summaryrefslogtreecommitdiff
path: root/src/mongo/db/sorter/sorted_file_writer.h
blob: ba82676e49b5538101bccbdbe5f437c47c516b4b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
/**
 *    Copyright (C) 2021-present MongoDB, Inc.
 *
 *    This program is free software: you can redistribute it and/or modify
 *    it under the terms of the Server Side Public License, version 1,
 *    as published by MongoDB, Inc.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    Server Side Public License for more details.
 *
 *    You should have received a copy of the Server Side Public License
 *    along with this program. If not, see
 *    <http://www.mongodb.com/licensing/server-side-public-license>.
 *
 *    As a special exception, the copyright holders give permission to link the
 *    code of portions of this program with the OpenSSL library under certain
 *    conditions as described in each individual source file and distribute
 *    linked combinations including the program with the OpenSSL library. You
 *    must comply with the Server Side Public License in all respects for
 *    all of the code used other than as permitted herein. If you modify file(s)
 *    with this exception, you may extend this exception to your version of the
 *    file(s), but you are not obligated to do so. If you do not wish to do so,
 *    delete this exception statement from your version. If you delete this
 *    exception statement from all source files in the program, then also delete
 *    it in the license file.
 */

#pragma once

#include "mongo/db/sorter/file.h"
#include "mongo/db/sorter/file_iterator.h"
#include "mongo/db/sorter/options.h"
#include "mongo/db/sorter/sorted_data_iterator.h"
#include "mongo/db/sorter/util.h"
#include "mongo/s/is_mongos.h"

namespace mongo::sorter {
template <typename Key, typename Value>
class SortedFileWriter {
public:
    using Iterator = SortedDataIterator<Key, Value>;
    using Settings = std::pair<typename Key::SorterDeserializeSettings,
                               typename Value::SorterDeserializeSettings>;

    SortedFileWriter(File* file,
                     const boost::optional<std::string>& dbName = boost::none,
                     const Settings& settings = Settings())
        : _settings(settings),
          _file(file),
          _fileStartOffset(_file->currentOffset()),
          _dbName(dbName) {
        invariant(!isMongos());
    }

    SortedFileWriter(const SortedFileWriter&) = delete;
    SortedFileWriter& operator=(const SortedFileWriter&) = delete;

    void addAlreadySorted(const Key& key, const Value& val) {
        // Offset that points to the place in the buffer where a new data object will be stored.
        int nextObjPos = _buffer.len();

        // Add serialized key and value to the buffer.
        key.serializeForSorter(_buffer);
        val.serializeForSorter(_buffer);

        // Serializing the key and value grows the buffer, but _buffer.buf() still points to the
        // beginning. Use _buffer.len() to determine portion of buffer containing new datum.
        _checksum =
            addDataToChecksum(_buffer.buf() + nextObjPos, _buffer.len() - nextObjPos, _checksum);

        if (_buffer.len() > 64 * 1024) {
            _spill();
        }
    }

    std::unique_ptr<Iterator> done() {
        _spill();

        return std::make_unique<FileIterator<Key, Value>>(
            _file, _fileStartOffset, _file->currentOffset(), _checksum, _settings, _dbName);
    }

private:
    void _spill() {
        int32_t size = _buffer.len();
        char* outBuffer = _buffer.buf();

        if (size == 0) {
            return;
        }

        std::string compressed;
        compress(outBuffer, size, &compressed);
        invariant(compressed.size() <= size_t(std::numeric_limits<int32_t>::max()));

        const bool shouldCompress = compressed.size() < size_t(_buffer.len() / 10 * 9);
        if (shouldCompress) {
            size = compressed.size();
            outBuffer = const_cast<char*>(compressed.data());
        }

        std::unique_ptr<char[]> out;
        if (auto encryptionHooks = getEncryptionHooksIfEnabled()) {
            size_t protectedSizeMax = size + encryptionHooks->additionalBytesForProtectedBuffer();
            out.reset(new char[protectedSizeMax]);
            size_t resultLen;
            Status status =
                encryptionHooks->protectTmpData(reinterpret_cast<const uint8_t*>(outBuffer),
                                                size,
                                                reinterpret_cast<uint8_t*>(out.get()),
                                                protectedSizeMax,
                                                &resultLen,
                                                _dbName);
            uassert(28842,
                    str::stream() << "Failed to compress data: " << status.toString(),
                    status.isOK());
            outBuffer = out.get();
            size = resultLen;
        }

        // Negative size means compressed.
        size = shouldCompress ? -size : size;
        _file->write(reinterpret_cast<const char*>(&size), sizeof(size));
        _file->write(outBuffer, std::abs(size));

        _buffer.reset();
    }

    const Settings _settings;
    File* _file;
    BufBuilder _buffer;

    // Keeps track of the hash of all data objects spilled to disk. Passed to the FileIterator
    // to ensure data has not been corrupted after reading from disk.
    uint32_t _checksum = 0;

    // Tracks where in the file we started writing the sorted data range so that the information can
    // be given to the Iterator in done().
    std::streamoff _fileStartOffset;

    boost::optional<std::string> _dbName;
};
}  // namespace mongo::sorter