wonder/docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 修复所有 Mermaid 图表语法兼容性问题
Deploy Docs / deploy (push) Successful in 9s
Details

Browse Source
This commit is contained in:
wonder
2026-08-24 03:14:45 +00:00
parent a4ddd3f48e
commit 6a26c8b499
3 changed files with 81 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/algorithm/bloom-filter.md
+30 -39
View File
@@ -20,30 +20,28 @@
```mermaid ```mermaid
graph LR graph LR
subgraph 插入元素x["插入元素 x"] X["元素 x"] --> H1["h1(x) = 3"]
X["x"] --> H1["h₁(x) = 3"] X --> H2["h2(x) = 7"]
X --> H2["h₂(x) = 7"] X --> H3["h3(x) = 11"]
X --> H3["h₃(x) = 11"] H1 --> B3["bit[3] = 1"]
H1 --> B3["bit[3] = 1"] H2 --> B7["bit[7] = 1"]
H2 --> B7["bit[7] = 1"] H3 --> B11["bit[11] = 1"]
H3 --> B11["bit[11] = 1"]
end
``` ```
```mermaid ```mermaid
graph LR graph LR
subgraph 查询y["查询元素 y — 一定不存在"] subgraph qy["查询元素 y - 一定不存在"]
Y["y"] --> YH1["h₁(y) = 3 → bit[3]=1 ✓"] Y["y"] --> YH1["h1(y)=3 bit[3]=1"]
Y --> YH2["h₂(y) = 5 → bit[5]=0 ✗"] Y --> YH2["h2(y)=5 bit[5]=0"]
YH1 --> YR["结论：一定不存在"] YH1 --> YR["结论: 一定不存在"]
YH2 --> YR YH2 --> YR
end end
subgraph 查询z["查询元素 z — 假阳性"] subgraph qz["查询元素 z - 假阳性"]
Z["z"] --> ZH1["h₁(z)=3 → bit[3]=1 ✓"] Z["z"] --> ZH1["h1(z)=3 bit[3]=1"]
Z --> ZH2["h₂(z)=7 → bit[7]=1 ✓"] Z --> ZH2["h2(z)=7 bit[7]=1"]
Z --> ZH3["h₃(z)=11 → bit[11]=1 ✓"] Z --> ZH3["h3(z)=11 bit[11]=1"]
ZH1 --> ZR["结论：可能存在<br/>⚠️ 实际未插入（假阳性）"] ZH1 --> ZR["结论: 可能存在 / 实际未插入"]
ZH2 --> ZR ZH2 --> ZR
ZH3 --> ZR ZH3 --> ZR
end end
@@ -51,15 +49,8 @@ graph LR
```mermaid ```mermaid
graph LR graph LR
subgraph 位数组["位数组 (m=16)"] b0["0"] --- b1["0"] --- b2["0"] --- b3["1"] --- b4["0"] --- b5["0"] --- b6["0"] --- b7["1"]
direction LR b7 --- b8["0"] --- b9["0"] --- b10["0"] --- b11["1"] --- b12["0"] --- b13["0"] --- b14["0"] --- b15["0"]
b0["0"] --- b1["0"] --- b2["0"] --- b3["1"] --- b4["0"] --- b5["0"] --- b6["0"] --- b7["1"]
b7 --- b8["0"] --- b9["0"] --- b10["0"] --- b11["1"] --- b12["0"] --- b13["0"] --- b14["0"] --- b15["0"]
end
插入元素x -.->|h₁ h₂ h₃| b3
插入元素x -.-> b7
插入元素x -.-> b11
``` ```
### 假阳性率 ### 假阳性率
@@ -81,32 +72,32 @@ $$p \approx \left(1 - e^{-kn/m}\right)^k$$
```mermaid ```mermaid
graph TB graph TB
subgraph BF["布隆过滤器 — 极致省空间"] subgraph BF["布隆过滤器 - 极致省空间"]
B1["位数组 m bit"] --> B2["k 个哈希函数"] B1["位数组 m bit"] --> B2["k 个哈希函数"]
B2 --> B3["插入: O(k)"] B2 --> B3["插入: O(k)"]
B2 --> B4["查询: O(k)"] B2 --> B4["查询: O(k)"]
B2 --> B5["删除: ❌"] B2 --> B5["删除: 不支持"]
B2 --> B6["假阳性: 有"] B2 --> B6["假阳性: 有"]
end end
subgraph HS["HashSet — 精确但占空间"] subgraph HS["HashSet - 精确但占空间"]
HS1["存完整元素"] --> HS2["哈希表"] HS1["存完整元素"] --> HS2["哈希表"]
HS2 --> HS3["插入: O(1)"] HS2 --> HS3["插入: O(1)"]
HS2 --> HS4["查询: O(1)"] HS2 --> HS4["查询: O(1)"]
HS2 --> HS5["删除: ✅"] HS2 --> HS5["删除: 支持"]
HS2 --> HS6["假阳性: 无"] HS2 --> HS6["假阳性: 无"]
end end
subgraph CBF["Counting Bloom — 可删除"] subgraph CBF["Counting Bloom - 可删除"]
C1["计数器数组 4m bit"] --> C2["k 个哈希函数"] C1["计数器数组 4m bit"] --> C2["k 个哈希函数"]
C2 --> C3["插入: O(k)"] C2 --> C3["插入: O(k)"]
C2 --> C4["查询: O(k)"] C2 --> C4["查询: O(k)"]
C2 --> C5["删除: ✅"] C2 --> C5["删除: 支持"]
C2 --> C6["假阳性: 有"] C2 --> C6["假阳性: 有"]
end end
BF -.->|"约 4x 空间差"| CBF BF -.->|"约 4x 空间差"| CBF
HS -.->|"约 4~10x 空间差"| BF HS -.->|"约 4-10x 空间差"| BF
``` ```
| | 布隆过滤器 | HashSet | Counting Bloom Filter | | | 布隆过滤器 | HashSet | Counting Bloom Filter |
@@ -207,16 +198,16 @@ sequenceDiagram
participant DB as DB participant DB as DB
C->>BF: 查询 user:50 C->>BF: 查询 user:50
BF-->>C: 一定不存在 ✗ BF-->>C: 一定不存在
C-->>C: 直接返回，不查缓存/DB C-->>C: 直接返回 不查缓存和DB
C->>BF: 查询 user:100 C->>BF: 查询 user:100
BF-->>C: 可能存在 ✓ BF-->>C: 可能存在
C->>R: GET user:100 C->>R: GET user:100
alt 缓存命中 alt 缓存命中
R-->>C: 返回数据 ✅ R-->>C: 返回数据
else 缓存 miss else 缓存miss
C->>DB: SELECT * FROM users WHERE id=100 C->>DB: SELECT
DB-->>C: 返回数据 DB-->>C: 返回数据
C->>R: SET user:100 + TTL C->>R: SET user:100 + TTL
end end
docs/algorithm/heavykeeper.md
+22 -53
View File
@@ -19,24 +19,14 @@
```mermaid ```mermaid
graph LR graph LR
subgraph 数据流["高速数据流"] F1["流A: 10000次"] --> HK["HeavyKeeper"]
F1["流 A: 10000次 🐘"] F2["流B: 8000次"] --> HK
F2["流 B: 8000次 🐘"] F3["流C: 1次"] --> HK
F3["流 C: 1次 🐭"] F4["流D: 2次"] --> HK
F4["流 D: 2次 🐭"] F5["流E: 1次"] --> HK
F5["流 E: 1次 🐭"]
F6["流 ...: 1次 🐭"]
end
F1 --> HK["HeavyKeeper"] HK --> TOP["Top-K: 流A~10000 流B~8000"]
F2 --> HK HK -.->|"老鼠流衰减淘汰"| GONE["流C~E: 归零"]
F3 --> HK
F4 --> HK
F5 --> HK
F6 --> HK
HK --> TOP["Top-K 结果:<br/>流 A: ~10000<br/>流 B: ~8000"]
HK -.->|老鼠流被衰减淘汰| GONE["流 C~E: 归零 🗑️"]
``` ```
### 背景：为什么需要 HeavyKeeper ### 背景：为什么需要 HeavyKeeper
@@ -53,26 +43,21 @@ graph LR
```mermaid ```mermaid
graph TB graph TB
Input["插入流 x"] --> Loop["遍历 d 行"] Input["插入流 x"] --> Loop["遍历 d 行"]
Loop --> Hash["pos = hi(x) mod w"]
Loop --> Hash["pos = hᵢ(x) mod w"]
Hash --> Check{"bucket[pos]?"} Hash --> Check{"bucket[pos]?"}
Check -->|"flowID == x"| Hit["count++"] Check -->|"flowID == x"| Hit["count++"]
Check -->|"flowID == 空"| Empty["写入 (x, 1)"] Check -->|"flowID == 空"| Empty["写入 (x, 1)"]
Check -->|"flowID ≠ x"| Conflict{"random() < p?"} Check -->|"flowID != x"| Conflict{"random() < p?"}
Conflict -->|"否"| Skip["跳过"] Conflict -->|"否"| Skip["跳过"]
Conflict -->|"是"| Decay["count--"] Conflict -->|"是"| Decay["count--"]
Decay --> Zero{"count == 0?"} Decay --> Zero{"count == 0?"}
Zero -->|"是"| Replace["替换为 (x, 1)"] Zero -->|"是"| Replace["替换为 (x, 1)"]
Zero -->|"否"| Skip2["保留原流"] Zero -->|"否"| Keep["保留原流"]
Hit --> NextRow["下一行"] Hit --> NextRow["下一行"]
Empty --> NextRow Empty --> NextRow
Skip --> NextRow Skip --> NextRow
Replace --> NextRow Replace --> NextRow
Skip2 --> NextRow Keep --> NextRow
NextRow --> Loop NextRow --> Loop
style Hit fill:#4caf50,color:#fff style Hit fill:#4caf50,color:#fff
@@ -83,17 +68,6 @@ graph TB
```mermaid ```mermaid
graph TB graph TB
subgraph 数据结构["HeavyKeeper 结构 (d=3, w=8)"]
direction TB
Row0["行 0: h₀(x)"]
Row1["行 1: h₁(x)"]
Row2["行 2: h₂(x)"]
Row0 --- B00["流C:3"] --- B01["流A:10000"] --- B02[" "] --- B03["流D:1"] --- B04["流A:9500"] --- B05[" "] --- B06["流B:8000"] --- B07["流A:9800"]
Row1 --- B10["流B:7500"] --- B11[" "] --- B12["流A:10200"] --- B13["流E:1"] --- B14[" "] --- B15["流B:8200"] --- B16[" "] --- B17["流A:9000"]
Row2 --- B20[" "] --- B21["流A:10100"] --- B22["流C:2"] --- B23["流B:7800"] --- B24[" "] --- B25["流A:9900"] --- B26[" "] --- B27["流D:0🗑️"]
end
Query["查询流 A"] --> Max["取各行最大 count = 10200"] Query["查询流 A"] --> Max["取各行最大 count = 10200"]
``` ```
@@ -126,20 +100,20 @@ Top-k 查询：
```mermaid ```mermaid
graph LR graph LR
subgraph p0["p = 0 — 无衰减"] subgraph p0["p=0 无衰减"]
P0E["老鼠流永不清除<br/>噪声累积，Top-K 精度低"] P0E["老鼠流永不清除 / 噪声累积 / Top-K精度低"]
end end
subgraph pok["p 适中 (0.01~0.1) — 最佳"] subgraph pok["p适中 0.01-0.1 最佳"]
POKE["老鼠流: count=1 → 一次衰减→0 🗑️<br/>大象流: count=10000 → -1 无感 ✅<br/>Top-K 精度高"] POKE["老鼠流count=1 一次衰减归零 / 大象流count=10000 -1无感 / Top-K精度高"]
end end
subgraph pbig["p 过大 (>0.3)"] subgraph pbig["p过大 大于0.3"]
PBIGE["大象流也被严重衰减<br/>估计偏低，Top-K 不准"] PBIGE["大象流也被严重衰减 / 估计偏低 / Top-K不准"]
end end
p0 -->|"增大 p"| pok p0 -->|"增大p"| pok
pok -->|"继续增大 p"| pbig pok -->|"继续增大p"| pbig
``` ```
| 衰减概率 p | 效果 | | 衰减概率 p | 效果 |
@@ -304,14 +278,9 @@ func sortDesc(items []Item) {
```mermaid ```mermaid
graph LR graph LR
Log["Nginx Access Log<br/>stdin 流式读取"] --> Parse["提取 Client IP"] Log["Nginx Access Log"] --> Parse["提取 Client IP"]
Parse --> HK["HeavyKeeper<br/>4行 × 65536桶 × 5%衰减<br/>≈ 2MB"] Parse --> HK["HeavyKeeper / 4行x65536桶 / 5%衰减 / 约2MB"]
HK --> TopK["Top-10 热门 IP"] HK --> TopK["Top-10 热门IP"]
subgraph 流量模型
Elephant["192.168.1.100 🐘<br/>10.0.0.5 🐘"] -->|"高频"| HK
Mouse["172.16.x.x 🐭<br/>大量低频 IP"] -->|"衰减淘汰"| HK
end
``` ```
```go ```go
docs/architecture/cache/cache-breakdown-avalanche-penetration.md
Vendored
+29 -37
View File
@@ -17,22 +17,22 @@
```mermaid ```mermaid
graph TB graph TB
subgraph 击穿["🔓 缓存击穿 — 单热点 key 过期"] subgraph bd["缓存击穿 - 单热点key过期"]
B1["热 key 过期"] --> B2["大量并发同时 miss"] B1["热 key 过期"] --> B2["大量并发同时 miss"]
B2 --> B3["同时回源 DB"] B2 --> B3["同时回源 DB"]
B3 --> B4["DB 瞬时尖峰 💥"] B3 --> B4["DB 瞬时尖峰"]
end end
subgraph 雪崩["❄️ 缓存雪崩 — 大面积 key 集中失效"] subgraph av["缓存雪崩 - 大面积key集中失效"]
A1["大量 key 同时刻过期<br/>或缓存节点宕机"] --> A2["请求大面积 miss"] A1["大量 key 同时刻过期 或 缓存节点宕机"] --> A2["请求大面积 miss"]
A2 --> A3["全部涌向 DB"] A2 --> A3["全部涌向 DB"]
A3 --> A4["DB 持续高压 💥"] A3 --> A4["DB 持续高压"]
end end
subgraph 穿透["🕳️ 缓存穿透 — 查不存在的数据"] subgraph pn["缓存穿透 - 查不存在的数据"]
C1["请求查询不存在的 key"] --> C2["缓存永远 miss"] C1["请求查询不存在的 key"] --> C2["缓存永远 miss"]
C2 --> C3["每次直达 DB"] C2 --> C3["每次直达 DB"]
C3 --> C4["DB 持续高压 💥"] C3 --> C4["DB 持续高压"]
end end
``` ```
@@ -51,18 +51,18 @@ graph TB
```mermaid ```mermaid
graph LR graph LR
subgraph 击穿["击穿"] subgraph bd["击穿"]
A1["A1 永不过期"] A1["A1 永不过期"]
A2["A2 加锁排队<br/>singleflight"] A2["A2 加锁排队 / singleflight"]
end end
subgraph 雪崩["雪崩"] subgraph av["雪崩"]
B1["B1 加锁/限流"] B1["B1 加锁/限流"]
B2["B2 随机失效"] B2["B2 随机失效"]
B3["B3 Redis 高可用<br/>多级缓存"] B3["B3 Redis高可用 / 多级缓存"]
end end
subgraph 穿透["穿透"] subgraph pn["穿透"]
C1["C1 参数校验"] C1["C1 参数校验"]
C2["C2 缓存空对象"] C2["C2 缓存空对象"]
C3["C3 布隆过滤器"] C3["C3 布隆过滤器"]
@@ -245,23 +245,23 @@ func (s *Service) GetWithRateLimit(ctx context.Context, key string) (any, error)
```mermaid ```mermaid
graph LR graph LR
subgraph 无 Jitter["❌ 无随机偏移"] subgraph no_jitter["无随机偏移"]
T1["key_a TTL=30min"] --> E1["同时过期"] T1["key_a TTL=30min"] --> E1["同时过期"]
T2["key_b TTL=30min"] --> E1 T2["key_b TTL=30min"] --> E1
T3["key_c TTL=30min"] --> E1 T3["key_c TTL=30min"] --> E1
E1 --> CRASH["DB 雪崩 💥"] E1 --> CRASH["DB 雪崩"]
end end
subgraph 有 Jitter["✅ 有随机偏移"] subgraph has_jitter["有随机偏移"]
J1["key_a TTL=30m+2m"] --> D1["32min 过期"] J1["key_a TTL=30m+2m"] --> D1["32min 过期"]
J2["key_b TTL=30m+7m"] --> D2["37min 过期"] J2["key_b TTL=30m+7m"] --> D2["37min 过期"]
J3["key_c TTL=30m+4m"] --> D3["34min 过期"] J3["key_c TTL=30m+4m"] --> D3["34min 过期"]
D1 --> SAFE["DB 压力分散 ✅"] D1 --> SAFE["DB 压力分散"]
D2 --> SAFE D2 --> SAFE
D3 --> SAFE D3 --> SAFE
end end
无 Jitter -.->|加 jitter| 有 Jitter no_jitter -.->|"加 jitter"| has_jitter
``` ```
```go ```go
@@ -284,20 +284,12 @@ for _, item := range items {
```mermaid ```mermaid
graph TB graph TB
subgraph 多级缓存架构 Client["客户端请求"] --> L1["L1 本地缓存 / bigcache / ristretto"]
Client["客户端请求"] L1 -->|"miss"| L2["L2 Redis / Sentinel / Cluster"]
L1["L1 本地缓存<br/>bigcache / ristretto"] L2 -->|"miss"| L3["L3 DB"]
L2["L2 Redis<br/>Sentinel / Cluster"] L3 --> L2
L3["L3 DB"] L2 --> L1
L1 -.->|"Redis不可用时降级"| Client
Client --> L1
L1 -->|miss| L2
L2 -->|miss| L3
L3 --> L2
L2 --> L1
L1 -.->|Redis 不可用时<br/>降级到本地| Client
end
``` ```
| 方案 | 说明 | | 方案 | 说明 |
@@ -391,12 +383,12 @@ func (s *Service) GetWithNullCache(ctx context.Context, key string) (any, error)
```mermaid ```mermaid
graph LR graph LR
Req["请求"] --> BF{"布隆过滤器"} Req["请求"] --> BF{"布隆过滤器"}
BF -->|"一定不存在 ✗"| Reject["直接拒绝<br/>不查缓存/DB"] BF -->|"一定不存在"| Reject["直接拒绝 / 不查缓存和DB"]
BF -->|"可能存在 ✓"| Cache{"Redis 缓存"} BF -->|"可能存在"| Cache{"Redis 缓存"}
Cache -->|hit| Return["返回数据"] Cache -->|"hit"| Return["返回数据"]
Cache -->|miss| DB["查询 DB"] Cache -->|"miss"| DB["查询 DB"]
DB -->|有数据| Cache DB -->|"有数据"| Cache2["回写缓存"]
DB -->|无数据| Null["缓存空对象<br/>短 TTL"] DB -->|"无数据"| Null["缓存空对象 / 短TTL"]
``` ```
```go ```go