|
| 1 | +// Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved. |
| 2 | +// |
| 3 | +// Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +// you may not use this file except in compliance with the License. |
| 5 | +// You may obtain a copy of the License at |
| 6 | +// |
| 7 | +// http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +// |
| 9 | +// Unless required by applicable law or agreed to in writing, software |
| 10 | +// distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +// See the License for the specific language governing permissions and |
| 13 | +// limitations under the License. |
| 14 | + |
| 15 | +#pragma once |
| 16 | + |
| 17 | +#include <functional> |
| 18 | +#include <iostream> |
| 19 | +#include <memory> |
| 20 | +#include <string> |
| 21 | +#include <vector> |
| 22 | +#include "paddle/fluid/distributed/ps.pb.h" |
| 23 | +#include "paddle/fluid/string/string_helper.h" |
| 24 | + |
| 25 | +namespace paddle { |
| 26 | +namespace distributed { |
| 27 | +struct FsDataConverter { |
| 28 | + std::string converter; |
| 29 | + std::string deconverter; |
| 30 | +}; |
| 31 | + |
| 32 | +struct FsChannelConfig { |
| 33 | + std::string path; // path of file |
| 34 | + std::string converter; // data converter |
| 35 | + std::string deconverter; |
| 36 | +}; |
| 37 | + |
| 38 | +class FsReadChannel { |
| 39 | + public: |
| 40 | + FsReadChannel() : _buffer_size(0) {} |
| 41 | + explicit FsReadChannel(uint32_t buffer_size) : _buffer_size(buffer_size) {} |
| 42 | + virtual ~FsReadChannel() {} |
| 43 | + FsReadChannel(FsReadChannel&&) = delete; |
| 44 | + FsReadChannel(const FsReadChannel&) = delete; |
| 45 | + int open(std::shared_ptr<FILE> fp, const FsChannelConfig& config) { |
| 46 | + _file = fp; |
| 47 | + return 0; |
| 48 | + } |
| 49 | + inline int close() { |
| 50 | + _file.reset(); |
| 51 | + return 0; |
| 52 | + } |
| 53 | + |
| 54 | + inline uint32_t read_line(std::string& line_data) { // NOLINT |
| 55 | + line_data.clear(); |
| 56 | + char buffer = '\0'; |
| 57 | + size_t read_count = 0; |
| 58 | + while (1 == fread(&buffer, 1, 1, _file.get()) && buffer != '\n') { |
| 59 | + ++read_count; |
| 60 | + line_data.append(&buffer, 1); |
| 61 | + } |
| 62 | + if (read_count == 0 && buffer != '\n') { |
| 63 | + return -1; |
| 64 | + } |
| 65 | + return 0; |
| 66 | + } |
| 67 | + |
| 68 | + private: |
| 69 | + uint32_t _buffer_size; |
| 70 | + FsChannelConfig _config; |
| 71 | + std::shared_ptr<FILE> _file; |
| 72 | +}; |
| 73 | +class FsWriteChannel { |
| 74 | + public: |
| 75 | + FsWriteChannel() : _buffer_size(0) {} |
| 76 | + explicit FsWriteChannel(uint32_t buffer_size) : _buffer_size(buffer_size) {} |
| 77 | + virtual ~FsWriteChannel() {} |
| 78 | + FsWriteChannel(FsWriteChannel&&) = delete; |
| 79 | + FsWriteChannel(const FsWriteChannel&) = delete; |
| 80 | + |
| 81 | + int open(std::shared_ptr<FILE> fp, const FsChannelConfig& config) { |
| 82 | + _file = fp; |
| 83 | + |
| 84 | + // the buffer has set in fs.cc |
| 85 | + // if (_buffer_size != 0) { |
| 86 | + // _buffer = std::shared_ptr<char>(new char[_buffer_size]); |
| 87 | + |
| 88 | + // CHECK(0 == setvbuf(&*_file, _buffer.get(), _IOFBF, _buffer_size)); |
| 89 | + //} |
| 90 | + return 0; |
| 91 | + } |
| 92 | + |
| 93 | + inline void flush() { return; } |
| 94 | + |
| 95 | + inline int close() { |
| 96 | + flush(); |
| 97 | + _file.reset(); |
| 98 | + return 0; |
| 99 | + } |
| 100 | + |
| 101 | + inline uint32_t write_line(const char* data, uint32_t size) { |
| 102 | + size_t write_count = fwrite_unlocked(data, 1, size, _file.get()); |
| 103 | + if (write_count != size) { |
| 104 | + return -1; |
| 105 | + } |
| 106 | + write_count = fwrite_unlocked("\n", 1, 1, _file.get()); |
| 107 | + if (write_count != 1) { |
| 108 | + return -1; |
| 109 | + } |
| 110 | + return 0; |
| 111 | + } |
| 112 | + inline uint32_t write_line(const std::string& data) { |
| 113 | + return write_line(data.c_str(), data.size()); |
| 114 | + } |
| 115 | + |
| 116 | + private: |
| 117 | + uint32_t _buffer_size; |
| 118 | + FsChannelConfig _config; |
| 119 | + std::shared_ptr<FILE> _file; |
| 120 | + std::shared_ptr<char> _buffer; |
| 121 | +}; |
| 122 | + |
| 123 | +class AfsClient { |
| 124 | + public: |
| 125 | + AfsClient() {} |
| 126 | + virtual ~AfsClient() {} |
| 127 | + AfsClient(AfsClient&&) = delete; |
| 128 | + AfsClient(const AfsClient&) = delete; |
| 129 | + |
| 130 | + int initialize(const FsClientParameter& fs_client_param); |
| 131 | + int initialize(const std::string& hadoop_bin, const std::string& uri, |
| 132 | + const std::string& user, const std::string& passwd, |
| 133 | + int buffer_size_param = (1L << 25)); |
| 134 | + int initialize(const std::string& hadoop_bin, const std::string& uri, |
| 135 | + const std::string& ugi, int buffer_size_param = (1L << 25)); |
| 136 | + |
| 137 | + // open file in 'w' or 'r' |
| 138 | + std::shared_ptr<FsReadChannel> open_r(const FsChannelConfig& config, |
| 139 | + uint32_t buffer_size = 0, |
| 140 | + int* err_no = nullptr); |
| 141 | + std::shared_ptr<FsWriteChannel> open_w(const FsChannelConfig& config, |
| 142 | + uint32_t buffer_size = 0, |
| 143 | + int* err_no = nullptr); |
| 144 | + |
| 145 | + // remove file in path, path maybe a reg, such as 'part-000-*' |
| 146 | + void remove(const std::string& path); |
| 147 | + void remove_dir(const std::string& dir); |
| 148 | + |
| 149 | + // list files in path, path maybe a dir with reg |
| 150 | + std::vector<std::string> list(const std::string& path); |
| 151 | + |
| 152 | + // exist or not |
| 153 | + bool exist(const std::string& dir); |
| 154 | +}; |
| 155 | +} // namespace distributed |
| 156 | +} // namespace paddle |
0 commit comments