be/src/io/cache/file_range_planner.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 | | #include "io/fs/file_range_coalescer.h" |
25 | | |
26 | | namespace doris::io { |
27 | | |
28 | | struct ReadAheadStatistics; |
29 | | |
30 | | struct FileRangePlanOptions { |
31 | | /// Limits for the initial range coalescing pass. |
32 | | FileRangeCoalesceOptions coalesce_options; |
33 | | /// File Cache block size used when considering boundary-block completion. |
34 | | size_t cache_block_size {1}; |
35 | | /// Minimum input-byte coverage required before completing a boundary block. |
36 | | double block_fill_min_coverage {1.0}; |
37 | | |
38 | | Status validate() const; |
39 | | }; |
40 | | |
41 | | /// The location of one input range in its final read buffer. |
42 | | struct FileRangeLocation { |
43 | | /// Index into FileRangePlan::ranges. |
44 | | size_t range_index {0}; |
45 | | /// Offset of the original input's first byte within that physical range buffer. |
46 | | size_t buffer_offset {0}; |
47 | | |
48 | 42 | bool operator==(const FileRangeLocation&) const = default; |
49 | | }; |
50 | | |
51 | | struct FileRangePlan { |
52 | | /// Physical ranges to read after coalescing and optional cache-block completion. |
53 | | std::vector<FileRange> ranges; |
54 | | /// One location per input in caller-supplied order; every input is contained by that range. |
55 | | std::vector<FileRangeLocation> input_locations; |
56 | | |
57 | 27 | bool operator==(const FileRangePlan&) const = default; |
58 | | }; |
59 | | |
60 | | /// Builds a read-only plan without allocating buffers or performing file IO. |
61 | | class FileRangePlanner { |
62 | | public: |
63 | | /// `input_ranges` must be sorted by offset and mutually disjoint. The planner first coalesces |
64 | | /// them, then completes high-coverage cache blocks when the resulting physical ranges remain |
65 | | /// within `max_range_bytes`. One input larger than that limit remains a standalone read. The |
66 | | /// physical EOF block uses its valid file bytes as the coverage denominator. |
67 | | static Status plan(const std::vector<FileRange>& input_ranges, size_t file_size, |
68 | | const FileRangePlanOptions& options, FileRangePlan* output_plan, |
69 | | ReadAheadStatistics* statistics = nullptr); |
70 | | }; |
71 | | |
72 | | } // namespace doris::io |