risingwave_backup/
lib.rs

1// Copyright 2025 RisingWave Labs
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#![allow(clippy::derive_partial_eq_without_eq)]
16#![feature(trait_alias)]
17#![feature(type_alias_impl_trait)]
18#![feature(custom_test_frameworks)]
19#![feature(map_try_insert)]
20#![feature(btree_extract_if)]
21#![feature(let_chains)]
22#![feature(error_generic_member_access)]
23#![feature(coverage_attribute)]
24
25pub mod error;
26pub mod meta_snapshot;
27pub mod meta_snapshot_v1;
28pub mod meta_snapshot_v2;
29pub mod storage;
30
31use std::collections::{HashMap, HashSet};
32
33use itertools::Itertools;
34use risingwave_common::RW_VERSION;
35use risingwave_hummock_sdk::state_table_info::StateTableInfo;
36use risingwave_hummock_sdk::version::HummockVersion;
37use risingwave_hummock_sdk::{HummockRawObjectId, HummockVersionId};
38use risingwave_pb::backup_service::{PbMetaSnapshotManifest, PbMetaSnapshotMetadata};
39use serde::{Deserialize, Serialize};
40
41use crate::error::{BackupError, BackupResult};
42
43pub type MetaSnapshotId = u64;
44pub type MetaBackupJobId = u64;
45
46/// `MetaSnapshotMetadata` is metadata of `MetaSnapshot`.
47#[derive(Serialize, Deserialize, Clone)]
48pub struct MetaSnapshotMetadata {
49    pub id: MetaSnapshotId,
50    pub hummock_version_id: HummockVersionId,
51    // rename to `ssts` for backward compatibility
52    #[serde(rename = "ssts")]
53    pub objects: HashSet<HummockRawObjectId>,
54    #[serde(default)]
55    pub format_version: u32,
56    pub remarks: Option<String>,
57    #[serde(default)]
58    pub state_table_info: HashMap<u32, StateTableInfo>,
59    pub rw_version: Option<String>,
60}
61
62impl MetaSnapshotMetadata {
63    pub fn new(
64        id: MetaSnapshotId,
65        v: &HummockVersion,
66        format_version: u32,
67        remarks: Option<String>,
68    ) -> Self {
69        Self {
70            id,
71            hummock_version_id: v.id,
72            objects: v
73                .get_object_ids(false)
74                .map(|object_id| object_id.as_raw())
75                .collect(),
76            format_version,
77            remarks,
78            state_table_info: v
79                .state_table_info
80                .info()
81                .iter()
82                .map(|(id, info)| (id.table_id, info.into()))
83                .collect(),
84            rw_version: Some(RW_VERSION.to_owned()),
85        }
86    }
87}
88
89/// `MetaSnapshotManifest` is the source of truth for valid `MetaSnapshot`.
90#[derive(Serialize, Deserialize, Default, Clone)]
91pub struct MetaSnapshotManifest {
92    pub manifest_id: u64,
93    pub snapshot_metadata: Vec<MetaSnapshotMetadata>,
94}
95
96pub fn xxhash64_checksum(data: &[u8]) -> u64 {
97    twox_hash::XxHash64::oneshot(0, data)
98}
99
100pub fn xxhash64_verify(data: &[u8], checksum: u64) -> BackupResult<()> {
101    let data_checksum = xxhash64_checksum(data);
102    if data_checksum != checksum {
103        return Err(BackupError::ChecksumMismatch {
104            expected: checksum,
105            found: data_checksum,
106        });
107    }
108    Ok(())
109}
110
111impl From<&MetaSnapshotMetadata> for PbMetaSnapshotMetadata {
112    fn from(m: &MetaSnapshotMetadata) -> Self {
113        Self {
114            id: m.id,
115            hummock_version_id: m.hummock_version_id.to_u64(),
116            format_version: Some(m.format_version),
117            remarks: m.remarks.clone(),
118            state_table_info: m
119                .state_table_info
120                .iter()
121                .map(|(t, i)| (*t, i.into()))
122                .collect(),
123            rw_version: m.rw_version.clone(),
124        }
125    }
126}
127
128impl From<&MetaSnapshotManifest> for PbMetaSnapshotManifest {
129    fn from(m: &MetaSnapshotManifest) -> Self {
130        Self {
131            manifest_id: m.manifest_id,
132            snapshot_metadata: m.snapshot_metadata.iter().map_into().collect_vec(),
133        }
134    }
135}