mirror of
https://github.com/telemt/telemt.git
synced 2026-04-15 09:34:10 +03:00
Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
89222e7123 | ||
|
|
2468ee15e7 | ||
|
|
3440aa9fcd | ||
|
|
ce9698d39b | ||
|
|
ddfe7c5cfa | ||
|
|
01893f3712 | ||
|
|
8ae741ec72 | ||
|
|
6856466cef | ||
|
|
68292fbd26 | ||
|
|
e90c42ae68 | ||
|
|
9f9a5dce0d | ||
|
|
6739cd8d01 | ||
|
|
6cc8d9cb00 | ||
|
|
ce375b62e4 | ||
|
|
95971ac62c |
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "telemt"
|
||||
version = "3.3.5"
|
||||
version = "3.3.6"
|
||||
edition = "2024"
|
||||
|
||||
[dependencies]
|
||||
|
||||
179
README.md
179
README.md
@@ -19,18 +19,24 @@
|
||||
|
||||
### 🇷🇺 RU
|
||||
|
||||
#### Релиз 3.3.3 LTS - 6 марта
|
||||
#### Релиз 3.3.5 LTS - 6 марта
|
||||
|
||||
6 марта мы выпустили Telemt **3.3.3**
|
||||
6 марта мы выпустили Telemt **3.3.5**
|
||||
|
||||
Это первая версия telemt работающая в комплексных условиях и при этом предоставляющая API
|
||||
Это [3.3.5 - первая LTS-версия telemt](https://github.com/telemt/telemt/releases/tag/3.3.5)!
|
||||
|
||||
В ней используется новый алгоритм - ME NoWait, который вместе с Adaptive Floor и моделью усовершенствованного доступа к KDF Fingerprint на RwLock позволяет достигать максимальную производительность, даже в условиях lossy-сети
|
||||
В ней используется:
|
||||
- новый алгоритм ME NoWait для непревзойдённо быстрого восстановления пула
|
||||
- Adaptive Floor, поддерживающий количество ME Writer на оптимальном уровне
|
||||
- модель усовершенствованного доступа к KDF Fingerprint на RwLock
|
||||
- строгая привязка Middle-End к DC-ID с предсказуемым алгоритмом деградации и самовосстановления
|
||||
|
||||
Будем рады вашему фидбеку и предложениям по улучшению — особенно в части **статистики** и **UX**
|
||||
Telemt Control API V1 в 3.3.5 включает:
|
||||
- несколько режимов работы в зависимости от доступных ресурсов
|
||||
- снапшот-модель для живых метрик без вмешательства в hot-path
|
||||
- минималистичный набор запросов для управления пользователями
|
||||
|
||||
Релиз:
|
||||
[3.3.3](https://github.com/telemt/telemt/releases/tag/3.3.3)
|
||||
Будем рады вашему фидбеку и предложениям по улучшению — особенно в части **API**, **статистики**, **UX**
|
||||
|
||||
---
|
||||
|
||||
@@ -47,18 +53,24 @@
|
||||
|
||||
### 🇬🇧 EN
|
||||
|
||||
#### Release 3.3.3 LTS - March 6
|
||||
#### Release 3.3.5 LTS - March 6
|
||||
|
||||
On March 6, we released Telemt **3.3.3**
|
||||
|
||||
This is the first telemt's version designed to operate reliably in complex network conditions while also providing a runtime API!
|
||||
This is [3.3.5 - the first LTS release of telemt](https://github.com/telemt/telemt/releases/tag/3.3.5)
|
||||
|
||||
The release introduces a new algorithm — ME NoWait, which combined with Adaptive Floor and an improved KDF Fingerprint access model based on RwLock, it enables the system to achieve maximum performance even in lossy network environments
|
||||
It introduces:
|
||||
- the new ME NoWait algorithm for exceptionally fast pool recovery
|
||||
- Adaptive Floor, which maintains the number of ME Writers at an optimal level
|
||||
- an improved KDF Fingerprint access model based on RwLock
|
||||
- strict binding of Middle-End instances to DC-ID with a predictable degradation and self-recovery algorithm
|
||||
|
||||
We are looking forward to your feedback and improvement proposals — especially regarding **statistics** and **UX**
|
||||
Telemt Control API V1 in version 3.3.5 includes:
|
||||
- multiple operating modes depending on available resources
|
||||
- a snapshot-based model for live metrics without interfering with the hot path
|
||||
- a minimalistic request set for user management
|
||||
|
||||
Release:
|
||||
[3.3.3](https://github.com/telemt/telemt/releases/tag/3.3.3)
|
||||
We are looking forward to your feedback and improvement proposals — especially regarding **API**, **statistics**, **UX**
|
||||
|
||||
---
|
||||
|
||||
@@ -81,31 +93,6 @@ We welcome ideas, architectural feedback, and pull requests.
|
||||
|
||||
⚓ Our ***Middle-End Pool*** is fastest by design in standard scenarios, compared to other implementations of connecting to the Middle-End Proxy: non dramatically, but usual
|
||||
|
||||
# GOTO
|
||||
- [Features](#features)
|
||||
- [Quick Start Guide](#quick-start-guide)
|
||||
- [How to use?](#how-to-use)
|
||||
- [Systemd Method](#telemt-via-systemd)
|
||||
- [Configuration](#configuration)
|
||||
- [Minimal Configuration](#minimal-configuration-for-first-start)
|
||||
- [Advanced](#advanced)
|
||||
- [Adtag](#adtag)
|
||||
- [Listening and Announce IPs](#listening-and-announce-ips)
|
||||
- [Upstream Manager](#upstream-manager)
|
||||
- [IP](#bind-on-ip)
|
||||
- [SOCKS](#socks45-as-upstream)
|
||||
- [FAQ](#faq)
|
||||
- [Recognizability for DPI + crawler](#recognizability-for-dpi-and-crawler)
|
||||
- [Telegram Calls](#telegram-calls-via-mtproxy)
|
||||
- [DPI](#how-does-dpi-see-mtproxy-tls)
|
||||
- [Whitelist on Network Level](#whitelist-on-ip)
|
||||
- [Too many open files](#too-many-open-files)
|
||||
- [Build](#build)
|
||||
- [Docker](#docker)
|
||||
- [Why Rust?](#why-rust)
|
||||
|
||||
## Features
|
||||
|
||||
- Full support for all official MTProto proxy modes:
|
||||
- Classic
|
||||
- Secure - with `dd` prefix
|
||||
@@ -116,59 +103,40 @@ We welcome ideas, architectural feedback, and pull requests.
|
||||
- Graceful shutdown on Ctrl+C
|
||||
- Extensive logging via `trace` and `debug` with `RUST_LOG` method
|
||||
|
||||
# GOTO
|
||||
- [Telemt - MTProxy on Rust + Tokio](#telemt---mtproxy-on-rust--tokio)
|
||||
- [NEWS and EMERGENCY](#news-and-emergency)
|
||||
- [✈️ Telemt 3 is released!](#️-telemt-3-is-released)
|
||||
- [🇷🇺 RU](#-ru)
|
||||
- [Релиз 3.3.5 LTS - 6 марта](#релиз-335-lts---6-марта)
|
||||
- [🇬🇧 EN](#-en)
|
||||
- [Release 3.3.5 LTS - March 6](#release-335-lts---march-6)
|
||||
- [Features](#features)
|
||||
- [GOTO](#goto)
|
||||
- [Quick Start Guide](#quick-start-guide)
|
||||
- [FAQ](#faq)
|
||||
- [Recognizability for DPI and crawler](#recognizability-for-dpi-and-crawler)
|
||||
- [Client WITH secret-key accesses the MTProxy resource:](#client-with-secret-key-accesses-the-mtproxy-resource)
|
||||
- [Client WITHOUT secret-key gets transparent access to the specified resource:](#client-without-secret-key-gets-transparent-access-to-the-specified-resource)
|
||||
- [Telegram Calls via MTProxy](#telegram-calls-via-mtproxy)
|
||||
- [How does DPI see MTProxy TLS?](#how-does-dpi-see-mtproxy-tls)
|
||||
- [Whitelist on IP](#whitelist-on-ip)
|
||||
- [Too many open files](#too-many-open-files)
|
||||
- [Build](#build)
|
||||
- [Why Rust?](#why-rust)
|
||||
- [Issues](#issues)
|
||||
- [Roadmap](#roadmap)
|
||||
|
||||
|
||||
## Quick Start Guide
|
||||
|
||||
### [Quick Start Guide RU](docs/QUICK_START_GUIDE.ru.md)
|
||||
### [Quick Start Guide EN](docs/QUICK_START_GUIDE.en.md)
|
||||
|
||||
|
||||
### Advanced
|
||||
#### Adtag (per-user)
|
||||
To use channel advertising and usage statistics from Telegram, get an Adtag from [@mtproxybot](https://t.me/mtproxybot). Set it per user in `[access.user_ad_tags]` (32 hex chars):
|
||||
```toml
|
||||
[access.user_ad_tags]
|
||||
username1 = "11111111111111111111111111111111" # Replace with your tag from @mtproxybot
|
||||
username2 = "22222222222222222222222222222222"
|
||||
```
|
||||
#### Listening and Announce IPs
|
||||
To specify listening address and/or address in links, add to section `[[server.listeners]]` of config.toml:
|
||||
```toml
|
||||
[[server.listeners]]
|
||||
ip = "0.0.0.0" # 0.0.0.0 = all IPs; your IP = specific listening
|
||||
announce_ip = "1.2.3.4" # IP in links; comment with # if not used
|
||||
```
|
||||
#### Upstream Manager
|
||||
To specify upstream, add to section `[[upstreams]]` of config.toml:
|
||||
##### Bind on IP
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "direct"
|
||||
weight = 1
|
||||
enabled = true
|
||||
interface = "192.168.1.100" # Change to your outgoing IP
|
||||
```
|
||||
##### SOCKS4/5 as Upstream
|
||||
- Without Auth:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
|
||||
- With Auth:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
username = "user" # Username for Auth on SOCKS-server
|
||||
password = "pass" # Password for Auth on SOCKS-server
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
- [Quick Start Guide RU](docs/QUICK_START_GUIDE.ru.md)
|
||||
- [Quick Start Guide EN](docs/QUICK_START_GUIDE.en.md)
|
||||
|
||||
## FAQ
|
||||
|
||||
- [FAQ RU](docs/FAQ.ru.md)
|
||||
- [FAQ EN](docs/FAQ.en.md)
|
||||
|
||||
### Recognizability for DPI and crawler
|
||||
Since version 1.1.0.0, we have debugged masking perfectly: for all clients without "presenting" a key,
|
||||
we transparently direct traffic to the target host!
|
||||
@@ -313,41 +281,6 @@ chmod +x /bin/telemt
|
||||
telemt config.toml
|
||||
```
|
||||
|
||||
## Docker
|
||||
**Quick start (Docker Compose)**
|
||||
|
||||
1. Edit `config.toml` in repo root (at least: port, users secrets, tls_domain)
|
||||
2. Start container:
|
||||
```bash
|
||||
docker compose up -d --build
|
||||
```
|
||||
3. Check logs:
|
||||
```bash
|
||||
docker compose logs -f telemt
|
||||
```
|
||||
4. Stop:
|
||||
```bash
|
||||
docker compose down
|
||||
```
|
||||
|
||||
**Notes**
|
||||
- `docker-compose.yml` maps `./config.toml` to `/app/config.toml` (read-only)
|
||||
- By default it publishes `443:443` and runs with dropped capabilities (only `NET_BIND_SERVICE` is added)
|
||||
- If you really need host networking (usually only for some IPv6 setups) uncomment `network_mode: host`
|
||||
|
||||
**Run without Compose**
|
||||
```bash
|
||||
docker build -t telemt:local .
|
||||
docker run --name telemt --restart unless-stopped \
|
||||
-p 443:443 \
|
||||
-e RUST_LOG=info \
|
||||
-v "$PWD/config.toml:/app/config.toml:ro" \
|
||||
--read-only \
|
||||
--cap-drop ALL --cap-add NET_BIND_SERVICE \
|
||||
--ulimit nofile=65536:65536 \
|
||||
telemt:local
|
||||
```
|
||||
|
||||
## Why Rust?
|
||||
- Long-running reliability and idempotent behavior
|
||||
- Rust's deterministic resource management - RAII
|
||||
|
||||
112
docs/FAQ.en.md
Normal file
112
docs/FAQ.en.md
Normal file
@@ -0,0 +1,112 @@
|
||||
## How to set up "proxy sponsor" channel and statistics via @MTProxybot bot
|
||||
|
||||
1. Go to @MTProxybot bot.
|
||||
2. Enter the command `/newproxy`
|
||||
3. Send the server IP and port. For example: 1.2.3.4:443
|
||||
4. Open the config `nano /etc/telemt.toml`.
|
||||
5. Copy and send the user secret from the [access.users] section to the bot.
|
||||
6. Copy the tag received from the bot. For example 1234567890abcdef1234567890abcdef.
|
||||
> [!WARNING]
|
||||
> The link provided by the bot will not work. Do not copy or use it!
|
||||
7. Uncomment the ad_tag parameter and enter the tag received from the bot.
|
||||
8. Uncomment/add the parameter `use_middle_proxy = true`.
|
||||
|
||||
Config example:
|
||||
```toml
|
||||
[general]
|
||||
ad_tag = "1234567890abcdef1234567890abcdef"
|
||||
use_middle_proxy = true
|
||||
```
|
||||
9. Save the config. Ctrl+S -> Ctrl+X.
|
||||
10. Restart telemt `systemctl restart telemt`.
|
||||
11. In the bot, send the command /myproxies and select the added server.
|
||||
12. Click the "Set promotion" button.
|
||||
13. Send a **public link** to the channel. Private channels cannot be added!
|
||||
14. Wait approximately 1 hour for the information to update on Telegram servers.
|
||||
> [!WARNING]
|
||||
> You will not see the "proxy sponsor" if you are already subscribed to the channel.
|
||||
|
||||
**You can also set up different channels for different users.**
|
||||
```toml
|
||||
[access.user_ad_tags]
|
||||
hello = "ad_tag"
|
||||
hello2 = "ad_tag2"
|
||||
```
|
||||
|
||||
## How many people can use 1 link
|
||||
|
||||
By default, 1 link can be used by any number of people.
|
||||
You can limit the number of IPs using the proxy.
|
||||
```toml
|
||||
[access.user_max_unique_ips]
|
||||
hello = 1
|
||||
```
|
||||
This parameter limits how many unique IPs can use 1 link simultaneously. If one user disconnects, a second user can connect. Also, multiple users can sit behind the same IP.
|
||||
|
||||
## How to create multiple different links
|
||||
|
||||
1. Generate the required number of secrets `openssl rand -hex 16`
|
||||
2. Open the config `nano /etc/telemt.toml`
|
||||
3. Add new users.
|
||||
```toml
|
||||
[access.users]
|
||||
user1 = "00000000000000000000000000000001"
|
||||
user2 = "00000000000000000000000000000002"
|
||||
user3 = "00000000000000000000000000000003"
|
||||
```
|
||||
4. Save the config. Ctrl+S -> Ctrl+X. You don't need to restart telemt.
|
||||
5. Get the links via `journalctl -u telemt -n -g "links" --no-pager -o cat | tac`
|
||||
|
||||
## How to view metrics
|
||||
|
||||
1. Open the config `nano /etc/telemt.toml`
|
||||
2. Add the following parameters
|
||||
```toml
|
||||
[server]
|
||||
metrics_port = 9090
|
||||
metrics_whitelist = ["127.0.0.1/32", "::1/128", "0.0.0.0/0"]
|
||||
```
|
||||
3. Save the config. Ctrl+S -> Ctrl+X.
|
||||
4. Metrics are available at SERVER_IP:9090/metrics.
|
||||
> [!WARNING]
|
||||
> "0.0.0.0/0" in metrics_whitelist opens access from any IP. Replace with your own IP. For example "1.2.3.4"
|
||||
|
||||
## Additional parameters
|
||||
|
||||
### Domain in link instead of IP
|
||||
To specify a domain in the links, add to the `[general.links]` section of the config file.
|
||||
```toml
|
||||
[general.links]
|
||||
public_host = "proxy.example.com"
|
||||
```
|
||||
|
||||
### Upstream Manager
|
||||
To specify an upstream, add to the `[[upstreams]]` section of the config.toml file:
|
||||
#### Binding to IP
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "direct"
|
||||
weight = 1
|
||||
enabled = true
|
||||
interface = "192.168.1.100" # Change to your outgoing IP
|
||||
```
|
||||
#### SOCKS4/5 as Upstream
|
||||
- Without authentication:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
|
||||
- With authentication:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
username = "user" # Username for Auth on SOCKS-server
|
||||
password = "pass" # Password for Auth on SOCKS-server
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
@@ -1,4 +1,4 @@
|
||||
## Как настроить канал "спонсор прокси"
|
||||
## Как настроить канал "спонсор прокси" и статистику через бота @MTProxybot
|
||||
|
||||
1. Зайти в бота @MTProxybot.
|
||||
2. Ввести команду `/newproxy`
|
||||
@@ -70,3 +70,43 @@ metrics_whitelist = ["127.0.0.1/32", "::1/128", "0.0.0.0/0"]
|
||||
4. Метрики доступны по адресу SERVER_IP:9090/metrics.
|
||||
> [!WARNING]
|
||||
> "0.0.0.0/0" в metrics_whitelist открывает доступ с любого IP. Замените на свой ip. Например "1.2.3.4"
|
||||
|
||||
## Дополнительные параметры
|
||||
|
||||
### Домен в ссылке вместо IP
|
||||
Чтобы указать домен в ссылках, добавьте в секцию `[general.links]` файла config.
|
||||
```toml
|
||||
[general.links]
|
||||
public_host = "proxy.example.com"
|
||||
```
|
||||
|
||||
### Upstream Manager
|
||||
Чтобы указать апстрим, добавьте в секцию `[[upstreams]]` файла config.toml:
|
||||
#### Привязка к IP
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "direct"
|
||||
weight = 1
|
||||
enabled = true
|
||||
interface = "192.168.1.100" # Change to your outgoing IP
|
||||
```
|
||||
#### SOCKS4/5 как Upstream
|
||||
- Без авторизации:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
|
||||
- С авторизацией:
|
||||
```toml
|
||||
[[upstreams]]
|
||||
type = "socks5" # Specify SOCKS4 or SOCKS5
|
||||
address = "1.2.3.4:1234" # SOCKS-server Address
|
||||
username = "user" # Username for Auth on SOCKS-server
|
||||
password = "pass" # Password for Auth on SOCKS-server
|
||||
weight = 1 # Set Weight for Scenarios
|
||||
enabled = true
|
||||
```
|
||||
|
||||
@@ -67,6 +67,12 @@ classic = false
|
||||
secure = false
|
||||
tls = true
|
||||
|
||||
[server.api]
|
||||
enabled = true
|
||||
# listen = "127.0.0.1:9091"
|
||||
# whitelist = ["127.0.0.1/32"]
|
||||
# read_only = true
|
||||
|
||||
# === Anti-Censorship & Masking ===
|
||||
[censorship]
|
||||
tls_domain = "petrovich.ru"
|
||||
@@ -75,6 +81,7 @@ tls_domain = "petrovich.ru"
|
||||
# format: "username" = "32_hex_chars_secret"
|
||||
hello = "00000000000000000000000000000000"
|
||||
```
|
||||
|
||||
then Ctrl+S -> Ctrl+X to save
|
||||
|
||||
> [!WARNING]
|
||||
@@ -115,7 +122,12 @@ then Ctrl+S -> Ctrl+X to save
|
||||
|
||||
**5.** For automatic startup at system boot, enter `systemctl enable telemt`
|
||||
|
||||
**6.** To get the links, enter `journalctl -u telemt -n -g "links" --no-pager -o cat | tac`
|
||||
**6.** To get the link(s), enter
|
||||
```bash
|
||||
curl -s http://127.0.0.1:9091/v1/users | jq
|
||||
```
|
||||
|
||||
> Any number of people can use one link.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -67,6 +67,12 @@ classic = false
|
||||
secure = false
|
||||
tls = true
|
||||
|
||||
[server.api]
|
||||
enabled = true
|
||||
# listen = "127.0.0.1:9091"
|
||||
# whitelist = ["127.0.0.1/32"]
|
||||
# read_only = true
|
||||
|
||||
# === Anti-Censorship & Masking ===
|
||||
[censorship]
|
||||
tls_domain = "petrovich.ru"
|
||||
@@ -75,6 +81,7 @@ tls_domain = "petrovich.ru"
|
||||
# format: "username" = "32_hex_chars_secret"
|
||||
hello = "00000000000000000000000000000000"
|
||||
```
|
||||
|
||||
Затем нажмите Ctrl+S -> Ctrl+X, чтобы сохранить
|
||||
|
||||
> [!WARNING]
|
||||
@@ -115,9 +122,14 @@ WantedBy=multi-user.target
|
||||
|
||||
**5.** Для автоматического запуска при запуске системы в введите `systemctl enable telemt`
|
||||
|
||||
**6.** Для получения ссылки введите `journalctl -u telemt -n -g "links" --no-pager -o cat | tac`
|
||||
**6.** Для получения ссылки/ссылок введите
|
||||
```bash
|
||||
curl -s http://127.0.0.1:9091/v1/users | jq
|
||||
```
|
||||
> Одной ссылкой модет пользоваться сколько угодно человек.
|
||||
|
||||
> [!WARNING]
|
||||
> Рабочую ссылку может выдать только команда из 6 пункта. Не пытайтесь делать ее самостоятельно или копировать откуда-либо!
|
||||
> Рабочую ссылку может выдать только команда из 6 пункта. Не пытайтесь делать ее самостоятельно или копировать откуда-либо если вы не уверены в том, что делаете!
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -269,6 +269,10 @@ pub(super) struct DcStatus {
|
||||
pub(super) available_endpoints: usize,
|
||||
pub(super) available_pct: f64,
|
||||
pub(super) required_writers: usize,
|
||||
pub(super) floor_min: usize,
|
||||
pub(super) floor_target: usize,
|
||||
pub(super) floor_max: usize,
|
||||
pub(super) floor_capped: bool,
|
||||
pub(super) alive_writers: usize,
|
||||
pub(super) coverage_pct: f64,
|
||||
pub(super) rtt_ms: Option<f64>,
|
||||
@@ -308,7 +312,17 @@ pub(super) struct MinimalMeRuntimeData {
|
||||
pub(super) floor_mode: &'static str,
|
||||
pub(super) adaptive_floor_idle_secs: u64,
|
||||
pub(super) adaptive_floor_min_writers_single_endpoint: u8,
|
||||
pub(super) adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
pub(super) adaptive_floor_recover_grace_secs: u64,
|
||||
pub(super) adaptive_floor_writers_per_core_total: u16,
|
||||
pub(super) adaptive_floor_cpu_cores_override: u16,
|
||||
pub(super) adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
pub(super) adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
pub(super) adaptive_floor_cpu_cores_detected: u32,
|
||||
pub(super) adaptive_floor_cpu_cores_effective: u32,
|
||||
pub(super) adaptive_floor_global_cap_raw: u64,
|
||||
pub(super) adaptive_floor_global_cap_effective: u64,
|
||||
pub(super) adaptive_floor_target_writers_total: u64,
|
||||
pub(super) me_keepalive_enabled: bool,
|
||||
pub(super) me_keepalive_interval_secs: u64,
|
||||
pub(super) me_keepalive_jitter_secs: u64,
|
||||
|
||||
@@ -349,6 +349,10 @@ async fn get_minimal_payload_cached(
|
||||
available_endpoints: entry.available_endpoints,
|
||||
available_pct: entry.available_pct,
|
||||
required_writers: entry.required_writers,
|
||||
floor_min: entry.floor_min,
|
||||
floor_target: entry.floor_target,
|
||||
floor_max: entry.floor_max,
|
||||
floor_capped: entry.floor_capped,
|
||||
alive_writers: entry.alive_writers,
|
||||
coverage_pct: entry.coverage_pct,
|
||||
rtt_ms: entry.rtt_ms,
|
||||
@@ -366,7 +370,21 @@ async fn get_minimal_payload_cached(
|
||||
adaptive_floor_idle_secs: runtime.adaptive_floor_idle_secs,
|
||||
adaptive_floor_min_writers_single_endpoint: runtime
|
||||
.adaptive_floor_min_writers_single_endpoint,
|
||||
adaptive_floor_min_writers_multi_endpoint: runtime
|
||||
.adaptive_floor_min_writers_multi_endpoint,
|
||||
adaptive_floor_recover_grace_secs: runtime.adaptive_floor_recover_grace_secs,
|
||||
adaptive_floor_writers_per_core_total: runtime
|
||||
.adaptive_floor_writers_per_core_total,
|
||||
adaptive_floor_cpu_cores_override: runtime.adaptive_floor_cpu_cores_override,
|
||||
adaptive_floor_max_extra_writers_single_per_core: runtime
|
||||
.adaptive_floor_max_extra_writers_single_per_core,
|
||||
adaptive_floor_max_extra_writers_multi_per_core: runtime
|
||||
.adaptive_floor_max_extra_writers_multi_per_core,
|
||||
adaptive_floor_cpu_cores_detected: runtime.adaptive_floor_cpu_cores_detected,
|
||||
adaptive_floor_cpu_cores_effective: runtime.adaptive_floor_cpu_cores_effective,
|
||||
adaptive_floor_global_cap_raw: runtime.adaptive_floor_global_cap_raw,
|
||||
adaptive_floor_global_cap_effective: runtime.adaptive_floor_global_cap_effective,
|
||||
adaptive_floor_target_writers_total: runtime.adaptive_floor_target_writers_total,
|
||||
me_keepalive_enabled: runtime.me_keepalive_enabled,
|
||||
me_keepalive_interval_secs: runtime.me_keepalive_interval_secs,
|
||||
me_keepalive_jitter_secs: runtime.me_keepalive_jitter_secs,
|
||||
|
||||
@@ -60,7 +60,12 @@ pub(super) struct EffectiveMiddleProxyLimits {
|
||||
pub(super) floor_mode: &'static str,
|
||||
pub(super) adaptive_floor_idle_secs: u64,
|
||||
pub(super) adaptive_floor_min_writers_single_endpoint: u8,
|
||||
pub(super) adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
pub(super) adaptive_floor_recover_grace_secs: u64,
|
||||
pub(super) adaptive_floor_writers_per_core_total: u16,
|
||||
pub(super) adaptive_floor_cpu_cores_override: u16,
|
||||
pub(super) adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
pub(super) adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
pub(super) reconnect_max_concurrent_per_dc: u32,
|
||||
pub(super) reconnect_backoff_base_ms: u64,
|
||||
pub(super) reconnect_backoff_cap_ms: u64,
|
||||
@@ -183,7 +188,22 @@ pub(super) fn build_limits_effective_data(cfg: &ProxyConfig) -> EffectiveLimitsD
|
||||
adaptive_floor_min_writers_single_endpoint: cfg
|
||||
.general
|
||||
.me_adaptive_floor_min_writers_single_endpoint,
|
||||
adaptive_floor_min_writers_multi_endpoint: cfg
|
||||
.general
|
||||
.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
adaptive_floor_recover_grace_secs: cfg.general.me_adaptive_floor_recover_grace_secs,
|
||||
adaptive_floor_writers_per_core_total: cfg
|
||||
.general
|
||||
.me_adaptive_floor_writers_per_core_total,
|
||||
adaptive_floor_cpu_cores_override: cfg
|
||||
.general
|
||||
.me_adaptive_floor_cpu_cores_override,
|
||||
adaptive_floor_max_extra_writers_single_per_core: cfg
|
||||
.general
|
||||
.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
adaptive_floor_max_extra_writers_multi_per_core: cfg
|
||||
.general
|
||||
.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
reconnect_max_concurrent_per_dc: cfg.general.me_reconnect_max_concurrent_per_dc,
|
||||
reconnect_backoff_base_ms: cfg.general.me_reconnect_backoff_base_ms,
|
||||
reconnect_backoff_cap_ms: cfg.general.me_reconnect_backoff_cap_ms,
|
||||
|
||||
@@ -11,7 +11,12 @@ const DEFAULT_ME_RECONNECT_FAST_RETRY_COUNT: u32 = 16;
|
||||
const DEFAULT_ME_SINGLE_ENDPOINT_SHADOW_WRITERS: u8 = 2;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_IDLE_SECS: u64 = 90;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_MIN_WRITERS_SINGLE_ENDPOINT: u8 = 1;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_MIN_WRITERS_MULTI_ENDPOINT: u8 = 1;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_RECOVER_GRACE_SECS: u64 = 180;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_WRITERS_PER_CORE_TOTAL: u16 = 48;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_CPU_CORES_OVERRIDE: u16 = 0;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_EXTRA_WRITERS_SINGLE_PER_CORE: u16 = 1;
|
||||
const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_EXTRA_WRITERS_MULTI_PER_CORE: u16 = 2;
|
||||
const DEFAULT_USER_MAX_UNIQUE_IPS_WINDOW_SECS: u64 = 30;
|
||||
const DEFAULT_UPSTREAM_CONNECT_RETRY_ATTEMPTS: u32 = 2;
|
||||
const DEFAULT_UPSTREAM_UNHEALTHY_FAIL_THRESHOLD: u32 = 5;
|
||||
@@ -247,10 +252,30 @@ pub(crate) fn default_me_adaptive_floor_min_writers_single_endpoint() -> u8 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_MIN_WRITERS_SINGLE_ENDPOINT
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_min_writers_multi_endpoint() -> u8 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_MIN_WRITERS_MULTI_ENDPOINT
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_recover_grace_secs() -> u64 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_RECOVER_GRACE_SECS
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_writers_per_core_total() -> u16 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_WRITERS_PER_CORE_TOTAL
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_cpu_cores_override() -> u16 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_CPU_CORES_OVERRIDE
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_max_extra_writers_single_per_core() -> u16 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_MAX_EXTRA_WRITERS_SINGLE_PER_CORE
|
||||
}
|
||||
|
||||
pub(crate) fn default_me_adaptive_floor_max_extra_writers_multi_per_core() -> u16 {
|
||||
DEFAULT_ME_ADAPTIVE_FLOOR_MAX_EXTRA_WRITERS_MULTI_PER_CORE
|
||||
}
|
||||
|
||||
pub(crate) fn default_upstream_connect_retry_attempts() -> u32 {
|
||||
DEFAULT_UPSTREAM_CONNECT_RETRY_ATTEMPTS
|
||||
}
|
||||
|
||||
@@ -78,7 +78,12 @@ pub struct HotFields {
|
||||
pub me_floor_mode: MeFloorMode,
|
||||
pub me_adaptive_floor_idle_secs: u64,
|
||||
pub me_adaptive_floor_min_writers_single_endpoint: u8,
|
||||
pub me_adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
pub me_adaptive_floor_recover_grace_secs: u64,
|
||||
pub me_adaptive_floor_writers_per_core_total: u16,
|
||||
pub me_adaptive_floor_cpu_cores_override: u16,
|
||||
pub me_adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
pub me_adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
pub me_route_backpressure_base_timeout_ms: u64,
|
||||
pub me_route_backpressure_high_timeout_ms: u64,
|
||||
pub me_route_backpressure_high_watermark_pct: u8,
|
||||
@@ -150,9 +155,24 @@ impl HotFields {
|
||||
me_adaptive_floor_min_writers_single_endpoint: cfg
|
||||
.general
|
||||
.me_adaptive_floor_min_writers_single_endpoint,
|
||||
me_adaptive_floor_min_writers_multi_endpoint: cfg
|
||||
.general
|
||||
.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
me_adaptive_floor_recover_grace_secs: cfg
|
||||
.general
|
||||
.me_adaptive_floor_recover_grace_secs,
|
||||
me_adaptive_floor_writers_per_core_total: cfg
|
||||
.general
|
||||
.me_adaptive_floor_writers_per_core_total,
|
||||
me_adaptive_floor_cpu_cores_override: cfg
|
||||
.general
|
||||
.me_adaptive_floor_cpu_cores_override,
|
||||
me_adaptive_floor_max_extra_writers_single_per_core: cfg
|
||||
.general
|
||||
.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
me_adaptive_floor_max_extra_writers_multi_per_core: cfg
|
||||
.general
|
||||
.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
me_route_backpressure_base_timeout_ms: cfg.general.me_route_backpressure_base_timeout_ms,
|
||||
me_route_backpressure_high_timeout_ms: cfg.general.me_route_backpressure_high_timeout_ms,
|
||||
me_route_backpressure_high_watermark_pct: cfg.general.me_route_backpressure_high_watermark_pct,
|
||||
@@ -273,8 +293,18 @@ fn overlay_hot_fields(old: &ProxyConfig, new: &ProxyConfig) -> ProxyConfig {
|
||||
cfg.general.me_adaptive_floor_idle_secs = new.general.me_adaptive_floor_idle_secs;
|
||||
cfg.general.me_adaptive_floor_min_writers_single_endpoint =
|
||||
new.general.me_adaptive_floor_min_writers_single_endpoint;
|
||||
cfg.general.me_adaptive_floor_min_writers_multi_endpoint =
|
||||
new.general.me_adaptive_floor_min_writers_multi_endpoint;
|
||||
cfg.general.me_adaptive_floor_recover_grace_secs =
|
||||
new.general.me_adaptive_floor_recover_grace_secs;
|
||||
cfg.general.me_adaptive_floor_writers_per_core_total =
|
||||
new.general.me_adaptive_floor_writers_per_core_total;
|
||||
cfg.general.me_adaptive_floor_cpu_cores_override =
|
||||
new.general.me_adaptive_floor_cpu_cores_override;
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_single_per_core =
|
||||
new.general.me_adaptive_floor_max_extra_writers_single_per_core;
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_multi_per_core =
|
||||
new.general.me_adaptive_floor_max_extra_writers_multi_per_core;
|
||||
cfg.general.me_route_backpressure_base_timeout_ms =
|
||||
new.general.me_route_backpressure_base_timeout_ms;
|
||||
cfg.general.me_route_backpressure_high_timeout_ms =
|
||||
@@ -697,15 +727,30 @@ fn log_changes(
|
||||
|| old_hot.me_adaptive_floor_idle_secs != new_hot.me_adaptive_floor_idle_secs
|
||||
|| old_hot.me_adaptive_floor_min_writers_single_endpoint
|
||||
!= new_hot.me_adaptive_floor_min_writers_single_endpoint
|
||||
|| old_hot.me_adaptive_floor_min_writers_multi_endpoint
|
||||
!= new_hot.me_adaptive_floor_min_writers_multi_endpoint
|
||||
|| old_hot.me_adaptive_floor_recover_grace_secs
|
||||
!= new_hot.me_adaptive_floor_recover_grace_secs
|
||||
|| old_hot.me_adaptive_floor_writers_per_core_total
|
||||
!= new_hot.me_adaptive_floor_writers_per_core_total
|
||||
|| old_hot.me_adaptive_floor_cpu_cores_override
|
||||
!= new_hot.me_adaptive_floor_cpu_cores_override
|
||||
|| old_hot.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
!= new_hot.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
|| old_hot.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
!= new_hot.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
{
|
||||
info!(
|
||||
"config reload: me_floor: mode={:?} idle={}s min_single={} recover_grace={}s",
|
||||
"config reload: me_floor: mode={:?} idle={}s min_single={} min_multi={} recover_grace={}s per_core_total={} cores_override={} extra_single_per_core={} extra_multi_per_core={}",
|
||||
new_hot.me_floor_mode,
|
||||
new_hot.me_adaptive_floor_idle_secs,
|
||||
new_hot.me_adaptive_floor_min_writers_single_endpoint,
|
||||
new_hot.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
new_hot.me_adaptive_floor_recover_grace_secs,
|
||||
new_hot.me_adaptive_floor_writers_per_core_total,
|
||||
new_hot.me_adaptive_floor_cpu_cores_override,
|
||||
new_hot.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
new_hot.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -312,6 +312,21 @@ impl ProxyConfig {
|
||||
));
|
||||
}
|
||||
|
||||
if config.general.me_adaptive_floor_min_writers_multi_endpoint == 0
|
||||
|| config.general.me_adaptive_floor_min_writers_multi_endpoint > 32
|
||||
{
|
||||
return Err(ProxyError::Config(
|
||||
"general.me_adaptive_floor_min_writers_multi_endpoint must be within [1, 32]"
|
||||
.to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
if config.general.me_adaptive_floor_writers_per_core_total == 0 {
|
||||
return Err(ProxyError::Config(
|
||||
"general.me_adaptive_floor_writers_per_core_total must be > 0".to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
if config.general.me_single_endpoint_outage_backoff_min_ms == 0 {
|
||||
return Err(ProxyError::Config(
|
||||
"general.me_single_endpoint_outage_backoff_min_ms must be > 0".to_string(),
|
||||
|
||||
@@ -520,10 +520,31 @@ pub struct GeneralConfig {
|
||||
#[serde(default = "default_me_adaptive_floor_min_writers_single_endpoint")]
|
||||
pub me_adaptive_floor_min_writers_single_endpoint: u8,
|
||||
|
||||
/// Minimum writer target for multi-endpoint DC groups in adaptive floor mode.
|
||||
#[serde(default = "default_me_adaptive_floor_min_writers_multi_endpoint")]
|
||||
pub me_adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
|
||||
/// Grace period in seconds to hold static floor after activity in adaptive mode.
|
||||
#[serde(default = "default_me_adaptive_floor_recover_grace_secs")]
|
||||
pub me_adaptive_floor_recover_grace_secs: u64,
|
||||
|
||||
/// Global ME writer budget per logical CPU core in adaptive mode.
|
||||
#[serde(default = "default_me_adaptive_floor_writers_per_core_total")]
|
||||
pub me_adaptive_floor_writers_per_core_total: u16,
|
||||
|
||||
/// Override logical CPU core count for adaptive floor calculations.
|
||||
/// Set to 0 to use runtime auto-detection.
|
||||
#[serde(default = "default_me_adaptive_floor_cpu_cores_override")]
|
||||
pub me_adaptive_floor_cpu_cores_override: u16,
|
||||
|
||||
/// Per-core max extra writers above base required floor for single-endpoint DC groups.
|
||||
#[serde(default = "default_me_adaptive_floor_max_extra_writers_single_per_core")]
|
||||
pub me_adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
|
||||
/// Per-core max extra writers above base required floor for multi-endpoint DC groups.
|
||||
#[serde(default = "default_me_adaptive_floor_max_extra_writers_multi_per_core")]
|
||||
pub me_adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
|
||||
/// Connect attempts for the selected upstream before returning error/fallback.
|
||||
#[serde(default = "default_upstream_connect_retry_attempts")]
|
||||
pub upstream_connect_retry_attempts: u32,
|
||||
@@ -775,7 +796,12 @@ impl Default for GeneralConfig {
|
||||
me_floor_mode: MeFloorMode::default(),
|
||||
me_adaptive_floor_idle_secs: default_me_adaptive_floor_idle_secs(),
|
||||
me_adaptive_floor_min_writers_single_endpoint: default_me_adaptive_floor_min_writers_single_endpoint(),
|
||||
me_adaptive_floor_min_writers_multi_endpoint: default_me_adaptive_floor_min_writers_multi_endpoint(),
|
||||
me_adaptive_floor_recover_grace_secs: default_me_adaptive_floor_recover_grace_secs(),
|
||||
me_adaptive_floor_writers_per_core_total: default_me_adaptive_floor_writers_per_core_total(),
|
||||
me_adaptive_floor_cpu_cores_override: default_me_adaptive_floor_cpu_cores_override(),
|
||||
me_adaptive_floor_max_extra_writers_single_per_core: default_me_adaptive_floor_max_extra_writers_single_per_core(),
|
||||
me_adaptive_floor_max_extra_writers_multi_per_core: default_me_adaptive_floor_max_extra_writers_multi_per_core(),
|
||||
upstream_connect_retry_attempts: default_upstream_connect_retry_attempts(),
|
||||
upstream_connect_retry_backoff_ms: default_upstream_connect_retry_backoff_ms(),
|
||||
upstream_connect_budget_ms: default_upstream_connect_budget_ms(),
|
||||
|
||||
@@ -786,7 +786,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
|
||||
config.general.me_floor_mode,
|
||||
config.general.me_adaptive_floor_idle_secs,
|
||||
config.general.me_adaptive_floor_min_writers_single_endpoint,
|
||||
config.general.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
config.general.me_adaptive_floor_recover_grace_secs,
|
||||
config.general.me_adaptive_floor_writers_per_core_total,
|
||||
config.general.me_adaptive_floor_cpu_cores_override,
|
||||
config.general.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
config.general.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
config.general.hardswap,
|
||||
config.general.me_pool_drain_ttl_secs,
|
||||
config.general.effective_me_pool_force_close_secs(),
|
||||
|
||||
127
src/metrics.rs
127
src/metrics.rs
@@ -968,6 +968,133 @@ async fn render_metrics(stats: &Stats, config: &ProxyConfig, ip_tracker: &UserIp
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_adaptive_floor_cpu_cores_detected Runtime detected logical CPU cores for adaptive floor"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# TYPE telemt_me_adaptive_floor_cpu_cores_detected gauge"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_adaptive_floor_cpu_cores_detected {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_cpu_cores_detected_gauge()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_adaptive_floor_cpu_cores_effective Runtime effective logical CPU cores for adaptive floor"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# TYPE telemt_me_adaptive_floor_cpu_cores_effective gauge"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_adaptive_floor_cpu_cores_effective {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_cpu_cores_effective_gauge()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_adaptive_floor_global_cap_raw Runtime raw global adaptive floor cap"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# TYPE telemt_me_adaptive_floor_global_cap_raw gauge"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_adaptive_floor_global_cap_raw {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_global_cap_raw_gauge()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_adaptive_floor_global_cap_effective Runtime effective global adaptive floor cap"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# TYPE telemt_me_adaptive_floor_global_cap_effective gauge"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_adaptive_floor_global_cap_effective {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_global_cap_effective_gauge()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_adaptive_floor_target_writers_total Runtime adaptive floor target writers total"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# TYPE telemt_me_adaptive_floor_target_writers_total gauge"
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_adaptive_floor_target_writers_total {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_target_writers_total_gauge()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_floor_cap_block_total Reconnect attempts blocked by adaptive floor caps"
|
||||
);
|
||||
let _ = writeln!(out, "# TYPE telemt_me_floor_cap_block_total counter");
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_floor_cap_block_total {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_cap_block_total()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_floor_swap_idle_total Adaptive floor cap recovery via idle writer swap"
|
||||
);
|
||||
let _ = writeln!(out, "# TYPE telemt_me_floor_swap_idle_total counter");
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_floor_swap_idle_total {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_swap_idle_total()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"# HELP telemt_me_floor_swap_idle_failed_total Failed idle swap attempts under adaptive floor caps"
|
||||
);
|
||||
let _ = writeln!(out, "# TYPE telemt_me_floor_swap_idle_failed_total counter");
|
||||
let _ = writeln!(
|
||||
out,
|
||||
"telemt_me_floor_swap_idle_failed_total {}",
|
||||
if me_allows_normal {
|
||||
stats.get_me_floor_swap_idle_failed_total()
|
||||
} else {
|
||||
0
|
||||
}
|
||||
);
|
||||
|
||||
let _ = writeln!(out, "# HELP telemt_secure_padding_invalid_total Invalid secure frame lengths");
|
||||
let _ = writeln!(out, "# TYPE telemt_secure_padding_invalid_total counter");
|
||||
|
||||
@@ -75,6 +75,14 @@ pub struct Stats {
|
||||
me_floor_mode_switch_total: AtomicU64,
|
||||
me_floor_mode_switch_static_to_adaptive_total: AtomicU64,
|
||||
me_floor_mode_switch_adaptive_to_static_total: AtomicU64,
|
||||
me_floor_cpu_cores_detected_gauge: AtomicU64,
|
||||
me_floor_cpu_cores_effective_gauge: AtomicU64,
|
||||
me_floor_global_cap_raw_gauge: AtomicU64,
|
||||
me_floor_global_cap_effective_gauge: AtomicU64,
|
||||
me_floor_target_writers_total_gauge: AtomicU64,
|
||||
me_floor_cap_block_total: AtomicU64,
|
||||
me_floor_swap_idle_total: AtomicU64,
|
||||
me_floor_swap_idle_failed_total: AtomicU64,
|
||||
me_handshake_error_codes: DashMap<i32, AtomicU64>,
|
||||
me_route_drop_no_conn: AtomicU64,
|
||||
me_route_drop_channel_closed: AtomicU64,
|
||||
@@ -676,6 +684,52 @@ impl Stats {
|
||||
.fetch_add(1, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn set_me_floor_cpu_cores_detected_gauge(&self, value: u64) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_cpu_cores_detected_gauge
|
||||
.store(value, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn set_me_floor_cpu_cores_effective_gauge(&self, value: u64) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_cpu_cores_effective_gauge
|
||||
.store(value, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn set_me_floor_global_cap_raw_gauge(&self, value: u64) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_global_cap_raw_gauge
|
||||
.store(value, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn set_me_floor_global_cap_effective_gauge(&self, value: u64) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_global_cap_effective_gauge
|
||||
.store(value, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn set_me_floor_target_writers_total_gauge(&self, value: u64) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_target_writers_total_gauge
|
||||
.store(value, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn increment_me_floor_cap_block_total(&self) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_cap_block_total.fetch_add(1, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn increment_me_floor_swap_idle_total(&self) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_swap_idle_total.fetch_add(1, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn increment_me_floor_swap_idle_failed_total(&self) {
|
||||
if self.telemetry_me_allows_normal() {
|
||||
self.me_floor_swap_idle_failed_total
|
||||
.fetch_add(1, Ordering::Relaxed);
|
||||
}
|
||||
}
|
||||
pub fn get_connects_all(&self) -> u64 { self.connects_all.load(Ordering::Relaxed) }
|
||||
pub fn get_connects_bad(&self) -> u64 { self.connects_bad.load(Ordering::Relaxed) }
|
||||
pub fn get_current_connections_direct(&self) -> u64 {
|
||||
@@ -781,6 +835,34 @@ impl Stats {
|
||||
self.me_floor_mode_switch_adaptive_to_static_total
|
||||
.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_cpu_cores_detected_gauge(&self) -> u64 {
|
||||
self.me_floor_cpu_cores_detected_gauge
|
||||
.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_cpu_cores_effective_gauge(&self) -> u64 {
|
||||
self.me_floor_cpu_cores_effective_gauge
|
||||
.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_global_cap_raw_gauge(&self) -> u64 {
|
||||
self.me_floor_global_cap_raw_gauge.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_global_cap_effective_gauge(&self) -> u64 {
|
||||
self.me_floor_global_cap_effective_gauge
|
||||
.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_target_writers_total_gauge(&self) -> u64 {
|
||||
self.me_floor_target_writers_total_gauge
|
||||
.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_cap_block_total(&self) -> u64 {
|
||||
self.me_floor_cap_block_total.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_swap_idle_total(&self) -> u64 {
|
||||
self.me_floor_swap_idle_total.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_floor_swap_idle_failed_total(&self) -> u64 {
|
||||
self.me_floor_swap_idle_failed_total.load(Ordering::Relaxed)
|
||||
}
|
||||
pub fn get_me_handshake_error_code_counts(&self) -> Vec<(i32, u64)> {
|
||||
let mut out: Vec<(i32, u64)> = self
|
||||
.me_handshake_error_codes
|
||||
|
||||
@@ -315,7 +315,12 @@ async fn run_update_cycle(
|
||||
cfg.general.me_floor_mode,
|
||||
cfg.general.me_adaptive_floor_idle_secs,
|
||||
cfg.general.me_adaptive_floor_min_writers_single_endpoint,
|
||||
cfg.general.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
cfg.general.me_adaptive_floor_recover_grace_secs,
|
||||
cfg.general.me_adaptive_floor_writers_per_core_total,
|
||||
cfg.general.me_adaptive_floor_cpu_cores_override,
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
);
|
||||
|
||||
let required_cfg_snapshots = cfg.general.me_config_stable_snapshots.max(1);
|
||||
@@ -527,7 +532,12 @@ pub async fn me_config_updater(
|
||||
cfg.general.me_floor_mode,
|
||||
cfg.general.me_adaptive_floor_idle_secs,
|
||||
cfg.general.me_adaptive_floor_min_writers_single_endpoint,
|
||||
cfg.general.me_adaptive_floor_min_writers_multi_endpoint,
|
||||
cfg.general.me_adaptive_floor_recover_grace_secs,
|
||||
cfg.general.me_adaptive_floor_writers_per_core_total,
|
||||
cfg.general.me_adaptive_floor_cpu_cores_override,
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_single_per_core,
|
||||
cfg.general.me_adaptive_floor_max_extra_writers_multi_per_core,
|
||||
);
|
||||
let new_secs = cfg.general.effective_update_every_secs().max(1);
|
||||
if new_secs == update_every_secs {
|
||||
|
||||
@@ -23,6 +23,25 @@ const IDLE_REFRESH_TRIGGER_JITTER_SECS: u64 = 5;
|
||||
const IDLE_REFRESH_RETRY_SECS: u64 = 8;
|
||||
const IDLE_REFRESH_SUCCESS_GUARD_SECS: u64 = 5;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
struct DcFloorPlanEntry {
|
||||
dc: i32,
|
||||
endpoints: Vec<SocketAddr>,
|
||||
alive: usize,
|
||||
min_required: usize,
|
||||
target_required: usize,
|
||||
max_required: usize,
|
||||
has_bound_clients: bool,
|
||||
floor_capped: bool,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
struct FamilyFloorPlan {
|
||||
by_dc: HashMap<i32, DcFloorPlanEntry>,
|
||||
global_cap_effective_total: usize,
|
||||
target_writers_total: usize,
|
||||
}
|
||||
|
||||
pub async fn me_health_monitor(pool: Arc<MePool>, rng: Arc<SecureRandom>, _min_connections: usize) {
|
||||
let mut backoff: HashMap<(i32, IpFamily), u64> = HashMap::new();
|
||||
let mut next_attempt: HashMap<(i32, IpFamily), Instant> = HashMap::new();
|
||||
@@ -129,22 +148,33 @@ async fn check_family(
|
||||
.push(writer.id);
|
||||
}
|
||||
let writer_idle_since = pool.registry.writer_idle_since_snapshot().await;
|
||||
let floor_plan = build_family_floor_plan(
|
||||
pool,
|
||||
family,
|
||||
&dc_endpoints,
|
||||
&live_addr_counts,
|
||||
&live_writer_ids_by_addr,
|
||||
adaptive_idle_since,
|
||||
adaptive_recover_until,
|
||||
)
|
||||
.await;
|
||||
pool.set_adaptive_floor_runtime_caps(
|
||||
floor_plan.global_cap_effective_total,
|
||||
floor_plan.target_writers_total,
|
||||
);
|
||||
|
||||
for (dc, endpoints) in dc_endpoints {
|
||||
if endpoints.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let key = (dc, family);
|
||||
let reduce_for_idle = should_reduce_floor_for_idle(
|
||||
pool,
|
||||
key,
|
||||
&endpoints,
|
||||
&live_writer_ids_by_addr,
|
||||
adaptive_idle_since,
|
||||
adaptive_recover_until,
|
||||
)
|
||||
.await;
|
||||
let required = pool.required_writers_for_dc_with_floor_mode(endpoints.len(), reduce_for_idle);
|
||||
let required = floor_plan
|
||||
.by_dc
|
||||
.get(&dc)
|
||||
.map(|entry| entry.target_required)
|
||||
.unwrap_or_else(|| {
|
||||
pool.required_writers_for_dc_with_floor_mode(endpoints.len(), false)
|
||||
});
|
||||
let alive = endpoints
|
||||
.iter()
|
||||
.map(|addr| *live_addr_counts.get(addr).unwrap_or(&0))
|
||||
@@ -251,6 +281,36 @@ async fn check_family(
|
||||
|
||||
let mut restored = 0usize;
|
||||
for _ in 0..missing {
|
||||
if pool.floor_mode() == MeFloorMode::Adaptive
|
||||
&& pool.active_writer_count_total().await >= floor_plan.global_cap_effective_total
|
||||
{
|
||||
let swapped = maybe_swap_idle_writer_for_cap(
|
||||
pool,
|
||||
rng,
|
||||
dc,
|
||||
family,
|
||||
&endpoints,
|
||||
&live_writer_ids_by_addr,
|
||||
&writer_idle_since,
|
||||
)
|
||||
.await;
|
||||
if swapped {
|
||||
pool.stats.increment_me_floor_swap_idle_total();
|
||||
restored += 1;
|
||||
continue;
|
||||
}
|
||||
pool.stats.increment_me_floor_cap_block_total();
|
||||
pool.stats.increment_me_floor_swap_idle_failed_total();
|
||||
debug!(
|
||||
dc = %dc,
|
||||
?family,
|
||||
alive,
|
||||
required,
|
||||
global_cap_effective_total = floor_plan.global_cap_effective_total,
|
||||
"Adaptive floor cap reached, reconnect attempt blocked"
|
||||
);
|
||||
break;
|
||||
}
|
||||
let res = tokio::time::timeout(
|
||||
pool.me_one_timeout,
|
||||
pool.connect_endpoints_round_robin(&endpoints, rng.as_ref()),
|
||||
@@ -323,6 +383,280 @@ async fn check_family(
|
||||
}
|
||||
}
|
||||
|
||||
fn adaptive_floor_class_min(
|
||||
pool: &Arc<MePool>,
|
||||
endpoint_count: usize,
|
||||
base_required: usize,
|
||||
) -> usize {
|
||||
if endpoint_count <= 1 {
|
||||
let min_single = (pool
|
||||
.me_adaptive_floor_min_writers_single_endpoint
|
||||
.load(std::sync::atomic::Ordering::Relaxed) as usize)
|
||||
.max(1);
|
||||
min_single.min(base_required.max(1))
|
||||
} else {
|
||||
pool.adaptive_floor_min_writers_multi_endpoint()
|
||||
.min(base_required.max(1))
|
||||
}
|
||||
}
|
||||
|
||||
fn adaptive_floor_class_max(
|
||||
pool: &Arc<MePool>,
|
||||
endpoint_count: usize,
|
||||
base_required: usize,
|
||||
cpu_cores: usize,
|
||||
) -> usize {
|
||||
let extra_per_core = if endpoint_count <= 1 {
|
||||
pool.adaptive_floor_max_extra_single_per_core()
|
||||
} else {
|
||||
pool.adaptive_floor_max_extra_multi_per_core()
|
||||
};
|
||||
base_required.saturating_add(cpu_cores.saturating_mul(extra_per_core))
|
||||
}
|
||||
|
||||
fn list_writer_ids_for_endpoints(
|
||||
endpoints: &[SocketAddr],
|
||||
live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
|
||||
) -> Vec<u64> {
|
||||
let mut out = Vec::<u64>::new();
|
||||
for endpoint in endpoints {
|
||||
if let Some(ids) = live_writer_ids_by_addr.get(endpoint) {
|
||||
out.extend(ids.iter().copied());
|
||||
}
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
async fn build_family_floor_plan(
|
||||
pool: &Arc<MePool>,
|
||||
family: IpFamily,
|
||||
dc_endpoints: &HashMap<i32, Vec<SocketAddr>>,
|
||||
live_addr_counts: &HashMap<SocketAddr, usize>,
|
||||
live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
|
||||
adaptive_idle_since: &mut HashMap<(i32, IpFamily), Instant>,
|
||||
adaptive_recover_until: &mut HashMap<(i32, IpFamily), Instant>,
|
||||
) -> FamilyFloorPlan {
|
||||
let mut entries = Vec::<DcFloorPlanEntry>::new();
|
||||
let mut by_dc = HashMap::<i32, DcFloorPlanEntry>::new();
|
||||
let mut family_active_total = 0usize;
|
||||
|
||||
let floor_mode = pool.floor_mode();
|
||||
let is_adaptive = floor_mode == MeFloorMode::Adaptive;
|
||||
let cpu_cores = pool.adaptive_floor_effective_cpu_cores().max(1);
|
||||
|
||||
for (dc, endpoints) in dc_endpoints {
|
||||
if endpoints.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let key = (*dc, family);
|
||||
let reduce_for_idle = should_reduce_floor_for_idle(
|
||||
pool,
|
||||
key,
|
||||
endpoints,
|
||||
live_writer_ids_by_addr,
|
||||
adaptive_idle_since,
|
||||
adaptive_recover_until,
|
||||
)
|
||||
.await;
|
||||
let base_required = pool.required_writers_for_dc(endpoints.len()).max(1);
|
||||
let min_required = if is_adaptive {
|
||||
adaptive_floor_class_min(pool, endpoints.len(), base_required)
|
||||
} else {
|
||||
base_required
|
||||
};
|
||||
let mut max_required = if is_adaptive {
|
||||
adaptive_floor_class_max(pool, endpoints.len(), base_required, cpu_cores)
|
||||
} else {
|
||||
base_required
|
||||
};
|
||||
if max_required < min_required {
|
||||
max_required = min_required;
|
||||
}
|
||||
let desired_raw = if is_adaptive && reduce_for_idle {
|
||||
min_required
|
||||
} else {
|
||||
base_required
|
||||
};
|
||||
let target_required = desired_raw.clamp(min_required, max_required);
|
||||
let alive = endpoints
|
||||
.iter()
|
||||
.map(|endpoint| live_addr_counts.get(endpoint).copied().unwrap_or(0))
|
||||
.sum::<usize>();
|
||||
family_active_total = family_active_total.saturating_add(alive);
|
||||
let writer_ids = list_writer_ids_for_endpoints(endpoints, live_writer_ids_by_addr);
|
||||
let has_bound_clients = has_bound_clients_on_endpoint(pool, &writer_ids).await;
|
||||
|
||||
entries.push(DcFloorPlanEntry {
|
||||
dc: *dc,
|
||||
endpoints: endpoints.clone(),
|
||||
alive,
|
||||
min_required,
|
||||
target_required,
|
||||
max_required,
|
||||
has_bound_clients,
|
||||
floor_capped: false,
|
||||
});
|
||||
}
|
||||
|
||||
if entries.is_empty() {
|
||||
return FamilyFloorPlan {
|
||||
by_dc,
|
||||
global_cap_effective_total: 0,
|
||||
target_writers_total: 0,
|
||||
};
|
||||
}
|
||||
|
||||
if !is_adaptive {
|
||||
let target_total = entries
|
||||
.iter()
|
||||
.map(|entry| entry.target_required)
|
||||
.sum::<usize>();
|
||||
let active_total = pool.active_writer_count_total().await;
|
||||
for entry in entries {
|
||||
by_dc.insert(entry.dc, entry);
|
||||
}
|
||||
return FamilyFloorPlan {
|
||||
by_dc,
|
||||
global_cap_effective_total: active_total.max(target_total),
|
||||
target_writers_total: target_total,
|
||||
};
|
||||
}
|
||||
|
||||
let global_cap_raw = pool.adaptive_floor_global_cap_raw();
|
||||
let total_active = pool.active_writer_count_total().await;
|
||||
let other_active = total_active.saturating_sub(family_active_total);
|
||||
let min_sum = entries
|
||||
.iter()
|
||||
.map(|entry| entry.min_required)
|
||||
.sum::<usize>();
|
||||
let mut target_sum = entries
|
||||
.iter()
|
||||
.map(|entry| entry.target_required)
|
||||
.sum::<usize>();
|
||||
let family_cap = global_cap_raw
|
||||
.saturating_sub(other_active)
|
||||
.max(min_sum);
|
||||
if target_sum > family_cap {
|
||||
entries.sort_by_key(|entry| {
|
||||
(
|
||||
entry.has_bound_clients,
|
||||
std::cmp::Reverse(entry.target_required.saturating_sub(entry.min_required)),
|
||||
std::cmp::Reverse(entry.alive),
|
||||
entry.dc.abs(),
|
||||
entry.dc,
|
||||
entry.endpoints.len(),
|
||||
entry.max_required,
|
||||
)
|
||||
});
|
||||
let mut changed = true;
|
||||
while target_sum > family_cap && changed {
|
||||
changed = false;
|
||||
for entry in &mut entries {
|
||||
if target_sum <= family_cap {
|
||||
break;
|
||||
}
|
||||
if entry.target_required > entry.min_required {
|
||||
entry.target_required -= 1;
|
||||
entry.floor_capped = true;
|
||||
target_sum -= 1;
|
||||
changed = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for entry in entries {
|
||||
by_dc.insert(entry.dc, entry);
|
||||
}
|
||||
let global_cap_effective_total = global_cap_raw.max(other_active.saturating_add(min_sum));
|
||||
let target_writers_total = other_active.saturating_add(target_sum);
|
||||
FamilyFloorPlan {
|
||||
by_dc,
|
||||
global_cap_effective_total,
|
||||
target_writers_total,
|
||||
}
|
||||
}
|
||||
|
||||
async fn maybe_swap_idle_writer_for_cap(
|
||||
pool: &Arc<MePool>,
|
||||
rng: &Arc<SecureRandom>,
|
||||
dc: i32,
|
||||
family: IpFamily,
|
||||
endpoints: &[SocketAddr],
|
||||
live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
|
||||
writer_idle_since: &HashMap<u64, u64>,
|
||||
) -> bool {
|
||||
let now_epoch_secs = MePool::now_epoch_secs();
|
||||
let mut candidate: Option<(u64, SocketAddr, u64)> = None;
|
||||
for endpoint in endpoints {
|
||||
let Some(writer_ids) = live_writer_ids_by_addr.get(endpoint) else {
|
||||
continue;
|
||||
};
|
||||
for writer_id in writer_ids {
|
||||
if !pool.registry.is_writer_empty(*writer_id).await {
|
||||
continue;
|
||||
}
|
||||
let Some(idle_since_epoch_secs) = writer_idle_since.get(writer_id).copied() else {
|
||||
continue;
|
||||
};
|
||||
let idle_age_secs = now_epoch_secs.saturating_sub(idle_since_epoch_secs);
|
||||
if candidate
|
||||
.as_ref()
|
||||
.map(|(_, _, age)| idle_age_secs > *age)
|
||||
.unwrap_or(true)
|
||||
{
|
||||
candidate = Some((*writer_id, *endpoint, idle_age_secs));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let Some((old_writer_id, endpoint, idle_age_secs)) = candidate else {
|
||||
return false;
|
||||
};
|
||||
|
||||
let connected = match tokio::time::timeout(pool.me_one_timeout, pool.connect_one(endpoint, rng.as_ref())).await {
|
||||
Ok(Ok(())) => true,
|
||||
Ok(Err(error)) => {
|
||||
debug!(
|
||||
dc = %dc,
|
||||
?family,
|
||||
%endpoint,
|
||||
old_writer_id,
|
||||
idle_age_secs,
|
||||
%error,
|
||||
"Adaptive floor cap swap connect failed"
|
||||
);
|
||||
false
|
||||
}
|
||||
Err(_) => {
|
||||
debug!(
|
||||
dc = %dc,
|
||||
?family,
|
||||
%endpoint,
|
||||
old_writer_id,
|
||||
idle_age_secs,
|
||||
"Adaptive floor cap swap connect timed out"
|
||||
);
|
||||
false
|
||||
}
|
||||
};
|
||||
if !connected {
|
||||
return false;
|
||||
}
|
||||
|
||||
pool.mark_writer_draining_with_timeout(old_writer_id, pool.force_close_timeout(), false)
|
||||
.await;
|
||||
info!(
|
||||
dc = %dc,
|
||||
?family,
|
||||
%endpoint,
|
||||
old_writer_id,
|
||||
idle_age_secs,
|
||||
"Adaptive floor cap swap: idle writer rotated"
|
||||
);
|
||||
true
|
||||
}
|
||||
|
||||
async fn maybe_refresh_idle_writer_for_dc(
|
||||
pool: &Arc<MePool>,
|
||||
rng: &Arc<SecureRandom>,
|
||||
@@ -438,19 +772,15 @@ async fn should_reduce_floor_for_idle(
|
||||
adaptive_idle_since: &mut HashMap<(i32, IpFamily), Instant>,
|
||||
adaptive_recover_until: &mut HashMap<(i32, IpFamily), Instant>,
|
||||
) -> bool {
|
||||
if endpoints.len() != 1 || pool.floor_mode() != MeFloorMode::Adaptive {
|
||||
if pool.floor_mode() != MeFloorMode::Adaptive {
|
||||
adaptive_idle_since.remove(&key);
|
||||
adaptive_recover_until.remove(&key);
|
||||
return false;
|
||||
}
|
||||
|
||||
let now = Instant::now();
|
||||
let endpoint = endpoints[0];
|
||||
let writer_ids = live_writer_ids_by_addr
|
||||
.get(&endpoint)
|
||||
.map(Vec::as_slice)
|
||||
.unwrap_or(&[]);
|
||||
let has_bound_clients = has_bound_clients_on_endpoint(pool, writer_ids).await;
|
||||
let writer_ids = list_writer_ids_for_endpoints(endpoints, live_writer_ids_by_addr);
|
||||
let has_bound_clients = has_bound_clients_on_endpoint(pool, &writer_ids).await;
|
||||
if has_bound_clients {
|
||||
adaptive_idle_since.remove(&key);
|
||||
adaptive_recover_until.insert(key, now + pool.adaptive_floor_recover_grace_duration());
|
||||
|
||||
@@ -111,7 +111,17 @@ pub struct MePool {
|
||||
pub(super) me_floor_mode: AtomicU8,
|
||||
pub(super) me_adaptive_floor_idle_secs: AtomicU64,
|
||||
pub(super) me_adaptive_floor_min_writers_single_endpoint: AtomicU8,
|
||||
pub(super) me_adaptive_floor_min_writers_multi_endpoint: AtomicU8,
|
||||
pub(super) me_adaptive_floor_recover_grace_secs: AtomicU64,
|
||||
pub(super) me_adaptive_floor_writers_per_core_total: AtomicU32,
|
||||
pub(super) me_adaptive_floor_cpu_cores_override: AtomicU32,
|
||||
pub(super) me_adaptive_floor_max_extra_writers_single_per_core: AtomicU32,
|
||||
pub(super) me_adaptive_floor_max_extra_writers_multi_per_core: AtomicU32,
|
||||
pub(super) me_adaptive_floor_cpu_cores_detected: AtomicU32,
|
||||
pub(super) me_adaptive_floor_cpu_cores_effective: AtomicU32,
|
||||
pub(super) me_adaptive_floor_global_cap_raw: AtomicU64,
|
||||
pub(super) me_adaptive_floor_global_cap_effective: AtomicU64,
|
||||
pub(super) me_adaptive_floor_target_writers_total: AtomicU64,
|
||||
pub(super) proxy_map_v4: Arc<RwLock<HashMap<i32, Vec<(IpAddr, u16)>>>>,
|
||||
pub(super) proxy_map_v6: Arc<RwLock<HashMap<i32, Vec<(IpAddr, u16)>>>>,
|
||||
pub(super) default_dc: AtomicI32,
|
||||
@@ -217,7 +227,12 @@ impl MePool {
|
||||
me_floor_mode: MeFloorMode,
|
||||
me_adaptive_floor_idle_secs: u64,
|
||||
me_adaptive_floor_min_writers_single_endpoint: u8,
|
||||
me_adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
me_adaptive_floor_recover_grace_secs: u64,
|
||||
me_adaptive_floor_writers_per_core_total: u16,
|
||||
me_adaptive_floor_cpu_cores_override: u16,
|
||||
me_adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
me_adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
hardswap: bool,
|
||||
me_pool_drain_ttl_secs: u64,
|
||||
me_pool_force_close_secs: u64,
|
||||
@@ -314,9 +329,29 @@ impl MePool {
|
||||
me_adaptive_floor_min_writers_single_endpoint: AtomicU8::new(
|
||||
me_adaptive_floor_min_writers_single_endpoint,
|
||||
),
|
||||
me_adaptive_floor_min_writers_multi_endpoint: AtomicU8::new(
|
||||
me_adaptive_floor_min_writers_multi_endpoint,
|
||||
),
|
||||
me_adaptive_floor_recover_grace_secs: AtomicU64::new(
|
||||
me_adaptive_floor_recover_grace_secs,
|
||||
),
|
||||
me_adaptive_floor_writers_per_core_total: AtomicU32::new(
|
||||
me_adaptive_floor_writers_per_core_total as u32,
|
||||
),
|
||||
me_adaptive_floor_cpu_cores_override: AtomicU32::new(
|
||||
me_adaptive_floor_cpu_cores_override as u32,
|
||||
),
|
||||
me_adaptive_floor_max_extra_writers_single_per_core: AtomicU32::new(
|
||||
me_adaptive_floor_max_extra_writers_single_per_core as u32,
|
||||
),
|
||||
me_adaptive_floor_max_extra_writers_multi_per_core: AtomicU32::new(
|
||||
me_adaptive_floor_max_extra_writers_multi_per_core as u32,
|
||||
),
|
||||
me_adaptive_floor_cpu_cores_detected: AtomicU32::new(1),
|
||||
me_adaptive_floor_cpu_cores_effective: AtomicU32::new(1),
|
||||
me_adaptive_floor_global_cap_raw: AtomicU64::new(0),
|
||||
me_adaptive_floor_global_cap_effective: AtomicU64::new(0),
|
||||
me_adaptive_floor_target_writers_total: AtomicU64::new(0),
|
||||
pool_size: 2,
|
||||
proxy_map_v4: Arc::new(RwLock::new(proxy_map_v4)),
|
||||
proxy_map_v6: Arc::new(RwLock::new(proxy_map_v6)),
|
||||
@@ -399,7 +434,12 @@ impl MePool {
|
||||
floor_mode: MeFloorMode,
|
||||
adaptive_floor_idle_secs: u64,
|
||||
adaptive_floor_min_writers_single_endpoint: u8,
|
||||
adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
adaptive_floor_recover_grace_secs: u64,
|
||||
adaptive_floor_writers_per_core_total: u16,
|
||||
adaptive_floor_cpu_cores_override: u16,
|
||||
adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
) {
|
||||
self.hardswap.store(hardswap, Ordering::Relaxed);
|
||||
self.me_pool_drain_ttl_secs
|
||||
@@ -443,8 +483,24 @@ impl MePool {
|
||||
.store(adaptive_floor_idle_secs, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_min_writers_single_endpoint
|
||||
.store(adaptive_floor_min_writers_single_endpoint, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_min_writers_multi_endpoint
|
||||
.store(adaptive_floor_min_writers_multi_endpoint, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_recover_grace_secs
|
||||
.store(adaptive_floor_recover_grace_secs, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_writers_per_core_total
|
||||
.store(adaptive_floor_writers_per_core_total as u32, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_cpu_cores_override
|
||||
.store(adaptive_floor_cpu_cores_override as u32, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
.store(
|
||||
adaptive_floor_max_extra_writers_single_per_core as u32,
|
||||
Ordering::Relaxed,
|
||||
);
|
||||
self.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
.store(
|
||||
adaptive_floor_max_extra_writers_multi_per_core as u32,
|
||||
Ordering::Relaxed,
|
||||
);
|
||||
if previous_floor_mode != floor_mode {
|
||||
self.stats.increment_me_floor_mode_switch_total();
|
||||
match (previous_floor_mode, floor_mode) {
|
||||
@@ -515,6 +571,13 @@ impl MePool {
|
||||
self.proxy_secret.read().await.key_selector
|
||||
}
|
||||
|
||||
pub(super) async fn active_writer_count_total(&self) -> usize {
|
||||
let ws = self.writers.read().await;
|
||||
ws.iter()
|
||||
.filter(|w| !w.draining.load(Ordering::Relaxed))
|
||||
.count()
|
||||
}
|
||||
|
||||
pub(super) async fn secret_snapshot(&self) -> SecretSnapshot {
|
||||
self.proxy_secret.read().await.clone()
|
||||
}
|
||||
@@ -551,6 +614,82 @@ impl MePool {
|
||||
)
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_min_writers_multi_endpoint(&self) -> usize {
|
||||
(self
|
||||
.me_adaptive_floor_min_writers_multi_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_writers_per_core_total(&self) -> usize {
|
||||
(self
|
||||
.me_adaptive_floor_writers_per_core_total
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_max_extra_single_per_core(&self) -> usize {
|
||||
self.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
.load(Ordering::Relaxed) as usize
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_max_extra_multi_per_core(&self) -> usize {
|
||||
self.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
.load(Ordering::Relaxed) as usize
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_detected_cpu_cores(&self) -> usize {
|
||||
std::thread::available_parallelism()
|
||||
.map(|value| value.get())
|
||||
.unwrap_or(1)
|
||||
.max(1)
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_effective_cpu_cores(&self) -> usize {
|
||||
let detected = self.adaptive_floor_detected_cpu_cores();
|
||||
let override_cores = self
|
||||
.me_adaptive_floor_cpu_cores_override
|
||||
.load(Ordering::Relaxed) as usize;
|
||||
let effective = if override_cores == 0 {
|
||||
detected
|
||||
} else {
|
||||
override_cores.max(1)
|
||||
};
|
||||
self.me_adaptive_floor_cpu_cores_detected
|
||||
.store(detected as u32, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_cpu_cores_effective
|
||||
.store(effective as u32, Ordering::Relaxed);
|
||||
self.stats
|
||||
.set_me_floor_cpu_cores_detected_gauge(detected as u64);
|
||||
self.stats
|
||||
.set_me_floor_cpu_cores_effective_gauge(effective as u64);
|
||||
effective
|
||||
}
|
||||
|
||||
pub(super) fn adaptive_floor_global_cap_raw(&self) -> usize {
|
||||
let cores = self.adaptive_floor_effective_cpu_cores();
|
||||
let cap = cores.saturating_mul(self.adaptive_floor_writers_per_core_total());
|
||||
self.me_adaptive_floor_global_cap_raw
|
||||
.store(cap as u64, Ordering::Relaxed);
|
||||
self.stats.set_me_floor_global_cap_raw_gauge(cap as u64);
|
||||
cap
|
||||
}
|
||||
|
||||
pub(super) fn set_adaptive_floor_runtime_caps(
|
||||
&self,
|
||||
global_cap_effective: usize,
|
||||
target_writers_total: usize,
|
||||
) {
|
||||
self.me_adaptive_floor_global_cap_effective
|
||||
.store(global_cap_effective as u64, Ordering::Relaxed);
|
||||
self.me_adaptive_floor_target_writers_total
|
||||
.store(target_writers_total as u64, Ordering::Relaxed);
|
||||
self.stats
|
||||
.set_me_floor_global_cap_effective_gauge(global_cap_effective as u64);
|
||||
self.stats
|
||||
.set_me_floor_target_writers_total_gauge(target_writers_total as u64);
|
||||
}
|
||||
|
||||
pub(super) fn required_writers_for_dc_with_floor_mode(
|
||||
&self,
|
||||
endpoint_count: usize,
|
||||
@@ -560,13 +699,20 @@ impl MePool {
|
||||
if !reduce_for_idle {
|
||||
return base_required;
|
||||
}
|
||||
if endpoint_count != 1 || self.floor_mode() != MeFloorMode::Adaptive {
|
||||
if self.floor_mode() != MeFloorMode::Adaptive {
|
||||
return base_required;
|
||||
}
|
||||
let min_writers = (self
|
||||
.me_adaptive_floor_min_writers_single_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1);
|
||||
let min_writers = if endpoint_count == 1 {
|
||||
(self
|
||||
.me_adaptive_floor_min_writers_single_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
} else {
|
||||
(self
|
||||
.me_adaptive_floor_min_writers_multi_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
};
|
||||
base_required.min(min_writers)
|
||||
}
|
||||
|
||||
|
||||
@@ -28,6 +28,10 @@ pub(crate) struct MeApiDcStatusSnapshot {
|
||||
pub available_endpoints: usize,
|
||||
pub available_pct: f64,
|
||||
pub required_writers: usize,
|
||||
pub floor_min: usize,
|
||||
pub floor_target: usize,
|
||||
pub floor_max: usize,
|
||||
pub floor_capped: bool,
|
||||
pub alive_writers: usize,
|
||||
pub coverage_pct: f64,
|
||||
pub rtt_ms: Option<f64>,
|
||||
@@ -72,7 +76,17 @@ pub(crate) struct MeApiRuntimeSnapshot {
|
||||
pub floor_mode: &'static str,
|
||||
pub adaptive_floor_idle_secs: u64,
|
||||
pub adaptive_floor_min_writers_single_endpoint: u8,
|
||||
pub adaptive_floor_min_writers_multi_endpoint: u8,
|
||||
pub adaptive_floor_recover_grace_secs: u64,
|
||||
pub adaptive_floor_writers_per_core_total: u16,
|
||||
pub adaptive_floor_cpu_cores_override: u16,
|
||||
pub adaptive_floor_max_extra_writers_single_per_core: u16,
|
||||
pub adaptive_floor_max_extra_writers_multi_per_core: u16,
|
||||
pub adaptive_floor_cpu_cores_detected: u32,
|
||||
pub adaptive_floor_cpu_cores_effective: u32,
|
||||
pub adaptive_floor_global_cap_raw: u64,
|
||||
pub adaptive_floor_global_cap_effective: u64,
|
||||
pub adaptive_floor_target_writers_total: u64,
|
||||
pub me_keepalive_enabled: bool,
|
||||
pub me_keepalive_interval_secs: u64,
|
||||
pub me_keepalive_jitter_secs: u64,
|
||||
@@ -275,14 +289,43 @@ impl MePool {
|
||||
let mut dcs = Vec::<MeApiDcStatusSnapshot>::with_capacity(endpoints_by_dc.len());
|
||||
let mut available_endpoints = 0usize;
|
||||
let mut alive_writers = 0usize;
|
||||
let floor_mode = self.floor_mode();
|
||||
let adaptive_cpu_cores = (self
|
||||
.me_adaptive_floor_cpu_cores_effective
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1);
|
||||
for (dc, endpoints) in endpoints_by_dc {
|
||||
let endpoint_count = endpoints.len();
|
||||
let dc_available_endpoints = endpoints
|
||||
.iter()
|
||||
.filter(|endpoint| live_writers_by_endpoint.contains_key(endpoint))
|
||||
.count();
|
||||
let base_required = self.required_writers_for_dc(endpoint_count);
|
||||
let dc_required_writers =
|
||||
self.required_writers_for_dc_with_floor_mode(endpoint_count, false);
|
||||
let floor_min = if endpoint_count <= 1 {
|
||||
(self
|
||||
.me_adaptive_floor_min_writers_single_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
.min(base_required.max(1))
|
||||
} else {
|
||||
(self
|
||||
.me_adaptive_floor_min_writers_multi_endpoint
|
||||
.load(Ordering::Relaxed) as usize)
|
||||
.max(1)
|
||||
.min(base_required.max(1))
|
||||
};
|
||||
let extra_per_core = if endpoint_count <= 1 {
|
||||
self.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
.load(Ordering::Relaxed) as usize
|
||||
} else {
|
||||
self.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
.load(Ordering::Relaxed) as usize
|
||||
};
|
||||
let floor_max = base_required.saturating_add(adaptive_cpu_cores.saturating_mul(extra_per_core));
|
||||
let floor_capped = matches!(floor_mode, MeFloorMode::Adaptive)
|
||||
&& dc_required_writers < base_required;
|
||||
let dc_alive_writers = live_writers_by_dc.get(&dc).copied().unwrap_or(0);
|
||||
let dc_load = activity
|
||||
.active_sessions_by_target_dc
|
||||
@@ -302,6 +345,10 @@ impl MePool {
|
||||
available_endpoints: dc_available_endpoints,
|
||||
available_pct: ratio_pct(dc_available_endpoints, endpoint_count),
|
||||
required_writers: dc_required_writers,
|
||||
floor_min,
|
||||
floor_target: dc_required_writers,
|
||||
floor_max,
|
||||
floor_capped,
|
||||
alive_writers: dc_alive_writers,
|
||||
coverage_pct: ratio_pct(dc_alive_writers, dc_required_writers),
|
||||
rtt_ms: dc_rtt_ms,
|
||||
@@ -378,9 +425,39 @@ impl MePool {
|
||||
adaptive_floor_min_writers_single_endpoint: self
|
||||
.me_adaptive_floor_min_writers_single_endpoint
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_min_writers_multi_endpoint: self
|
||||
.me_adaptive_floor_min_writers_multi_endpoint
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_recover_grace_secs: self
|
||||
.me_adaptive_floor_recover_grace_secs
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_writers_per_core_total: self
|
||||
.me_adaptive_floor_writers_per_core_total
|
||||
.load(Ordering::Relaxed) as u16,
|
||||
adaptive_floor_cpu_cores_override: self
|
||||
.me_adaptive_floor_cpu_cores_override
|
||||
.load(Ordering::Relaxed) as u16,
|
||||
adaptive_floor_max_extra_writers_single_per_core: self
|
||||
.me_adaptive_floor_max_extra_writers_single_per_core
|
||||
.load(Ordering::Relaxed) as u16,
|
||||
adaptive_floor_max_extra_writers_multi_per_core: self
|
||||
.me_adaptive_floor_max_extra_writers_multi_per_core
|
||||
.load(Ordering::Relaxed) as u16,
|
||||
adaptive_floor_cpu_cores_detected: self
|
||||
.me_adaptive_floor_cpu_cores_detected
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_cpu_cores_effective: self
|
||||
.me_adaptive_floor_cpu_cores_effective
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_global_cap_raw: self
|
||||
.me_adaptive_floor_global_cap_raw
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_global_cap_effective: self
|
||||
.me_adaptive_floor_global_cap_effective
|
||||
.load(Ordering::Relaxed),
|
||||
adaptive_floor_target_writers_total: self
|
||||
.me_adaptive_floor_target_writers_total
|
||||
.load(Ordering::Relaxed),
|
||||
me_keepalive_enabled: self.me_keepalive_enabled,
|
||||
me_keepalive_interval_secs: self.me_keepalive_interval.as_secs(),
|
||||
me_keepalive_jitter_secs: self.me_keepalive_jitter.as_secs(),
|
||||
|
||||
403
tools/aesdiag.py
Normal file
403
tools/aesdiag.py
Normal file
@@ -0,0 +1,403 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
AES-CBC validation tool for telemt middle proxy logs with support for noop padding.
|
||||
|
||||
Parses log lines containing:
|
||||
- "ME diag: derived keys and handshake plaintext" (provides write_key, write_iv, hs_plain)
|
||||
- "ME diag: handshake ciphertext" (provides hs_cipher)
|
||||
|
||||
For each pair it:
|
||||
- Decrypts the ciphertext using the provided key and IV.
|
||||
- Compares the beginning of the decrypted data with hs_plain.
|
||||
- Attempts to identify the actual padding scheme (PKCS#7, zero padding, noop padding).
|
||||
- Re-encrypts with different paddings and reports mismatches block by block.
|
||||
- Accumulates statistics for final summary.
|
||||
"""
|
||||
|
||||
import sys
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from Crypto.Cipher import AES
|
||||
|
||||
# Constants
|
||||
NOOP_FRAME = bytes([0x04, 0x00, 0x00, 0x00]) # noop frame used for padding
|
||||
|
||||
def hex_str_to_bytes(hex_str):
|
||||
"""Convert a hex string like 'aa bb cc' to bytes."""
|
||||
return bytes.fromhex(hex_str.replace(' ', ''))
|
||||
|
||||
def parse_params(line):
|
||||
"""Extract key=value pairs where value is a space-separated hex string."""
|
||||
pattern = r'(\w+)=((?:[0-9a-f]{2} )*[0-9a-f]{2})'
|
||||
return {key: val for key, val in re.findall(pattern, line)}
|
||||
|
||||
def pkcs7_pad(data, block_size=16):
|
||||
"""Apply PKCS#7 padding to the given data."""
|
||||
pad_len = block_size - (len(data) % block_size)
|
||||
if pad_len == 0:
|
||||
pad_len = block_size
|
||||
return data + bytes([pad_len]) * pad_len
|
||||
|
||||
def zero_pad(data, block_size=16):
|
||||
"""Pad with zeros to the next block boundary."""
|
||||
pad_len = block_size - (len(data) % block_size)
|
||||
if pad_len == block_size:
|
||||
return data # already full blocks, no zero padding needed
|
||||
return data + bytes(pad_len)
|
||||
|
||||
def noop_pad(data):
|
||||
"""
|
||||
Pad with minimal number of noop frames (b'\\x04\\x00\\x00\\x00')
|
||||
to reach a multiple of 16 bytes.
|
||||
"""
|
||||
block_size = 16
|
||||
frame_len = len(NOOP_FRAME) # 4
|
||||
remainder = len(data) % block_size
|
||||
if remainder == 0:
|
||||
return data # no padding needed
|
||||
# We need to add k frames such that (len(data) + k*frame_len) % block_size == 0
|
||||
# => k*frame_len ≡ -remainder (mod block_size)
|
||||
# Since frame_len=4 and block_size=16, we need k*4 ≡ (16-remainder) mod 16
|
||||
# k must be an integer in {1,2,3} (because 4*4=16 ≡0 mod16, so k=4 gives remainder 0, but then total increase=16,
|
||||
# but if remainder==0 we already handled; if remainder!=0, k=4 gives (len+16)%16 == remainder, not 0,
|
||||
# so k=4 doesn't solve unless remainder=0. Actually 4*4=16 ≡0, so k=4 gives (len+16)%16 = remainder, so still not 0.
|
||||
# The equation is k*4 ≡ (16-remainder) mod 16. Let r=16-remainder (1..15). Then k ≡ r*inv(4) mod 4? Since mod 16,
|
||||
# 4 has no inverse modulo 16 because gcd(4,16)=4. So solutions exist only if r is multiple of 4.
|
||||
# Therefore remainder must be 4,8,12 (so that r = 12,8,4). This matches the idea that noop padding is only added
|
||||
# when the plaintext length mod 16 is 4,8,12. In our logs it's always 44 mod16=12, so r=4, so k=1 works.
|
||||
# For safety, we compute k as (block_size - remainder) // frame_len, but this only works if that value is integer.
|
||||
need = block_size - remainder
|
||||
if need % frame_len != 0:
|
||||
# This shouldn't happen by protocol, but if it does, fall back to adding full blocks of noop until multiple.
|
||||
# We'll add ceil(need/frame_len) frames.
|
||||
k = (need + frame_len - 1) // frame_len
|
||||
else:
|
||||
k = need // frame_len
|
||||
return data + NOOP_FRAME * k
|
||||
|
||||
def unpad_pkcs7(data):
|
||||
"""Remove PKCS#7 padding (assumes correct padding)."""
|
||||
if not data:
|
||||
return data
|
||||
pad_len = data[-1]
|
||||
if pad_len < 1 or pad_len > 16:
|
||||
return data # not valid PKCS#7, return as is
|
||||
# Check that all padding bytes are equal to pad_len
|
||||
if all(b == pad_len for b in data[-pad_len:]):
|
||||
return data[:-pad_len]
|
||||
return data
|
||||
|
||||
def is_noop_padded(decrypted, plain_log):
|
||||
"""
|
||||
Check if the extra bytes after plain_log in decrypted consist of one or more NOOP_FRAMEs.
|
||||
Returns True if they do, False otherwise.
|
||||
"""
|
||||
extra = decrypted[len(plain_log):]
|
||||
if len(extra) == 0:
|
||||
return False
|
||||
# Split into chunks of 4
|
||||
if len(extra) % 4 != 0:
|
||||
return False
|
||||
for i in range(0, len(extra), 4):
|
||||
if extra[i:i+4] != NOOP_FRAME:
|
||||
return False
|
||||
return True
|
||||
|
||||
def main():
|
||||
derived_list = [] # entries from "derived keys and handshake plaintext"
|
||||
cipher_list = [] # entries from "handshake ciphertext"
|
||||
|
||||
for line in sys.stdin:
|
||||
if 'ME diag: derived keys and handshake plaintext' in line:
|
||||
params = parse_params(line)
|
||||
if all(k in params for k in ('write_key', 'write_iv', 'hs_plain')):
|
||||
derived_list.append(params)
|
||||
elif 'ME diag: handshake ciphertext' in line:
|
||||
params = parse_params(line)
|
||||
if 'hs_cipher' in params:
|
||||
cipher_list.append(params)
|
||||
|
||||
# Warn about count mismatch but process as many pairs as possible
|
||||
n_pairs = min(len(derived_list), len(cipher_list))
|
||||
if len(derived_list) != len(cipher_list):
|
||||
print(f"\n[WARN] Number of derived entries ({len(derived_list)}) "
|
||||
f"differs from cipher entries ({len(cipher_list)}). "
|
||||
f"Processing first {n_pairs} pairs.\n")
|
||||
|
||||
# Statistics accumulators
|
||||
stats = {
|
||||
'total': n_pairs,
|
||||
'key_length_ok': 0,
|
||||
'iv_length_ok': 0,
|
||||
'cipher_aligned': 0,
|
||||
'decryption_match_start': 0, # first bytes equal hs_plain
|
||||
'pkcs7_after_unpad_matches': 0, # after removing PKCS7, equals hs_plain
|
||||
'extra_bytes_all_zero': 0, # extra bytes after hs_plain are zero
|
||||
'extra_bytes_noop': 0, # extra bytes are noop frames
|
||||
'pkcs7_encrypt_ok': 0, # re-encryption with PKCS7 matches ciphertext
|
||||
'zero_encrypt_ok': 0, # re-encryption with zero padding matches
|
||||
'noop_encrypt_ok': 0, # re-encryption with noop padding matches
|
||||
'no_padding_encrypt_ok': 0, # only if plaintext multiple of 16 and matches
|
||||
'no_padding_applicable': 0, # number of tests where plaintext len %16 ==0
|
||||
}
|
||||
|
||||
detailed_results = [] # store per-test summary for final heuristic
|
||||
|
||||
for idx, (der, ciph) in enumerate(zip(derived_list[:n_pairs], cipher_list[:n_pairs]), 1):
|
||||
print(f"\n{'='*60}")
|
||||
print(f"Test #{idx}")
|
||||
print(f"{'='*60}")
|
||||
|
||||
# Local stats for this test
|
||||
test_stats = defaultdict(bool)
|
||||
|
||||
try:
|
||||
key = hex_str_to_bytes(der['write_key'])
|
||||
iv = hex_str_to_bytes(der['write_iv'])
|
||||
plain_log = hex_str_to_bytes(der['hs_plain'])
|
||||
ciphertext = hex_str_to_bytes(ciph['hs_cipher'])
|
||||
|
||||
# Basic sanity checks
|
||||
print(f"[INFO] Key length : {len(key)} bytes (expected 32)")
|
||||
print(f"[INFO] IV length : {len(iv)} bytes (expected 16)")
|
||||
print(f"[INFO] hs_plain length : {len(plain_log)} bytes")
|
||||
print(f"[INFO] hs_cipher length : {len(ciphertext)} bytes")
|
||||
|
||||
if len(key) == 32:
|
||||
stats['key_length_ok'] += 1
|
||||
test_stats['key_ok'] = True
|
||||
else:
|
||||
print("[WARN] Key length is not 32 bytes – AES-256 requires 32-byte key.")
|
||||
|
||||
if len(iv) == 16:
|
||||
stats['iv_length_ok'] += 1
|
||||
test_stats['iv_ok'] = True
|
||||
else:
|
||||
print("[WARN] IV length is not 16 bytes – AES-CBC requires 16-byte IV.")
|
||||
|
||||
if len(ciphertext) % 16 == 0:
|
||||
stats['cipher_aligned'] += 1
|
||||
test_stats['cipher_aligned'] = True
|
||||
else:
|
||||
print("[ERROR] Ciphertext length is not a multiple of 16 – invalid AES-CBC block alignment.")
|
||||
# Skip further processing for this test
|
||||
detailed_results.append(test_stats)
|
||||
continue
|
||||
|
||||
# --- Decryption test ---
|
||||
cipher_dec = AES.new(key, AES.MODE_CBC, iv)
|
||||
decrypted = cipher_dec.decrypt(ciphertext)
|
||||
print(f"[INFO] Decrypted ({len(decrypted)} bytes): {decrypted.hex()}")
|
||||
|
||||
# Compare beginning with hs_plain
|
||||
match_len = min(len(plain_log), len(decrypted))
|
||||
if decrypted[:match_len] == plain_log[:match_len]:
|
||||
print(f"[OK] First {match_len} bytes match hs_plain.")
|
||||
stats['decryption_match_start'] += 1
|
||||
test_stats['decrypt_start_ok'] = True
|
||||
else:
|
||||
print(f"[FAIL] First bytes do NOT match hs_plain.")
|
||||
for i in range(match_len):
|
||||
if decrypted[i] != plain_log[i]:
|
||||
print(f" First mismatch at byte {i}: hs_plain={plain_log[i]:02x}, decrypted={decrypted[i]:02x}")
|
||||
break
|
||||
test_stats['decrypt_start_ok'] = False
|
||||
|
||||
# --- Try to identify actual padding ---
|
||||
# Remove possible PKCS#7 padding from decrypted data
|
||||
decrypted_unpadded = unpad_pkcs7(decrypted)
|
||||
if decrypted_unpadded != decrypted:
|
||||
print(f"[INFO] After removing PKCS#7 padding: {len(decrypted_unpadded)} bytes left.")
|
||||
if decrypted_unpadded == plain_log:
|
||||
print("[OK] Decrypted data with PKCS#7 removed exactly matches hs_plain.")
|
||||
stats['pkcs7_after_unpad_matches'] += 1
|
||||
test_stats['pkcs7_unpad_matches'] = True
|
||||
else:
|
||||
print("[INFO] Decrypted (PKCS#7 removed) does NOT match hs_plain.")
|
||||
test_stats['pkcs7_unpad_matches'] = False
|
||||
else:
|
||||
print("[INFO] No valid PKCS#7 padding detected in decrypted data.")
|
||||
test_stats['pkcs7_unpad_matches'] = False
|
||||
|
||||
# Check if the extra bytes after hs_plain in decrypted are all zero (zero padding)
|
||||
extra = decrypted[len(plain_log):]
|
||||
if extra and all(b == 0 for b in extra):
|
||||
print("[INFO] Extra bytes after hs_plain are all zeros – likely zero padding.")
|
||||
stats['extra_bytes_all_zero'] += 1
|
||||
test_stats['extra_zero'] = True
|
||||
else:
|
||||
test_stats['extra_zero'] = False
|
||||
|
||||
# Check for noop padding in extra bytes
|
||||
if is_noop_padded(decrypted, plain_log):
|
||||
print(f"[OK] Extra bytes after hs_plain consist of noop frames ({NOOP_FRAME.hex()}).")
|
||||
stats['extra_bytes_noop'] += 1
|
||||
test_stats['extra_noop'] = True
|
||||
else:
|
||||
test_stats['extra_noop'] = False
|
||||
if extra:
|
||||
print(f"[INFO] Extra bytes after hs_plain (hex): {extra.hex()}")
|
||||
|
||||
# --- Re-encryption tests ---
|
||||
# PKCS#7
|
||||
padded_pkcs7 = pkcs7_pad(plain_log)
|
||||
cipher_enc = AES.new(key, AES.MODE_CBC, iv)
|
||||
computed_pkcs7 = cipher_enc.encrypt(padded_pkcs7)
|
||||
if computed_pkcs7 == ciphertext:
|
||||
print("[OK] PKCS#7 padding produces the expected ciphertext.")
|
||||
stats['pkcs7_encrypt_ok'] += 1
|
||||
test_stats['pkcs7_enc_ok'] = True
|
||||
else:
|
||||
print("[FAIL] PKCS#7 padding does NOT match the ciphertext.")
|
||||
test_stats['pkcs7_enc_ok'] = False
|
||||
# Show block where first difference occurs
|
||||
block_size = 16
|
||||
for blk in range(len(ciphertext)//block_size):
|
||||
start = blk*block_size
|
||||
exp = ciphertext[start:start+block_size]
|
||||
comp = computed_pkcs7[start:start+block_size]
|
||||
if exp != comp:
|
||||
print(f" First difference in block {blk}:")
|
||||
print(f" expected : {exp.hex()}")
|
||||
print(f" computed : {comp.hex()}")
|
||||
break
|
||||
|
||||
# Zero padding
|
||||
padded_zero = zero_pad(plain_log)
|
||||
# Ensure multiple of 16
|
||||
if len(padded_zero) % 16 != 0:
|
||||
padded_zero += bytes(16 - (len(padded_zero)%16))
|
||||
cipher_enc_zero = AES.new(key, AES.MODE_CBC, iv)
|
||||
computed_zero = cipher_enc_zero.encrypt(padded_zero)
|
||||
if computed_zero == ciphertext:
|
||||
print("[OK] Zero padding produces the expected ciphertext.")
|
||||
stats['zero_encrypt_ok'] += 1
|
||||
test_stats['zero_enc_ok'] = True
|
||||
else:
|
||||
print("[INFO] Zero padding does NOT match (expected, unless log used PKCS#7).")
|
||||
test_stats['zero_enc_ok'] = False
|
||||
|
||||
# Noop padding
|
||||
padded_noop = noop_pad(plain_log)
|
||||
# Ensure multiple of 16 (noop_pad already returns multiple of 16)
|
||||
cipher_enc_noop = AES.new(key, AES.MODE_CBC, iv)
|
||||
computed_noop = cipher_enc_noop.encrypt(padded_noop)
|
||||
if computed_noop == ciphertext:
|
||||
print("[OK] Noop padding produces the expected ciphertext.")
|
||||
stats['noop_encrypt_ok'] += 1
|
||||
test_stats['noop_enc_ok'] = True
|
||||
else:
|
||||
print("[FAIL] Noop padding does NOT match the ciphertext.")
|
||||
test_stats['noop_enc_ok'] = False
|
||||
# Show block difference if needed
|
||||
for blk in range(len(ciphertext)//16):
|
||||
start = blk*16
|
||||
if computed_noop[start:start+16] != ciphertext[start:start+16]:
|
||||
print(f" First difference in block {blk}:")
|
||||
print(f" expected : {ciphertext[start:start+16].hex()}")
|
||||
print(f" computed : {computed_noop[start:start+16].hex()}")
|
||||
break
|
||||
|
||||
# No padding (only possible if plaintext is already multiple of 16)
|
||||
if len(plain_log) % 16 == 0:
|
||||
stats['no_padding_applicable'] += 1
|
||||
cipher_enc_nopad = AES.new(key, AES.MODE_CBC, iv)
|
||||
computed_nopad = cipher_enc_nopad.encrypt(plain_log)
|
||||
if computed_nopad == ciphertext:
|
||||
print("[OK] No padding (plaintext multiple of 16) matches.")
|
||||
stats['no_padding_encrypt_ok'] += 1
|
||||
test_stats['no_pad_enc_ok'] = True
|
||||
else:
|
||||
print("[INFO] No padding does NOT match.")
|
||||
test_stats['no_pad_enc_ok'] = False
|
||||
else:
|
||||
print("[INFO] Skipping no‑padding test because plaintext length is not a multiple of 16.")
|
||||
|
||||
except Exception as e:
|
||||
print(f"[EXCEPTION] {e}")
|
||||
test_stats['exception'] = True
|
||||
|
||||
detailed_results.append(test_stats)
|
||||
|
||||
# --- Final statistics and heuristic summary ---
|
||||
print("\n" + "="*60)
|
||||
print("STATISTICS SUMMARY")
|
||||
print("="*60)
|
||||
print(f"Total tests processed : {stats['total']}")
|
||||
print(f"Key length OK (32) : {stats['key_length_ok']}/{stats['total']}")
|
||||
print(f"IV length OK (16) : {stats['iv_length_ok']}/{stats['total']}")
|
||||
print(f"Ciphertext 16-byte aligned : {stats['cipher_aligned']}/{stats['total']}")
|
||||
print(f"Decryption starts with hs_plain : {stats['decryption_match_start']}/{stats['total']}")
|
||||
print(f"After PKCS#7 removal matches : {stats['pkcs7_after_unpad_matches']}/{stats['total']}")
|
||||
print(f"Extra bytes after hs_plain are 0 : {stats['extra_bytes_all_zero']}/{stats['total']}")
|
||||
print(f"Extra bytes are noop frames : {stats['extra_bytes_noop']}/{stats['total']}")
|
||||
print(f"PKCS#7 re-encryption OK : {stats['pkcs7_encrypt_ok']}/{stats['total']}")
|
||||
print(f"Zero padding re-encryption OK : {stats['zero_encrypt_ok']}/{stats['total']}")
|
||||
print(f"Noop padding re-encryption OK : {stats['noop_encrypt_ok']}/{stats['total']}")
|
||||
if stats['no_padding_applicable'] > 0:
|
||||
print(f"No-padding applicable tests : {stats['no_padding_applicable']}")
|
||||
print(f"No-padding re-encryption OK : {stats['no_padding_encrypt_ok']}/{stats['no_padding_applicable']}")
|
||||
|
||||
# Heuristic: determine most likely padding
|
||||
print("\n" + "="*60)
|
||||
print("HEURISTIC CONCLUSION")
|
||||
print("="*60)
|
||||
|
||||
if stats['decryption_match_start'] == stats['total']:
|
||||
print("✓ All tests: first bytes of decrypted data match hs_plain → keys and IV are correct.")
|
||||
else:
|
||||
print("✗ Some tests: first bytes mismatch → possible key/IV issues or corrupted ciphertext.")
|
||||
|
||||
# Guess padding based on re-encryption success and extra bytes
|
||||
candidates = []
|
||||
if stats['pkcs7_encrypt_ok'] == stats['total']:
|
||||
candidates.append("PKCS#7")
|
||||
if stats['zero_encrypt_ok'] == stats['total']:
|
||||
candidates.append("zero padding")
|
||||
if stats['noop_encrypt_ok'] == stats['total']:
|
||||
candidates.append("noop padding")
|
||||
if stats['no_padding_applicable'] == stats['total'] and stats['no_padding_encrypt_ok'] == stats['total']:
|
||||
candidates.append("no padding")
|
||||
|
||||
if len(candidates) == 1:
|
||||
print(f"✓ All tests consistent with padding scheme: {candidates[0]}.")
|
||||
elif len(candidates) > 1:
|
||||
print(f"⚠ Multiple padding schemes succeed in all tests: {', '.join(candidates)}. This is unusual.")
|
||||
else:
|
||||
# No scheme succeeded in all tests – look at ratios
|
||||
print("Mixed padding results:")
|
||||
total = stats['total']
|
||||
pkcs7_ratio = stats['pkcs7_encrypt_ok'] / total if total else 0
|
||||
zero_ratio = stats['zero_encrypt_ok'] / total if total else 0
|
||||
noop_ratio = stats['noop_encrypt_ok'] / total if total else 0
|
||||
print(f" PKCS#7 success = {stats['pkcs7_encrypt_ok']}/{total} ({pkcs7_ratio*100:.1f}%)")
|
||||
print(f" Zero success = {stats['zero_encrypt_ok']}/{total} ({zero_ratio*100:.1f}%)")
|
||||
print(f" Noop success = {stats['noop_encrypt_ok']}/{total} ({noop_ratio*100:.1f}%)")
|
||||
|
||||
if noop_ratio > max(pkcs7_ratio, zero_ratio):
|
||||
print("→ Noop padding is most frequent. Check if extra bytes are indeed noop frames.")
|
||||
elif pkcs7_ratio > zero_ratio:
|
||||
print("→ PKCS#7 is most frequent, but fails in some tests.")
|
||||
elif zero_ratio > pkcs7_ratio:
|
||||
print("→ Zero padding is most frequent, but fails in some tests.")
|
||||
else:
|
||||
print("→ No clear winner; possibly a different padding scheme or random data.")
|
||||
|
||||
# Additional heuristics based on extra bytes
|
||||
if stats['extra_bytes_noop'] == stats['total']:
|
||||
print("✓ All tests: extra bytes after hs_plain are noop frames → strongly indicates noop padding.")
|
||||
if stats['extra_bytes_all_zero'] == stats['total']:
|
||||
print("✓ All tests: extra bytes are zeros → suggests zero padding.")
|
||||
|
||||
# Final health check
|
||||
if (stats['decryption_match_start'] == stats['total'] and
|
||||
(stats['pkcs7_encrypt_ok'] == stats['total'] or
|
||||
stats['zero_encrypt_ok'] == stats['total'] or
|
||||
stats['noop_encrypt_ok'] == stats['total'] or
|
||||
stats['no_padding_encrypt_ok'] == stats['no_padding_applicable'] == stats['total'])):
|
||||
print("\n✅ OVERALL: All tests consistent. The encryption parameters and padding are correct.")
|
||||
else:
|
||||
print("\n⚠️ OVERALL: Inconsistencies detected. Review the detailed output for failing tests.")
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user