that 256 KB readahead size provides the best performance, based on
// experiments, for auto readahead. Experiment data is in PR #3282.
size_t default_max_read_ahead_size = 256 * 1024;
size_t readahead_size = (verify_checksums_readahead_size != 0)
? verify_checksums_readahead_size
: default_max_read_ahead_size;
FilePrefetchBuffer prefetch_buffer(
reader.get(), readahead_size /* readadhead_size */,
readahead_size /* max_readahead_size */, !allow_mmap_reads /* enable */);
Slice slice;
uint64_t offset = 0;
while (size > 0) {
size_t bytes_to_read =
static_cast<size_t>(std::min(uint64_t{readahead_size}, size));
if (!prefetch_buffer.TryReadFromCache(offset, bytes_to_read, &slice,
false)) {
return IOStatus::Corruption("file read failed");
}
if (slice.size() == 0) {
return IOStatus::Corruption("file too small");
}
checksum_generator->Update(slice.data(), slice.size());
size -= slice.size();
offset += slice.size();
}
checksum_generator->Finalize();
*file_checksum = checksum_generator->GetChecksum();
*file_checksum_func_name = checksum_generator->Name();
return IOStatus::OK();
}
} // namespace ROCKSDB_NAMESPACE