rocksdb/table/sst_file_reader.cc

92 lines
3.1 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).
#ifndef ROCKSDB_LITE
#include "rocksdb/sst_file_reader.h"
#include "db/db_iter.h"
#include "db/dbformat.h"
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
#include "env/composite_env_wrapper.h"
#include "file/random_access_file_reader.h"
#include "options/cf_options.h"
#include "table/get_context.h"
#include "table/table_builder.h"
#include "table/table_reader.h"
namespace rocksdb {
struct SstFileReader::Rep {
Options options;
EnvOptions soptions;
ImmutableCFOptions ioptions;
MutableCFOptions moptions;
std::unique_ptr<TableReader> table_reader;
Rep(const Options& opts)
: options(opts),
soptions(options),
ioptions(options),
moptions(ColumnFamilyOptions(options)) {}
};
SstFileReader::SstFileReader(const Options& options) : rep_(new Rep(options)) {}
SstFileReader::~SstFileReader() {}
Status SstFileReader::Open(const std::string& file_path) {
auto r = rep_.get();
Status s;
uint64_t file_size = 0;
std::unique_ptr<RandomAccessFile> file;
std::unique_ptr<RandomAccessFileReader> file_reader;
s = r->options.env->GetFileSize(file_path, &file_size);
if (s.ok()) {
s = r->options.env->NewRandomAccessFile(file_path, &file, r->soptions);
}
if (s.ok()) {
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
file_reader.reset(new RandomAccessFileReader(
NewLegacyRandomAccessFileWrapper(file), file_path));
}
if (s.ok()) {
TableReaderOptions t_opt(r->ioptions, r->moptions.prefix_extractor.get(),
r->soptions, r->ioptions.internal_comparator);
// Allow open file with global sequence number for backward compatibility.
t_opt.largest_seqno = kMaxSequenceNumber;
s = r->options.table_factory->NewTableReader(t_opt, std::move(file_reader),
file_size, &r->table_reader);
}
return s;
}
Iterator* SstFileReader::NewIterator(const ReadOptions& options) {
auto r = rep_.get();
auto sequence = options.snapshot != nullptr
? options.snapshot->GetSequenceNumber()
: kMaxSequenceNumber;
auto internal_iter = r->table_reader->NewIterator(
options, r->moptions.prefix_extractor.get(), /*arena=*/nullptr,
/*skip_filters=*/false, TableReaderCaller::kSSTFileReader);
return NewDBIterator(r->options.env, options, r->ioptions, r->moptions,
r->ioptions.user_comparator, internal_iter, sequence,
r->moptions.max_sequential_skip_in_iterations,
nullptr /* read_callback */);
}
std::shared_ptr<const TableProperties> SstFileReader::GetTableProperties()
const {
return rep_->table_reader->GetTableProperties();
}
Status SstFileReader::VerifyChecksum(const ReadOptions& read_options) {
return rep_->table_reader->VerifyChecksum(read_options,
TableReaderCaller::kSSTFileReader);
}
} // namespace rocksdb
#endif // !ROCKSDB_LITE