be/src/io/fs/file_range_coalescer.h
Line | Count | Source |
1 | | // Licensed to the Apache Software Foundation (ASF) under one |
2 | | // or more contributor license agreements. See the NOTICE file |
3 | | // distributed with this work for additional information |
4 | | // regarding copyright ownership. The ASF licenses this file |
5 | | // to you under the Apache License, Version 2.0 (the |
6 | | // "License"); you may not use this file except in compliance |
7 | | // with the License. You may obtain a copy of the License at |
8 | | // |
9 | | // http://www.apache.org/licenses/LICENSE-2.0 |
10 | | // |
11 | | // Unless required by applicable law or agreed to in writing, |
12 | | // software distributed under the License is distributed on an |
13 | | // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
14 | | // KIND, either express or implied. See the License for the |
15 | | // specific language governing permissions and limitations |
16 | | // under the License. |
17 | | |
18 | | #pragma once |
19 | | |
20 | | #include <cstddef> |
21 | | #include <vector> |
22 | | |
23 | | #include "common/status.h" |
24 | | |
25 | | namespace doris::io { |
26 | | |
27 | | /// A half-open byte range [offset, offset + size) in one file. |
28 | | struct FileRange { |
29 | | size_t offset {0}; |
30 | | size_t size {0}; |
31 | | |
32 | 1.51k | size_t end() const { return offset + size; } |
33 | | |
34 | 418 | bool operator==(const FileRange&) const = default; |
35 | | }; |
36 | | |
37 | | /// Limits applied while adjacent input ranges are grouped into one physical read. |
38 | | struct FileRangeCoalesceOptions { |
39 | | /// Maximum unread gap that may be included between two input ranges. |
40 | | size_t max_gap_bytes {0}; |
41 | | /// Maximum size of a combined range. One indivisible input may exceed this limit. |
42 | | size_t max_range_bytes {1}; |
43 | | /// Maximum combined-range bytes divided by bytes covered by its input ranges. |
44 | | double max_read_amplification_ratio {1.0}; |
45 | | |
46 | | /// Validate the option values independently of any input ranges. |
47 | | Status validate() const; |
48 | | }; |
49 | | |
50 | | /// Groups sorted file ranges without performing file IO. |
51 | | class FileRangeCoalescer { |
52 | | public: |
53 | | /// `options` must have passed validation. Each input range must be non-empty. Input ranges |
54 | | /// must be sorted by offset and mutually disjoint. Callers establish these invariants before |
55 | | /// entering the hot path. |
56 | | /// `max_range_bytes` limits combining multiple inputs; one indivisible input may be larger and |
57 | | /// is returned unchanged. |
58 | | static std::vector<FileRange> coalesce(const std::vector<FileRange>& input_ranges, |
59 | | const FileRangeCoalesceOptions& options); |
60 | | }; |
61 | | |
62 | | } // namespace doris::io |