优化和收尾

This commit is contained in:
LIm1tZz7 committed 2026-09-25 14:21:55 +08:00
1 parent 7f5bcc289e
commit 9e8c5f1ef0
33 files changed
+3332 -598

No files matched your search

+334
View File
@@ -0,0 +1,334 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "bitflags"
version = "2.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3ded4057c258ba199e2d26386d3af3780957ecaee6c4ef4041c6b4b8b97c0b06"
[[package]]
name = "cfg-if"
version = "1.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4e7648175b45a9a48536d676f68d918270699102aa8dab5496df06904c914600"
[[package]]
name = "chusql-storage"
version = "0.1.0"
dependencies = [
"interprocess",
"serde",
"serde_json",
"toml",
]
[[package]]
name = "chusql-storage-bench"
version = "0.1.0"
dependencies = [
"chusql-storage",
"serde_json",
"tempfile",
]
[[package]]
name = "doctest-file"
version = "1.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2db04e74f0a9a93103b50e90b96024c9b2bdca8bce6a632ec71b88736d3d359"
[[package]]
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "errno"
version = "0.3.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys",
]
[[package]]
name = "fastrand"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da7c62ceae207dd37ea5b845da6a0696c799f85e97da1ab5b7910be3c1c80223"
[[package]]
name = "getrandom"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "300e883d756b2e4ec94e02791f39b04b522276138852cfc41d9fb7e904106099"
dependencies = [
"cfg-if",
"libc",
"r-efi",
]
[[package]]
name = "hashbrown"
version = "0.17.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed5909b6e89a2db4456e54cd5f673791d7eca6732202bbf2a9cc504fe2f9b84a"
[[package]]
name = "indexmap"
version = "2.14.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cc4e190f5d26ca7051642629da2c52fc03bde85a03197c99408dcd291734c855"
dependencies = [
"equivalent",
"hashbrown",
]
[[package]]
name = "interprocess"
version = "2.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6cb02ffbf25e8ef0f4a95bff054eef75f6d1bf16919474cf2caa63b21997478a"
dependencies = [
"doctest-file",
"libc",
"recvmsg",
"widestring",
"windows-sys",
]
[[package]]
name = "itoa"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
[[package]]
name = "libc"
version = "0.2.189"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2"
[[package]]
name = "linux-raw-sys"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
[[package]]
name = "memchr"
version = "2.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
[[package]]
name = "once_cell"
version = "1.21.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
[[package]]
name = "proc-macro2"
version = "1.0.107"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "985e7ec9bb745e6ce6535b544d84d6cd6f7ad8bd711c398938ae983b91a766d9"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.47"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fbf4db142a473a8d80c26bbf18454ed458bf8d26c8219c331daecfdbd079001"
dependencies = [
"proc-macro2",
]
[[package]]
name = "r-efi"
version = "6.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
[[package]]
name = "recvmsg"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d3edd4d5d42c92f0a659926464d4cce56b562761267ecf0f469d85b7de384175"
[[package]]
name = "rustix"
version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
dependencies = [
"bitflags",
"errno",
"libc",
"linux-raw-sys",
"windows-sys",
]
[[package]]
name = "serde"
version = "1.0.229"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
dependencies = [
"serde_core",
"serde_derive",
]
[[package]]
name = "serde_core"
version = "1.0.229"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.229"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.151"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
dependencies = [
"itoa",
"memchr",
"serde",
"serde_core",
"zmij",
]
[[package]]
name = "serde_spanned"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
dependencies = [
"serde",
]
[[package]]
name = "syn"
version = "3.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8593e8e72159ed2257d083c7a454a85cbf854f37a0966d8d483aff8c8a3ebcee"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "tempfile"
version = "3.27.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
dependencies = [
"fastrand",
"getrandom",
"once_cell",
"rustix",
"windows-sys",
]
[[package]]
name = "toml"
version = "0.8.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
dependencies = [
"serde",
"serde_spanned",
"toml_datetime",
"toml_edit",
]
[[package]]
name = "toml_datetime"
version = "0.6.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
dependencies = [
"serde",
]
[[package]]
name = "toml_edit"
version = "0.22.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
dependencies = [
"indexmap",
"serde",
"serde_spanned",
"toml_datetime",
"toml_write",
"winnow",
]
[[package]]
name = "toml_write"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
[[package]]
name = "unicode-ident"
version = "1.0.26"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d245f478577f809a851594d02313b640fb437e0bb33866753cff937863096954"
[[package]]
name = "widestring"
version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72069c3113ab32ab29e5584db3c6ec55d416895e60715417b5b883a357c3e471"
[[package]]
name = "windows-link"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
[[package]]
name = "windows-sys"
version = "0.61.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
dependencies = [
"windows-link",
]
[[package]]
name = "winnow"
version = "0.7.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df79d97927682d2fd8adb29682d1140b343be4ac0f08fd68b7765d9c059d3945"
dependencies = [
"memchr",
]
[[package]]
name = "zmij"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
+16
View File
@@ -0,0 +1,16 @@
[package]
name = "chusql-storage-bench"
version = "0.1.0"
edition = "2024"
# 存储层基准单独成包,不混进功能代码(见同目录 README)。
[dependencies]
chusql-storage = { path = "../../chusql-storage" }
serde_json = "1"
[dev-dependencies]
tempfile = "3"
[[bench]]
name = "storage"
harness = false
-36
View File
@@ -1,36 +0,0 @@
# chusql-storage 基准测试(预留)
这个目录预留给 **Rust 存储层** 的基准测试代码,目前 `chusql-storage/` 还没有开工,
所以这里先占位。
## 计划放什么
`chusql-storage` 做的是磁盘那一层的事情,性能指标和查询层完全不同 ——
查询层关心"少算几行",存储层关心"少读几次盘"。所以基准要分开测:
| 待测模块 | 关心的指标 |
| -------- | ---------- |
| 页管理 | 单页读写延迟、顺序读 vs 随机读吞吐 |
| B+ 树 | 插入/查找/范围扫描的耗时随数据量增长的趋势 |
| 缓冲池 | 命中率、缺页次数、替换策略(LRU 等)的对比 |
| WAL | 追加写吞吐、日志落盘延迟、恢复耗时 |
| 崩溃恢复 | 从日志重放的时间、恢复后数据一致性 |
## 用什么
Rust 侧的基准测试一般用 [criterion](https://github.com/bheisler/criterion.rs):
```
benchmark/chusql-storage/
├── Cargo.toml
└── benches/
├── page.rs
├── btree.rs
├── buffer_pool.rs
└── wal.rs
```
跑法:`cargo bench`
另外还要和 Haskell 层对齐口径:查询层的基准是"整条查询的耗时",
存储层的基准是"单次 IO / 单次查找的耗时",两边不要混在一起比。
+353
View File
@@ -0,0 +1,353 @@
//! 存储层基准:页 IO、B+ 树、堆表、WAL 与服务端写入路径。
//!
//! 用 `std::time::Instant` 计时,不引第三方基准框架,离线也能跑。
//! 每项跑 `rounds` 轮取最快一轮:存储层的抖动主要来自 fsync 与调度,
//! 取最快一轮最接近"这套代码本身要花多久"。
//!
//! 跑法:`cargo bench`(可选环境变量 `CHUSQL_BENCH_N` 改规模,默认 2000)
use std::time::{Duration, Instant};
use chusql_storage::btree::DiskBTree;
use chusql_storage::config::{DEFAULT_BTREE_ORDER, DEFAULT_PAGE_SIZE};
use chusql_storage::heap::HeapTable;
use chusql_storage::page::{Page, PageFile};
use chusql_storage::protocol::Row;
use chusql_storage::wal::{Wal, WalOp};
use serde_json::json;
// 工具
/// 跑一个操作 `ops` 次,量总耗时并折算每次耗时
fn bench<F: FnMut()>(label: &str, ops: usize, rounds: usize, mut f: F) {
let mut best = Duration::MAX;
for _ in 0..rounds {
let t0 = Instant::now();
f();
let d = t0.elapsed();
if d < best {
best = d;
}
}
let per = best.as_secs_f64() * 1e6 / ops as f64;
println!(
"{:<38} {:>9.2} ms {:>10.3} us/次",
label,
best.as_secs_f64() * 1e3,
per
);
}
/// 只量一次(fsync 类操作太慢,不适合反复跑)
fn bench_once<F: FnOnce()>(label: &str, ops: usize, f: F) {
let t0 = Instant::now();
f();
let d = t0.elapsed();
let per = d.as_secs_f64() * 1e6 / ops as f64;
println!(
"{:<38} {:>9.2} ms {:>10.3} us/次",
label,
d.as_secs_f64() * 1e3,
per
);
}
/// 造一行
fn row(id: i64) -> Row {
let mut m = Row::new();
m.insert("id".to_string(), json!(id));
m.insert("name".to_string(), json!(format!("user{}", id)));
m
}
/// 小随机数发生器,避免引 rand
fn next_rand(state: &mut u64) -> u64 {
*state = state.wrapping_mul(6364136223846793005).wrapping_add(1442695040888963407);
*state >> 33
}
// 页 IO
/// 顺序写 / 顺序读 / 随机读
fn bench_page(dir: &std::path::Path, n: usize) {
let path = dir.join("page.db");
let mut pf = PageFile::with_options(&path, DEFAULT_PAGE_SIZE, 1024).unwrap();
bench("page 顺序写(含 flush)", n, 3, || {
pf.truncate().unwrap();
for i in 0..n {
pf.write_page(&Page::new(i as u64, DEFAULT_PAGE_SIZE)).unwrap();
}
pf.flush().unwrap();
});
drop(pf);
// 池子故意开小,让顺序读真的去读盘
let mut pf = PageFile::with_options(&path, DEFAULT_PAGE_SIZE, 16).unwrap();
bench("page 顺序读(池 16,基本都缺页)", n, 3, || {
for i in 0..n {
pf.read_page(i as u64).unwrap();
}
});
let mut pf = PageFile::with_options(&path, DEFAULT_PAGE_SIZE, 16).unwrap();
let mut state = 12345u64;
bench("page 随机读(池 16)", n, 3, || {
for _ in 0..n {
let id = next_rand(&mut state) % n as u64;
pf.read_page(id).unwrap();
}
});
// 池子开大、工作集比池子还大:每次缺页都要挑一个牺牲页
let mut pf = PageFile::with_options(&path, DEFAULT_PAGE_SIZE, 1024).unwrap();
let mut state = 999u64;
bench("page 随机读(池 1024,工作集 > 池)", n, 3, || {
for _ in 0..n {
let id = next_rand(&mut state) % n as u64;
pf.read_page(id).unwrap();
}
});
println!(
" (池 1024:命中 {}/{})",
pf.hits(),
pf.hits() + pf.misses()
);
}
// B+ 树
/// 插入、点查、全量遍历
fn bench_btree(dir: &std::path::Path, n: usize) {
let path = dir.join("bt.idx");
let _ = std::fs::remove_file(&path);
let mut bt = DiskBTree::open(&path, DEFAULT_PAGE_SIZE, DEFAULT_BTREE_ORDER, 1024).unwrap();
bench("btree 插入(含 flush)", n, 2, || {
bt.clear().unwrap();
for i in 0..n {
bt.insert(i as i64, i as u64).unwrap();
}
bt.flush().unwrap();
});
bench("btree 点查(全部命中)", n, 3, || {
for i in 0..n {
bt.get(i as i64).unwrap().expect("key must exist");
}
});
bench("btree 全量遍历", n, 3, || {
let v = bt.iter_all().unwrap();
assert_eq!(v.len(), n);
});
}
// 堆表
/// 插行、全表扫描、按索引取行
fn bench_heap(dir: &std::path::Path, n: usize) {
let path = dir.join("heap.db");
let idx = dir.join("heap.idx");
let _ = std::fs::remove_file(&path);
let _ = std::fs::remove_file(&idx);
let mut t = HeapTable::open(&path, DEFAULT_PAGE_SIZE, 1024).unwrap();
bench("heap 插入(只在缓冲池,不 flush)", n, 2, || {
t.replace_all(&[]).unwrap();
for i in 0..n {
t.insert_row(&row(i as i64)).unwrap();
}
});
bench("heap 插入 + flush", n, 2, || {
t.replace_all(&[]).unwrap();
for i in 0..n {
t.insert_row(&row(i as i64)).unwrap();
}
t.flush().unwrap();
});
bench("heap 批量插入 + flush(一次落盘)", n, 2, || {
t.replace_all(&[]).unwrap();
let rows: Vec<Row> = (0..n as i64).map(row).collect();
t.insert_rows(&rows).unwrap();
t.flush().unwrap();
});
bench("heap 全表扫描", n, 3, || {
let rows = t.scan().unwrap();
assert_eq!(rows.len(), n);
});
}
// WAL
/// 追加写与清空
fn bench_wal(dir: &std::path::Path, n: usize) {
let path = dir.join("wal.log");
let _ = std::fs::remove_file(&path);
let wal = Wal::new(&path);
let op = WalOp::Insert {
table: "t".to_string(),
row: row(1),
};
bench_once("wal 追加(每条都 fsync)", n, || {
for _ in 0..n {
wal.append(&op).unwrap();
}
});
wal.clear().unwrap();
bench_once("wal 清空(每条都 fsync)", n, || {
for _ in 0..n {
wal.clear().unwrap();
}
});
wal.clear().unwrap();
bench_once("wal 截断(不落盘)", n, || {
for _ in 0..n {
wal.truncate().unwrap();
}
});
// 拆分:一次 fsync 本身多贵,一次 open 多贵
use std::fs::OpenOptions;
use std::io::Write;
// 大小和一条真实的 WAL 记录同量级(~200 字节)
let bytes = vec![0u8; 200];
bench_once(" └ open + write + fsync", n, || {
for _ in 0..n {
let mut f = OpenOptions::new()
.create(true)
.append(true)
.open(&path)
.unwrap();
f.write_all(&bytes).unwrap();
f.sync_data().unwrap();
}
});
let mut open_file = OpenOptions::new()
.create(true)
.append(true)
.open(&path)
.unwrap();
bench_once(" └ 复用句柄:write + fsync", n, || {
for _ in 0..n {
open_file.write_all(&bytes).unwrap();
open_file.sync_data().unwrap();
}
});
bench_once(" └ only fsync(不开不写)", n, || {
for _ in 0..n {
open_file.sync_data().unwrap();
}
});
bench_once(" └ only open/close", n, || {
for _ in 0..n {
let _ = OpenOptions::new()
.create(true)
.append(true)
.open(&path)
.unwrap();
}
});
wal.clear().unwrap();
}
// 服务端写入路径
/// 复刻 server.rs 里 write_via_wal 的顺序:清 WAL -> 写 WAL -> 改数据 -> flush -> 清 WAL
fn bench_write_path(dir: &std::path::Path, n: usize) {
let path = dir.join("wp.db");
let idx = dir.join("wp.idx");
let wal_path = dir.join("wp.wal");
let _ = std::fs::remove_file(&path);
let _ = std::fs::remove_file(&idx);
let _ = std::fs::remove_file(&wal_path);
let mut t = HeapTable::open_indexed(
&path,
&idx,
DEFAULT_PAGE_SIZE,
DEFAULT_BTREE_ORDER,
1024,
)
.unwrap();
let wal = Wal::new(&wal_path);
bench_once("写入路径 单条 INSERT(端到端)", n, || {
for i in 0..n as i64 {
wal.truncate().unwrap();
let op = WalOp::Insert {
table: "t".to_string(),
row: row(i),
};
wal.append(&op).unwrap();
t.insert_row(&row(i)).unwrap();
t.flush().unwrap();
wal.clear().unwrap();
}
});
// 拆开量,好定位时间花在哪一步
bench_once(" └ wal.truncate()(不落盘)", n, || {
for _ in 0..n {
wal.truncate().unwrap();
}
});
let op = WalOp::Insert {
table: "t".to_string(),
row: row(1),
};
bench_once(" └ wal.append()(含 fsync)", n, || {
for _ in 0..n {
wal.append(&op).unwrap();
}
});
wal.clear().unwrap();
bench_once(" └ wal.clear()(含 fsync)", n, || {
for _ in 0..n {
wal.clear().unwrap();
}
});
bench_once(" └ heap.insert_row()(含写索引)", n, || {
// 主循环已经插过 0..n 了,这里换个号段,免得撞上"索引列唯一"
for i in n as i64..2 * n as i64 {
t.insert_row(&row(i)).unwrap();
}
});
bench_once(" └ heap.flush()", n, || {
for _ in 0..n {
t.flush().unwrap();
}
});
}
fn main() {
let n: usize = std::env::var("CHUSQL_BENCH_N")
.ok()
.and_then(|v| v.parse().ok())
.unwrap_or(2000);
println!("chusql-storage 基准:n = {},页大小 = {} 字节,btree order = {}",
n, DEFAULT_PAGE_SIZE, DEFAULT_BTREE_ORDER);
println!("每项取最快一轮;带 fsync 的项只跑一次(跑多了太慢)\n");
let dir = tempfile::tempdir().unwrap();
println!("[页 IO]");
bench_page(dir.path(), n);
println!("\n[B+ 树]");
bench_btree(dir.path(), n);
println!("\n[堆表]");
bench_heap(dir.path(), n);
println!("\n[WAL]");
bench_wal(dir.path(), n.min(200));
println!("\n[服务端写入路径]");
bench_write_path(dir.path(), n.min(200));
}