Merge pull request #370 from telemt/bump

Update Cargo.toml

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "telemt"
-version = "3.3.7"
+version = "3.3.11"
 edition = "2024"
 
 [dependencies]

config.toml

@@ -4,7 +4,7 @@
 
 # === General Settings ===
 [general]
-use_middle_proxy = false
+use_middle_proxy = true
 # Global ad_tag fallback when user has no per-user tag in [access.user_ad_tags]
 # ad_tag = "00000000000000000000000000000000"
 # Per-user ad_tag in [access.user_ad_tags] (32 hex from @MTProxybot)

docs/QUICK_START_GUIDE.ru.md

@@ -126,7 +126,7 @@ WantedBy=multi-user.target
 ```bash
 curl -s http://127.0.0.1:9091/v1/users | jq
 ```
-> Одной ссылкой модет пользоваться сколько угодно человек.
+> Одной ссылкой может пользоваться сколько угодно человек.
 
 > [!WARNING]
 > 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!

install.sh

@@ -1,73 +1,93 @@
-sudo bash -c '
+#!/bin/sh
-set -e
+set -eu
 
-# --- Проверка на существующую установку ---
+REPO="${REPO:-telemt/telemt}"
-if systemctl list-unit-files | grep -q telemt.service; then
+BIN_NAME="${BIN_NAME:-telemt}"
-    # --- РЕЖИМ ОБНОВЛЕНИЯ ---
+VERSION="${1:-${VERSION:-latest}}"
-    echo "--- Обнаружена существующая установка Telemt. Запускаю обновление... ---"
+INSTALL_DIR="${INSTALL_DIR:-/usr/local/bin}"
 
-    echo "[*] Остановка службы telemt..."
+say() {
-    systemctl stop telemt || true # Игнорируем ошибку, если служба уже остановлена
+    printf '%s\n' "$*"
+}
 
-    echo "[1/2] Скачивание последней версии Telemt..."
+die() {
-    wget -qO- "https://github.com/telemt/telemt/releases/latest/download/telemt-$(uname -m)-linux-$(ldd --version 2>&1 | grep -iq musl && echo musl || echo gnu).tar.gz" | tar -xz
+    printf 'Error: %s\n' "$*" >&2
+    exit 1
+}
 
-    echo "[1/2] Замена исполняемого файла в /usr/local/bin..."
+need_cmd() {
-    mv telemt /usr/local/bin/telemt
+    command -v "$1" >/dev/null 2>&1 || die "required command not found: $1"
-    chmod +x /usr/local/bin/telemt
+}
 
-    echo "[2/2] Запуск службы..."
+detect_arch() {
-    systemctl start telemt
+    arch="$(uname -m)"
+    case "$arch" in
+        x86_64|amd64) printf 'x86_64\n' ;;
+        aarch64|arm64) printf 'aarch64\n' ;;
+        *) die "unsupported architecture: $arch" ;;
+    esac
+}
 
-    echo "--- Обновление Telemt успешно завершено! ---"
+detect_libc() {
-    echo
+    case "$(ldd --version 2>&1 || true)" in
-    echo "Для проверки статуса службы выполните:"
+        *musl*) printf 'musl\n' ;;
-    echo "   systemctl status telemt"
+        *) printf 'gnu\n' ;;
+    esac
+}
 
-else
+fetch_to_stdout() {
-    # --- РЕЖИМ НОВОЙ УСТАНОВКИ ---
+    url="$1"
-    echo "--- Начало автоматической установки Telemt ---"
+    if command -v curl >/dev/null 2>&1; then
+        curl -fsSL "$url"
+    elif command -v wget >/dev/null 2>&1; then
+        wget -qO- "$url"
+    else
+        die "neither curl nor wget is installed"
+    fi
+}
 
-    # Шаг 1: Скачивание и установка бинарного файла
+install_binary() {
-    echo "[1/5] Скачивание последней версии Telemt..."
+    src="$1"
-    wget -qO- "https://github.com/telemt/telemt/releases/latest/download/telemt-$(uname -m)-linux-$(ldd --version 2>&1 | grep -iq musl && echo musl || echo gnu).tar.gz" | tar -xz
+    dst="$2"
 
-    echo "[1/5] Перемещение исполняемого файла в /usr/local/bin и установка прав..."
+    if [ -w "$INSTALL_DIR" ] || { [ ! -e "$INSTALL_DIR" ] && [ -w "$(dirname "$INSTALL_DIR")" ]; }; then
-    mv telemt /usr/local/bin/telemt
+        mkdir -p "$INSTALL_DIR"
-    chmod +x /usr/local/bin/telemt
+        install -m 0755 "$src" "$dst"
+    elif command -v sudo >/dev/null 2>&1; then
+        sudo mkdir -p "$INSTALL_DIR"
+        sudo install -m 0755 "$src" "$dst"
+    else
+        die "cannot write to $INSTALL_DIR and sudo is not available"
+    fi
+}
 
-    # Шаг 2: Генерация секрета
+need_cmd uname
-    echo "[2/5] Генерация секретного ключа..."
+need_cmd tar
-    SECRET=$(openssl rand -hex 16)
+need_cmd mktemp
+need_cmd grep
+need_cmd install
 
-    # Шаг 3: Создание файла конфигурации
+ARCH="$(detect_arch)"
-    echo "[3/5] Создание файла конфигурации /etc/telemt.toml..."
+LIBC="$(detect_libc)"
-    printf "# === General Settings ===\n[general]\n[general.modes]\nclassic = false\nsecure = false\ntls = true\n\n# === Anti-Censorship & Masking ===\n[censorship]\n# !!! ВАЖНО: Замените на ваш домен или домен, который вы хотите использовать для маскировки !!!\ntls_domain = \"petrovich.ru\"\n\n[access.users]\nhello = \"%s\"\n" "$SECRET" > /etc/telemt.toml
 
-    # Шаг 4: Создание службы Systemd
+case "$VERSION" in
-    echo "[4/5] Создание службы systemd..."
+    latest)
-    printf "[Unit]\nDescription=Telemt Proxy\nAfter=network.target\n\n[Service]\nType=simple\nExecStart=/usr/local/bin/telemt /etc/telemt.toml\nRestart=on-failure\nRestartSec=5\nLimitNOFILE=65536\n\n[Install]\nWantedBy=multi-user.target\n" > /etc/systemd/system/telemt.service
+        URL="https://github.com/$REPO/releases/latest/download/${BIN_NAME}-${ARCH}-linux-${LIBC}.tar.gz"
+        ;;
+    *)
+        URL="https://github.com/$REPO/releases/download/${VERSION}/${BIN_NAME}-${ARCH}-linux-${LIBC}.tar.gz"
+        ;;
+esac
 
-    # Шаг 5: Запуск службы
+TMPDIR="$(mktemp -d)"
-    echo "[5/5] Перезагрузка systemd, запуск и включение службы telemt..."
+trap 'rm -rf "$TMPDIR"' EXIT INT TERM
-    systemctl daemon-reload
-    systemctl start telemt
-    systemctl enable telemt
 
-    echo "--- Установка и запуск Telemt успешно завершены! ---"
+say "Installing $BIN_NAME ($VERSION) for $ARCH-linux-$LIBC..."
-    echo
+fetch_to_stdout "$URL" | tar -xzf - -C "$TMPDIR"
-    echo "ВАЖНАЯ ИНФОРМАЦИЯ:"
+
-    echo "==================="
+[ -f "$TMPDIR/$BIN_NAME" ] || die "archive did not contain $BIN_NAME"
-    echo "1. Вам НЕОБХОДИМО отредактировать файл /etc/telemt.toml и заменить '\''petrovich.ru'\'' на другой домен"
+
-    echo "   с помощью команды:"
+install_binary "$TMPDIR/$BIN_NAME" "$INSTALL_DIR/$BIN_NAME"
-    echo "   nano /etc/telemt.toml"
+
-    echo "   После редактирования файла перезапустите службу командой:"
+say "Installed: $INSTALL_DIR/$BIN_NAME"
-    echo "   sudo systemctl restart telemt"
+"$INSTALL_DIR/$BIN_NAME" --version 2>/dev/null || true
-    echo
-    echo "2. Для проверки статуса службы выполните команду:"
-    echo "   systemctl status telemt"
-    echo
-    echo "3. Для получения ссылок на подключение выполните команду:"
-    echo "   journalctl -u telemt -n -g '\''links'\'' --no-pager -o cat | tac"
-fi
-'

src/api/mod.rs

@@ -11,11 +11,12 @@ use hyper::server::conn::http1;
 use hyper::service::service_fn;
 use hyper::{Method, Request, Response, StatusCode};
 use tokio::net::TcpListener;
-use tokio::sync::{Mutex, watch};
+use tokio::sync::{Mutex, RwLock, watch};
 use tracing::{debug, info, warn};
 
 use crate::config::ProxyConfig;
 use crate::ip_tracker::UserIpTracker;
+use crate::startup::StartupTracker;
 use crate::stats::Stats;
 use crate::transport::middle_proxy::MePool;
 use crate::transport::UpstreamManager;
@@ -25,6 +26,7 @@ mod events;
 mod http_utils;
 mod model;
 mod runtime_edge;
+mod runtime_init;
 mod runtime_min;
 mod runtime_stats;
 mod runtime_watch;
@@ -41,6 +43,7 @@ use runtime_edge::{
     EdgeConnectionsCacheEntry, build_runtime_connections_summary_data,
     build_runtime_events_recent_data,
 };
+use runtime_init::build_runtime_initialization_data;
 use runtime_min::{
     build_runtime_me_pool_state_data, build_runtime_me_quality_data, build_runtime_nat_stun_data,
     build_runtime_upstream_quality_data, build_security_whitelist_data,
@@ -67,7 +70,7 @@ pub(super) struct ApiRuntimeState {
 pub(super) struct ApiShared {
     pub(super) stats: Arc<Stats>,
     pub(super) ip_tracker: Arc<UserIpTracker>,
-    pub(super) me_pool: Option<Arc<MePool>>,
+    pub(super) me_pool: Arc<RwLock<Option<Arc<MePool>>>>,
     pub(super) upstream_manager: Arc<UpstreamManager>,
     pub(super) config_path: PathBuf,
     pub(super) startup_detected_ip_v4: Option<IpAddr>,
@@ -79,6 +82,7 @@ pub(super) struct ApiShared {
     pub(super) runtime_events: Arc<ApiEventStore>,
     pub(super) request_id: Arc<AtomicU64>,
     pub(super) runtime_state: Arc<ApiRuntimeState>,
+    pub(super) startup_tracker: Arc<StartupTracker>,
 }
 
 impl ApiShared {
@@ -91,7 +95,7 @@ pub async fn serve(
     listen: SocketAddr,
     stats: Arc<Stats>,
     ip_tracker: Arc<UserIpTracker>,
-    me_pool: Option<Arc<MePool>>,
+    me_pool: Arc<RwLock<Option<Arc<MePool>>>>,
     upstream_manager: Arc<UpstreamManager>,
     config_rx: watch::Receiver<Arc<ProxyConfig>>,
     admission_rx: watch::Receiver<bool>,
@@ -99,6 +103,7 @@ pub async fn serve(
     startup_detected_ip_v4: Option<IpAddr>,
     startup_detected_ip_v6: Option<IpAddr>,
     process_started_at_epoch_secs: u64,
+    startup_tracker: Arc<StartupTracker>,
 ) {
     let listener = match TcpListener::bind(listen).await {
         Ok(listener) => listener,
@@ -138,6 +143,7 @@ pub async fn serve(
         )),
         request_id: Arc::new(AtomicU64::new(1)),
         runtime_state: runtime_state.clone(),
+        startup_tracker,
     });
 
     spawn_runtime_watchers(
@@ -248,7 +254,12 @@ async fn handle(
             }
             ("GET", "/v1/runtime/gates") => {
                 let revision = current_revision(&shared.config_path).await?;
-                let data = build_runtime_gates_data(shared.as_ref(), cfg.as_ref());
+                let data = build_runtime_gates_data(shared.as_ref(), cfg.as_ref()).await;
+                Ok(success_response(StatusCode::OK, data, revision))
+            }
+            ("GET", "/v1/runtime/initialization") => {
+                let revision = current_revision(&shared.config_path).await?;
+                let data = build_runtime_initialization_data(shared.as_ref()).await;
                 Ok(success_response(StatusCode::OK, data, revision))
             }
             ("GET", "/v1/limits/effective") => {

src/api/model.rs

@@ -266,6 +266,7 @@ pub(super) struct MeWritersData {
 pub(super) struct DcStatus {
     pub(super) dc: i16,
     pub(super) endpoints: Vec<String>,
+    pub(super) endpoint_writers: Vec<DcEndpointWriters>,
     pub(super) available_endpoints: usize,
     pub(super) available_pct: f64,
     pub(super) required_writers: usize,
@@ -279,6 +280,12 @@ pub(super) struct DcStatus {
     pub(super) load: usize,
 }
 
+#[derive(Serialize, Clone)]
+pub(super) struct DcEndpointWriters {
+    pub(super) endpoint: String,
+    pub(super) active_writers: usize,
+}
+
 #[derive(Serialize, Clone)]
 pub(super) struct DcStatusData {
     pub(super) middle_proxy_enabled: bool,
@@ -318,11 +325,21 @@ pub(super) struct MinimalMeRuntimeData {
     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_max_active_writers_per_core: u16,
+    pub(super) adaptive_floor_max_warm_writers_per_core: u16,
+    pub(super) adaptive_floor_max_active_writers_global: u32,
+    pub(super) adaptive_floor_max_warm_writers_global: u32,
     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) adaptive_floor_active_cap_configured: u64,
+    pub(super) adaptive_floor_active_cap_effective: u64,
+    pub(super) adaptive_floor_warm_cap_configured: u64,
+    pub(super) adaptive_floor_warm_cap_effective: u64,
+    pub(super) adaptive_floor_active_writers_current: u64,
+    pub(super) adaptive_floor_warm_writers_current: u64,
     pub(super) me_keepalive_enabled: bool,
     pub(super) me_keepalive_interval_secs: u64,
     pub(super) me_keepalive_jitter_secs: u64,
@@ -344,6 +361,8 @@ pub(super) struct MinimalMeRuntimeData {
     pub(super) me_single_endpoint_outage_backoff_max_ms: u64,
     pub(super) me_single_endpoint_shadow_rotate_every_secs: u64,
     pub(super) me_deterministic_writer_sort: bool,
+    pub(super) me_writer_pick_mode: &'static str,
+    pub(super) me_writer_pick_sample_size: u8,
     pub(super) me_socks_kdf_policy: &'static str,
     pub(super) quarantined_endpoints_total: usize,
     pub(super) quarantined_endpoints: Vec<MinimalQuarantineData>,

src/api/runtime_init.rs

@@ -0,0 +1,186 @@
+use serde::Serialize;
+
+use crate::startup::{
+    COMPONENT_ME_CONNECTIVITY_PING, COMPONENT_ME_POOL_CONSTRUCT, COMPONENT_ME_POOL_INIT_STAGE1,
+    COMPONENT_ME_PROXY_CONFIG_V4, COMPONENT_ME_PROXY_CONFIG_V6, COMPONENT_ME_SECRET_FETCH,
+    StartupComponentStatus, StartupMeStatus, compute_progress_pct,
+};
+
+use super::ApiShared;
+
+#[derive(Serialize)]
+pub(super) struct RuntimeInitializationComponentData {
+    pub(super) id: &'static str,
+    pub(super) title: &'static str,
+    pub(super) status: &'static str,
+    pub(super) started_at_epoch_ms: Option<u64>,
+    pub(super) finished_at_epoch_ms: Option<u64>,
+    pub(super) duration_ms: Option<u64>,
+    pub(super) attempts: u32,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(super) details: Option<String>,
+}
+
+#[derive(Serialize)]
+pub(super) struct RuntimeInitializationMeData {
+    pub(super) status: &'static str,
+    pub(super) current_stage: String,
+    pub(super) progress_pct: f64,
+    pub(super) init_attempt: u32,
+    pub(super) retry_limit: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(super) last_error: Option<String>,
+}
+
+#[derive(Serialize)]
+pub(super) struct RuntimeInitializationData {
+    pub(super) status: &'static str,
+    pub(super) degraded: bool,
+    pub(super) current_stage: String,
+    pub(super) progress_pct: f64,
+    pub(super) started_at_epoch_secs: u64,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(super) ready_at_epoch_secs: Option<u64>,
+    pub(super) total_elapsed_ms: u64,
+    pub(super) transport_mode: String,
+    pub(super) me: RuntimeInitializationMeData,
+    pub(super) components: Vec<RuntimeInitializationComponentData>,
+}
+
+#[derive(Clone)]
+pub(super) struct RuntimeStartupSummaryData {
+    pub(super) status: &'static str,
+    pub(super) stage: String,
+    pub(super) progress_pct: f64,
+}
+
+pub(super) async fn build_runtime_startup_summary(shared: &ApiShared) -> RuntimeStartupSummaryData {
+    let snapshot = shared.startup_tracker.snapshot().await;
+    let me_pool_progress = current_me_pool_stage_progress(shared).await;
+    let progress_pct = compute_progress_pct(&snapshot, me_pool_progress);
+    RuntimeStartupSummaryData {
+        status: snapshot.status.as_str(),
+        stage: snapshot.current_stage,
+        progress_pct,
+    }
+}
+
+pub(super) async fn build_runtime_initialization_data(
+    shared: &ApiShared,
+) -> RuntimeInitializationData {
+    let snapshot = shared.startup_tracker.snapshot().await;
+    let me_pool_progress = current_me_pool_stage_progress(shared).await;
+    let progress_pct = compute_progress_pct(&snapshot, me_pool_progress);
+    let me_progress_pct = compute_me_progress_pct(&snapshot, me_pool_progress);
+
+    RuntimeInitializationData {
+        status: snapshot.status.as_str(),
+        degraded: snapshot.degraded,
+        current_stage: snapshot.current_stage,
+        progress_pct,
+        started_at_epoch_secs: snapshot.started_at_epoch_secs,
+        ready_at_epoch_secs: snapshot.ready_at_epoch_secs,
+        total_elapsed_ms: snapshot.total_elapsed_ms,
+        transport_mode: snapshot.transport_mode,
+        me: RuntimeInitializationMeData {
+            status: snapshot.me.status.as_str(),
+            current_stage: snapshot.me.current_stage,
+            progress_pct: me_progress_pct,
+            init_attempt: snapshot.me.init_attempt,
+            retry_limit: snapshot.me.retry_limit,
+            last_error: snapshot.me.last_error,
+        },
+        components: snapshot
+            .components
+            .into_iter()
+            .map(|component| RuntimeInitializationComponentData {
+                id: component.id,
+                title: component.title,
+                status: component.status.as_str(),
+                started_at_epoch_ms: component.started_at_epoch_ms,
+                finished_at_epoch_ms: component.finished_at_epoch_ms,
+                duration_ms: component.duration_ms,
+                attempts: component.attempts,
+                details: component.details,
+            })
+            .collect(),
+    }
+}
+
+fn compute_me_progress_pct(
+    snapshot: &crate::startup::StartupSnapshot,
+    me_pool_progress: Option<f64>,
+) -> f64 {
+    match snapshot.me.status {
+        StartupMeStatus::Pending => 0.0,
+        StartupMeStatus::Ready | StartupMeStatus::Failed | StartupMeStatus::Skipped => 100.0,
+        StartupMeStatus::Initializing => {
+            let mut total_weight = 0.0f64;
+            let mut completed_weight = 0.0f64;
+            for component in &snapshot.components {
+                if !is_me_component(component.id) {
+                    continue;
+                }
+                total_weight += component.weight;
+                let unit_progress = match component.status {
+                    StartupComponentStatus::Pending => 0.0,
+                    StartupComponentStatus::Running => {
+                        if component.id == COMPONENT_ME_POOL_INIT_STAGE1 {
+                            me_pool_progress.unwrap_or(0.0).clamp(0.0, 1.0)
+                        } else {
+                            0.0
+                        }
+                    }
+                    StartupComponentStatus::Ready
+                    | StartupComponentStatus::Failed
+                    | StartupComponentStatus::Skipped => 1.0,
+                };
+                completed_weight += component.weight * unit_progress;
+            }
+            if total_weight <= f64::EPSILON {
+                0.0
+            } else {
+                ((completed_weight / total_weight) * 100.0).clamp(0.0, 100.0)
+            }
+        }
+    }
+}
+
+fn is_me_component(component_id: &str) -> bool {
+    matches!(
+        component_id,
+        COMPONENT_ME_SECRET_FETCH
+            | COMPONENT_ME_PROXY_CONFIG_V4
+            | COMPONENT_ME_PROXY_CONFIG_V6
+            | COMPONENT_ME_POOL_CONSTRUCT
+            | COMPONENT_ME_POOL_INIT_STAGE1
+            | COMPONENT_ME_CONNECTIVITY_PING
+    )
+}
+
+async fn current_me_pool_stage_progress(shared: &ApiShared) -> Option<f64> {
+    let snapshot = shared.startup_tracker.snapshot().await;
+    if snapshot.me.status != StartupMeStatus::Initializing {
+        return None;
+    }
+
+    let pool = shared.me_pool.read().await.clone()?;
+    let status = pool.api_status_snapshot().await;
+    let configured_dc_groups = status.configured_dc_groups;
+    let covered_dc_groups = status
+        .dcs
+        .iter()
+        .filter(|dc| dc.alive_writers > 0)
+        .count();
+
+    let dc_coverage = ratio_01(covered_dc_groups, configured_dc_groups);
+    let writer_coverage = ratio_01(status.alive_writers, status.required_writers);
+    Some((0.7 * dc_coverage + 0.3 * writer_coverage).clamp(0.0, 1.0))
+}
+
+fn ratio_01(part: usize, total: usize) -> f64 {
+    if total == 0 {
+        return 0.0;
+    }
+    ((part as f64) / (total as f64)).clamp(0.0, 1.0)
+}

src/api/runtime_min.rs

@@ -260,7 +260,7 @@ pub(super) fn build_security_whitelist_data(cfg: &ProxyConfig) -> SecurityWhitel
 
 pub(super) async fn build_runtime_me_pool_state_data(shared: &ApiShared) -> RuntimeMePoolStateData {
     let now_epoch_secs = now_epoch_secs();
-    let Some(pool) = &shared.me_pool else {
+    let Some(pool) = shared.me_pool.read().await.clone() else {
         return RuntimeMePoolStateData {
             enabled: false,
             reason: Some(SOURCE_UNAVAILABLE_REASON),
@@ -350,7 +350,7 @@ pub(super) async fn build_runtime_me_pool_state_data(shared: &ApiShared) -> Runt
 
 pub(super) async fn build_runtime_me_quality_data(shared: &ApiShared) -> RuntimeMeQualityData {
     let now_epoch_secs = now_epoch_secs();
-    let Some(pool) = &shared.me_pool else {
+    let Some(pool) = shared.me_pool.read().await.clone() else {
         return RuntimeMeQualityData {
             enabled: false,
             reason: Some(SOURCE_UNAVAILABLE_REASON),
@@ -486,7 +486,7 @@ pub(super) async fn build_runtime_upstream_quality_data(
 
 pub(super) async fn build_runtime_nat_stun_data(shared: &ApiShared) -> RuntimeNatStunData {
     let now_epoch_secs = now_epoch_secs();
-    let Some(pool) = &shared.me_pool else {
+    let Some(pool) = shared.me_pool.read().await.clone() else {
         return RuntimeNatStunData {
             enabled: false,
             reason: Some(SOURCE_UNAVAILABLE_REASON),

src/api/runtime_stats.rs

@@ -7,10 +7,10 @@ use crate::transport::UpstreamRouteKind;
 
 use super::ApiShared;
 use super::model::{
-    DcStatus, DcStatusData, MeWriterStatus, MeWritersData, MeWritersSummary, MinimalAllData,
+    DcEndpointWriters, DcStatus, DcStatusData, MeWriterStatus, MeWritersData, MeWritersSummary,
-    MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData, MinimalQuarantineData,
+    MinimalAllData, MinimalAllPayload, MinimalDcPathData, MinimalMeRuntimeData,
-    UpstreamDcStatus, UpstreamStatus, UpstreamSummaryData, UpstreamsData, ZeroAllData,
+    MinimalQuarantineData, UpstreamDcStatus, UpstreamStatus, UpstreamSummaryData, UpstreamsData,
-    ZeroCodeCount, ZeroCoreData, ZeroDesyncData, ZeroMiddleProxyData, ZeroPoolData,
+    ZeroAllData, ZeroCodeCount, ZeroCoreData, ZeroDesyncData, ZeroMiddleProxyData, ZeroPoolData,
     ZeroUpstreamData,
 };
 
@@ -297,7 +297,7 @@ async fn get_minimal_payload_cached(
         }
     }
 
-    let pool = shared.me_pool.as_ref()?;
+    let pool = shared.me_pool.read().await.clone()?;
     let status = pool.api_status_snapshot().await;
     let runtime = pool.api_runtime_snapshot().await;
     let generated_at_epoch_secs = status.generated_at_epoch_secs;
@@ -346,6 +346,14 @@ async fn get_minimal_payload_cached(
                     .into_iter()
                     .map(|value| value.to_string())
                     .collect(),
+                endpoint_writers: entry
+                    .endpoint_writers
+                    .into_iter()
+                    .map(|coverage| DcEndpointWriters {
+                        endpoint: coverage.endpoint.to_string(),
+                        active_writers: coverage.active_writers,
+                    })
+                    .collect(),
                 available_endpoints: entry.available_endpoints,
                 available_pct: entry.available_pct,
                 required_writers: entry.required_writers,
@@ -380,11 +388,25 @@ async fn get_minimal_payload_cached(
             .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_max_active_writers_per_core: runtime
+            .adaptive_floor_max_active_writers_per_core,
+        adaptive_floor_max_warm_writers_per_core: runtime
+            .adaptive_floor_max_warm_writers_per_core,
+        adaptive_floor_max_active_writers_global: runtime
+            .adaptive_floor_max_active_writers_global,
+        adaptive_floor_max_warm_writers_global: runtime
+            .adaptive_floor_max_warm_writers_global,
         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,
+        adaptive_floor_active_cap_configured: runtime.adaptive_floor_active_cap_configured,
+        adaptive_floor_active_cap_effective: runtime.adaptive_floor_active_cap_effective,
+        adaptive_floor_warm_cap_configured: runtime.adaptive_floor_warm_cap_configured,
+        adaptive_floor_warm_cap_effective: runtime.adaptive_floor_warm_cap_effective,
+        adaptive_floor_active_writers_current: runtime.adaptive_floor_active_writers_current,
+        adaptive_floor_warm_writers_current: runtime.adaptive_floor_warm_writers_current,
         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,
@@ -408,6 +430,8 @@ async fn get_minimal_payload_cached(
         me_single_endpoint_shadow_rotate_every_secs: runtime
             .me_single_endpoint_shadow_rotate_every_secs,
         me_deterministic_writer_sort: runtime.me_deterministic_writer_sort,
+        me_writer_pick_mode: runtime.me_writer_pick_mode,
+        me_writer_pick_sample_size: runtime.me_writer_pick_sample_size,
         me_socks_kdf_policy: runtime.me_socks_kdf_policy,
         quarantined_endpoints_total: runtime.quarantined_endpoints.len(),
         quarantined_endpoints: runtime

src/api/runtime_zero.rs

@@ -2,9 +2,10 @@ use std::sync::atomic::Ordering;
 
 use serde::Serialize;
 
-use crate::config::{MeFloorMode, ProxyConfig, UserMaxUniqueIpsMode};
+use crate::config::{MeFloorMode, MeWriterPickMode, ProxyConfig, UserMaxUniqueIpsMode};
 
 use super::ApiShared;
+use super::runtime_init::build_runtime_startup_summary;
 
 #[derive(Serialize)]
 pub(super) struct SystemInfoData {
@@ -34,6 +35,9 @@ pub(super) struct RuntimeGatesData {
     pub(super) me_runtime_ready: bool,
     pub(super) me2dc_fallback_enabled: bool,
     pub(super) use_middle_proxy: bool,
+    pub(super) startup_status: &'static str,
+    pub(super) startup_stage: String,
+    pub(super) startup_progress_pct: f64,
 }
 
 #[derive(Serialize)]
@@ -66,10 +70,16 @@ pub(super) struct EffectiveMiddleProxyLimits {
     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_max_active_writers_per_core: u16,
+    pub(super) adaptive_floor_max_warm_writers_per_core: u16,
+    pub(super) adaptive_floor_max_active_writers_global: u32,
+    pub(super) adaptive_floor_max_warm_writers_global: u32,
     pub(super) reconnect_max_concurrent_per_dc: u32,
     pub(super) reconnect_backoff_base_ms: u64,
     pub(super) reconnect_backoff_cap_ms: u64,
     pub(super) reconnect_fast_retry_count: u32,
+    pub(super) writer_pick_mode: &'static str,
+    pub(super) writer_pick_sample_size: u8,
     pub(super) me2dc_fallback: bool,
 }
 
@@ -142,12 +152,18 @@ pub(super) fn build_system_info_data(
     }
 }
 
-pub(super) fn build_runtime_gates_data(shared: &ApiShared, cfg: &ProxyConfig) -> RuntimeGatesData {
+pub(super) async fn build_runtime_gates_data(
+    shared: &ApiShared,
+    cfg: &ProxyConfig,
+) -> RuntimeGatesData {
+    let startup_summary = build_runtime_startup_summary(shared).await;
     let me_runtime_ready = if !cfg.general.use_middle_proxy {
         true
     } else {
         shared
             .me_pool
+            .read()
+            .await
             .as_ref()
             .map(|pool| pool.is_runtime_ready())
             .unwrap_or(false)
@@ -159,6 +175,9 @@ pub(super) fn build_runtime_gates_data(shared: &ApiShared, cfg: &ProxyConfig) ->
         me_runtime_ready,
         me2dc_fallback_enabled: cfg.general.me2dc_fallback,
         use_middle_proxy: cfg.general.use_middle_proxy,
+        startup_status: startup_summary.status,
+        startup_stage: startup_summary.stage,
+        startup_progress_pct: startup_summary.progress_pct,
     }
 }
 
@@ -204,10 +223,24 @@ pub(super) fn build_limits_effective_data(cfg: &ProxyConfig) -> EffectiveLimitsD
             adaptive_floor_max_extra_writers_multi_per_core: cfg
                 .general
                 .me_adaptive_floor_max_extra_writers_multi_per_core,
+            adaptive_floor_max_active_writers_per_core: cfg
+                .general
+                .me_adaptive_floor_max_active_writers_per_core,
+            adaptive_floor_max_warm_writers_per_core: cfg
+                .general
+                .me_adaptive_floor_max_warm_writers_per_core,
+            adaptive_floor_max_active_writers_global: cfg
+                .general
+                .me_adaptive_floor_max_active_writers_global,
+            adaptive_floor_max_warm_writers_global: cfg
+                .general
+                .me_adaptive_floor_max_warm_writers_global,
             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,
             reconnect_fast_retry_count: cfg.general.me_reconnect_fast_retry_count,
+            writer_pick_mode: me_writer_pick_mode_label(cfg.general.me_writer_pick_mode),
+            writer_pick_sample_size: cfg.general.me_writer_pick_sample_size,
             me2dc_fallback: cfg.general.me2dc_fallback,
         },
         user_ip_policy: EffectiveUserIpPolicyLimits {
@@ -245,3 +278,10 @@ fn me_floor_mode_label(mode: MeFloorMode) -> &'static str {
         MeFloorMode::Adaptive => "adaptive",
     }
 }
+
+fn me_writer_pick_mode_label(mode: MeWriterPickMode) -> &'static str {
+    match mode {
+        MeWriterPickMode::SortedRr => "sorted_rr",
+        MeWriterPickMode::P2c => "p2c",
+    }
+}

src/config/defaults.rs

@@ -17,6 +17,18 @@ 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_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_PER_CORE: u16 = 64;
+const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_PER_CORE: u16 = 64;
+const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_GLOBAL: u32 = 256;
+const DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_GLOBAL: u32 = 256;
+const DEFAULT_ME_WRITER_CMD_CHANNEL_CAPACITY: usize = 1024;
+const DEFAULT_ME_ROUTE_CHANNEL_CAPACITY: usize = 512;
+const DEFAULT_ME_C2ME_CHANNEL_CAPACITY: usize = 256;
+const DEFAULT_ME_WRITER_PICK_SAMPLE_SIZE: u8 = 3;
+const DEFAULT_ME_HEALTH_INTERVAL_MS_UNHEALTHY: u64 = 1000;
+const DEFAULT_ME_HEALTH_INTERVAL_MS_HEALTHY: u64 = 3000;
+const DEFAULT_ME_ADMISSION_POLL_MS: u64 = 1000;
+const DEFAULT_ME_WARN_RATE_LIMIT_MS: u64 = 5000;
 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;
@@ -276,6 +288,54 @@ pub(crate) fn default_me_adaptive_floor_max_extra_writers_multi_per_core() -> u1
     DEFAULT_ME_ADAPTIVE_FLOOR_MAX_EXTRA_WRITERS_MULTI_PER_CORE
 }
 
+pub(crate) fn default_me_adaptive_floor_max_active_writers_per_core() -> u16 {
+    DEFAULT_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_PER_CORE
+}
+
+pub(crate) fn default_me_adaptive_floor_max_warm_writers_per_core() -> u16 {
+    DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_PER_CORE
+}
+
+pub(crate) fn default_me_adaptive_floor_max_active_writers_global() -> u32 {
+    DEFAULT_ME_ADAPTIVE_FLOOR_MAX_ACTIVE_WRITERS_GLOBAL
+}
+
+pub(crate) fn default_me_adaptive_floor_max_warm_writers_global() -> u32 {
+    DEFAULT_ME_ADAPTIVE_FLOOR_MAX_WARM_WRITERS_GLOBAL
+}
+
+pub(crate) fn default_me_writer_cmd_channel_capacity() -> usize {
+    DEFAULT_ME_WRITER_CMD_CHANNEL_CAPACITY
+}
+
+pub(crate) fn default_me_route_channel_capacity() -> usize {
+    DEFAULT_ME_ROUTE_CHANNEL_CAPACITY
+}
+
+pub(crate) fn default_me_c2me_channel_capacity() -> usize {
+    DEFAULT_ME_C2ME_CHANNEL_CAPACITY
+}
+
+pub(crate) fn default_me_writer_pick_sample_size() -> u8 {
+    DEFAULT_ME_WRITER_PICK_SAMPLE_SIZE
+}
+
+pub(crate) fn default_me_health_interval_ms_unhealthy() -> u64 {
+    DEFAULT_ME_HEALTH_INTERVAL_MS_UNHEALTHY
+}
+
+pub(crate) fn default_me_health_interval_ms_healthy() -> u64 {
+    DEFAULT_ME_HEALTH_INTERVAL_MS_HEALTHY
+}
+
+pub(crate) fn default_me_admission_poll_ms() -> u64 {
+    DEFAULT_ME_ADMISSION_POLL_MS
+}
+
+pub(crate) fn default_me_warn_rate_limit_ms() -> u64 {
+    DEFAULT_ME_WARN_RATE_LIMIT_MS
+}
+
 pub(crate) fn default_upstream_connect_retry_attempts() -> u32 {
     DEFAULT_UPSTREAM_CONNECT_RETRY_ATTEMPTS
 }

src/config/hot_reload.rs

@@ -29,7 +29,10 @@ use notify::{EventKind, RecursiveMode, Watcher, recommended_watcher};
 use tokio::sync::{mpsc, watch};
 use tracing::{error, info, warn};
 
-use crate::config::{LogLevel, MeBindStaleMode, MeFloorMode, MeSocksKdfPolicy, MeTelemetryLevel};
+use crate::config::{
+    LogLevel, MeBindStaleMode, MeFloorMode, MeSocksKdfPolicy, MeTelemetryLevel,
+    MeWriterPickMode,
+};
 use super::load::ProxyConfig;
 
 // ── Hot fields ────────────────────────────────────────────────────────────────
@@ -57,6 +60,8 @@ pub struct HotFields {
     pub me_bind_stale_ttl_secs: u64,
     pub me_secret_atomic_snapshot: bool,
     pub me_deterministic_writer_sort: bool,
+    pub me_writer_pick_mode: MeWriterPickMode,
+    pub me_writer_pick_sample_size: u8,
     pub me_single_endpoint_shadow_writers: u8,
     pub me_single_endpoint_outage_mode_enabled: bool,
     pub me_single_endpoint_outage_disable_quarantine: bool,
@@ -84,9 +89,17 @@ pub struct HotFields {
     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_adaptive_floor_max_active_writers_per_core: u16,
+    pub me_adaptive_floor_max_warm_writers_per_core: u16,
+    pub me_adaptive_floor_max_active_writers_global: u32,
+    pub me_adaptive_floor_max_warm_writers_global: u32,
     pub me_route_backpressure_base_timeout_ms: u64,
     pub me_route_backpressure_high_timeout_ms: u64,
     pub me_route_backpressure_high_watermark_pct: u8,
+    pub me_health_interval_ms_unhealthy: u64,
+    pub me_health_interval_ms_healthy: u64,
+    pub me_admission_poll_ms: u64,
+    pub me_warn_rate_limit_ms: u64,
     pub users:                   std::collections::HashMap<String, String>,
     pub user_ad_tags:            std::collections::HashMap<String, String>,
     pub user_max_tcp_conns:      std::collections::HashMap<String, usize>,
@@ -122,6 +135,8 @@ impl HotFields {
             me_bind_stale_ttl_secs: cfg.general.me_bind_stale_ttl_secs,
             me_secret_atomic_snapshot: cfg.general.me_secret_atomic_snapshot,
             me_deterministic_writer_sort: cfg.general.me_deterministic_writer_sort,
+            me_writer_pick_mode: cfg.general.me_writer_pick_mode,
+            me_writer_pick_sample_size: cfg.general.me_writer_pick_sample_size,
             me_single_endpoint_shadow_writers: cfg.general.me_single_endpoint_shadow_writers,
             me_single_endpoint_outage_mode_enabled: cfg
                 .general
@@ -173,9 +188,25 @@ impl HotFields {
             me_adaptive_floor_max_extra_writers_multi_per_core: cfg
                 .general
                 .me_adaptive_floor_max_extra_writers_multi_per_core,
+            me_adaptive_floor_max_active_writers_per_core: cfg
+                .general
+                .me_adaptive_floor_max_active_writers_per_core,
+            me_adaptive_floor_max_warm_writers_per_core: cfg
+                .general
+                .me_adaptive_floor_max_warm_writers_per_core,
+            me_adaptive_floor_max_active_writers_global: cfg
+                .general
+                .me_adaptive_floor_max_active_writers_global,
+            me_adaptive_floor_max_warm_writers_global: cfg
+                .general
+                .me_adaptive_floor_max_warm_writers_global,
             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,
+            me_health_interval_ms_unhealthy: cfg.general.me_health_interval_ms_unhealthy,
+            me_health_interval_ms_healthy: cfg.general.me_health_interval_ms_healthy,
+            me_admission_poll_ms: cfg.general.me_admission_poll_ms,
+            me_warn_rate_limit_ms: cfg.general.me_warn_rate_limit_ms,
             users:                   cfg.access.users.clone(),
             user_ad_tags:            cfg.access.user_ad_tags.clone(),
             user_max_tcp_conns:      cfg.access.user_max_tcp_conns.clone(),
@@ -268,6 +299,8 @@ fn overlay_hot_fields(old: &ProxyConfig, new: &ProxyConfig) -> ProxyConfig {
     cfg.general.me_bind_stale_ttl_secs = new.general.me_bind_stale_ttl_secs;
     cfg.general.me_secret_atomic_snapshot = new.general.me_secret_atomic_snapshot;
     cfg.general.me_deterministic_writer_sort = new.general.me_deterministic_writer_sort;
+    cfg.general.me_writer_pick_mode = new.general.me_writer_pick_mode;
+    cfg.general.me_writer_pick_sample_size = new.general.me_writer_pick_sample_size;
     cfg.general.me_single_endpoint_shadow_writers = new.general.me_single_endpoint_shadow_writers;
     cfg.general.me_single_endpoint_outage_mode_enabled =
         new.general.me_single_endpoint_outage_mode_enabled;
@@ -305,12 +338,24 @@ fn overlay_hot_fields(old: &ProxyConfig, new: &ProxyConfig) -> ProxyConfig {
         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_adaptive_floor_max_active_writers_per_core =
+        new.general.me_adaptive_floor_max_active_writers_per_core;
+    cfg.general.me_adaptive_floor_max_warm_writers_per_core =
+        new.general.me_adaptive_floor_max_warm_writers_per_core;
+    cfg.general.me_adaptive_floor_max_active_writers_global =
+        new.general.me_adaptive_floor_max_active_writers_global;
+    cfg.general.me_adaptive_floor_max_warm_writers_global =
+        new.general.me_adaptive_floor_max_warm_writers_global;
     cfg.general.me_route_backpressure_base_timeout_ms =
         new.general.me_route_backpressure_base_timeout_ms;
     cfg.general.me_route_backpressure_high_timeout_ms =
         new.general.me_route_backpressure_high_timeout_ms;
     cfg.general.me_route_backpressure_high_watermark_pct =
         new.general.me_route_backpressure_high_watermark_pct;
+    cfg.general.me_health_interval_ms_unhealthy = new.general.me_health_interval_ms_unhealthy;
+    cfg.general.me_health_interval_ms_healthy = new.general.me_health_interval_ms_healthy;
+    cfg.general.me_admission_poll_ms = new.general.me_admission_poll_ms;
+    cfg.general.me_warn_rate_limit_ms = new.general.me_warn_rate_limit_ms;
 
     cfg.access.users = new.access.users.clone();
     cfg.access.user_ad_tags = new.access.user_ad_tags.clone();
@@ -647,11 +692,15 @@ fn log_changes(
     }
     if old_hot.me_secret_atomic_snapshot != new_hot.me_secret_atomic_snapshot
         || old_hot.me_deterministic_writer_sort != new_hot.me_deterministic_writer_sort
+        || old_hot.me_writer_pick_mode != new_hot.me_writer_pick_mode
+        || old_hot.me_writer_pick_sample_size != new_hot.me_writer_pick_sample_size
     {
         info!(
-            "config reload: me_runtime_flags: secret_atomic_snapshot={} deterministic_sort={}",
+            "config reload: me_runtime_flags: secret_atomic_snapshot={} deterministic_sort={} writer_pick_mode={:?} writer_pick_sample_size={}",
             new_hot.me_secret_atomic_snapshot,
-            new_hot.me_deterministic_writer_sort
+            new_hot.me_deterministic_writer_sort,
+            new_hot.me_writer_pick_mode,
+            new_hot.me_writer_pick_sample_size,
         );
     }
     if old_hot.me_single_endpoint_shadow_writers != new_hot.me_single_endpoint_shadow_writers
@@ -739,9 +788,17 @@ fn log_changes(
             != 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
+        || old_hot.me_adaptive_floor_max_active_writers_per_core
+            != new_hot.me_adaptive_floor_max_active_writers_per_core
+        || old_hot.me_adaptive_floor_max_warm_writers_per_core
+            != new_hot.me_adaptive_floor_max_warm_writers_per_core
+        || old_hot.me_adaptive_floor_max_active_writers_global
+            != new_hot.me_adaptive_floor_max_active_writers_global
+        || old_hot.me_adaptive_floor_max_warm_writers_global
+            != new_hot.me_adaptive_floor_max_warm_writers_global
     {
         info!(
-            "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={}",
+            "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={} max_active_per_core={} max_warm_per_core={} max_active_global={} max_warm_global={}",
             new_hot.me_floor_mode,
             new_hot.me_adaptive_floor_idle_secs,
             new_hot.me_adaptive_floor_min_writers_single_endpoint,
@@ -751,6 +808,10 @@ fn log_changes(
             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,
+            new_hot.me_adaptive_floor_max_active_writers_per_core,
+            new_hot.me_adaptive_floor_max_warm_writers_per_core,
+            new_hot.me_adaptive_floor_max_active_writers_global,
+            new_hot.me_adaptive_floor_max_warm_writers_global,
         );
     }
 
@@ -760,12 +821,21 @@ fn log_changes(
             != new_hot.me_route_backpressure_high_timeout_ms
         || old_hot.me_route_backpressure_high_watermark_pct
             != new_hot.me_route_backpressure_high_watermark_pct
+        || old_hot.me_health_interval_ms_unhealthy
+            != new_hot.me_health_interval_ms_unhealthy
+        || old_hot.me_health_interval_ms_healthy != new_hot.me_health_interval_ms_healthy
+        || old_hot.me_admission_poll_ms != new_hot.me_admission_poll_ms
+        || old_hot.me_warn_rate_limit_ms != new_hot.me_warn_rate_limit_ms
     {
         info!(
-            "config reload: me_route_backpressure: base={}ms high={}ms watermark={}%",
+            "config reload: me_route_backpressure: base={}ms high={}ms watermark={}%; me_health_interval: unhealthy={}ms healthy={}ms; me_admission_poll={}ms; me_warn_rate_limit={}ms",
             new_hot.me_route_backpressure_base_timeout_ms,
             new_hot.me_route_backpressure_high_timeout_ms,
             new_hot.me_route_backpressure_high_watermark_pct,
+            new_hot.me_health_interval_ms_unhealthy,
+            new_hot.me_health_interval_ms_healthy,
+            new_hot.me_admission_poll_ms,
+            new_hot.me_warn_rate_limit_ms,
         );
     }
 

src/config/load.rs

@@ -285,6 +285,48 @@ impl ProxyConfig {
             ));
         }
 
+        if config.general.me_writer_cmd_channel_capacity == 0 {
+            return Err(ProxyError::Config(
+                "general.me_writer_cmd_channel_capacity must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_route_channel_capacity == 0 {
+            return Err(ProxyError::Config(
+                "general.me_route_channel_capacity must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_c2me_channel_capacity == 0 {
+            return Err(ProxyError::Config(
+                "general.me_c2me_channel_capacity must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_health_interval_ms_unhealthy == 0 {
+            return Err(ProxyError::Config(
+                "general.me_health_interval_ms_unhealthy must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_health_interval_ms_healthy == 0 {
+            return Err(ProxyError::Config(
+                "general.me_health_interval_ms_healthy must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_admission_poll_ms == 0 {
+            return Err(ProxyError::Config(
+                "general.me_admission_poll_ms must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_warn_rate_limit_ms == 0 {
+            return Err(ProxyError::Config(
+                "general.me_warn_rate_limit_ms must be > 0".to_string(),
+            ));
+        }
+
         if config.access.user_max_unique_ips_window_secs == 0 {
             return Err(ProxyError::Config(
                 "access.user_max_unique_ips_window_secs must be > 0".to_string(),
@@ -327,6 +369,30 @@ impl ProxyConfig {
             ));
         }
 
+        if config.general.me_adaptive_floor_max_active_writers_per_core == 0 {
+            return Err(ProxyError::Config(
+                "general.me_adaptive_floor_max_active_writers_per_core must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_adaptive_floor_max_warm_writers_per_core == 0 {
+            return Err(ProxyError::Config(
+                "general.me_adaptive_floor_max_warm_writers_per_core must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_adaptive_floor_max_active_writers_global == 0 {
+            return Err(ProxyError::Config(
+                "general.me_adaptive_floor_max_active_writers_global must be > 0".to_string(),
+            ));
+        }
+
+        if config.general.me_adaptive_floor_max_warm_writers_global == 0 {
+            return Err(ProxyError::Config(
+                "general.me_adaptive_floor_max_warm_writers_global 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(),
@@ -453,6 +519,12 @@ impl ProxyConfig {
             ));
         }
 
+        if !(2..=4).contains(&config.general.me_writer_pick_sample_size) {
+            return Err(ProxyError::Config(
+                "general.me_writer_pick_sample_size must be within [2, 4]".to_string(),
+            ));
+        }
+
         if config.general.me_route_inline_recovery_attempts == 0 {
             return Err(ProxyError::Config(
                 "general.me_route_inline_recovery_attempts must be > 0".to_string(),
@@ -1238,6 +1310,46 @@ mod tests {
         let _ = std::fs::remove_file(path);
     }
 
+    #[test]
+    fn me_adaptive_floor_max_active_writers_per_core_zero_is_rejected() {
+        let toml = r#"
+            [general]
+            me_adaptive_floor_max_active_writers_per_core = 0
+
+            [censorship]
+            tls_domain = "example.com"
+
+            [access.users]
+            user = "00000000000000000000000000000000"
+        "#;
+        let dir = std::env::temp_dir();
+        let path = dir.join("telemt_me_adaptive_floor_max_active_per_core_zero_test.toml");
+        std::fs::write(&path, toml).unwrap();
+        let err = ProxyConfig::load(&path).unwrap_err().to_string();
+        assert!(err.contains("general.me_adaptive_floor_max_active_writers_per_core must be > 0"));
+        let _ = std::fs::remove_file(path);
+    }
+
+    #[test]
+    fn me_adaptive_floor_max_warm_writers_global_zero_is_rejected() {
+        let toml = r#"
+            [general]
+            me_adaptive_floor_max_warm_writers_global = 0
+
+            [censorship]
+            tls_domain = "example.com"
+
+            [access.users]
+            user = "00000000000000000000000000000000"
+        "#;
+        let dir = std::env::temp_dir();
+        let path = dir.join("telemt_me_adaptive_floor_max_warm_global_zero_test.toml");
+        std::fs::write(&path, toml).unwrap();
+        let err = ProxyConfig::load(&path).unwrap_err().to_string();
+        assert!(err.contains("general.me_adaptive_floor_max_warm_writers_global must be > 0"));
+        let _ = std::fs::remove_file(path);
+    }
+
     #[test]
     fn upstream_connect_retry_attempts_zero_is_rejected() {
         let toml = r#"

src/config/types.rs

@@ -212,6 +212,32 @@ impl MeRouteNoWriterMode {
     }
 }
 
+/// Middle-End writer selection mode for new client bindings.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize, Default)]
+#[serde(rename_all = "snake_case")]
+pub enum MeWriterPickMode {
+    SortedRr,
+    #[default]
+    P2c,
+}
+
+impl MeWriterPickMode {
+    pub fn as_u8(self) -> u8 {
+        match self {
+            MeWriterPickMode::SortedRr => 0,
+            MeWriterPickMode::P2c => 1,
+        }
+    }
+
+    pub fn from_u8(raw: u8) -> Self {
+        match raw {
+            0 => MeWriterPickMode::SortedRr,
+            1 => MeWriterPickMode::P2c,
+            _ => MeWriterPickMode::P2c,
+        }
+    }
+}
+
 /// Per-user unique source IP limit mode.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize, Default)]
 #[serde(rename_all = "snake_case")]
@@ -420,6 +446,18 @@ pub struct GeneralConfig {
     #[serde(default = "default_rpc_proxy_req_every")]
     pub rpc_proxy_req_every: u64,
 
+    /// Capacity of per-ME writer command channel.
+    #[serde(default = "default_me_writer_cmd_channel_capacity")]
+    pub me_writer_cmd_channel_capacity: usize,
+
+    /// Capacity of per-connection ME response route channel.
+    #[serde(default = "default_me_route_channel_capacity")]
+    pub me_route_channel_capacity: usize,
+
+    /// Capacity of per-client command queue from client reader to ME sender task.
+    #[serde(default = "default_me_c2me_channel_capacity")]
+    pub me_c2me_channel_capacity: usize,
+
     /// Max pending ciphertext buffer per client writer (bytes).
     /// Controls FakeTLS backpressure vs throughput.
     #[serde(default = "default_crypto_pending_buffer")]
@@ -545,6 +583,22 @@ pub struct GeneralConfig {
     #[serde(default = "default_me_adaptive_floor_max_extra_writers_multi_per_core")]
     pub me_adaptive_floor_max_extra_writers_multi_per_core: u16,
 
+    /// Hard cap for active ME writers per logical CPU core.
+    #[serde(default = "default_me_adaptive_floor_max_active_writers_per_core")]
+    pub me_adaptive_floor_max_active_writers_per_core: u16,
+
+    /// Hard cap for warm ME writers per logical CPU core.
+    #[serde(default = "default_me_adaptive_floor_max_warm_writers_per_core")]
+    pub me_adaptive_floor_max_warm_writers_per_core: u16,
+
+    /// Hard global cap for active ME writers.
+    #[serde(default = "default_me_adaptive_floor_max_active_writers_global")]
+    pub me_adaptive_floor_max_active_writers_global: u32,
+
+    /// Hard global cap for warm ME writers.
+    #[serde(default = "default_me_adaptive_floor_max_warm_writers_global")]
+    pub me_adaptive_floor_max_warm_writers_global: u32,
+
     /// Connect attempts for the selected upstream before returning error/fallback.
     #[serde(default = "default_upstream_connect_retry_attempts")]
     pub upstream_connect_retry_attempts: u32,
@@ -604,6 +658,22 @@ pub struct GeneralConfig {
     #[serde(default = "default_me_route_backpressure_high_watermark_pct")]
     pub me_route_backpressure_high_watermark_pct: u8,
 
+    /// Health monitor interval in milliseconds while writer coverage is degraded.
+    #[serde(default = "default_me_health_interval_ms_unhealthy")]
+    pub me_health_interval_ms_unhealthy: u64,
+
+    /// Health monitor interval in milliseconds while writer coverage is stable.
+    #[serde(default = "default_me_health_interval_ms_healthy")]
+    pub me_health_interval_ms_healthy: u64,
+
+    /// Poll interval in milliseconds for conditional-admission state checks.
+    #[serde(default = "default_me_admission_poll_ms")]
+    pub me_admission_poll_ms: u64,
+
+    /// Cooldown for repetitive ME warning logs in milliseconds.
+    #[serde(default = "default_me_warn_rate_limit_ms")]
+    pub me_warn_rate_limit_ms: u64,
+
     /// ME route behavior when no writer is immediately available.
     #[serde(default)]
     pub me_route_no_writer_mode: MeRouteNoWriterMode,
@@ -738,6 +808,14 @@ pub struct GeneralConfig {
     #[serde(default = "default_me_deterministic_writer_sort")]
     pub me_deterministic_writer_sort: bool,
 
+    /// Writer selection mode for ME route bind path.
+    #[serde(default)]
+    pub me_writer_pick_mode: MeWriterPickMode,
+
+    /// Number of candidates sampled by writer picker in `p2c` mode.
+    #[serde(default = "default_me_writer_pick_sample_size")]
+    pub me_writer_pick_sample_size: u8,
+
     /// Enable NTP drift check at startup.
     #[serde(default = "default_ntp_check")]
     pub ntp_check: bool,
@@ -780,6 +858,9 @@ impl Default for GeneralConfig {
             me_keepalive_jitter_secs: default_keepalive_jitter(),
             me_keepalive_payload_random: default_true(),
             rpc_proxy_req_every: default_rpc_proxy_req_every(),
+            me_writer_cmd_channel_capacity: default_me_writer_cmd_channel_capacity(),
+            me_route_channel_capacity: default_me_route_channel_capacity(),
+            me_c2me_channel_capacity: default_me_c2me_channel_capacity(),
             me_warmup_stagger_enabled: default_true(),
             me_warmup_step_delay_ms: default_warmup_step_delay_ms(),
             me_warmup_step_jitter_ms: default_warmup_step_jitter_ms(),
@@ -802,6 +883,10 @@ impl Default for GeneralConfig {
             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(),
+            me_adaptive_floor_max_active_writers_per_core: default_me_adaptive_floor_max_active_writers_per_core(),
+            me_adaptive_floor_max_warm_writers_per_core: default_me_adaptive_floor_max_warm_writers_per_core(),
+            me_adaptive_floor_max_active_writers_global: default_me_adaptive_floor_max_active_writers_global(),
+            me_adaptive_floor_max_warm_writers_global: default_me_adaptive_floor_max_warm_writers_global(),
             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(),
@@ -817,6 +902,10 @@ impl Default for GeneralConfig {
             me_route_backpressure_base_timeout_ms: default_me_route_backpressure_base_timeout_ms(),
             me_route_backpressure_high_timeout_ms: default_me_route_backpressure_high_timeout_ms(),
             me_route_backpressure_high_watermark_pct: default_me_route_backpressure_high_watermark_pct(),
+            me_health_interval_ms_unhealthy: default_me_health_interval_ms_unhealthy(),
+            me_health_interval_ms_healthy: default_me_health_interval_ms_healthy(),
+            me_admission_poll_ms: default_me_admission_poll_ms(),
+            me_warn_rate_limit_ms: default_me_warn_rate_limit_ms(),
             me_route_no_writer_mode: MeRouteNoWriterMode::default(),
             me_route_no_writer_wait_ms: default_me_route_no_writer_wait_ms(),
             me_route_inline_recovery_attempts: default_me_route_inline_recovery_attempts(),
@@ -857,6 +946,8 @@ impl Default for GeneralConfig {
             me_reinit_trigger_channel: default_me_reinit_trigger_channel(),
             me_reinit_coalesce_window_ms: default_me_reinit_coalesce_window_ms(),
             me_deterministic_writer_sort: default_me_deterministic_writer_sort(),
+            me_writer_pick_mode: MeWriterPickMode::default(),
+            me_writer_pick_sample_size: default_me_writer_pick_sample_size(),
             ntp_check: default_ntp_check(),
             ntp_servers: default_ntp_servers(),
             auto_degradation_enabled: default_true(),

src/ip_tracker.rs

@@ -5,6 +5,7 @@
 use std::collections::HashMap;
 use std::net::IpAddr;
 use std::sync::Arc;
+use std::sync::atomic::{AtomicU64, Ordering};
 use std::time::{Duration, Instant};
 
 use tokio::sync::RwLock;
@@ -18,6 +19,7 @@ pub struct UserIpTracker {
     max_ips: Arc<RwLock<HashMap<String, usize>>>,
     limit_mode: Arc<RwLock<UserMaxUniqueIpsMode>>,
     limit_window: Arc<RwLock<Duration>>,
+    last_compact_epoch_secs: Arc<AtomicU64>,
 }
 
 impl UserIpTracker {
@@ -28,6 +30,54 @@ impl UserIpTracker {
             max_ips: Arc::new(RwLock::new(HashMap::new())),
             limit_mode: Arc::new(RwLock::new(UserMaxUniqueIpsMode::ActiveWindow)),
             limit_window: Arc::new(RwLock::new(Duration::from_secs(30))),
+            last_compact_epoch_secs: Arc::new(AtomicU64::new(0)),
+        }
+    }
+
+    fn now_epoch_secs() -> u64 {
+        std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap_or_default()
+            .as_secs()
+    }
+
+    async fn maybe_compact_empty_users(&self) {
+        const COMPACT_INTERVAL_SECS: u64 = 60;
+        let now_epoch_secs = Self::now_epoch_secs();
+        let last_compact_epoch_secs = self.last_compact_epoch_secs.load(Ordering::Relaxed);
+        if now_epoch_secs.saturating_sub(last_compact_epoch_secs) < COMPACT_INTERVAL_SECS {
+            return;
+        }
+        if self
+            .last_compact_epoch_secs
+            .compare_exchange(
+                last_compact_epoch_secs,
+                now_epoch_secs,
+                Ordering::AcqRel,
+                Ordering::Relaxed,
+            )
+            .is_err()
+        {
+            return;
+        }
+
+        let mut active_ips = self.active_ips.write().await;
+        let mut recent_ips = self.recent_ips.write().await;
+        let mut users = Vec::<String>::with_capacity(active_ips.len().saturating_add(recent_ips.len()));
+        users.extend(active_ips.keys().cloned());
+        for user in recent_ips.keys() {
+            if !active_ips.contains_key(user) {
+                users.push(user.clone());
+            }
+        }
+
+        for user in users {
+            let active_empty = active_ips.get(&user).map(|ips| ips.is_empty()).unwrap_or(true);
+            let recent_empty = recent_ips.get(&user).map(|ips| ips.is_empty()).unwrap_or(true);
+            if active_empty && recent_empty {
+                active_ips.remove(&user);
+                recent_ips.remove(&user);
+            }
         }
     }
 
@@ -63,6 +113,7 @@ impl UserIpTracker {
     }
 
     pub async fn check_and_add(&self, username: &str, ip: IpAddr) -> Result<(), String> {
+        self.maybe_compact_empty_users().await;
         let limit = {
             let max_ips = self.max_ips.read().await;
             max_ips.get(username).copied()
@@ -116,6 +167,7 @@ impl UserIpTracker {
     }
 
     pub async fn remove_ip(&self, username: &str, ip: IpAddr) {
+        self.maybe_compact_empty_users().await;
         let mut active_ips = self.active_ips.write().await;
         if let Some(user_ips) = active_ips.get_mut(username) {
             if let Some(count) = user_ips.get_mut(&ip) {

src/main.rs

@@ -8,7 +8,7 @@ use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
 use rand::Rng;
 use tokio::net::TcpListener;
 use tokio::signal;
-use tokio::sync::{Semaphore, mpsc, watch};
+use tokio::sync::{RwLock, Semaphore, mpsc, watch};
 use tracing::{debug, error, info, warn};
 use tracing_subscriber::{EnvFilter, fmt, prelude::*, reload};
 #[cfg(unix)]
@@ -26,6 +26,7 @@ mod protocol;
 mod proxy;
 mod stats;
 mod stream;
+mod startup;
 mod transport;
 mod tls_front;
 mod util;
@@ -39,6 +40,14 @@ use crate::proxy::ClientHandler;
 use crate::stats::beobachten::BeobachtenStore;
 use crate::stats::telemetry::TelemetryPolicy;
 use crate::stats::{ReplayChecker, Stats};
+use crate::startup::{
+    COMPONENT_API_BOOTSTRAP, COMPONENT_CONFIG_LOAD, COMPONENT_CONFIG_WATCHER_START,
+    COMPONENT_DC_CONNECTIVITY_PING, COMPONENT_LISTENERS_BIND, COMPONENT_ME_CONNECTIVITY_PING,
+    COMPONENT_ME_POOL_CONSTRUCT, COMPONENT_ME_POOL_INIT_STAGE1, COMPONENT_ME_PROXY_CONFIG_V4,
+    COMPONENT_ME_PROXY_CONFIG_V6, COMPONENT_ME_SECRET_FETCH, COMPONENT_METRICS_START,
+    COMPONENT_NETWORK_PROBE, COMPONENT_RUNTIME_READY, COMPONENT_TLS_FRONT_BOOTSTRAP,
+    COMPONENT_TRACING_INIT, StartupMeStatus, StartupTracker,
+};
 use crate::stream::BufferPool;
 use crate::transport::middle_proxy::{
     MePool, ProxyConfigData, fetch_proxy_config_with_raw, format_me_route, format_sample_line,
@@ -373,6 +382,10 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         .duration_since(UNIX_EPOCH)
         .unwrap_or_default()
         .as_secs();
+    let startup_tracker = Arc::new(StartupTracker::new(process_started_at_epoch_secs));
+    startup_tracker
+        .start_component(COMPONENT_CONFIG_LOAD, Some("load and validate config".to_string()))
+        .await;
     let (config_path, cli_silent, cli_log_level) = parse_cli();
 
     let mut config = match ProxyConfig::load(&config_path) {
@@ -399,6 +412,9 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         eprintln!("[telemt] Invalid network.dns_overrides: {}", e);
         std::process::exit(1);
     }
+    startup_tracker
+        .complete_component(COMPONENT_CONFIG_LOAD, Some("config is ready".to_string()))
+        .await;
 
     let has_rust_log = std::env::var("RUST_LOG").is_ok();
     let effective_log_level = if cli_silent {
@@ -410,6 +426,9 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     };
 
     let (filter_layer, filter_handle) = reload::Layer::new(EnvFilter::new("info"));
+    startup_tracker
+        .start_component(COMPONENT_TRACING_INIT, Some("initialize tracing subscriber".to_string()))
+        .await;
 
     // Configure color output based on config
     let fmt_layer = if config.general.disable_colors {
@@ -422,6 +441,9 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         .with(filter_layer)
         .with(fmt_layer)
         .init();
+    startup_tracker
+        .complete_component(COMPONENT_TRACING_INIT, Some("tracing initialized".to_string()))
+        .await;
 
     info!("Telemt MTProxy v{}", env!("CARGO_PKG_VERSION"));
     info!("Log level: {}", effective_log_level);
@@ -473,6 +495,95 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         config.general.upstream_connect_failfast_hard_errors,
         stats.clone(),
     ));
+    let ip_tracker = Arc::new(UserIpTracker::new());
+    ip_tracker.load_limits(&config.access.user_max_unique_ips).await;
+    ip_tracker
+        .set_limit_policy(
+            config.access.user_max_unique_ips_mode,
+            config.access.user_max_unique_ips_window_secs,
+        )
+        .await;
+    if !config.access.user_max_unique_ips.is_empty() {
+        info!(
+            "IP limits configured for {} users",
+            config.access.user_max_unique_ips.len()
+        );
+    }
+    if !config.network.dns_overrides.is_empty() {
+        info!(
+            "Runtime DNS overrides configured: {} entries",
+            config.network.dns_overrides.len()
+        );
+    }
+
+    let (api_config_tx, api_config_rx) = watch::channel(Arc::new(config.clone()));
+    let initial_admission_open = !config.general.use_middle_proxy;
+    let (admission_tx, admission_rx) = watch::channel(initial_admission_open);
+    let api_me_pool = Arc::new(RwLock::new(None::<Arc<MePool>>));
+    startup_tracker
+        .start_component(COMPONENT_API_BOOTSTRAP, Some("spawn API listener task".to_string()))
+        .await;
+
+    if config.server.api.enabled {
+        let listen = match config.server.api.listen.parse::<SocketAddr>() {
+            Ok(listen) => listen,
+            Err(error) => {
+                warn!(
+                    error = %error,
+                    listen = %config.server.api.listen,
+                    "Invalid server.api.listen; API is disabled"
+                );
+                SocketAddr::from(([127, 0, 0, 1], 0))
+            }
+        };
+        if listen.port() != 0 {
+            let stats_api = stats.clone();
+            let ip_tracker_api = ip_tracker.clone();
+            let me_pool_api = api_me_pool.clone();
+            let upstream_manager_api = upstream_manager.clone();
+            let config_rx_api = api_config_rx.clone();
+            let admission_rx_api = admission_rx.clone();
+            let config_path_api = std::path::PathBuf::from(&config_path);
+            let startup_tracker_api = startup_tracker.clone();
+            tokio::spawn(async move {
+                api::serve(
+                    listen,
+                    stats_api,
+                    ip_tracker_api,
+                    me_pool_api,
+                    upstream_manager_api,
+                    config_rx_api,
+                    admission_rx_api,
+                    config_path_api,
+                    None,
+                    None,
+                    process_started_at_epoch_secs,
+                    startup_tracker_api,
+                )
+                .await;
+            });
+            startup_tracker
+                .complete_component(
+                    COMPONENT_API_BOOTSTRAP,
+                    Some(format!("api task spawned on {}", listen)),
+                )
+                .await;
+        } else {
+            startup_tracker
+                .skip_component(
+                    COMPONENT_API_BOOTSTRAP,
+                    Some("server.api.listen has zero port".to_string()),
+                )
+                .await;
+        }
+    } else {
+        startup_tracker
+            .skip_component(
+                COMPONENT_API_BOOTSTRAP,
+                Some("server.api.enabled is false".to_string()),
+            )
+            .await;
+    }
 
     let mut tls_domains = Vec::with_capacity(1 + config.censorship.tls_domains.len());
     tls_domains.push(config.censorship.tls_domain.clone());
@@ -483,6 +594,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     }
 
     // Start TLS front fetching in background immediately, in parallel with STUN probing.
+    startup_tracker
+        .start_component(
+            COMPONENT_TLS_FRONT_BOOTSTRAP,
+            Some("initialize TLS front cache/bootstrap tasks".to_string()),
+        )
+        .await;
     let tls_cache: Option<Arc<TlsFrontCache>> = if config.censorship.tls_emulation {
         let cache = Arc::new(TlsFrontCache::new(
             &tls_domains,
@@ -603,9 +720,26 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
 
         Some(cache)
     } else {
+        startup_tracker
+            .skip_component(
+                COMPONENT_TLS_FRONT_BOOTSTRAP,
+                Some("censorship.tls_emulation is false".to_string()),
+            )
+            .await;
         None
     };
+    if tls_cache.is_some() {
+        startup_tracker
+            .complete_component(
+                COMPONENT_TLS_FRONT_BOOTSTRAP,
+                Some("tls front cache is initialized".to_string()),
+            )
+            .await;
+    }
 
+    startup_tracker
+        .start_component(COMPONENT_NETWORK_PROBE, Some("probe network capabilities".to_string()))
+        .await;
     let probe = run_probe(
         &config.network,
         config.general.middle_proxy_nat_probe,
@@ -614,32 +748,18 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     .await?;
     let decision = decide_network_capabilities(&config.network, &probe);
     log_probe_result(&probe, &decision);
+    startup_tracker
+        .complete_component(
+            COMPONENT_NETWORK_PROBE,
+            Some("network capabilities determined".to_string()),
+        )
+        .await;
 
     let prefer_ipv6 = decision.prefer_ipv6();
     let mut use_middle_proxy = config.general.use_middle_proxy;
     let beobachten = Arc::new(BeobachtenStore::new());
     let rng = Arc::new(SecureRandom::new());
 
-    // IP Tracker initialization
-    let ip_tracker = Arc::new(UserIpTracker::new());
-    ip_tracker.load_limits(&config.access.user_max_unique_ips).await;
-    ip_tracker
-        .set_limit_policy(
-            config.access.user_max_unique_ips_mode,
-            config.access.user_max_unique_ips_window_secs,
-        )
-        .await;
-    
-    if !config.access.user_max_unique_ips.is_empty() {
-        info!("IP limits configured for {} users", config.access.user_max_unique_ips.len());
-    }
-    if !config.network.dns_overrides.is_empty() {
-        info!(
-            "Runtime DNS overrides configured: {} entries",
-            config.network.dns_overrides.len()
-        );
-    }
-
     // Connection concurrency limit
     let max_connections = Arc::new(Semaphore::new(10_000));
 
@@ -657,6 +777,59 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         }
     }
 
+    if use_middle_proxy {
+        startup_tracker
+            .set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_SECRET_FETCH)
+            .await;
+        startup_tracker
+            .start_component(
+                COMPONENT_ME_SECRET_FETCH,
+                Some("fetch proxy-secret from source/cache".to_string()),
+            )
+            .await;
+        startup_tracker
+            .set_me_retry_limit(if !me2dc_fallback || me_init_retry_attempts == 0 {
+                "unlimited".to_string()
+            } else {
+                me_init_retry_attempts.to_string()
+            })
+            .await;
+    } else {
+        startup_tracker
+            .set_me_status(StartupMeStatus::Skipped, "skipped")
+            .await;
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_SECRET_FETCH,
+                Some("middle proxy mode disabled".to_string()),
+            )
+            .await;
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_PROXY_CONFIG_V4,
+                Some("middle proxy mode disabled".to_string()),
+            )
+            .await;
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_PROXY_CONFIG_V6,
+                Some("middle proxy mode disabled".to_string()),
+            )
+            .await;
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_POOL_CONSTRUCT,
+                Some("middle proxy mode disabled".to_string()),
+            )
+            .await;
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_POOL_INIT_STAGE1,
+                Some("middle proxy mode disabled".to_string()),
+            )
+            .await;
+    }
+
     // =====================================================================
     // Middle Proxy initialization (if enabled)
     // =====================================================================
@@ -694,6 +867,9 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
             {
                 Ok(proxy_secret) => break Some(proxy_secret),
                 Err(e) => {
+                    startup_tracker
+                        .set_me_last_error(Some(e.to_string()))
+                        .await;
                     if me2dc_fallback {
                         error!(
                             error = %e,
@@ -713,6 +889,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         };
         match proxy_secret {
             Some(proxy_secret) => {
+                startup_tracker
+                    .complete_component(
+                        COMPONENT_ME_SECRET_FETCH,
+                        Some("proxy-secret loaded".to_string()),
+                    )
+                    .await;
                 info!(
                     secret_len = proxy_secret.len(),
                     key_sig = format_args!(
@@ -731,6 +913,15 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                     "Proxy-secret loaded"
                 );
 
+                startup_tracker
+                    .start_component(
+                        COMPONENT_ME_PROXY_CONFIG_V4,
+                        Some("load startup proxy-config v4".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_PROXY_CONFIG_V4)
+                    .await;
                 let cfg_v4 = load_startup_proxy_config_snapshot(
                     "https://core.telegram.org/getProxyConfig",
                     config.general.proxy_config_v4_cache_path.as_deref(),
@@ -738,6 +929,30 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                     "getProxyConfig",
                 )
                 .await;
+                if cfg_v4.is_some() {
+                    startup_tracker
+                        .complete_component(
+                            COMPONENT_ME_PROXY_CONFIG_V4,
+                            Some("proxy-config v4 loaded".to_string()),
+                        )
+                        .await;
+                } else {
+                    startup_tracker
+                        .fail_component(
+                            COMPONENT_ME_PROXY_CONFIG_V4,
+                            Some("proxy-config v4 unavailable".to_string()),
+                        )
+                        .await;
+                }
+                startup_tracker
+                    .start_component(
+                        COMPONENT_ME_PROXY_CONFIG_V6,
+                        Some("load startup proxy-config v6".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_PROXY_CONFIG_V6)
+                    .await;
                 let cfg_v6 = load_startup_proxy_config_snapshot(
                     "https://core.telegram.org/getProxyConfigV6",
                     config.general.proxy_config_v6_cache_path.as_deref(),
@@ -745,8 +960,32 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                     "getProxyConfigV6",
                 )
                 .await;
+                if cfg_v6.is_some() {
+                    startup_tracker
+                        .complete_component(
+                            COMPONENT_ME_PROXY_CONFIG_V6,
+                            Some("proxy-config v6 loaded".to_string()),
+                        )
+                        .await;
+                } else {
+                    startup_tracker
+                        .fail_component(
+                            COMPONENT_ME_PROXY_CONFIG_V6,
+                            Some("proxy-config v6 unavailable".to_string()),
+                        )
+                        .await;
+                }
 
                 if let (Some(cfg_v4), Some(cfg_v6)) = (cfg_v4, cfg_v6) {
+                    startup_tracker
+                        .start_component(
+                            COMPONENT_ME_POOL_CONSTRUCT,
+                            Some("construct ME pool".to_string()),
+                        )
+                        .await;
+                    startup_tracker
+                        .set_me_status(StartupMeStatus::Initializing, COMPONENT_ME_POOL_CONSTRUCT)
+                        .await;
                     let pool = MePool::new(
                         proxy_tag.clone(),
                         proxy_secret,
@@ -792,6 +1031,10 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                         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.me_adaptive_floor_max_active_writers_per_core,
+                        config.general.me_adaptive_floor_max_warm_writers_per_core,
+                        config.general.me_adaptive_floor_max_active_writers_global,
+                        config.general.me_adaptive_floor_max_warm_writers_global,
                         config.general.hardswap,
                         config.general.me_pool_drain_ttl_secs,
                         config.general.effective_me_pool_force_close_secs(),
@@ -804,21 +1047,60 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                         config.general.me_bind_stale_ttl_secs,
                         config.general.me_secret_atomic_snapshot,
                         config.general.me_deterministic_writer_sort,
+                        config.general.me_writer_pick_mode,
+                        config.general.me_writer_pick_sample_size,
                         config.general.me_socks_kdf_policy,
+                        config.general.me_writer_cmd_channel_capacity,
+                        config.general.me_route_channel_capacity,
                         config.general.me_route_backpressure_base_timeout_ms,
                         config.general.me_route_backpressure_high_timeout_ms,
                         config.general.me_route_backpressure_high_watermark_pct,
+                        config.general.me_health_interval_ms_unhealthy,
+                        config.general.me_health_interval_ms_healthy,
+                        config.general.me_warn_rate_limit_ms,
                         config.general.me_route_no_writer_mode,
                         config.general.me_route_no_writer_wait_ms,
                         config.general.me_route_inline_recovery_attempts,
                         config.general.me_route_inline_recovery_wait_ms,
                     );
+                    startup_tracker
+                        .complete_component(
+                            COMPONENT_ME_POOL_CONSTRUCT,
+                            Some("ME pool object created".to_string()),
+                        )
+                        .await;
+                    *api_me_pool.write().await = Some(pool.clone());
+                    startup_tracker
+                        .start_component(
+                            COMPONENT_ME_POOL_INIT_STAGE1,
+                            Some("initialize ME pool writers".to_string()),
+                        )
+                        .await;
+                    startup_tracker
+                        .set_me_status(
+                            StartupMeStatus::Initializing,
+                            COMPONENT_ME_POOL_INIT_STAGE1,
+                        )
+                        .await;
 
                     let mut init_attempt: u32 = 0;
                     loop {
                         init_attempt = init_attempt.saturating_add(1);
+                        startup_tracker.set_me_init_attempt(init_attempt).await;
                         match pool.init(pool_size, &rng).await {
                             Ok(()) => {
+                                startup_tracker
+                                    .set_me_last_error(None)
+                                    .await;
+                                startup_tracker
+                                    .complete_component(
+                                        COMPONENT_ME_POOL_INIT_STAGE1,
+                                        Some("ME pool initialized".to_string()),
+                                    )
+                                    .await;
+                                startup_tracker
+                                    .set_me_status(StartupMeStatus::Ready, "ready")
+                                    .await;
                                 info!(
                                     attempt = init_attempt,
                                     "Middle-End pool initialized successfully"
@@ -838,8 +1120,20 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                                 break Some(pool);
                             }
                             Err(e) => {
+                                startup_tracker
+                                    .set_me_last_error(Some(e.to_string()))
+                                    .await;
                                 let retries_limited = me2dc_fallback && me_init_retry_attempts > 0;
                                 if retries_limited && init_attempt >= me_init_retry_attempts {
+                                    startup_tracker
+                                        .fail_component(
+                                            COMPONENT_ME_POOL_INIT_STAGE1,
+                                            Some("ME init retry budget exhausted".to_string()),
+                                        )
+                                        .await;
+                                    startup_tracker
+                                        .set_me_status(StartupMeStatus::Failed, "failed")
+                                        .await;
                                     error!(
                                         error = %e,
                                         attempt = init_attempt,
@@ -879,10 +1173,60 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                         }
                     }
                 } else {
+                    startup_tracker
+                        .skip_component(
+                            COMPONENT_ME_POOL_CONSTRUCT,
+                            Some("ME configs are incomplete".to_string()),
+                        )
+                        .await;
+                    startup_tracker
+                        .fail_component(
+                            COMPONENT_ME_POOL_INIT_STAGE1,
+                            Some("ME configs are incomplete".to_string()),
+                        )
+                        .await;
+                    startup_tracker
+                        .set_me_status(StartupMeStatus::Failed, "failed")
+                        .await;
                     None
                 }
             }
-            None => None,
+            None => {
+                startup_tracker
+                    .fail_component(
+                        COMPONENT_ME_SECRET_FETCH,
+                        Some("proxy-secret unavailable".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .skip_component(
+                        COMPONENT_ME_PROXY_CONFIG_V4,
+                        Some("proxy-secret unavailable".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .skip_component(
+                        COMPONENT_ME_PROXY_CONFIG_V6,
+                        Some("proxy-secret unavailable".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .skip_component(
+                        COMPONENT_ME_POOL_CONSTRUCT,
+                        Some("proxy-secret unavailable".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .fail_component(
+                        COMPONENT_ME_POOL_INIT_STAGE1,
+                        Some("proxy-secret unavailable".to_string()),
+                    )
+                    .await;
+                startup_tracker
+                    .set_me_status(StartupMeStatus::Failed, "failed")
+                    .await;
+                None
+            }
         }
     } else {
         None
@@ -890,12 +1234,33 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
 
     // If ME failed to initialize, force direct-only mode.
     if me_pool.is_some() {
+        startup_tracker
+            .set_transport_mode("middle_proxy")
+            .await;
+        startup_tracker
+            .set_degraded(false)
+            .await;
         info!("Transport: Middle-End Proxy - all DC-over-RPC");
     } else {
         let _ = use_middle_proxy;
         use_middle_proxy = false;
         // Make runtime config reflect direct-only mode for handlers.
         config.general.use_middle_proxy = false;
+        startup_tracker
+            .set_transport_mode("direct")
+            .await;
+        startup_tracker
+            .set_degraded(true)
+            .await;
+        if me2dc_fallback {
+            startup_tracker
+                .set_me_status(StartupMeStatus::Failed, "fallback_to_direct")
+                .await;
+        } else {
+            startup_tracker
+                .set_me_status(StartupMeStatus::Skipped, "skipped")
+                .await;
+        }
         info!("Transport: Direct DC - TCP - standard DC-over-TCP");
     }
 
@@ -910,6 +1275,21 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     let buffer_pool = Arc::new(BufferPool::with_config(16 * 1024, 4096));
 
     // Middle-End ping before DC connectivity
+    if me_pool.is_some() {
+        startup_tracker
+            .start_component(
+                COMPONENT_ME_CONNECTIVITY_PING,
+                Some("run startup ME connectivity check".to_string()),
+            )
+            .await;
+    } else {
+        startup_tracker
+            .skip_component(
+                COMPONENT_ME_CONNECTIVITY_PING,
+                Some("ME pool is not available".to_string()),
+            )
+            .await;
+    }
     if let Some(ref pool) = me_pool {
         let me_results = run_me_ping(pool, &rng).await;
 
@@ -979,9 +1359,21 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
             }
         }
         info!("============================================================");
+        startup_tracker
+            .complete_component(
+                COMPONENT_ME_CONNECTIVITY_PING,
+                Some("startup ME connectivity check completed".to_string()),
+            )
+            .await;
     }
 
     info!("================= Telegram DC Connectivity =================");
+    startup_tracker
+        .start_component(
+            COMPONENT_DC_CONNECTIVITY_PING,
+            Some("run startup DC connectivity check".to_string()),
+        )
+        .await;
 
     let ping_results = upstream_manager
         .ping_all_dcs(
@@ -1061,9 +1453,21 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
 			info!("============================================================");
 		}
 	}
+    startup_tracker
+        .complete_component(
+            COMPONENT_DC_CONNECTIVITY_PING,
+            Some("startup DC connectivity check completed".to_string()),
+        )
+        .await;
 
     let initialized_secs = process_started_at.elapsed().as_secs();
     let second_suffix = if initialized_secs == 1 { "" } else { "s" };
+    startup_tracker
+        .start_component(
+            COMPONENT_RUNTIME_READY,
+            Some("finalize startup runtime state".to_string()),
+        )
+        .await;
     info!("===================== Telegram Startup =====================");
     info!(
         "  DC/ME Initialized in {} second{}",
@@ -1074,6 +1478,7 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     if let Some(ref pool) = me_pool {
         pool.set_runtime_ready(true);
     }
+    *api_me_pool.write().await = me_pool.clone();
 
     // Background tasks
     let um_clone = upstream_manager.clone();
@@ -1105,6 +1510,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     // ── Hot-reload watcher ────────────────────────────────────────────────
     // Uses inotify to detect file changes instantly (SIGHUP also works).
     // detected_ip_v4/v6 are passed so newly added users get correct TG links.
+    startup_tracker
+        .start_component(
+            COMPONENT_CONFIG_WATCHER_START,
+            Some("spawn config hot-reload watcher".to_string()),
+        )
+        .await;
     let (config_rx, mut log_level_rx): (
         tokio::sync::watch::Receiver<Arc<ProxyConfig>>,
         tokio::sync::watch::Receiver<LogLevel>,
@@ -1114,6 +1525,23 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         detected_ip_v4,
         detected_ip_v6,
     );
+    startup_tracker
+        .complete_component(
+            COMPONENT_CONFIG_WATCHER_START,
+            Some("config hot-reload watcher started".to_string()),
+        )
+        .await;
+    let mut config_rx_api_bridge = config_rx.clone();
+    let api_config_tx_bridge = api_config_tx.clone();
+    tokio::spawn(async move {
+        loop {
+            if config_rx_api_bridge.changed().await.is_err() {
+                break;
+            }
+            let cfg = config_rx_api_bridge.borrow_and_update().clone();
+            api_config_tx_bridge.send_replace(cfg);
+        }
+    });
 
     let stats_policy = stats.clone();
     let mut config_rx_policy = config_rx.clone();
@@ -1244,6 +1672,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         });
     }
 
+    startup_tracker
+        .start_component(
+            COMPONENT_LISTENERS_BIND,
+            Some("bind TCP/Unix listeners".to_string()),
+        )
+        .await;
     let mut listeners = Vec::new();
 
     for listener_conf in &config.server.listeners {
@@ -1345,7 +1779,6 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
         print_proxy_links(&host, port, &config);
     }
 
-    let (admission_tx, admission_rx) = watch::channel(true);
     if config.general.use_middle_proxy {
         if let Some(pool) = me_pool.as_ref() {
             let initial_open = pool.admission_ready_conditional_cast().await;
@@ -1358,11 +1791,24 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
 
             let pool_for_gate = pool.clone();
             let admission_tx_gate = admission_tx.clone();
+            let mut config_rx_gate = config_rx.clone();
+            let mut admission_poll_ms = config.general.me_admission_poll_ms.max(1);
             tokio::spawn(async move {
                 let mut gate_open = initial_open;
                 let mut open_streak = if initial_open { 1u32 } else { 0u32 };
                 let mut close_streak = if initial_open { 0u32 } else { 1u32 };
                 loop {
+                    tokio::select! {
+                        changed = config_rx_gate.changed() => {
+                            if changed.is_err() {
+                                break;
+                            }
+                            let cfg = config_rx_gate.borrow_and_update().clone();
+                            admission_poll_ms = cfg.general.me_admission_poll_ms.max(1);
+                            continue;
+                        }
+                        _ = tokio::time::sleep(Duration::from_millis(admission_poll_ms)) => {}
+                    }
                     let ready = pool_for_gate.admission_ready_conditional_cast().await;
                     if ready {
                         open_streak = open_streak.saturating_add(1);
@@ -1387,7 +1833,6 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
                             );
                         }
                     }
-                    tokio::time::sleep(Duration::from_millis(250)).await;
                 }
             });
         } else {
@@ -1495,6 +1940,16 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
             }
         });
     }
+    startup_tracker
+        .complete_component(
+            COMPONENT_LISTENERS_BIND,
+            Some(format!(
+                "listeners configured tcp={} unix={}",
+                listeners.len(),
+                has_unix_listener
+            )),
+        )
+        .await;
 
     if listeners.is_empty() && !has_unix_listener {
         error!("No listeners. Exiting.");
@@ -1528,6 +1983,12 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
     });
 
     if let Some(port) = config.server.metrics_port {
+        startup_tracker
+            .start_component(
+                COMPONENT_METRICS_START,
+                Some(format!("spawn metrics endpoint on {}", port)),
+            )
+            .await;
         let stats = stats.clone();
         let beobachten = beobachten.clone();
         let config_rx_metrics = config_rx.clone();
@@ -1544,48 +2005,28 @@ async fn main() -> std::result::Result<(), Box<dyn std::error::Error>> {
             )
             .await;
         });
+        startup_tracker
+            .complete_component(
+                COMPONENT_METRICS_START,
+                Some("metrics task spawned".to_string()),
+            )
+            .await;
+    } else {
+        startup_tracker
+            .skip_component(
+                COMPONENT_METRICS_START,
+                Some("server.metrics_port is not configured".to_string()),
+            )
+            .await;
     }
 
-    if config.server.api.enabled {
+    startup_tracker
-        let listen = match config.server.api.listen.parse::<SocketAddr>() {
+        .complete_component(
-            Ok(listen) => listen,
+            COMPONENT_RUNTIME_READY,
-            Err(error) => {
+            Some("startup pipeline is fully initialized".to_string()),
-                warn!(
+        )
-                    error = %error,
+        .await;
-                    listen = %config.server.api.listen,
+    startup_tracker.mark_ready().await;
-                    "Invalid server.api.listen; API is disabled"
-                );
-                SocketAddr::from(([127, 0, 0, 1], 0))
-            }
-        };
-        if listen.port() != 0 {
-            let stats = stats.clone();
-            let ip_tracker_api = ip_tracker.clone();
-            let me_pool_api = me_pool.clone();
-            let upstream_manager_api = upstream_manager.clone();
-            let config_rx_api = config_rx.clone();
-            let admission_rx_api = admission_rx.clone();
-            let config_path_api = std::path::PathBuf::from(&config_path);
-            let startup_detected_ip_v4 = detected_ip_v4;
-            let startup_detected_ip_v6 = detected_ip_v6;
-            tokio::spawn(async move {
-                api::serve(
-                    listen,
-                    stats,
-                    ip_tracker_api,
-                    me_pool_api,
-                    upstream_manager_api,
-                    config_rx_api,
-                    admission_rx_api,
-                    config_path_api,
-                    startup_detected_ip_v4,
-                    startup_detected_ip_v6,
-                    process_started_at_epoch_secs,
-                )
-                .await;
-            });
-        }
-    }
 
     for (listener, listener_proxy_protocol) in listeners {
         let mut config_rx: tokio::sync::watch::Receiver<Arc<ProxyConfig>> = config_rx.clone();

src/metrics.rs

@@ -689,6 +689,135 @@ async fn render_metrics(stats: &Stats, config: &ProxyConfig, ip_tracker: &UserIp
         }
     );
 
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_writer_pick_total ME writer-pick outcomes by mode and result"
+    );
+    let _ = writeln!(out, "# TYPE telemt_me_writer_pick_total counter");
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"sorted_rr\",result=\"success_try\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_sorted_rr_success_try_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"sorted_rr\",result=\"success_fallback\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_sorted_rr_success_fallback_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"sorted_rr\",result=\"full\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_sorted_rr_full_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"sorted_rr\",result=\"closed\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_sorted_rr_closed_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"sorted_rr\",result=\"no_candidate\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_sorted_rr_no_candidate_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"p2c\",result=\"success_try\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_p2c_success_try_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"p2c\",result=\"success_fallback\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_p2c_success_fallback_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"p2c\",result=\"full\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_p2c_full_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"p2c\",result=\"closed\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_p2c_closed_total()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_total{{mode=\"p2c\",result=\"no_candidate\"}} {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_p2c_no_candidate_total()
+        } else {
+            0
+        }
+    );
+
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_writer_pick_blocking_fallback_total ME writer-pick blocking fallback attempts"
+    );
+    let _ = writeln!(
+        out,
+        "# TYPE telemt_me_writer_pick_blocking_fallback_total counter"
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_blocking_fallback_total {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_blocking_fallback_total()
+        } else {
+            0
+        }
+    );
+
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_writer_pick_mode_switch_total Writer-pick mode switches via runtime updates"
+    );
+    let _ = writeln!(out, "# TYPE telemt_me_writer_pick_mode_switch_total counter");
+    let _ = writeln!(
+        out,
+        "telemt_me_writer_pick_mode_switch_total {}",
+        if me_allows_normal {
+            stats.get_me_writer_pick_mode_switch_total()
+        } else {
+            0
+        }
+    );
+
     let _ = writeln!(
         out,
         "# HELP telemt_me_socks_kdf_policy_total SOCKS KDF policy outcomes"
@@ -1053,6 +1182,102 @@ async fn render_metrics(stats: &Stats, config: &ProxyConfig, ip_tracker: &UserIp
             0
         }
     );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_adaptive_floor_active_cap_configured Runtime configured active writer cap"
+    );
+    let _ = writeln!(
+        out,
+        "# TYPE telemt_me_adaptive_floor_active_cap_configured gauge"
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_adaptive_floor_active_cap_configured {}",
+        if me_allows_normal {
+            stats.get_me_floor_active_cap_configured_gauge()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_adaptive_floor_active_cap_effective Runtime effective active writer cap"
+    );
+    let _ = writeln!(
+        out,
+        "# TYPE telemt_me_adaptive_floor_active_cap_effective gauge"
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_adaptive_floor_active_cap_effective {}",
+        if me_allows_normal {
+            stats.get_me_floor_active_cap_effective_gauge()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_adaptive_floor_warm_cap_configured Runtime configured warm writer cap"
+    );
+    let _ = writeln!(
+        out,
+        "# TYPE telemt_me_adaptive_floor_warm_cap_configured gauge"
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_adaptive_floor_warm_cap_configured {}",
+        if me_allows_normal {
+            stats.get_me_floor_warm_cap_configured_gauge()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_adaptive_floor_warm_cap_effective Runtime effective warm writer cap"
+    );
+    let _ = writeln!(
+        out,
+        "# TYPE telemt_me_adaptive_floor_warm_cap_effective gauge"
+    );
+    let _ = writeln!(
+        out,
+        "telemt_me_adaptive_floor_warm_cap_effective {}",
+        if me_allows_normal {
+            stats.get_me_floor_warm_cap_effective_gauge()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_writers_active_current Current non-draining active ME writers"
+    );
+    let _ = writeln!(out, "# TYPE telemt_me_writers_active_current gauge");
+    let _ = writeln!(
+        out,
+        "telemt_me_writers_active_current {}",
+        if me_allows_normal {
+            stats.get_me_writers_active_current_gauge()
+        } else {
+            0
+        }
+    );
+    let _ = writeln!(
+        out,
+        "# HELP telemt_me_writers_warm_current Current non-draining warm ME writers"
+    );
+    let _ = writeln!(out, "# TYPE telemt_me_writers_warm_current gauge");
+    let _ = writeln!(
+        out,
+        "telemt_me_writers_warm_current {}",
+        if me_allows_normal {
+            stats.get_me_writers_warm_current_gauge()
+        } else {
+            0
+        }
+    );
     let _ = writeln!(
         out,
         "# HELP telemt_me_floor_cap_block_total Reconnect attempts blocked by adaptive floor caps"

src/proxy/middle_relay.rs

@@ -6,6 +6,7 @@ use std::sync::atomic::{AtomicU64, Ordering};
 use std::sync::{Arc, Mutex, OnceLock};
 use std::time::{Duration, Instant};
 
+use bytes::Bytes;
 use tokio::io::{AsyncRead, AsyncReadExt, AsyncWrite, AsyncWriteExt};
 use tokio::sync::{mpsc, oneshot};
 use tracing::{debug, trace, warn};
@@ -20,13 +21,13 @@ use crate::stream::{BufferPool, CryptoReader, CryptoWriter};
 use crate::transport::middle_proxy::{MePool, MeResponse, proto_flags_for_tag};
 
 enum C2MeCommand {
-    Data { payload: Vec<u8>, flags: u32 },
+    Data { payload: Bytes, flags: u32 },
     Close,
 }
 
 const DESYNC_DEDUP_WINDOW: Duration = Duration::from_secs(60);
 const DESYNC_ERROR_CLASS: &str = "frame_too_large_crypto_desync";
-const C2ME_CHANNEL_CAPACITY: usize = 1024;
+const C2ME_CHANNEL_CAPACITY_FALLBACK: usize = 128;
 const C2ME_SOFT_PRESSURE_MIN_FREE_SLOTS: usize = 64;
 const C2ME_SENDER_FAIRNESS_BUDGET: usize = 32;
 static DESYNC_DEDUP: OnceLock<Mutex<HashMap<u64, Instant>>> = OnceLock::new();
@@ -270,7 +271,11 @@ where
 
     let frame_limit = config.general.max_client_frame;
 
-    let (c2me_tx, mut c2me_rx) = mpsc::channel::<C2MeCommand>(C2ME_CHANNEL_CAPACITY);
+    let c2me_channel_capacity = config
+        .general
+        .me_c2me_channel_capacity
+        .max(C2ME_CHANNEL_CAPACITY_FALLBACK);
+    let (c2me_tx, mut c2me_rx) = mpsc::channel::<C2MeCommand>(c2me_channel_capacity);
     let me_pool_c2me = me_pool.clone();
     let effective_tag = effective_tag;
     let c2me_sender = tokio::spawn(async move {
@@ -283,7 +288,7 @@ where
                         success.dc_idx,
                         peer,
                         translated_local_addr,
-                        &payload,
+                        payload.as_ref(),
                         flags,
                         effective_tag.as_deref(),
                     ).await?;
@@ -479,7 +484,7 @@ async fn read_client_payload<R>(
     forensics: &RelayForensicsState,
     frame_counter: &mut u64,
     stats: &Stats,
-) -> Result<Option<(Vec<u8>, bool)>>
+) -> Result<Option<(Bytes, bool)>>
 where
     R: AsyncRead + Unpin + Send + 'static,
 {
@@ -578,7 +583,7 @@ where
             payload.truncate(secure_payload_len);
         }
         *frame_counter += 1;
-        return Ok(Some((payload, quickack)));
+        return Ok(Some((Bytes::from(payload), quickack)));
     }
 }
 
@@ -715,7 +720,7 @@ mod tests {
         enqueue_c2me_command(
             &tx,
             C2MeCommand::Data {
-                payload: vec![1, 2, 3],
+                payload: Bytes::from_static(&[1, 2, 3]),
                 flags: 0,
             },
         )
@@ -728,7 +733,7 @@ mod tests {
             .unwrap();
         match recv {
             C2MeCommand::Data { payload, flags } => {
-                assert_eq!(payload, vec![1, 2, 3]);
+                assert_eq!(payload.as_ref(), &[1, 2, 3]);
                 assert_eq!(flags, 0);
             }
             C2MeCommand::Close => panic!("unexpected close command"),
@@ -739,7 +744,7 @@ mod tests {
     async fn enqueue_c2me_command_falls_back_to_send_when_queue_is_full() {
         let (tx, mut rx) = mpsc::channel::<C2MeCommand>(1);
         tx.send(C2MeCommand::Data {
-            payload: vec![9],
+            payload: Bytes::from_static(&[9]),
             flags: 9,
         })
         .await
@@ -750,7 +755,7 @@ mod tests {
             enqueue_c2me_command(
                 &tx2,
                 C2MeCommand::Data {
-                    payload: vec![7, 7],
+                    payload: Bytes::from_static(&[7, 7]),
                     flags: 7,
                 },
             )
@@ -769,7 +774,7 @@ mod tests {
             .unwrap();
         match recv {
             C2MeCommand::Data { payload, flags } => {
-                assert_eq!(payload, vec![7, 7]);
+                assert_eq!(payload.as_ref(), &[7, 7]);
                 assert_eq!(flags, 7);
             }
             C2MeCommand::Close => panic!("unexpected close command"),

src/startup.rs

@@ -0,0 +1,373 @@
+use std::time::{Instant, SystemTime, UNIX_EPOCH};
+
+use tokio::sync::RwLock;
+
+pub const COMPONENT_CONFIG_LOAD: &str = "config_load";
+pub const COMPONENT_TRACING_INIT: &str = "tracing_init";
+pub const COMPONENT_API_BOOTSTRAP: &str = "api_bootstrap";
+pub const COMPONENT_TLS_FRONT_BOOTSTRAP: &str = "tls_front_bootstrap";
+pub const COMPONENT_NETWORK_PROBE: &str = "network_probe";
+pub const COMPONENT_ME_SECRET_FETCH: &str = "me_secret_fetch";
+pub const COMPONENT_ME_PROXY_CONFIG_V4: &str = "me_proxy_config_fetch_v4";
+pub const COMPONENT_ME_PROXY_CONFIG_V6: &str = "me_proxy_config_fetch_v6";
+pub const COMPONENT_ME_POOL_CONSTRUCT: &str = "me_pool_construct";
+pub const COMPONENT_ME_POOL_INIT_STAGE1: &str = "me_pool_init_stage1";
+pub const COMPONENT_ME_CONNECTIVITY_PING: &str = "me_connectivity_ping";
+pub const COMPONENT_DC_CONNECTIVITY_PING: &str = "dc_connectivity_ping";
+pub const COMPONENT_LISTENERS_BIND: &str = "listeners_bind";
+pub const COMPONENT_CONFIG_WATCHER_START: &str = "config_watcher_start";
+pub const COMPONENT_METRICS_START: &str = "metrics_start";
+pub const COMPONENT_RUNTIME_READY: &str = "runtime_ready";
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum StartupStatus {
+    Initializing,
+    Ready,
+}
+
+impl StartupStatus {
+    pub fn as_str(self) -> &'static str {
+        match self {
+            Self::Initializing => "initializing",
+            Self::Ready => "ready",
+        }
+    }
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum StartupComponentStatus {
+    Pending,
+    Running,
+    Ready,
+    Failed,
+    Skipped,
+}
+
+impl StartupComponentStatus {
+    pub fn as_str(self) -> &'static str {
+        match self {
+            Self::Pending => "pending",
+            Self::Running => "running",
+            Self::Ready => "ready",
+            Self::Failed => "failed",
+            Self::Skipped => "skipped",
+        }
+    }
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum StartupMeStatus {
+    Pending,
+    Initializing,
+    Ready,
+    Failed,
+    Skipped,
+}
+
+impl StartupMeStatus {
+    pub fn as_str(self) -> &'static str {
+        match self {
+            Self::Pending => "pending",
+            Self::Initializing => "initializing",
+            Self::Ready => "ready",
+            Self::Failed => "failed",
+            Self::Skipped => "skipped",
+        }
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct StartupComponentSnapshot {
+    pub id: &'static str,
+    pub title: &'static str,
+    pub weight: f64,
+    pub status: StartupComponentStatus,
+    pub started_at_epoch_ms: Option<u64>,
+    pub finished_at_epoch_ms: Option<u64>,
+    pub duration_ms: Option<u64>,
+    pub attempts: u32,
+    pub details: Option<String>,
+}
+
+#[derive(Clone, Debug)]
+pub struct StartupMeSnapshot {
+    pub status: StartupMeStatus,
+    pub current_stage: String,
+    pub init_attempt: u32,
+    pub retry_limit: String,
+    pub last_error: Option<String>,
+}
+
+#[derive(Clone, Debug)]
+pub struct StartupSnapshot {
+    pub status: StartupStatus,
+    pub degraded: bool,
+    pub current_stage: String,
+    pub started_at_epoch_secs: u64,
+    pub ready_at_epoch_secs: Option<u64>,
+    pub total_elapsed_ms: u64,
+    pub transport_mode: String,
+    pub me: StartupMeSnapshot,
+    pub components: Vec<StartupComponentSnapshot>,
+}
+
+#[derive(Clone, Debug)]
+struct StartupComponent {
+    id: &'static str,
+    title: &'static str,
+    weight: f64,
+    status: StartupComponentStatus,
+    started_at_epoch_ms: Option<u64>,
+    finished_at_epoch_ms: Option<u64>,
+    duration_ms: Option<u64>,
+    attempts: u32,
+    details: Option<String>,
+}
+
+#[derive(Clone, Debug)]
+struct StartupState {
+    status: StartupStatus,
+    degraded: bool,
+    current_stage: String,
+    started_at_epoch_secs: u64,
+    ready_at_epoch_secs: Option<u64>,
+    transport_mode: String,
+    me: StartupMeSnapshot,
+    components: Vec<StartupComponent>,
+}
+
+pub struct StartupTracker {
+    started_at_instant: Instant,
+    state: RwLock<StartupState>,
+}
+
+impl StartupTracker {
+    pub fn new(started_at_epoch_secs: u64) -> Self {
+        Self {
+            started_at_instant: Instant::now(),
+            state: RwLock::new(StartupState {
+                status: StartupStatus::Initializing,
+                degraded: false,
+                current_stage: COMPONENT_CONFIG_LOAD.to_string(),
+                started_at_epoch_secs,
+                ready_at_epoch_secs: None,
+                transport_mode: "unknown".to_string(),
+                me: StartupMeSnapshot {
+                    status: StartupMeStatus::Pending,
+                    current_stage: "pending".to_string(),
+                    init_attempt: 0,
+                    retry_limit: "unlimited".to_string(),
+                    last_error: None,
+                },
+                components: component_blueprint(),
+            }),
+        }
+    }
+
+    pub async fn set_transport_mode(&self, mode: &'static str) {
+        self.state.write().await.transport_mode = mode.to_string();
+    }
+
+    pub async fn set_degraded(&self, degraded: bool) {
+        self.state.write().await.degraded = degraded;
+    }
+
+    pub async fn start_component(&self, id: &'static str, details: Option<String>) {
+        let mut guard = self.state.write().await;
+        guard.current_stage = id.to_string();
+        if let Some(component) = guard.components.iter_mut().find(|component| component.id == id) {
+            if component.started_at_epoch_ms.is_none() {
+                component.started_at_epoch_ms = Some(now_epoch_ms());
+            }
+            component.attempts = component.attempts.saturating_add(1);
+            component.status = StartupComponentStatus::Running;
+            component.details = normalize_details(details);
+        }
+    }
+
+    pub async fn complete_component(&self, id: &'static str, details: Option<String>) {
+        self.finish_component(id, StartupComponentStatus::Ready, details)
+            .await;
+    }
+
+    pub async fn fail_component(&self, id: &'static str, details: Option<String>) {
+        self.finish_component(id, StartupComponentStatus::Failed, details)
+            .await;
+    }
+
+    pub async fn skip_component(&self, id: &'static str, details: Option<String>) {
+        self.finish_component(id, StartupComponentStatus::Skipped, details)
+            .await;
+    }
+
+    async fn finish_component(
+        &self,
+        id: &'static str,
+        status: StartupComponentStatus,
+        details: Option<String>,
+    ) {
+        let mut guard = self.state.write().await;
+        let finished_at = now_epoch_ms();
+        if let Some(component) = guard.components.iter_mut().find(|component| component.id == id) {
+            if component.started_at_epoch_ms.is_none() {
+                component.started_at_epoch_ms = Some(finished_at);
+                component.attempts = component.attempts.saturating_add(1);
+            }
+            component.finished_at_epoch_ms = Some(finished_at);
+            component.duration_ms = component
+                .started_at_epoch_ms
+                .map(|started_at| finished_at.saturating_sub(started_at));
+            component.status = status;
+            component.details = normalize_details(details);
+        }
+    }
+
+    pub async fn set_me_status(&self, status: StartupMeStatus, stage: &'static str) {
+        let mut guard = self.state.write().await;
+        guard.me.status = status;
+        guard.me.current_stage = stage.to_string();
+    }
+
+    pub async fn set_me_retry_limit(&self, retry_limit: String) {
+        self.state.write().await.me.retry_limit = retry_limit;
+    }
+
+    pub async fn set_me_init_attempt(&self, attempt: u32) {
+        self.state.write().await.me.init_attempt = attempt;
+    }
+
+    pub async fn set_me_last_error(&self, error: Option<String>) {
+        self.state.write().await.me.last_error = normalize_details(error);
+    }
+
+    pub async fn mark_ready(&self) {
+        let mut guard = self.state.write().await;
+        if guard.status == StartupStatus::Ready {
+            return;
+        }
+        guard.status = StartupStatus::Ready;
+        guard.current_stage = "ready".to_string();
+        guard.ready_at_epoch_secs = Some(now_epoch_secs());
+    }
+
+    pub async fn snapshot(&self) -> StartupSnapshot {
+        let guard = self.state.read().await;
+        StartupSnapshot {
+            status: guard.status,
+            degraded: guard.degraded,
+            current_stage: guard.current_stage.clone(),
+            started_at_epoch_secs: guard.started_at_epoch_secs,
+            ready_at_epoch_secs: guard.ready_at_epoch_secs,
+            total_elapsed_ms: self.started_at_instant.elapsed().as_millis() as u64,
+            transport_mode: guard.transport_mode.clone(),
+            me: guard.me.clone(),
+            components: guard
+                .components
+                .iter()
+                .map(|component| StartupComponentSnapshot {
+                    id: component.id,
+                    title: component.title,
+                    weight: component.weight,
+                    status: component.status,
+                    started_at_epoch_ms: component.started_at_epoch_ms,
+                    finished_at_epoch_ms: component.finished_at_epoch_ms,
+                    duration_ms: component.duration_ms,
+                    attempts: component.attempts,
+                    details: component.details.clone(),
+                })
+                .collect(),
+        }
+    }
+}
+
+pub fn compute_progress_pct(snapshot: &StartupSnapshot, me_stage_progress: Option<f64>) -> f64 {
+    if snapshot.status == StartupStatus::Ready {
+        return 100.0;
+    }
+
+    let mut total_weight = 0.0f64;
+    let mut completed_weight = 0.0f64;
+
+    for component in &snapshot.components {
+        total_weight += component.weight;
+        let unit_progress = match component.status {
+            StartupComponentStatus::Pending => 0.0,
+            StartupComponentStatus::Running => {
+                if component.id == COMPONENT_ME_POOL_INIT_STAGE1 {
+                    me_stage_progress.unwrap_or(0.0).clamp(0.0, 1.0)
+                } else {
+                    0.0
+                }
+            }
+            StartupComponentStatus::Ready
+            | StartupComponentStatus::Failed
+            | StartupComponentStatus::Skipped => 1.0,
+        };
+        completed_weight += component.weight * unit_progress;
+    }
+
+    if total_weight <= f64::EPSILON {
+        0.0
+    } else {
+        ((completed_weight / total_weight) * 100.0).clamp(0.0, 100.0)
+    }
+}
+
+fn component_blueprint() -> Vec<StartupComponent> {
+    vec![
+        component(COMPONENT_CONFIG_LOAD, "Config load", 5.0),
+        component(COMPONENT_TRACING_INIT, "Tracing init", 3.0),
+        component(COMPONENT_API_BOOTSTRAP, "API bootstrap", 5.0),
+        component(COMPONENT_TLS_FRONT_BOOTSTRAP, "TLS front bootstrap", 5.0),
+        component(COMPONENT_NETWORK_PROBE, "Network probe", 10.0),
+        component(COMPONENT_ME_SECRET_FETCH, "ME secret fetch", 8.0),
+        component(COMPONENT_ME_PROXY_CONFIG_V4, "ME config v4 fetch", 4.0),
+        component(COMPONENT_ME_PROXY_CONFIG_V6, "ME config v6 fetch", 4.0),
+        component(COMPONENT_ME_POOL_CONSTRUCT, "ME pool construct", 6.0),
+        component(COMPONENT_ME_POOL_INIT_STAGE1, "ME pool init stage1", 24.0),
+        component(COMPONENT_ME_CONNECTIVITY_PING, "ME connectivity ping", 6.0),
+        component(COMPONENT_DC_CONNECTIVITY_PING, "DC connectivity ping", 8.0),
+        component(COMPONENT_LISTENERS_BIND, "Listener bind", 8.0),
+        component(COMPONENT_CONFIG_WATCHER_START, "Config watcher start", 2.0),
+        component(COMPONENT_METRICS_START, "Metrics start", 1.0),
+        component(COMPONENT_RUNTIME_READY, "Runtime ready", 1.0),
+    ]
+}
+
+fn component(id: &'static str, title: &'static str, weight: f64) -> StartupComponent {
+    StartupComponent {
+        id,
+        title,
+        weight,
+        status: StartupComponentStatus::Pending,
+        started_at_epoch_ms: None,
+        finished_at_epoch_ms: None,
+        duration_ms: None,
+        attempts: 0,
+        details: None,
+    }
+}
+
+fn normalize_details(details: Option<String>) -> Option<String> {
+    details.map(|detail| {
+        if detail.len() <= 256 {
+            detail
+        } else {
+            detail[..256].to_string()
+        }
+    })
+}
+
+fn now_epoch_secs() -> u64 {
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_secs()
+}
+
+fn now_epoch_ms() -> u64 {
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_millis() as u64
+}

src/stats/mod.rs

@@ -6,7 +6,7 @@ pub mod beobachten;
 pub mod telemetry;
 
 use std::sync::atomic::{AtomicBool, AtomicU8, AtomicU64, Ordering};
-use std::time::{Instant, Duration};
+use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
 use dashmap::DashMap;
 use parking_lot::Mutex;
 use lru::LruCache;
@@ -16,7 +16,7 @@ use std::collections::hash_map::DefaultHasher;
 use std::collections::VecDeque;
 use tracing::debug;
 
-use crate::config::MeTelemetryLevel;
+use crate::config::{MeTelemetryLevel, MeWriterPickMode};
 use self::telemetry::TelemetryPolicy;
 
 // ============= Stats =============
@@ -80,6 +80,12 @@ pub struct Stats {
     me_floor_global_cap_raw_gauge: AtomicU64,
     me_floor_global_cap_effective_gauge: AtomicU64,
     me_floor_target_writers_total_gauge: AtomicU64,
+    me_floor_active_cap_configured_gauge: AtomicU64,
+    me_floor_active_cap_effective_gauge: AtomicU64,
+    me_floor_warm_cap_configured_gauge: AtomicU64,
+    me_floor_warm_cap_effective_gauge: AtomicU64,
+    me_writers_active_current_gauge: AtomicU64,
+    me_writers_warm_current_gauge: AtomicU64,
     me_floor_cap_block_total: AtomicU64,
     me_floor_swap_idle_total: AtomicU64,
     me_floor_swap_idle_failed_total: AtomicU64,
@@ -89,6 +95,18 @@ pub struct Stats {
     me_route_drop_queue_full: AtomicU64,
     me_route_drop_queue_full_base: AtomicU64,
     me_route_drop_queue_full_high: AtomicU64,
+    me_writer_pick_sorted_rr_success_try_total: AtomicU64,
+    me_writer_pick_sorted_rr_success_fallback_total: AtomicU64,
+    me_writer_pick_sorted_rr_full_total: AtomicU64,
+    me_writer_pick_sorted_rr_closed_total: AtomicU64,
+    me_writer_pick_sorted_rr_no_candidate_total: AtomicU64,
+    me_writer_pick_p2c_success_try_total: AtomicU64,
+    me_writer_pick_p2c_success_fallback_total: AtomicU64,
+    me_writer_pick_p2c_full_total: AtomicU64,
+    me_writer_pick_p2c_closed_total: AtomicU64,
+    me_writer_pick_p2c_no_candidate_total: AtomicU64,
+    me_writer_pick_blocking_fallback_total: AtomicU64,
+    me_writer_pick_mode_switch_total: AtomicU64,
     me_socks_kdf_strict_reject: AtomicU64,
     me_socks_kdf_compat_fallback: AtomicU64,
     secure_padding_invalid: AtomicU64,
@@ -119,6 +137,7 @@ pub struct Stats {
     telemetry_user_enabled: AtomicBool,
     telemetry_me_level: AtomicU8,
     user_stats: DashMap<String, UserStats>,
+    user_stats_last_cleanup_epoch_secs: AtomicU64,
     start_time: parking_lot::RwLock<Option<Instant>>,
 }
 
@@ -130,6 +149,7 @@ pub struct UserStats {
     pub octets_to_client: AtomicU64,
     pub msgs_from_client: AtomicU64,
     pub msgs_to_client: AtomicU64,
+    pub last_seen_epoch_secs: AtomicU64,
 }
 
 impl Stats {
@@ -178,6 +198,54 @@ impl Stats {
         }
     }
 
+    fn now_epoch_secs() -> u64 {
+        SystemTime::now()
+            .duration_since(UNIX_EPOCH)
+            .unwrap_or_default()
+            .as_secs()
+    }
+
+    fn touch_user_stats(stats: &UserStats) {
+        stats
+            .last_seen_epoch_secs
+            .store(Self::now_epoch_secs(), Ordering::Relaxed);
+    }
+
+    fn maybe_cleanup_user_stats(&self) {
+        const USER_STATS_CLEANUP_INTERVAL_SECS: u64 = 60;
+        const USER_STATS_IDLE_TTL_SECS: u64 = 24 * 60 * 60;
+
+        let now_epoch_secs = Self::now_epoch_secs();
+        let last_cleanup_epoch_secs = self
+            .user_stats_last_cleanup_epoch_secs
+            .load(Ordering::Relaxed);
+        if now_epoch_secs.saturating_sub(last_cleanup_epoch_secs)
+            < USER_STATS_CLEANUP_INTERVAL_SECS
+        {
+            return;
+        }
+        if self
+            .user_stats_last_cleanup_epoch_secs
+            .compare_exchange(
+                last_cleanup_epoch_secs,
+                now_epoch_secs,
+                Ordering::AcqRel,
+                Ordering::Relaxed,
+            )
+            .is_err()
+        {
+            return;
+        }
+
+        self.user_stats.retain(|_, stats| {
+            if stats.curr_connects.load(Ordering::Relaxed) > 0 {
+                return true;
+            }
+            let last_seen_epoch_secs = stats.last_seen_epoch_secs.load(Ordering::Relaxed);
+            now_epoch_secs.saturating_sub(last_seen_epoch_secs) <= USER_STATS_IDLE_TTL_SECS
+        });
+    }
+
     pub fn apply_telemetry_policy(&self, policy: TelemetryPolicy) {
         self.telemetry_core_enabled
             .store(policy.core_enabled, Ordering::Relaxed);
@@ -441,6 +509,93 @@ impl Stats {
             self.me_route_drop_queue_full_high.fetch_add(1, Ordering::Relaxed);
         }
     }
+    pub fn increment_me_writer_pick_success_try_total(&self, mode: MeWriterPickMode) {
+        if !self.telemetry_me_allows_normal() {
+            return;
+        }
+        match mode {
+            MeWriterPickMode::SortedRr => {
+                self.me_writer_pick_sorted_rr_success_try_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+            MeWriterPickMode::P2c => {
+                self.me_writer_pick_p2c_success_try_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+        }
+    }
+    pub fn increment_me_writer_pick_success_fallback_total(&self, mode: MeWriterPickMode) {
+        if !self.telemetry_me_allows_normal() {
+            return;
+        }
+        match mode {
+            MeWriterPickMode::SortedRr => {
+                self.me_writer_pick_sorted_rr_success_fallback_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+            MeWriterPickMode::P2c => {
+                self.me_writer_pick_p2c_success_fallback_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+        }
+    }
+    pub fn increment_me_writer_pick_full_total(&self, mode: MeWriterPickMode) {
+        if !self.telemetry_me_allows_normal() {
+            return;
+        }
+        match mode {
+            MeWriterPickMode::SortedRr => {
+                self.me_writer_pick_sorted_rr_full_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+            MeWriterPickMode::P2c => {
+                self.me_writer_pick_p2c_full_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+        }
+    }
+    pub fn increment_me_writer_pick_closed_total(&self, mode: MeWriterPickMode) {
+        if !self.telemetry_me_allows_normal() {
+            return;
+        }
+        match mode {
+            MeWriterPickMode::SortedRr => {
+                self.me_writer_pick_sorted_rr_closed_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+            MeWriterPickMode::P2c => {
+                self.me_writer_pick_p2c_closed_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+        }
+    }
+    pub fn increment_me_writer_pick_no_candidate_total(&self, mode: MeWriterPickMode) {
+        if !self.telemetry_me_allows_normal() {
+            return;
+        }
+        match mode {
+            MeWriterPickMode::SortedRr => {
+                self.me_writer_pick_sorted_rr_no_candidate_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+            MeWriterPickMode::P2c => {
+                self.me_writer_pick_p2c_no_candidate_total
+                    .fetch_add(1, Ordering::Relaxed);
+            }
+        }
+    }
+    pub fn increment_me_writer_pick_blocking_fallback_total(&self) {
+        if self.telemetry_me_allows_normal() {
+            self.me_writer_pick_blocking_fallback_total
+                .fetch_add(1, Ordering::Relaxed);
+        }
+    }
+    pub fn increment_me_writer_pick_mode_switch_total(&self) {
+        if self.telemetry_me_allows_normal() {
+            self.me_writer_pick_mode_switch_total
+                .fetch_add(1, Ordering::Relaxed);
+        }
+    }
     pub fn increment_me_socks_kdf_strict_reject(&self) {
         if self.telemetry_me_allows_normal() {
             self.me_socks_kdf_strict_reject.fetch_add(1, Ordering::Relaxed);
@@ -714,6 +869,42 @@ impl Stats {
                 .store(value, Ordering::Relaxed);
         }
     }
+    pub fn set_me_floor_active_cap_configured_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_floor_active_cap_configured_gauge
+                .store(value, Ordering::Relaxed);
+        }
+    }
+    pub fn set_me_floor_active_cap_effective_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_floor_active_cap_effective_gauge
+                .store(value, Ordering::Relaxed);
+        }
+    }
+    pub fn set_me_floor_warm_cap_configured_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_floor_warm_cap_configured_gauge
+                .store(value, Ordering::Relaxed);
+        }
+    }
+    pub fn set_me_floor_warm_cap_effective_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_floor_warm_cap_effective_gauge
+                .store(value, Ordering::Relaxed);
+        }
+    }
+    pub fn set_me_writers_active_current_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_writers_active_current_gauge
+                .store(value, Ordering::Relaxed);
+        }
+    }
+    pub fn set_me_writers_warm_current_gauge(&self, value: u64) {
+        if self.telemetry_me_allows_normal() {
+            self.me_writers_warm_current_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);
@@ -854,6 +1045,30 @@ impl Stats {
         self.me_floor_target_writers_total_gauge
             .load(Ordering::Relaxed)
     }
+    pub fn get_me_floor_active_cap_configured_gauge(&self) -> u64 {
+        self.me_floor_active_cap_configured_gauge
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_floor_active_cap_effective_gauge(&self) -> u64 {
+        self.me_floor_active_cap_effective_gauge
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_floor_warm_cap_configured_gauge(&self) -> u64 {
+        self.me_floor_warm_cap_configured_gauge
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_floor_warm_cap_effective_gauge(&self) -> u64 {
+        self.me_floor_warm_cap_effective_gauge
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writers_active_current_gauge(&self) -> u64 {
+        self.me_writers_active_current_gauge
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writers_warm_current_gauge(&self) -> u64 {
+        self.me_writers_warm_current_gauge
+            .load(Ordering::Relaxed)
+    }
     pub fn get_me_floor_cap_block_total(&self) -> u64 {
         self.me_floor_cap_block_total.load(Ordering::Relaxed)
     }
@@ -885,6 +1100,52 @@ impl Stats {
     pub fn get_me_route_drop_queue_full_high(&self) -> u64 {
         self.me_route_drop_queue_full_high.load(Ordering::Relaxed)
     }
+    pub fn get_me_writer_pick_sorted_rr_success_try_total(&self) -> u64 {
+        self.me_writer_pick_sorted_rr_success_try_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_sorted_rr_success_fallback_total(&self) -> u64 {
+        self.me_writer_pick_sorted_rr_success_fallback_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_sorted_rr_full_total(&self) -> u64 {
+        self.me_writer_pick_sorted_rr_full_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_sorted_rr_closed_total(&self) -> u64 {
+        self.me_writer_pick_sorted_rr_closed_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_sorted_rr_no_candidate_total(&self) -> u64 {
+        self.me_writer_pick_sorted_rr_no_candidate_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_p2c_success_try_total(&self) -> u64 {
+        self.me_writer_pick_p2c_success_try_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_p2c_success_fallback_total(&self) -> u64 {
+        self.me_writer_pick_p2c_success_fallback_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_p2c_full_total(&self) -> u64 {
+        self.me_writer_pick_p2c_full_total.load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_p2c_closed_total(&self) -> u64 {
+        self.me_writer_pick_p2c_closed_total.load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_p2c_no_candidate_total(&self) -> u64 {
+        self.me_writer_pick_p2c_no_candidate_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_blocking_fallback_total(&self) -> u64 {
+        self.me_writer_pick_blocking_fallback_total
+            .load(Ordering::Relaxed)
+    }
+    pub fn get_me_writer_pick_mode_switch_total(&self) -> u64 {
+        self.me_writer_pick_mode_switch_total
+            .load(Ordering::Relaxed)
+    }
     pub fn get_me_socks_kdf_strict_reject(&self) -> u64 {
         self.me_socks_kdf_strict_reject.load(Ordering::Relaxed)
     }
@@ -970,34 +1231,36 @@ impl Stats {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.connects.fetch_add(1, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.connects.fetch_add(1, Ordering::Relaxed);
-            .connects
-            .fetch_add(1, Ordering::Relaxed);
     }
     
     pub fn increment_user_curr_connects(&self, user: &str) {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.curr_connects.fetch_add(1, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.curr_connects.fetch_add(1, Ordering::Relaxed);
-            .curr_connects
-            .fetch_add(1, Ordering::Relaxed);
     }
     
     pub fn decrement_user_curr_connects(&self, user: &str) {
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             let counter = &stats.curr_connects;
             let mut current = counter.load(Ordering::Relaxed);
             loop {
@@ -1027,60 +1290,60 @@ impl Stats {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.octets_from_client.fetch_add(bytes, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.octets_from_client.fetch_add(bytes, Ordering::Relaxed);
-            .octets_from_client
-            .fetch_add(bytes, Ordering::Relaxed);
     }
     
     pub fn add_user_octets_to(&self, user: &str, bytes: u64) {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.octets_to_client.fetch_add(bytes, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.octets_to_client.fetch_add(bytes, Ordering::Relaxed);
-            .octets_to_client
-            .fetch_add(bytes, Ordering::Relaxed);
     }
     
     pub fn increment_user_msgs_from(&self, user: &str) {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.msgs_from_client.fetch_add(1, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.msgs_from_client.fetch_add(1, Ordering::Relaxed);
-            .msgs_from_client
-            .fetch_add(1, Ordering::Relaxed);
     }
     
     pub fn increment_user_msgs_to(&self, user: &str) {
         if !self.telemetry_user_enabled() {
             return;
         }
+        self.maybe_cleanup_user_stats();
         if let Some(stats) = self.user_stats.get(user) {
+            Self::touch_user_stats(stats.value());
             stats.msgs_to_client.fetch_add(1, Ordering::Relaxed);
             return;
         }
-        self.user_stats
+        let stats = self.user_stats.entry(user.to_string()).or_default();
-            .entry(user.to_string())
+        Self::touch_user_stats(stats.value());
-            .or_default()
+        stats.msgs_to_client.fetch_add(1, Ordering::Relaxed);
-            .msgs_to_client
-            .fetch_add(1, Ordering::Relaxed);
     }
     
     pub fn get_user_total_octets(&self, user: &str) -> u64 {

src/transport/middle_proxy/codec.rs

@@ -1,4 +1,5 @@
 use tokio::io::{AsyncReadExt, AsyncWriteExt};
+use bytes::Bytes;
 
 use crate::crypto::{AesCbc, crc32, crc32c};
 use crate::error::{ProxyError, Result};
@@ -6,8 +7,8 @@ use crate::protocol::constants::*;
 
 /// Commands sent to dedicated writer tasks to avoid mutex contention on TCP writes.
 pub(crate) enum WriterCommand {
-    Data(Vec<u8>),
+    Data(Bytes),
-    DataAndFlush(Vec<u8>),
+    DataAndFlush(Bytes),
     Close,
 }
 

src/transport/middle_proxy/config_updater.rs

@@ -306,6 +306,8 @@ async fn run_update_cycle(
         cfg.general.me_bind_stale_ttl_secs,
         cfg.general.me_secret_atomic_snapshot,
         cfg.general.me_deterministic_writer_sort,
+        cfg.general.me_writer_pick_mode,
+        cfg.general.me_writer_pick_sample_size,
         cfg.general.me_single_endpoint_shadow_writers,
         cfg.general.me_single_endpoint_outage_mode_enabled,
         cfg.general.me_single_endpoint_outage_disable_quarantine,
@@ -321,6 +323,13 @@ async fn run_update_cycle(
         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,
+        cfg.general.me_adaptive_floor_max_active_writers_per_core,
+        cfg.general.me_adaptive_floor_max_warm_writers_per_core,
+        cfg.general.me_adaptive_floor_max_active_writers_global,
+        cfg.general.me_adaptive_floor_max_warm_writers_global,
+        cfg.general.me_health_interval_ms_unhealthy,
+        cfg.general.me_health_interval_ms_healthy,
+        cfg.general.me_warn_rate_limit_ms,
     );
 
     let required_cfg_snapshots = cfg.general.me_config_stable_snapshots.max(1);
@@ -523,6 +532,8 @@ pub async fn me_config_updater(
                     cfg.general.me_bind_stale_ttl_secs,
                     cfg.general.me_secret_atomic_snapshot,
                     cfg.general.me_deterministic_writer_sort,
+                    cfg.general.me_writer_pick_mode,
+                    cfg.general.me_writer_pick_sample_size,
                     cfg.general.me_single_endpoint_shadow_writers,
                     cfg.general.me_single_endpoint_outage_mode_enabled,
                     cfg.general.me_single_endpoint_outage_disable_quarantine,
@@ -538,6 +549,13 @@ pub async fn me_config_updater(
                     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,
+                    cfg.general.me_adaptive_floor_max_active_writers_per_core,
+                    cfg.general.me_adaptive_floor_max_warm_writers_per_core,
+                    cfg.general.me_adaptive_floor_max_active_writers_global,
+                    cfg.general.me_adaptive_floor_max_warm_writers_global,
+                    cfg.general.me_health_interval_ms_unhealthy,
+                    cfg.general.me_health_interval_ms_healthy,
+                    cfg.general.me_warn_rate_limit_ms,
                 );
                 let new_secs = cfg.general.effective_update_every_secs().max(1);
                 if new_secs == update_every_secs {

src/transport/middle_proxy/handshake.rs

@@ -135,10 +135,15 @@ impl MePool {
     pub(crate) async fn connect_tcp(
         &self,
         addr: SocketAddr,
+        dc_idx_override: Option<i16>,
     ) -> Result<(TcpStream, f64, Option<UpstreamEgressInfo>)> {
         let start = Instant::now();
         let (stream, upstream_egress) = if let Some(upstream) = &self.upstream {
-            let dc_idx = self.resolve_dc_idx_for_endpoint(addr).await;
+            let dc_idx = if let Some(dc_idx) = dc_idx_override {
+                Some(dc_idx)
+            } else {
+                self.resolve_dc_idx_for_endpoint(addr).await
+            };
             let (stream, egress) = upstream.connect_with_details(addr, dc_idx, None).await?;
             (stream, Some(egress))
         } else {

src/transport/middle_proxy/health.rs

@@ -13,7 +13,6 @@ use crate::network::IpFamily;
 
 use super::MePool;
 
-const HEALTH_INTERVAL_SECS: u64 = 1;
 const JITTER_FRAC_NUM: u64 = 2; // jitter up to 50% of backoff
 #[allow(dead_code)]
 const MAX_CONCURRENT_PER_DC_DEFAULT: usize = 1;
@@ -42,7 +41,12 @@ struct DcFloorPlanEntry {
 #[derive(Debug, Clone)]
 struct FamilyFloorPlan {
     by_dc: HashMap<i32, DcFloorPlanEntry>,
-    global_cap_effective_total: usize,
+    active_cap_configured_total: usize,
+    active_cap_effective_total: usize,
+    warm_cap_configured_total: usize,
+    warm_cap_effective_total: usize,
+    active_writers_current: usize,
+    warm_writers_current: usize,
     target_writers_total: usize,
 }
 
@@ -57,10 +61,18 @@ pub async fn me_health_monitor(pool: Arc<MePool>, rng: Arc<SecureRandom>, _min_c
     let mut idle_refresh_next_attempt: HashMap<(i32, IpFamily), Instant> = HashMap::new();
     let mut adaptive_idle_since: HashMap<(i32, IpFamily), Instant> = HashMap::new();
     let mut adaptive_recover_until: HashMap<(i32, IpFamily), Instant> = HashMap::new();
+    let mut floor_warn_next_allowed: HashMap<(i32, IpFamily), Instant> = HashMap::new();
+    let mut degraded_interval = true;
     loop {
-        tokio::time::sleep(Duration::from_secs(HEALTH_INTERVAL_SECS)).await;
+        let interval = if degraded_interval {
+            pool.health_interval_unhealthy()
+        } else {
+            pool.health_interval_healthy()
+        };
+        tokio::time::sleep(interval).await;
         pool.prune_closed_writers().await;
-        check_family(
+        reap_draining_writers(&pool).await;
+        let v4_degraded = check_family(
             IpFamily::V4,
             &pool,
             &rng,
@@ -74,9 +86,10 @@ pub async fn me_health_monitor(pool: Arc<MePool>, rng: Arc<SecureRandom>, _min_c
             &mut idle_refresh_next_attempt,
             &mut adaptive_idle_since,
             &mut adaptive_recover_until,
+            &mut floor_warn_next_allowed,
         )
         .await;
-        check_family(
+        let v6_degraded = check_family(
             IpFamily::V6,
             &pool,
             &rng,
@@ -90,8 +103,32 @@ pub async fn me_health_monitor(pool: Arc<MePool>, rng: Arc<SecureRandom>, _min_c
             &mut idle_refresh_next_attempt,
             &mut adaptive_idle_since,
             &mut adaptive_recover_until,
+            &mut floor_warn_next_allowed,
         )
         .await;
+        degraded_interval = v4_degraded || v6_degraded;
+    }
+}
+
+async fn reap_draining_writers(pool: &Arc<MePool>) {
+    let now_epoch_secs = MePool::now_epoch_secs();
+    let writers = pool.writers.read().await.clone();
+    for writer in writers {
+        if !writer.draining.load(std::sync::atomic::Ordering::Relaxed) {
+            continue;
+        }
+        if pool.registry.is_writer_empty(writer.id).await {
+            pool.remove_writer_and_close_clients(writer.id).await;
+            continue;
+        }
+        let deadline_epoch_secs = writer
+            .drain_deadline_epoch_secs
+            .load(std::sync::atomic::Ordering::Relaxed);
+        if deadline_epoch_secs != 0 && now_epoch_secs >= deadline_epoch_secs {
+            warn!(writer_id = writer.id, "Drain timeout, force-closing");
+            pool.stats.increment_pool_force_close_total();
+            pool.remove_writer_and_close_clients(writer.id).await;
+        }
     }
 }
 
@@ -109,22 +146,25 @@ async fn check_family(
     idle_refresh_next_attempt: &mut HashMap<(i32, IpFamily), Instant>,
     adaptive_idle_since: &mut HashMap<(i32, IpFamily), Instant>,
     adaptive_recover_until: &mut HashMap<(i32, IpFamily), Instant>,
-) {
+    floor_warn_next_allowed: &mut HashMap<(i32, IpFamily), Instant>,
+) -> bool {
     let enabled = match family {
         IpFamily::V4 => pool.decision.ipv4_me,
         IpFamily::V6 => pool.decision.ipv6_me,
     };
     if !enabled {
-        return;
+        return false;
     }
 
+    let mut family_degraded = false;
+
     let mut dc_endpoints = HashMap::<i32, Vec<SocketAddr>>::new();
     let map_guard = match family {
         IpFamily::V4 => pool.proxy_map_v4.read().await,
         IpFamily::V6 => pool.proxy_map_v6.read().await,
     };
     for (dc, addrs) in map_guard.iter() {
-        let entry = dc_endpoints.entry(dc.abs()).or_default();
+        let entry = dc_endpoints.entry(*dc).or_default();
         for (ip, port) in addrs.iter().copied() {
             entry.push(SocketAddr::new(ip, port));
         }
@@ -141,31 +181,51 @@ async fn check_family(
         adaptive_recover_until.clear();
     }
 
-    let mut live_addr_counts = HashMap::<SocketAddr, usize>::new();
+    let mut live_addr_counts = HashMap::<(i32, SocketAddr), usize>::new();
-    let mut live_writer_ids_by_addr = HashMap::<SocketAddr, Vec<u64>>::new();
+    let mut live_writer_ids_by_addr = HashMap::<(i32, SocketAddr), Vec<u64>>::new();
     for writer in pool.writers.read().await.iter().filter(|w| {
         !w.draining.load(std::sync::atomic::Ordering::Relaxed)
     }) {
-        *live_addr_counts.entry(writer.addr).or_insert(0) += 1;
+        if !matches!(
+            super::pool::WriterContour::from_u8(
+                writer.contour.load(std::sync::atomic::Ordering::Relaxed),
+            ),
+            super::pool::WriterContour::Active
+        ) {
+            continue;
+        }
+        let key = (writer.writer_dc, writer.addr);
+        *live_addr_counts.entry(key).or_insert(0) += 1;
         live_writer_ids_by_addr
-            .entry(writer.addr)
+            .entry(key)
             .or_default()
             .push(writer.id);
     }
     let writer_idle_since = pool.registry.writer_idle_since_snapshot().await;
+    let bound_clients_by_writer = pool
+        .registry
+        .writer_activity_snapshot()
+        .await
+        .bound_clients_by_writer;
     let floor_plan = build_family_floor_plan(
         pool,
         family,
         &dc_endpoints,
         &live_addr_counts,
         &live_writer_ids_by_addr,
+        &bound_clients_by_writer,
         adaptive_idle_since,
         adaptive_recover_until,
     )
     .await;
     pool.set_adaptive_floor_runtime_caps(
-        floor_plan.global_cap_effective_total,
+        floor_plan.active_cap_configured_total,
+        floor_plan.active_cap_effective_total,
+        floor_plan.warm_cap_configured_total,
+        floor_plan.warm_cap_effective_total,
         floor_plan.target_writers_total,
+        floor_plan.active_writers_current,
+        floor_plan.warm_writers_current,
     );
 
     for (dc, endpoints) in dc_endpoints {
@@ -182,10 +242,11 @@ async fn check_family(
             });
         let alive = endpoints
             .iter()
-            .map(|addr| *live_addr_counts.get(addr).unwrap_or(&0))
+            .map(|addr| *live_addr_counts.get(&(dc, *addr)).unwrap_or(&0))
             .sum::<usize>();
 
         if endpoints.len() == 1 && pool.single_endpoint_outage_mode_enabled() && alive == 0 {
+            family_degraded = true;
             if single_endpoint_outage.insert(key) {
                 pool.stats.increment_me_single_endpoint_outage_enter_total();
                 warn!(
@@ -241,6 +302,7 @@ async fn check_family(
                 required,
                 &live_writer_ids_by_addr,
                 &writer_idle_since,
+                &bound_clients_by_writer,
                 idle_refresh_next_attempt,
             )
             .await;
@@ -254,12 +316,14 @@ async fn check_family(
                 alive,
                 required,
                 &live_writer_ids_by_addr,
+                &bound_clients_by_writer,
                 shadow_rotate_deadline,
             )
             .await;
             continue;
         }
         let missing = required - alive;
+        family_degraded = true;
 
         let now = Instant::now();
         if reconnect_budget == 0 {
@@ -290,7 +354,10 @@ async fn check_family(
         if *inflight.get(&key).unwrap_or(&0) >= max_concurrent {
             continue;
         }
-        if pool.has_refill_inflight_for_endpoints(&endpoints).await {
+        if pool
+            .has_refill_inflight_for_dc_key(super::pool::RefillDcKey { dc, family })
+            .await
+        {
             debug!(
                 dc = %dc,
                 ?family,
@@ -309,8 +376,8 @@ async fn check_family(
                 break;
             }
             reconnect_budget = reconnect_budget.saturating_sub(1);
-            if pool.floor_mode() == MeFloorMode::Adaptive
+            if pool.active_contour_writer_count_total().await
-                && pool.active_writer_count_total().await >= floor_plan.global_cap_effective_total
+                >= floor_plan.active_cap_effective_total
             {
                 let swapped = maybe_swap_idle_writer_for_cap(
                     pool,
@@ -320,6 +387,7 @@ async fn check_family(
                     &endpoints,
                     &live_writer_ids_by_addr,
                     &writer_idle_since,
+                    &bound_clients_by_writer,
                 )
                 .await;
                 if swapped {
@@ -334,14 +402,14 @@ async fn check_family(
                     ?family,
                     alive,
                     required,
-                    global_cap_effective_total = floor_plan.global_cap_effective_total,
+                    active_cap_effective_total = floor_plan.active_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()),
+                pool.connect_endpoints_round_robin(dc, &endpoints, rng.as_ref()),
             )
             .await;
             match res {
@@ -384,15 +452,23 @@ async fn check_family(
                 + Duration::from_millis(rand::rng().random_range(0..=jitter.max(1)));
             next_attempt.insert(key, now + wait);
             if pool.is_runtime_ready() {
-                warn!(
+                let warn_cooldown = pool.warn_rate_limit_duration();
-                    dc = %dc,
+                if should_emit_rate_limited_warn(
-                    ?family,
+                    floor_warn_next_allowed,
-                    alive = now_alive,
+                    key,
-                    required,
+                    now,
-                    endpoint_count = endpoints.len(),
+                    warn_cooldown,
-                    backoff_ms = next_ms,
+                ) {
-                    "DC writer floor is below required level, scheduled reconnect"
+                    warn!(
-                );
+                        dc = %dc,
+                        ?family,
+                        alive = now_alive,
+                        required,
+                        endpoint_count = endpoints.len(),
+                        backoff_ms = next_ms,
+                        "DC writer floor is below required level, scheduled reconnect"
+                    );
+                }
             } else {
                 info!(
                     dc = %dc,
@@ -409,6 +485,8 @@ async fn check_family(
             *v = v.saturating_sub(1);
         }
     }
+
+    family_degraded
 }
 
 fn health_reconnect_budget(pool: &Arc<MePool>, dc_groups: usize) -> usize {
@@ -420,6 +498,23 @@ fn health_reconnect_budget(pool: &Arc<MePool>, dc_groups: usize) -> usize {
         .clamp(HEALTH_RECONNECT_BUDGET_MIN, HEALTH_RECONNECT_BUDGET_MAX)
 }
 
+fn should_emit_rate_limited_warn(
+    next_allowed: &mut HashMap<(i32, IpFamily), Instant>,
+    key: (i32, IpFamily),
+    now: Instant,
+    cooldown: Duration,
+) -> bool {
+    let Some(ready_at) = next_allowed.get(&key).copied() else {
+        next_allowed.insert(key, now + cooldown);
+        return true;
+    };
+    if now >= ready_at {
+        next_allowed.insert(key, now + cooldown);
+        return true;
+    }
+    false
+}
+
 fn adaptive_floor_class_min(
     pool: &Arc<MePool>,
     endpoint_count: usize,
@@ -452,12 +547,13 @@ fn adaptive_floor_class_max(
 }
 
 fn list_writer_ids_for_endpoints(
+    dc: i32,
     endpoints: &[SocketAddr],
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, 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) {
+        if let Some(ids) = live_writer_ids_by_addr.get(&(dc, *endpoint)) {
             out.extend(ids.iter().copied());
         }
     }
@@ -468,8 +564,9 @@ async fn build_family_floor_plan(
     pool: &Arc<MePool>,
     family: IpFamily,
     dc_endpoints: &HashMap<i32, Vec<SocketAddr>>,
-    live_addr_counts: &HashMap<SocketAddr, usize>,
+    live_addr_counts: &HashMap<(i32, SocketAddr), usize>,
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, SocketAddr), Vec<u64>>,
+    bound_clients_by_writer: &HashMap<u64, usize>,
     adaptive_idle_since: &mut HashMap<(i32, IpFamily), Instant>,
     adaptive_recover_until: &mut HashMap<(i32, IpFamily), Instant>,
 ) -> FamilyFloorPlan {
@@ -480,6 +577,8 @@ async fn build_family_floor_plan(
     let floor_mode = pool.floor_mode();
     let is_adaptive = floor_mode == MeFloorMode::Adaptive;
     let cpu_cores = pool.adaptive_floor_effective_cpu_cores().max(1);
+    let (active_writers_current, warm_writers_current, _) =
+        pool.non_draining_writer_counts_by_contour().await;
 
     for (dc, endpoints) in dc_endpoints {
         if endpoints.is_empty() {
@@ -489,8 +588,10 @@ async fn build_family_floor_plan(
         let reduce_for_idle = should_reduce_floor_for_idle(
             pool,
             key,
+            *dc,
             endpoints,
             live_writer_ids_by_addr,
+            bound_clients_by_writer,
             adaptive_idle_since,
             adaptive_recover_until,
         )
@@ -517,11 +618,11 @@ async fn build_family_floor_plan(
         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))
+            .map(|endpoint| live_addr_counts.get(&(*dc, *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 writer_ids = list_writer_ids_for_endpoints(*dc, endpoints, live_writer_ids_by_addr);
-        let has_bound_clients = has_bound_clients_on_endpoint(pool, &writer_ids).await;
+        let has_bound_clients = has_bound_clients_on_endpoint(&writer_ids, bound_clients_by_writer);
 
         entries.push(DcFloorPlanEntry {
             dc: *dc,
@@ -536,9 +637,16 @@ async fn build_family_floor_plan(
     }
 
     if entries.is_empty() {
+        let active_cap_configured_total = pool.adaptive_floor_active_cap_configured_total();
+        let warm_cap_configured_total = pool.adaptive_floor_warm_cap_configured_total();
         return FamilyFloorPlan {
             by_dc,
-            global_cap_effective_total: 0,
+            active_cap_configured_total,
+            active_cap_effective_total: active_cap_configured_total,
+            warm_cap_configured_total,
+            warm_cap_effective_total: warm_cap_configured_total,
+            active_writers_current,
+            warm_writers_current,
             target_writers_total: 0,
         };
     }
@@ -548,20 +656,26 @@ async fn build_family_floor_plan(
             .iter()
             .map(|entry| entry.target_required)
             .sum::<usize>();
-        let active_total = pool.active_writer_count_total().await;
+        let active_cap_configured_total = pool.adaptive_floor_active_cap_configured_total();
+        let warm_cap_configured_total = pool.adaptive_floor_warm_cap_configured_total();
         for entry in entries {
             by_dc.insert(entry.dc, entry);
         }
         return FamilyFloorPlan {
             by_dc,
-            global_cap_effective_total: active_total.max(target_total),
+            active_cap_configured_total,
+            active_cap_effective_total: active_cap_configured_total.max(target_total),
+            warm_cap_configured_total,
+            warm_cap_effective_total: warm_cap_configured_total,
+            active_writers_current,
+            warm_writers_current,
             target_writers_total: target_total,
         };
     }
 
-    let global_cap_raw = pool.adaptive_floor_global_cap_raw();
+    let active_cap_configured_total = pool.adaptive_floor_active_cap_configured_total();
-    let total_active = pool.active_writer_count_total().await;
+    let warm_cap_configured_total = pool.adaptive_floor_warm_cap_configured_total();
-    let other_active = total_active.saturating_sub(family_active_total);
+    let other_active = active_writers_current.saturating_sub(family_active_total);
     let min_sum = entries
         .iter()
         .map(|entry| entry.min_required)
@@ -570,7 +684,7 @@ async fn build_family_floor_plan(
         .iter()
         .map(|entry| entry.target_required)
         .sum::<usize>();
-    let family_cap = global_cap_raw
+    let family_cap = active_cap_configured_total
         .saturating_sub(other_active)
         .max(min_sum);
     if target_sum > family_cap {
@@ -605,11 +719,17 @@ async fn build_family_floor_plan(
     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 active_cap_effective_total =
+        active_cap_configured_total.max(other_active.saturating_add(min_sum));
     let target_writers_total = other_active.saturating_add(target_sum);
     FamilyFloorPlan {
         by_dc,
-        global_cap_effective_total,
+        active_cap_configured_total,
+        active_cap_effective_total,
+        warm_cap_configured_total,
+        warm_cap_effective_total: warm_cap_configured_total,
+        active_writers_current,
+        warm_writers_current,
         target_writers_total,
     }
 }
@@ -620,17 +740,18 @@ async fn maybe_swap_idle_writer_for_cap(
     dc: i32,
     family: IpFamily,
     endpoints: &[SocketAddr],
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, SocketAddr), Vec<u64>>,
     writer_idle_since: &HashMap<u64, u64>,
+    bound_clients_by_writer: &HashMap<u64, usize>,
 ) -> 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 {
+        let Some(writer_ids) = live_writer_ids_by_addr.get(&(dc, *endpoint)) else {
             continue;
         };
         for writer_id in writer_ids {
-            if !pool.registry.is_writer_empty(*writer_id).await {
+            if bound_clients_by_writer.get(writer_id).copied().unwrap_or(0) > 0 {
                 continue;
             }
             let Some(idle_since_epoch_secs) = writer_idle_since.get(writer_id).copied() else {
@@ -651,7 +772,12 @@ async fn maybe_swap_idle_writer_for_cap(
         return false;
     };
 
-    let connected = match tokio::time::timeout(pool.me_one_timeout, pool.connect_one(endpoint, rng.as_ref())).await {
+    let connected = match tokio::time::timeout(
+        pool.me_one_timeout,
+        pool.connect_one_for_dc(endpoint, dc, rng.as_ref()),
+    )
+    .await
+    {
         Ok(Ok(())) => true,
         Ok(Err(error)) => {
             debug!(
@@ -703,8 +829,9 @@ async fn maybe_refresh_idle_writer_for_dc(
     endpoints: &[SocketAddr],
     alive: usize,
     required: usize,
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, SocketAddr), Vec<u64>>,
     writer_idle_since: &HashMap<u64, u64>,
+    bound_clients_by_writer: &HashMap<u64, usize>,
     idle_refresh_next_attempt: &mut HashMap<(i32, IpFamily), Instant>,
 ) {
     if alive < required {
@@ -721,10 +848,13 @@ async fn maybe_refresh_idle_writer_for_dc(
     let now_epoch_secs = MePool::now_epoch_secs();
     let mut candidate: Option<(u64, SocketAddr, u64, u64)> = None;
     for endpoint in endpoints {
-        let Some(writer_ids) = live_writer_ids_by_addr.get(endpoint) else {
+        let Some(writer_ids) = live_writer_ids_by_addr.get(&(dc, *endpoint)) else {
             continue;
         };
         for writer_id in writer_ids {
+            if bound_clients_by_writer.get(writer_id).copied().unwrap_or(0) > 0 {
+                continue;
+            }
             let Some(idle_since_epoch_secs) = writer_idle_since.get(writer_id).copied() else {
                 continue;
             };
@@ -748,7 +878,12 @@ async fn maybe_refresh_idle_writer_for_dc(
         return;
     };
 
-    let rotate_ok = match tokio::time::timeout(pool.me_one_timeout, pool.connect_one(endpoint, rng.as_ref())).await {
+    let rotate_ok = match tokio::time::timeout(
+        pool.me_one_timeout,
+        pool.connect_one_for_dc(endpoint, dc, rng.as_ref()),
+    )
+    .await
+    {
         Ok(Ok(())) => true,
         Ok(Err(error)) => {
             debug!(
@@ -804,8 +939,10 @@ async fn maybe_refresh_idle_writer_for_dc(
 async fn should_reduce_floor_for_idle(
     pool: &Arc<MePool>,
     key: (i32, IpFamily),
+    dc: i32,
     endpoints: &[SocketAddr],
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, SocketAddr), Vec<u64>>,
+    bound_clients_by_writer: &HashMap<u64, usize>,
     adaptive_idle_since: &mut HashMap<(i32, IpFamily), Instant>,
     adaptive_recover_until: &mut HashMap<(i32, IpFamily), Instant>,
 ) -> bool {
@@ -816,8 +953,8 @@ async fn should_reduce_floor_for_idle(
     }
 
     let now = Instant::now();
-    let writer_ids = list_writer_ids_for_endpoints(endpoints, live_writer_ids_by_addr);
+    let writer_ids = list_writer_ids_for_endpoints(dc, endpoints, live_writer_ids_by_addr);
-    let has_bound_clients = has_bound_clients_on_endpoint(pool, &writer_ids).await;
+    let has_bound_clients = has_bound_clients_on_endpoint(&writer_ids, bound_clients_by_writer);
     if has_bound_clients {
         adaptive_idle_since.remove(&key);
         adaptive_recover_until.insert(key, now + pool.adaptive_floor_recover_grace_duration());
@@ -836,13 +973,13 @@ async fn should_reduce_floor_for_idle(
     now.saturating_duration_since(*idle_since) >= pool.adaptive_floor_idle_duration()
 }
 
-async fn has_bound_clients_on_endpoint(pool: &Arc<MePool>, writer_ids: &[u64]) -> bool {
+fn has_bound_clients_on_endpoint(
-    for writer_id in writer_ids {
+    writer_ids: &[u64],
-        if !pool.registry.is_writer_empty(*writer_id).await {
+    bound_clients_by_writer: &HashMap<u64, usize>,
-            return true;
+) -> bool {
-        }
+    writer_ids
-    }
+        .iter()
-    false
+        .any(|writer_id| bound_clients_by_writer.get(writer_id).copied().unwrap_or(0) > 0)
 }
 
 async fn recover_single_endpoint_outage(
@@ -882,7 +1019,12 @@ async fn recover_single_endpoint_outage(
     let attempt_ok = if bypass_quarantine {
         pool.stats
             .increment_me_single_endpoint_quarantine_bypass_total();
-        match tokio::time::timeout(pool.me_one_timeout, pool.connect_one(endpoint, rng.as_ref())).await {
+        match tokio::time::timeout(
+            pool.me_one_timeout,
+            pool.connect_one_for_dc(endpoint, key.0, rng.as_ref()),
+        )
+        .await
+        {
             Ok(Ok(())) => true,
             Ok(Err(e)) => {
                 debug!(
@@ -908,7 +1050,7 @@ async fn recover_single_endpoint_outage(
         let one_endpoint = [endpoint];
         match tokio::time::timeout(
             pool.me_one_timeout,
-            pool.connect_endpoints_round_robin(&one_endpoint, rng.as_ref()),
+            pool.connect_endpoints_round_robin(key.0, &one_endpoint, rng.as_ref()),
         )
         .await
         {
@@ -972,7 +1114,8 @@ async fn maybe_rotate_single_endpoint_shadow(
     endpoints: &[SocketAddr],
     alive: usize,
     required: usize,
-    live_writer_ids_by_addr: &HashMap<SocketAddr, Vec<u64>>,
+    live_writer_ids_by_addr: &HashMap<(i32, SocketAddr), Vec<u64>>,
+    bound_clients_by_writer: &HashMap<u64, usize>,
     shadow_rotate_deadline: &mut HashMap<(i32, IpFamily), Instant>,
 ) {
     if endpoints.len() != 1 || alive < required {
@@ -1004,14 +1147,14 @@ async fn maybe_rotate_single_endpoint_shadow(
         return;
     }
 
-    let Some(writer_ids) = live_writer_ids_by_addr.get(&endpoint) else {
+    let Some(writer_ids) = live_writer_ids_by_addr.get(&(dc, endpoint)) else {
         shadow_rotate_deadline.insert(key, now + Duration::from_secs(SHADOW_ROTATE_RETRY_SECS));
         return;
     };
 
     let mut candidate_writer_id = None;
     for writer_id in writer_ids {
-        if pool.registry.is_writer_empty(*writer_id).await {
+        if bound_clients_by_writer.get(writer_id).copied().unwrap_or(0) == 0 {
             candidate_writer_id = Some(*writer_id);
             break;
         }
@@ -1030,7 +1173,12 @@ async fn maybe_rotate_single_endpoint_shadow(
         return;
     };
 
-    let rotate_ok = match tokio::time::timeout(pool.me_one_timeout, pool.connect_one(endpoint, rng.as_ref())).await {
+    let rotate_ok = match tokio::time::timeout(
+        pool.me_one_timeout,
+        pool.connect_one_for_dc(endpoint, dc, rng.as_ref()),
+    )
+    .await
+    {
         Ok(Ok(())) => true,
         Ok(Err(e)) => {
             debug!(

src/transport/middle_proxy/ping.rs

@@ -331,7 +331,7 @@ pub async fn run_me_ping(pool: &Arc<MePool>, rng: &SecureRandom) -> Vec<MePingRe
             let mut error = None;
             let mut route = None;
 
-            match pool.connect_tcp(addr).await {
+            match pool.connect_tcp(addr, None).await {
                 Ok((stream, conn_rtt, upstream_egress)) => {
                     connect_ms = Some(conn_rtt);
                     route = route_from_egress(upstream_egress);

src/transport/middle_proxy/pool.rs

@@ -7,7 +7,9 @@ use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
 use tokio::sync::{Mutex, Notify, RwLock, mpsc};
 use tokio_util::sync::CancellationToken;
 
-use crate::config::{MeBindStaleMode, MeFloorMode, MeRouteNoWriterMode, MeSocksKdfPolicy};
+use crate::config::{
+    MeBindStaleMode, MeFloorMode, MeRouteNoWriterMode, MeSocksKdfPolicy, MeWriterPickMode,
+};
 use crate::crypto::SecureRandom;
 use crate::network::IpFamily;
 use crate::network::probe::NetworkDecision;
@@ -22,18 +24,27 @@ pub(super) struct RefillDcKey {
     pub family: IpFamily,
 }
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
+pub(super) struct RefillEndpointKey {
+    pub dc: i32,
+    pub addr: SocketAddr,
+}
+
 #[derive(Clone)]
 pub struct MeWriter {
     pub id: u64,
     pub addr: SocketAddr,
+    pub writer_dc: i32,
     pub generation: u64,
     pub contour: Arc<AtomicU8>,
     pub created_at: Instant,
     pub tx: mpsc::Sender<WriterCommand>,
     pub cancel: CancellationToken,
     pub degraded: Arc<AtomicBool>,
+    pub rtt_ema_ms_x10: Arc<AtomicU32>,
     pub draining: Arc<AtomicBool>,
     pub draining_started_at_epoch_secs: Arc<AtomicU64>,
+    pub drain_deadline_epoch_secs: Arc<AtomicU64>,
     pub allow_drain_fallback: Arc<AtomicBool>,
 }
 
@@ -95,6 +106,7 @@ pub struct MePool {
     pub(super) me_keepalive_jitter: Duration,
     pub(super) me_keepalive_payload_random: bool,
     pub(super) rpc_proxy_req_every_secs: AtomicU64,
+    pub(super) writer_cmd_channel_capacity: usize,
     pub(super) me_warmup_stagger_enabled: bool,
     pub(super) me_warmup_step_delay: Duration,
     pub(super) me_warmup_step_jitter: Duration,
@@ -117,23 +129,34 @@ pub struct MePool {
     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_max_active_writers_per_core: AtomicU32,
+    pub(super) me_adaptive_floor_max_warm_writers_per_core: AtomicU32,
+    pub(super) me_adaptive_floor_max_active_writers_global: AtomicU32,
+    pub(super) me_adaptive_floor_max_warm_writers_global: 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) me_adaptive_floor_active_cap_configured: AtomicU64,
+    pub(super) me_adaptive_floor_active_cap_effective: AtomicU64,
+    pub(super) me_adaptive_floor_warm_cap_configured: AtomicU64,
+    pub(super) me_adaptive_floor_warm_cap_effective: AtomicU64,
+    pub(super) me_adaptive_floor_active_writers_current: AtomicU64,
+    pub(super) me_adaptive_floor_warm_writers_current: 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) endpoint_dc_map: Arc<RwLock<HashMap<SocketAddr, Option<i32>>>>,
     pub(super) default_dc: AtomicI32,
     pub(super) next_writer_id: AtomicU64,
     pub(super) ping_tracker: Arc<Mutex<HashMap<i64, (std::time::Instant, u64)>>>,
+    pub(super) ping_tracker_last_cleanup_epoch_ms: AtomicU64,
     pub(super) rtt_stats: Arc<Mutex<HashMap<u64, (f64, f64)>>>,
     pub(super) nat_reflection_cache: Arc<Mutex<NatReflectionCache>>,
     pub(super) nat_reflection_singleflight_v4: Arc<Mutex<()>>,
     pub(super) nat_reflection_singleflight_v6: Arc<Mutex<()>>,
     pub(super) writer_available: Arc<Notify>,
-    pub(super) refill_inflight: Arc<Mutex<HashSet<SocketAddr>>>,
+    pub(super) refill_inflight: Arc<Mutex<HashSet<RefillEndpointKey>>>,
     pub(super) refill_inflight_dc: Arc<Mutex<HashSet<RefillDcKey>>>,
     pub(super) conn_count: AtomicUsize,
     pub(super) stats: Arc<crate::stats::Stats>,
@@ -157,13 +180,19 @@ pub struct MePool {
     pub(super) me_bind_stale_ttl_secs: AtomicU64,
     pub(super) secret_atomic_snapshot: AtomicBool,
     pub(super) me_deterministic_writer_sort: AtomicBool,
+    pub(super) me_writer_pick_mode: AtomicU8,
+    pub(super) me_writer_pick_sample_size: AtomicU8,
     pub(super) me_socks_kdf_policy: AtomicU8,
     pub(super) me_route_no_writer_mode: AtomicU8,
     pub(super) me_route_no_writer_wait: Duration,
     pub(super) me_route_inline_recovery_attempts: u32,
     pub(super) me_route_inline_recovery_wait: Duration,
+    pub(super) me_health_interval_ms_unhealthy: AtomicU64,
+    pub(super) me_health_interval_ms_healthy: AtomicU64,
+    pub(super) me_warn_rate_limit_ms: AtomicU64,
     pub(super) runtime_ready: AtomicBool,
     pool_size: usize,
+    pub(super) preferred_endpoints_by_dc: Arc<RwLock<HashMap<i32, Vec<SocketAddr>>>>,
 }
 
 #[derive(Debug, Default)]
@@ -234,6 +263,10 @@ impl MePool {
         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,
+        me_adaptive_floor_max_active_writers_per_core: u16,
+        me_adaptive_floor_max_warm_writers_per_core: u16,
+        me_adaptive_floor_max_active_writers_global: u32,
+        me_adaptive_floor_max_warm_writers_global: u32,
         hardswap: bool,
         me_pool_drain_ttl_secs: u64,
         me_pool_force_close_secs: u64,
@@ -246,17 +279,28 @@ impl MePool {
         me_bind_stale_ttl_secs: u64,
         me_secret_atomic_snapshot: bool,
         me_deterministic_writer_sort: bool,
+        me_writer_pick_mode: MeWriterPickMode,
+        me_writer_pick_sample_size: u8,
         me_socks_kdf_policy: MeSocksKdfPolicy,
+        me_writer_cmd_channel_capacity: usize,
+        me_route_channel_capacity: usize,
         me_route_backpressure_base_timeout_ms: u64,
         me_route_backpressure_high_timeout_ms: u64,
         me_route_backpressure_high_watermark_pct: u8,
+        me_health_interval_ms_unhealthy: u64,
+        me_health_interval_ms_healthy: u64,
+        me_warn_rate_limit_ms: u64,
         me_route_no_writer_mode: MeRouteNoWriterMode,
         me_route_no_writer_wait_ms: u64,
         me_route_inline_recovery_attempts: u32,
         me_route_inline_recovery_wait_ms: u64,
     ) -> Arc<Self> {
         let endpoint_dc_map = Self::build_endpoint_dc_map_from_maps(&proxy_map_v4, &proxy_map_v6);
-        let registry = Arc::new(ConnRegistry::new());
+        let preferred_endpoints_by_dc =
+            Self::build_preferred_endpoints_by_dc(&decision, &proxy_map_v4, &proxy_map_v6);
+        let registry = Arc::new(ConnRegistry::with_route_channel_capacity(
+            me_route_channel_capacity,
+        ));
         registry.update_route_backpressure_policy(
             me_route_backpressure_base_timeout_ms,
             me_route_backpressure_high_timeout_ms,
@@ -303,6 +347,7 @@ impl MePool {
             me_keepalive_jitter: Duration::from_secs(me_keepalive_jitter_secs),
             me_keepalive_payload_random,
             rpc_proxy_req_every_secs: AtomicU64::new(rpc_proxy_req_every_secs),
+            writer_cmd_channel_capacity: me_writer_cmd_channel_capacity.max(1),
             me_warmup_stagger_enabled,
             me_warmup_step_delay: Duration::from_millis(me_warmup_step_delay_ms),
             me_warmup_step_jitter: Duration::from_millis(me_warmup_step_jitter_ms),
@@ -349,11 +394,29 @@ impl MePool {
             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_max_active_writers_per_core: AtomicU32::new(
+                me_adaptive_floor_max_active_writers_per_core as u32,
+            ),
+            me_adaptive_floor_max_warm_writers_per_core: AtomicU32::new(
+                me_adaptive_floor_max_warm_writers_per_core as u32,
+            ),
+            me_adaptive_floor_max_active_writers_global: AtomicU32::new(
+                me_adaptive_floor_max_active_writers_global,
+            ),
+            me_adaptive_floor_max_warm_writers_global: AtomicU32::new(
+                me_adaptive_floor_max_warm_writers_global,
+            ),
             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),
+            me_adaptive_floor_active_cap_configured: AtomicU64::new(0),
+            me_adaptive_floor_active_cap_effective: AtomicU64::new(0),
+            me_adaptive_floor_warm_cap_configured: AtomicU64::new(0),
+            me_adaptive_floor_warm_cap_effective: AtomicU64::new(0),
+            me_adaptive_floor_active_writers_current: AtomicU64::new(0),
+            me_adaptive_floor_warm_writers_current: 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)),
@@ -361,6 +424,7 @@ impl MePool {
             default_dc: AtomicI32::new(default_dc.unwrap_or(2)),
             next_writer_id: AtomicU64::new(1),
             ping_tracker: Arc::new(Mutex::new(HashMap::new())),
+            ping_tracker_last_cleanup_epoch_ms: AtomicU64::new(0),
             rtt_stats: Arc::new(Mutex::new(HashMap::new())),
             nat_reflection_cache: Arc::new(Mutex::new(NatReflectionCache::default())),
             nat_reflection_singleflight_v4: Arc::new(Mutex::new(())),
@@ -393,12 +457,18 @@ impl MePool {
             me_bind_stale_ttl_secs: AtomicU64::new(me_bind_stale_ttl_secs),
             secret_atomic_snapshot: AtomicBool::new(me_secret_atomic_snapshot),
             me_deterministic_writer_sort: AtomicBool::new(me_deterministic_writer_sort),
+            me_writer_pick_mode: AtomicU8::new(me_writer_pick_mode.as_u8()),
+            me_writer_pick_sample_size: AtomicU8::new(me_writer_pick_sample_size.clamp(2, 4)),
             me_socks_kdf_policy: AtomicU8::new(me_socks_kdf_policy.as_u8()),
             me_route_no_writer_mode: AtomicU8::new(me_route_no_writer_mode.as_u8()),
             me_route_no_writer_wait: Duration::from_millis(me_route_no_writer_wait_ms),
             me_route_inline_recovery_attempts,
             me_route_inline_recovery_wait: Duration::from_millis(me_route_inline_recovery_wait_ms),
+            me_health_interval_ms_unhealthy: AtomicU64::new(me_health_interval_ms_unhealthy.max(1)),
+            me_health_interval_ms_healthy: AtomicU64::new(me_health_interval_ms_healthy.max(1)),
+            me_warn_rate_limit_ms: AtomicU64::new(me_warn_rate_limit_ms.max(1)),
             runtime_ready: AtomicBool::new(false),
+            preferred_endpoints_by_dc: Arc::new(RwLock::new(preferred_endpoints_by_dc)),
         })
     }
 
@@ -428,6 +498,8 @@ impl MePool {
         bind_stale_ttl_secs: u64,
         secret_atomic_snapshot: bool,
         deterministic_writer_sort: bool,
+        writer_pick_mode: MeWriterPickMode,
+        writer_pick_sample_size: u8,
         single_endpoint_shadow_writers: u8,
         single_endpoint_outage_mode_enabled: bool,
         single_endpoint_outage_disable_quarantine: bool,
@@ -443,6 +515,13 @@ impl MePool {
         adaptive_floor_cpu_cores_override: u16,
         adaptive_floor_max_extra_writers_single_per_core: u16,
         adaptive_floor_max_extra_writers_multi_per_core: u16,
+        adaptive_floor_max_active_writers_per_core: u16,
+        adaptive_floor_max_warm_writers_per_core: u16,
+        adaptive_floor_max_active_writers_global: u32,
+        adaptive_floor_max_warm_writers_global: u32,
+        me_health_interval_ms_unhealthy: u64,
+        me_health_interval_ms_healthy: u64,
+        me_warn_rate_limit_ms: u64,
     ) {
         self.hardswap.store(hardswap, Ordering::Relaxed);
         self.me_pool_drain_ttl_secs
@@ -467,6 +546,14 @@ impl MePool {
             .store(secret_atomic_snapshot, Ordering::Relaxed);
         self.me_deterministic_writer_sort
             .store(deterministic_writer_sort, Ordering::Relaxed);
+        let previous_writer_pick_mode = self.writer_pick_mode();
+        self.me_writer_pick_mode
+            .store(writer_pick_mode.as_u8(), Ordering::Relaxed);
+        self.me_writer_pick_sample_size
+            .store(writer_pick_sample_size.clamp(2, 4), Ordering::Relaxed);
+        if previous_writer_pick_mode != writer_pick_mode {
+            self.stats.increment_me_writer_pick_mode_switch_total();
+        }
         self.me_single_endpoint_shadow_writers
             .store(single_endpoint_shadow_writers, Ordering::Relaxed);
         self.me_single_endpoint_outage_mode_enabled
@@ -504,6 +591,26 @@ impl MePool {
                 adaptive_floor_max_extra_writers_multi_per_core as u32,
                 Ordering::Relaxed,
             );
+        self.me_adaptive_floor_max_active_writers_per_core
+            .store(
+                adaptive_floor_max_active_writers_per_core as u32,
+                Ordering::Relaxed,
+            );
+        self.me_adaptive_floor_max_warm_writers_per_core
+            .store(
+                adaptive_floor_max_warm_writers_per_core as u32,
+                Ordering::Relaxed,
+            );
+        self.me_adaptive_floor_max_active_writers_global
+            .store(adaptive_floor_max_active_writers_global, Ordering::Relaxed);
+        self.me_adaptive_floor_max_warm_writers_global
+            .store(adaptive_floor_max_warm_writers_global, Ordering::Relaxed);
+        self.me_health_interval_ms_unhealthy
+            .store(me_health_interval_ms_unhealthy.max(1), Ordering::Relaxed);
+        self.me_health_interval_ms_healthy
+            .store(me_health_interval_ms_healthy.max(1), Ordering::Relaxed);
+        self.me_warn_rate_limit_ms
+            .store(me_warn_rate_limit_ms.max(1), Ordering::Relaxed);
         if previous_floor_mode != floor_mode {
             self.stats.increment_me_floor_mode_switch_total();
             match (previous_floor_mode, floor_mode) {
@@ -574,11 +681,26 @@ impl MePool {
         self.proxy_secret.read().await.key_selector
     }
 
-    pub(super) async fn active_writer_count_total(&self) -> usize {
+    pub(super) async fn non_draining_writer_counts_by_contour(&self) -> (usize, usize, usize) {
         let ws = self.writers.read().await;
-        ws.iter()
+        let mut active = 0usize;
-            .filter(|w| !w.draining.load(Ordering::Relaxed))
+        let mut warm = 0usize;
-            .count()
+        for writer in ws.iter() {
+            if writer.draining.load(Ordering::Relaxed) {
+                continue;
+            }
+            match WriterContour::from_u8(writer.contour.load(Ordering::Relaxed)) {
+                WriterContour::Active => active = active.saturating_add(1),
+                WriterContour::Warm => warm = warm.saturating_add(1),
+                WriterContour::Draining => {}
+            }
+        }
+        (active, warm, active.saturating_add(warm))
+    }
+
+    pub(super) async fn active_contour_writer_count_total(&self) -> usize {
+        let (active, _, _) = self.non_draining_writer_counts_by_contour().await;
+        active
     }
 
     pub(super) async fn secret_snapshot(&self) -> SecretSnapshot {
@@ -589,6 +711,16 @@ impl MePool {
         MeBindStaleMode::from_u8(self.me_bind_stale_mode.load(Ordering::Relaxed))
     }
 
+    pub(super) fn writer_pick_mode(&self) -> MeWriterPickMode {
+        MeWriterPickMode::from_u8(self.me_writer_pick_mode.load(Ordering::Relaxed))
+    }
+
+    pub(super) fn writer_pick_sample_size(&self) -> usize {
+        self.me_writer_pick_sample_size
+            .load(Ordering::Relaxed)
+            .clamp(2, 4) as usize
+    }
+
     pub(super) fn required_writers_for_dc(&self, endpoint_count: usize) -> usize {
         if endpoint_count == 0 {
             return 0;
@@ -624,13 +756,6 @@ impl MePool {
             .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
@@ -641,6 +766,34 @@ impl MePool {
             .load(Ordering::Relaxed) as usize
     }
 
+    pub(super) fn adaptive_floor_max_active_writers_per_core(&self) -> usize {
+        (self
+            .me_adaptive_floor_max_active_writers_per_core
+            .load(Ordering::Relaxed) as usize)
+            .max(1)
+    }
+
+    pub(super) fn adaptive_floor_max_warm_writers_per_core(&self) -> usize {
+        (self
+            .me_adaptive_floor_max_warm_writers_per_core
+            .load(Ordering::Relaxed) as usize)
+            .max(1)
+    }
+
+    pub(super) fn adaptive_floor_max_active_writers_global(&self) -> usize {
+        (self
+            .me_adaptive_floor_max_active_writers_global
+            .load(Ordering::Relaxed) as usize)
+            .max(1)
+    }
+
+    pub(super) fn adaptive_floor_max_warm_writers_global(&self) -> usize {
+        (self
+            .me_adaptive_floor_max_warm_writers_global
+            .load(Ordering::Relaxed) as usize)
+            .max(1)
+    }
+
     pub(super) fn adaptive_floor_detected_cpu_cores(&self) -> usize {
         std::thread::available_parallelism()
             .map(|value| value.get())
@@ -669,28 +822,126 @@ impl MePool {
         effective
     }
 
-    pub(super) fn adaptive_floor_global_cap_raw(&self) -> usize {
+    pub(super) fn adaptive_floor_active_cap_configured_total(&self) -> usize {
         let cores = self.adaptive_floor_effective_cpu_cores();
-        let cap = cores.saturating_mul(self.adaptive_floor_writers_per_core_total());
+        let per_core_cap = cores.saturating_mul(self.adaptive_floor_max_active_writers_per_core());
-        self.me_adaptive_floor_global_cap_raw
+        let configured = per_core_cap.min(self.adaptive_floor_max_active_writers_global());
-            .store(cap as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_active_cap_configured
-        self.stats.set_me_floor_global_cap_raw_gauge(cap as u64);
+            .store(configured as u64, Ordering::Relaxed);
-        cap
+        self.stats
+            .set_me_floor_active_cap_configured_gauge(configured as u64);
+        configured
+    }
+
+    pub(super) fn adaptive_floor_warm_cap_configured_total(&self) -> usize {
+        let cores = self.adaptive_floor_effective_cpu_cores();
+        let per_core_cap = cores.saturating_mul(self.adaptive_floor_max_warm_writers_per_core());
+        let configured = per_core_cap.min(self.adaptive_floor_max_warm_writers_global());
+        self.me_adaptive_floor_warm_cap_configured
+            .store(configured as u64, Ordering::Relaxed);
+        self.stats
+            .set_me_floor_warm_cap_configured_gauge(configured as u64);
+        configured
     }
 
     pub(super) fn set_adaptive_floor_runtime_caps(
         &self,
-        global_cap_effective: usize,
+        active_cap_configured: usize,
+        active_cap_effective: usize,
+        warm_cap_configured: usize,
+        warm_cap_effective: usize,
         target_writers_total: usize,
+        active_writers_current: usize,
+        warm_writers_current: usize,
     ) {
+        self.me_adaptive_floor_global_cap_raw
+            .store(active_cap_configured as u64, Ordering::Relaxed);
         self.me_adaptive_floor_global_cap_effective
-            .store(global_cap_effective as u64, Ordering::Relaxed);
+            .store(active_cap_effective as u64, Ordering::Relaxed);
         self.me_adaptive_floor_target_writers_total
             .store(target_writers_total as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_active_cap_configured
+            .store(active_cap_configured as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_active_cap_effective
+            .store(active_cap_effective as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_warm_cap_configured
+            .store(warm_cap_configured as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_warm_cap_effective
+            .store(warm_cap_effective as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_active_writers_current
+            .store(active_writers_current as u64, Ordering::Relaxed);
+        self.me_adaptive_floor_warm_writers_current
+            .store(warm_writers_current as u64, Ordering::Relaxed);
         self.stats
-            .set_me_floor_global_cap_effective_gauge(global_cap_effective as u64);
+            .set_me_floor_global_cap_raw_gauge(active_cap_configured as u64);
+        self.stats
+            .set_me_floor_global_cap_effective_gauge(active_cap_effective as u64);
         self.stats
             .set_me_floor_target_writers_total_gauge(target_writers_total as u64);
+        self.stats
+            .set_me_floor_active_cap_configured_gauge(active_cap_configured as u64);
+        self.stats
+            .set_me_floor_active_cap_effective_gauge(active_cap_effective as u64);
+        self.stats
+            .set_me_floor_warm_cap_configured_gauge(warm_cap_configured as u64);
+        self.stats
+            .set_me_floor_warm_cap_effective_gauge(warm_cap_effective as u64);
+        self.stats
+            .set_me_writers_active_current_gauge(active_writers_current as u64);
+        self.stats
+            .set_me_writers_warm_current_gauge(warm_writers_current as u64);
+    }
+
+    pub(super) async fn active_coverage_required_total(&self) -> usize {
+        let mut endpoints_by_dc = HashMap::<i32, HashSet<SocketAddr>>::new();
+
+        if self.decision.ipv4_me {
+            let map = self.proxy_map_v4.read().await;
+            for (dc, addrs) in map.iter() {
+                let entry = endpoints_by_dc.entry(*dc).or_default();
+                for (ip, port) in addrs.iter().copied() {
+                    entry.insert(SocketAddr::new(ip, port));
+                }
+            }
+        }
+
+        if self.decision.ipv6_me {
+            let map = self.proxy_map_v6.read().await;
+            for (dc, addrs) in map.iter() {
+                let entry = endpoints_by_dc.entry(*dc).or_default();
+                for (ip, port) in addrs.iter().copied() {
+                    entry.insert(SocketAddr::new(ip, port));
+                }
+            }
+        }
+
+        endpoints_by_dc
+            .values()
+            .map(|endpoints| self.required_writers_for_dc_with_floor_mode(endpoints.len(), false))
+            .sum()
+    }
+
+    pub(super) async fn can_open_writer_for_contour(
+        &self,
+        contour: WriterContour,
+        allow_coverage_override: bool,
+    ) -> bool {
+        let (active_writers, warm_writers, _) = self.non_draining_writer_counts_by_contour().await;
+        match contour {
+            WriterContour::Active => {
+                let active_cap = self.adaptive_floor_active_cap_configured_total();
+                if active_writers < active_cap {
+                    return true;
+                }
+                if !allow_coverage_override {
+                    return false;
+                }
+                let coverage_required = self.active_coverage_required_total().await;
+                active_writers < coverage_required
+            }
+            WriterContour::Warm => warm_writers < self.adaptive_floor_warm_cap_configured_total(),
+            WriterContour::Draining => true,
+        }
     }
 
     pub(super) fn required_writers_for_dc_with_floor_mode(
@@ -779,16 +1030,34 @@ impl MePool {
         if dc == 0 { 2 } else { dc }
     }
 
-    pub(super) fn dc_lookup_chain_for_target(&self, target_dc: i32) -> Vec<i32> {
+    pub(super) async fn has_configured_endpoints_for_dc(&self, dc: i32) -> bool {
-        let mut out = Vec::with_capacity(1);
+        if self.decision.ipv4_me {
-        if target_dc != 0 {
+            let map = self.proxy_map_v4.read().await;
-            out.push(target_dc);
+            if map.get(&dc).is_some_and(|endpoints| !endpoints.is_empty()) {
-        } else {
+                return true;
-            // Use default DC only when target DC is unknown and pinning is not established.
+            }
-            let fallback_dc = self.default_dc_for_routing();
-            out.push(fallback_dc);
         }
-        out
+
+        if self.decision.ipv6_me {
+            let map = self.proxy_map_v6.read().await;
+            if map.get(&dc).is_some_and(|endpoints| !endpoints.is_empty()) {
+                return true;
+            }
+        }
+
+        false
+    }
+
+    pub(super) async fn resolve_target_dc_for_routing(&self, target_dc: i32) -> (i32, bool) {
+        if target_dc == 0 {
+            return (self.default_dc_for_routing(), true);
+        }
+
+        if self.has_configured_endpoints_for_dc(target_dc).await {
+            return (target_dc, false);
+        }
+
+        (self.default_dc_for_routing(), true)
     }
 
     pub(super) async fn resolve_dc_for_endpoint(&self, addr: SocketAddr) -> i32 {
@@ -830,6 +1099,62 @@ impl MePool {
         }
     }
 
+    fn build_preferred_endpoints_by_dc(
+        decision: &NetworkDecision,
+        map_v4: &HashMap<i32, Vec<(IpAddr, u16)>>,
+        map_v6: &HashMap<i32, Vec<(IpAddr, u16)>>,
+    ) -> HashMap<i32, Vec<SocketAddr>> {
+        let mut out = HashMap::<i32, Vec<SocketAddr>>::new();
+        let mut dcs = HashSet::<i32>::new();
+        dcs.extend(map_v4.keys().copied());
+        dcs.extend(map_v6.keys().copied());
+
+        for dc in dcs {
+            let v4 = map_v4
+                .get(&dc)
+                .map(|items| {
+                    items
+                        .iter()
+                        .map(|(ip, port)| SocketAddr::new(*ip, *port))
+                        .collect::<Vec<_>>()
+                })
+                .unwrap_or_default();
+            let v6 = map_v6
+                .get(&dc)
+                .map(|items| {
+                    items
+                        .iter()
+                        .map(|(ip, port)| SocketAddr::new(*ip, *port))
+                        .collect::<Vec<_>>()
+                })
+                .unwrap_or_default();
+
+            let mut selected = if decision.effective_multipath {
+                let mut both = Vec::<SocketAddr>::with_capacity(v4.len().saturating_add(v6.len()));
+                if decision.prefer_ipv6() {
+                    both.extend(v6.iter().copied());
+                    both.extend(v4.iter().copied());
+                } else {
+                    both.extend(v4.iter().copied());
+                    both.extend(v6.iter().copied());
+                }
+                both
+            } else if decision.prefer_ipv6() {
+                if !v6.is_empty() { v6 } else { v4 }
+            } else if !v4.is_empty() {
+                v4
+            } else {
+                v6
+            };
+
+            selected.sort_unstable();
+            selected.dedup();
+            out.insert(dc, selected);
+        }
+
+        out
+    }
+
     fn build_endpoint_dc_map_from_maps(
         map_v4: &HashMap<i32, Vec<(IpAddr, u16)>>,
         map_v6: &HashMap<i32, Vec<(IpAddr, u16)>>,
@@ -852,6 +1177,25 @@ impl MePool {
         let map_v4 = self.proxy_map_v4.read().await.clone();
         let map_v6 = self.proxy_map_v6.read().await.clone();
         let rebuilt = Self::build_endpoint_dc_map_from_maps(&map_v4, &map_v6);
+        let preferred = Self::build_preferred_endpoints_by_dc(&self.decision, &map_v4, &map_v6);
         *self.endpoint_dc_map.write().await = rebuilt;
+        *self.preferred_endpoints_by_dc.write().await = preferred;
+    }
+
+    pub(super) async fn preferred_endpoints_for_dc(&self, dc: i32) -> Vec<SocketAddr> {
+        let guard = self.preferred_endpoints_by_dc.read().await;
+        guard.get(&dc).cloned().unwrap_or_default()
+    }
+
+    pub(super) fn health_interval_unhealthy(&self) -> Duration {
+        Duration::from_millis(self.me_health_interval_ms_unhealthy.load(Ordering::Relaxed).max(1))
+    }
+
+    pub(super) fn health_interval_healthy(&self) -> Duration {
+        Duration::from_millis(self.me_health_interval_ms_healthy.load(Ordering::Relaxed).max(1))
+    }
+
+    pub(super) fn warn_rate_limit_duration(&self) -> Duration {
+        Duration::from_millis(self.me_warn_rate_limit_ms.load(Ordering::Relaxed).max(1))
     }
 }

src/transport/middle_proxy/pool_config.rs

@@ -110,7 +110,10 @@ impl MePool {
     pub async fn reconnect_all(self: &Arc<Self>) {
         let ws = self.writers.read().await.clone();
         for w in ws {
-            if let Ok(()) = self.connect_one(w.addr, self.rng.as_ref()).await {
+            if let Ok(()) = self
+                .connect_one_for_dc(w.addr, w.writer_dc, self.rng.as_ref())
+                .await
+            {
                 self.mark_writer_draining(w.id).await;
                 tokio::time::sleep(Duration::from_secs(2)).await;
             }

src/transport/middle_proxy/pool_init.rs

@@ -55,7 +55,11 @@ impl MePool {
                     .iter()
                     .map(|(ip, port)| SocketAddr::new(*ip, *port))
                     .collect();
-                if self.active_writer_count_for_endpoints(&endpoints).await >= target_writers {
+                if self
+                    .active_writer_count_for_dc_endpoints(dc, &endpoints)
+                    .await
+                    >= target_writers
+                {
                     continue;
                 }
                 let pool = Arc::clone(self);
@@ -67,6 +71,7 @@ impl MePool {
                         target_writers,
                         rng_clone,
                         connect_concurrency,
+                        true,
                     )
                     .await
                 });
@@ -79,7 +84,7 @@ impl MePool {
                     .iter()
                     .map(|(ip, port)| SocketAddr::new(*ip, *port))
                     .collect();
-                if self.active_writer_count_for_endpoints(&endpoints).await == 0 {
+                if self.active_writer_count_for_dc_endpoints(*dc, &endpoints).await == 0 {
                     missing_dcs.push(*dc);
                 }
             }
@@ -110,6 +115,7 @@ impl MePool {
                                 target_writers,
                                 rng_clone_local,
                                 connect_concurrency,
+                                false,
                             )
                             .await
                     });
@@ -143,6 +149,7 @@ impl MePool {
         target_writers: usize,
         rng: Arc<SecureRandom>,
         connect_concurrency: usize,
+        allow_coverage_override: bool,
     ) -> bool {
         if addrs.is_empty() {
             return false;
@@ -156,7 +163,9 @@ impl MePool {
         let endpoint_set: HashSet<SocketAddr> = endpoints.iter().copied().collect();
 
         loop {
-            let alive = self.active_writer_count_for_endpoints(&endpoint_set).await;
+            let alive = self
+                .active_writer_count_for_dc_endpoints(dc, &endpoint_set)
+                .await;
             if alive >= target_writers {
                 info!(
                     dc = %dc,
@@ -174,9 +183,17 @@ impl MePool {
                 let pool = Arc::clone(&self);
                 let rng_clone = Arc::clone(&rng);
                 let endpoints_clone = endpoints.clone();
+                let generation = self.current_generation();
                 join.spawn(async move {
-                    pool.connect_endpoints_round_robin(&endpoints_clone, rng_clone.as_ref())
+                    pool.connect_endpoints_round_robin_with_generation_contour(
-                        .await
+                        dc,
+                        &endpoints_clone,
+                        rng_clone.as_ref(),
+                        generation,
+                        super::pool::WriterContour::Active,
+                        allow_coverage_override,
+                    )
+                    .await
                 });
             }
 
@@ -193,7 +210,9 @@ impl MePool {
                 }
             }
 
-            let alive_after = self.active_writer_count_for_endpoints(&endpoint_set).await;
+            let alive_after = self
+                .active_writer_count_for_dc_endpoints(dc, &endpoint_set)
+                .await;
             if alive_after >= target_writers {
                 info!(
                     dc = %dc,
@@ -204,12 +223,25 @@ impl MePool {
                 return true;
             }
             if !progress {
-                warn!(
+                let active_writers_current = self.active_contour_writer_count_total().await;
-                    dc = %dc,
+                let active_cap_configured = self.adaptive_floor_active_cap_configured_total();
-                    alive = alive_after,
+                if !allow_coverage_override && active_writers_current >= active_cap_configured {
-                    target_writers,
+                    info!(
-                    "All ME servers for DC failed at init"
+                        dc = %dc,
-                );
+                        alive = alive_after,
+                        target_writers,
+                        active_writers_current,
+                        active_cap_configured,
+                        "ME init saturation stopped by active writer cap"
+                    );
+                } else {
+                    warn!(
+                        dc = %dc,
+                        alive = alive_after,
+                        target_writers,
+                        "All ME servers for DC failed at init"
+                    );
+                }
                 return false;
             }
 

src/transport/middle_proxy/pool_refill.rs

@@ -1,4 +1,4 @@
-use std::collections::HashSet;
+use std::collections::{HashMap, HashSet};
 use std::net::SocketAddr;
 use std::sync::Arc;
 use std::sync::atomic::Ordering;
@@ -9,7 +9,7 @@ use tracing::{debug, info, warn};
 use crate::crypto::SecureRandom;
 use crate::network::IpFamily;
 
-use super::pool::{MePool, RefillDcKey, WriterContour};
+use super::pool::{MePool, RefillDcKey, RefillEndpointKey, WriterContour};
 
 const ME_FLAP_UPTIME_THRESHOLD_SECS: u64 = 20;
 const ME_FLAP_QUARANTINE_SECS: u64 = 25;
@@ -82,82 +82,79 @@ impl MePool {
         Vec::new()
     }
 
-    pub(super) async fn has_refill_inflight_for_endpoints(&self, endpoints: &[SocketAddr]) -> bool {
+    pub(super) async fn has_refill_inflight_for_dc_key(&self, key: RefillDcKey) -> bool {
-        if endpoints.is_empty() {
-            return false;
-        }
-
-        {
-            let guard = self.refill_inflight.lock().await;
-            if endpoints.iter().any(|addr| guard.contains(addr)) {
-                return true;
-            }
-        }
-
-        let dc_keys = self.resolve_refill_dc_keys_for_endpoints(endpoints).await;
-        if dc_keys.is_empty() {
-            return false;
-        }
         let guard = self.refill_inflight_dc.lock().await;
-        dc_keys.iter().any(|key| guard.contains(key))
+        guard.contains(&key)
-    }
-
-    async fn resolve_refill_dc_key_for_addr(&self, addr: SocketAddr) -> Option<RefillDcKey> {
-        let family = if addr.is_ipv4() {
-            IpFamily::V4
-        } else {
-            IpFamily::V6
-        };
-        Some(RefillDcKey {
-            dc: self.resolve_dc_for_endpoint(addr).await,
-            family,
-        })
-    }
-
-    async fn resolve_refill_dc_keys_for_endpoints(
-        &self,
-        endpoints: &[SocketAddr],
-    ) -> HashSet<RefillDcKey> {
-        let mut out = HashSet::<RefillDcKey>::new();
-        for addr in endpoints {
-            if let Some(key) = self.resolve_refill_dc_key_for_addr(*addr).await {
-                out.insert(key);
-            }
-        }
-        out
     }
 
     pub(super) async fn connect_endpoints_round_robin(
         self: &Arc<Self>,
+        dc: i32,
         endpoints: &[SocketAddr],
         rng: &SecureRandom,
     ) -> bool {
         self.connect_endpoints_round_robin_with_generation_contour(
+            dc,
             endpoints,
             rng,
             self.current_generation(),
             WriterContour::Active,
+            false,
         )
         .await
     }
 
     pub(super) async fn connect_endpoints_round_robin_with_generation_contour(
         self: &Arc<Self>,
+        dc: i32,
         endpoints: &[SocketAddr],
         rng: &SecureRandom,
         generation: u64,
         contour: WriterContour,
+        allow_coverage_override: bool,
     ) -> bool {
-        let candidates = self.connectable_endpoints(endpoints).await;
+        let mut candidates = self.connectable_endpoints(endpoints).await;
         if candidates.is_empty() {
             return false;
         }
+        if candidates.len() > 1 {
+            let mut active_by_endpoint = HashMap::<SocketAddr, usize>::new();
+            let ws = self.writers.read().await;
+            for writer in ws.iter() {
+                if writer.draining.load(Ordering::Relaxed) {
+                    continue;
+                }
+                if writer.writer_dc != dc {
+                    continue;
+                }
+                if !matches!(
+                    super::pool::WriterContour::from_u8(
+                        writer.contour.load(Ordering::Relaxed),
+                    ),
+                    super::pool::WriterContour::Active
+                ) {
+                    continue;
+                }
+                if candidates.contains(&writer.addr) {
+                    *active_by_endpoint.entry(writer.addr).or_insert(0) += 1;
+                }
+            }
+            drop(ws);
+            candidates.sort_by_key(|addr| (active_by_endpoint.get(addr).copied().unwrap_or(0), *addr));
+        }
         let start = (self.rr.fetch_add(1, Ordering::Relaxed) as usize) % candidates.len();
         for offset in 0..candidates.len() {
             let idx = (start + offset) % candidates.len();
             let addr = candidates[idx];
             match self
-                .connect_one_with_generation_contour(addr, rng, generation, contour)
+                .connect_one_with_generation_contour_for_dc_with_cap_policy(
+                    addr,
+                    rng,
+                    generation,
+                    contour,
+                    dc,
+                    allow_coverage_override,
+                )
                 .await
             {
                 Ok(()) => return true,
@@ -167,9 +164,8 @@ impl MePool {
         false
     }
 
-    async fn endpoints_for_same_dc(&self, addr: SocketAddr) -> Vec<SocketAddr> {
+    async fn endpoints_for_dc(&self, target_dc: i32) -> Vec<SocketAddr> {
         let mut endpoints = HashSet::<SocketAddr>::new();
-        let target_dc = self.resolve_dc_for_endpoint(addr).await;
 
         if self.decision.ipv4_me {
             let map = self.proxy_map_v4.read().await;
@@ -194,14 +190,14 @@ impl MePool {
         sorted
     }
 
-    async fn refill_writer_after_loss(self: &Arc<Self>, addr: SocketAddr) -> bool {
+    async fn refill_writer_after_loss(self: &Arc<Self>, addr: SocketAddr, writer_dc: i32) -> bool {
         let fast_retries = self.me_reconnect_fast_retry_count.max(1);
         let same_endpoint_quarantined = self.is_endpoint_quarantined(addr).await;
 
         if !same_endpoint_quarantined {
             for attempt in 0..fast_retries {
                 self.stats.increment_me_reconnect_attempt();
-                match self.connect_one(addr, self.rng.as_ref()).await {
+                match self.connect_one_for_dc(addr, writer_dc, self.rng.as_ref()).await {
                     Ok(()) => {
                         self.stats.increment_me_reconnect_success();
                         self.stats.increment_me_writer_restored_same_endpoint_total();
@@ -229,7 +225,7 @@ impl MePool {
             );
         }
 
-        let dc_endpoints = self.endpoints_for_same_dc(addr).await;
+        let dc_endpoints = self.endpoints_for_dc(writer_dc).await;
         if dc_endpoints.is_empty() {
             self.stats.increment_me_refill_failed_total();
             return false;
@@ -238,7 +234,7 @@ impl MePool {
         for attempt in 0..fast_retries {
             self.stats.increment_me_reconnect_attempt();
             if self
-                .connect_endpoints_round_robin(&dc_endpoints, self.rng.as_ref())
+                .connect_endpoints_round_robin(writer_dc, &dc_endpoints, self.rng.as_ref())
                 .await
             {
                 self.stats.increment_me_reconnect_success();
@@ -256,48 +252,63 @@ impl MePool {
         false
     }
 
-    pub(crate) fn trigger_immediate_refill(self: &Arc<Self>, addr: SocketAddr) {
+    pub(crate) fn trigger_immediate_refill_for_dc(self: &Arc<Self>, addr: SocketAddr, writer_dc: i32) {
+        let endpoint_key = RefillEndpointKey {
+            dc: writer_dc,
+            addr,
+        };
+        let pre_inserted = if let Ok(mut guard) = self.refill_inflight.try_lock() {
+            if !guard.insert(endpoint_key) {
+                self.stats.increment_me_refill_skipped_inflight_total();
+                return;
+            }
+            true
+        } else {
+            false
+        };
+
         let pool = Arc::clone(self);
         tokio::spawn(async move {
-            let dc_endpoints = pool.endpoints_for_same_dc(addr).await;
+            let dc_key = RefillDcKey {
-            let dc_keys = pool.resolve_refill_dc_keys_for_endpoints(&dc_endpoints).await;
+                dc: writer_dc,
+                family: if addr.is_ipv4() {
+                    IpFamily::V4
+                } else {
+                    IpFamily::V6
+                },
+            };
 
-            {
+            if !pre_inserted {
                 let mut guard = pool.refill_inflight.lock().await;
-                if !guard.insert(addr) {
+                if !guard.insert(endpoint_key) {
                     pool.stats.increment_me_refill_skipped_inflight_total();
                     return;
                 }
             }
 
-            if !dc_keys.is_empty() {
+            {
                 let mut dc_guard = pool.refill_inflight_dc.lock().await;
-                if dc_keys.iter().any(|key| dc_guard.contains(key)) {
+                if dc_guard.contains(&dc_key) {
                     pool.stats.increment_me_refill_skipped_inflight_total();
                     drop(dc_guard);
                     let mut guard = pool.refill_inflight.lock().await;
-                    guard.remove(&addr);
+                    guard.remove(&endpoint_key);
                     return;
                 }
-                dc_guard.extend(dc_keys.iter().copied());
+                dc_guard.insert(dc_key);
             }
 
             pool.stats.increment_me_refill_triggered_total();
-
+            let restored = pool.refill_writer_after_loss(addr, writer_dc).await;
-            let restored = pool.refill_writer_after_loss(addr).await;
             if !restored {
-                warn!(%addr, "ME immediate refill failed");
+                warn!(%addr, dc = writer_dc, "ME immediate refill failed");
             }
 
             let mut guard = pool.refill_inflight.lock().await;
-            guard.remove(&addr);
+            guard.remove(&endpoint_key);
             drop(guard);
-            if !dc_keys.is_empty() {
+            let mut dc_guard = pool.refill_inflight_dc.lock().await;
-                let mut dc_guard = pool.refill_inflight_dc.lock().await;
+            dc_guard.remove(&dc_key);
-                for key in &dc_keys {
-                    dc_guard.remove(key);
-                }
-            }
         });
     }
 }

src/transport/middle_proxy/pool_reinit.rs

@@ -62,7 +62,7 @@ impl MePool {
 
     fn coverage_ratio(
         desired_by_dc: &HashMap<i32, HashSet<SocketAddr>>,
-        active_writer_addrs: &HashSet<SocketAddr>,
+        active_writer_addrs: &HashSet<(i32, SocketAddr)>,
     ) -> (f32, Vec<i32>) {
         if desired_by_dc.is_empty() {
             return (1.0, Vec::new());
@@ -76,7 +76,7 @@ impl MePool {
             }
             if endpoints
                 .iter()
-                .any(|addr| active_writer_addrs.contains(addr))
+                .any(|addr| active_writer_addrs.contains(&(*dc, *addr)))
             {
                 covered += 1;
             } else {
@@ -91,32 +91,25 @@ impl MePool {
     }
 
     pub async fn reconcile_connections(self: &Arc<Self>, rng: &SecureRandom) {
-        let writers = self.writers.read().await;
-        let current: HashSet<SocketAddr> = writers
-            .iter()
-            .filter(|w| !w.draining.load(Ordering::Relaxed))
-            .map(|w| w.addr)
-            .collect();
-        drop(writers);
-
         for family in self.family_order() {
             let map = self.proxy_map_for_family(family).await;
-            for (_dc, addrs) in &map {
+            for (dc, addrs) in &map {
                 let dc_addrs: Vec<SocketAddr> = addrs
                     .iter()
                     .map(|(ip, port)| SocketAddr::new(*ip, *port))
                     .collect();
-                if !dc_addrs.iter().any(|a| current.contains(a)) {
+                let dc_endpoints: HashSet<SocketAddr> = dc_addrs.iter().copied().collect();
+                if self.active_writer_count_for_dc_endpoints(*dc, &dc_endpoints).await == 0 {
                     let mut shuffled = dc_addrs.clone();
                     shuffled.shuffle(&mut rand::rng());
                     for addr in shuffled {
-                        if self.connect_one(addr, rng).await.is_ok() {
+                        if self.connect_one_for_dc(addr, *dc, rng).await.is_ok() {
                             break;
                         }
                     }
                 }
             }
-            if !self.decision.effective_multipath && !current.is_empty() {
+            if !self.decision.effective_multipath && self.connection_count() > 0 {
                 break;
             }
         }
@@ -174,26 +167,30 @@ impl MePool {
         core.saturating_add(rand::rng().random_range(0..=jitter))
     }
 
-    async fn fresh_writer_count_for_endpoints(
+    async fn fresh_writer_count_for_dc_endpoints(
         &self,
         generation: u64,
+        dc: i32,
         endpoints: &HashSet<SocketAddr>,
     ) -> usize {
         let ws = self.writers.read().await;
         ws.iter()
             .filter(|w| !w.draining.load(Ordering::Relaxed))
             .filter(|w| w.generation == generation)
+            .filter(|w| w.writer_dc == dc)
             .filter(|w| endpoints.contains(&w.addr))
             .count()
     }
 
-    pub(super) async fn active_writer_count_for_endpoints(
+    pub(super) async fn active_writer_count_for_dc_endpoints(
         &self,
+        dc: i32,
         endpoints: &HashSet<SocketAddr>,
     ) -> usize {
         let ws = self.writers.read().await;
         ws.iter()
             .filter(|w| !w.draining.load(Ordering::Relaxed))
+            .filter(|w| w.writer_dc == dc)
             .filter(|w| endpoints.contains(&w.addr))
             .count()
     }
@@ -220,7 +217,7 @@ impl MePool {
             let required = self.required_writers_for_dc(endpoint_list.len());
             let mut completed = false;
             let mut last_fresh_count = self
-                .fresh_writer_count_for_endpoints(generation, endpoints)
+                .fresh_writer_count_for_dc_endpoints(generation, *dc, endpoints)
                 .await;
 
             for pass_idx in 0..total_passes {
@@ -247,10 +244,12 @@ impl MePool {
 
                     let connected = self
                         .connect_endpoints_round_robin_with_generation_contour(
+                            *dc,
                             &endpoint_list,
                             rng,
                             generation,
                             WriterContour::Warm,
+                            false,
                         )
                         .await;
                     debug!(
@@ -265,7 +264,7 @@ impl MePool {
                 }
 
                 last_fresh_count = self
-                    .fresh_writer_count_for_endpoints(generation, endpoints)
+                    .fresh_writer_count_for_dc_endpoints(generation, *dc, endpoints)
                     .await;
                 if last_fresh_count >= required {
                     completed = true;
@@ -377,10 +376,10 @@ impl MePool {
         }
 
         let writers = self.writers.read().await;
-        let active_writer_addrs: HashSet<SocketAddr> = writers
+        let active_writer_addrs: HashSet<(i32, SocketAddr)> = writers
             .iter()
             .filter(|w| !w.draining.load(Ordering::Relaxed))
-            .map(|w| w.addr)
+            .map(|w| (w.writer_dc, w.addr))
             .collect();
         let min_ratio = Self::permille_to_ratio(
             self.me_pool_min_fresh_ratio_permille
@@ -410,6 +409,7 @@ impl MePool {
                     .iter()
                     .filter(|w| !w.draining.load(Ordering::Relaxed))
                     .filter(|w| w.generation == generation)
+                    .filter(|w| w.writer_dc == *dc)
                     .filter(|w| endpoints.contains(&w.addr))
                     .count();
                 if fresh_count < required {
@@ -438,9 +438,9 @@ impl MePool {
             self.promote_warm_generation_to_active(generation).await;
         }
 
-        let desired_addrs: HashSet<SocketAddr> = desired_by_dc
+        let desired_addrs: HashSet<(i32, SocketAddr)> = desired_by_dc
-            .values()
+            .iter()
-            .flat_map(|set| set.iter().copied())
+            .flat_map(|(dc, set)| set.iter().copied().map(|addr| (*dc, addr)))
             .collect();
 
         let stale_writer_ids: Vec<u64> = writers
@@ -450,7 +450,7 @@ impl MePool {
                 if hardswap {
                     w.generation < generation
                 } else {
-                    !desired_addrs.contains(&w.addr)
+                    !desired_addrs.contains(&(w.writer_dc, w.addr))
                 }
             })
             .map(|w| w.id)

src/transport/middle_proxy/pool_status.rs

@@ -25,6 +25,7 @@ pub(crate) struct MeApiWriterStatusSnapshot {
 pub(crate) struct MeApiDcStatusSnapshot {
     pub dc: i16,
     pub endpoints: Vec<SocketAddr>,
+    pub endpoint_writers: Vec<MeApiDcEndpointWriterSnapshot>,
     pub available_endpoints: usize,
     pub available_pct: f64,
     pub required_writers: usize,
@@ -38,6 +39,12 @@ pub(crate) struct MeApiDcStatusSnapshot {
     pub load: usize,
 }
 
+#[derive(Clone, Debug)]
+pub(crate) struct MeApiDcEndpointWriterSnapshot {
+    pub endpoint: SocketAddr,
+    pub active_writers: usize,
+}
+
 #[derive(Clone, Debug)]
 pub(crate) struct MeApiStatusSnapshot {
     pub generated_at_epoch_secs: u64,
@@ -82,11 +89,21 @@ pub(crate) struct MeApiRuntimeSnapshot {
     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_max_active_writers_per_core: u16,
+    pub adaptive_floor_max_warm_writers_per_core: u16,
+    pub adaptive_floor_max_active_writers_global: u32,
+    pub adaptive_floor_max_warm_writers_global: u32,
     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 adaptive_floor_active_cap_configured: u64,
+    pub adaptive_floor_active_cap_effective: u64,
+    pub adaptive_floor_warm_cap_configured: u64,
+    pub adaptive_floor_warm_cap_effective: u64,
+    pub adaptive_floor_active_writers_current: u64,
+    pub adaptive_floor_warm_writers_current: u64,
     pub me_keepalive_enabled: bool,
     pub me_keepalive_interval_secs: u64,
     pub me_keepalive_jitter_secs: u64,
@@ -108,6 +125,8 @@ pub(crate) struct MeApiRuntimeSnapshot {
     pub me_single_endpoint_outage_backoff_max_ms: u64,
     pub me_single_endpoint_shadow_rotate_every_secs: u64,
     pub me_deterministic_writer_sort: bool,
+    pub me_writer_pick_mode: &'static str,
+    pub me_writer_pick_sample_size: u8,
     pub me_socks_kdf_policy: &'static str,
     pub quarantined_endpoints: Vec<MeApiQuarantinedEndpointSnapshot>,
     pub network_path: Vec<MeApiDcPathSnapshot>,
@@ -130,19 +149,18 @@ impl MePool {
         }
 
         let writers = self.writers.read().await.clone();
-        let mut live_writers_by_endpoint = HashMap::<SocketAddr, usize>::new();
+        let mut live_writers_by_dc = HashMap::<i16, usize>::new();
         for writer in writers {
             if writer.draining.load(Ordering::Relaxed) {
                 continue;
             }
-            *live_writers_by_endpoint.entry(writer.addr).or_insert(0) += 1;
+            if let Ok(dc) = i16::try_from(writer.writer_dc) {
+                *live_writers_by_dc.entry(dc).or_insert(0) += 1;
+            }
         }
 
-        for endpoints in endpoints_by_dc.values() {
+        for dc in endpoints_by_dc.keys() {
-            let alive: usize = endpoints
+            let alive = live_writers_by_dc.get(dc).copied().unwrap_or(0);
-                .iter()
-                .map(|endpoint| live_writers_by_endpoint.get(endpoint).copied().unwrap_or(0))
-                .sum();
             if alive == 0 {
                 return false;
             }
@@ -168,24 +186,23 @@ impl MePool {
         }
 
         let writers = self.writers.read().await.clone();
-        let mut live_writers_by_endpoint = HashMap::<SocketAddr, usize>::new();
+        let mut live_writers_by_dc = HashMap::<i16, usize>::new();
         for writer in writers {
             if writer.draining.load(Ordering::Relaxed) {
                 continue;
             }
-            *live_writers_by_endpoint.entry(writer.addr).or_insert(0) += 1;
+            if let Ok(dc) = i16::try_from(writer.writer_dc) {
+                *live_writers_by_dc.entry(dc).or_insert(0) += 1;
+            }
         }
 
-        for endpoints in endpoints_by_dc.values() {
+        for (dc, endpoints) in endpoints_by_dc {
             let endpoint_count = endpoints.len();
             if endpoint_count == 0 {
                 return false;
             }
             let required = self.required_writers_for_dc_with_floor_mode(endpoint_count, false);
-            let alive: usize = endpoints
+            let alive = live_writers_by_dc.get(&dc).copied().unwrap_or(0);
-                .iter()
-                .map(|endpoint| live_writers_by_endpoint.get(endpoint).copied().unwrap_or(0))
-                .sum();
             if alive < required {
                 return false;
             }
@@ -207,13 +224,6 @@ impl MePool {
             extend_signed_endpoints(&mut endpoints_by_dc, map);
         }
 
-        let mut endpoint_to_dc = HashMap::<SocketAddr, BTreeSet<i16>>::new();
-        for (dc, endpoints) in &endpoints_by_dc {
-            for endpoint in endpoints {
-                endpoint_to_dc.entry(*endpoint).or_default().insert(*dc);
-            }
-        }
-
         let configured_dc_groups = endpoints_by_dc.len();
         let configured_endpoints = endpoints_by_dc.values().map(BTreeSet::len).sum();
 
@@ -227,20 +237,14 @@ impl MePool {
         let rtt = self.rtt_stats.lock().await.clone();
         let writers = self.writers.read().await.clone();
 
-        let mut live_writers_by_endpoint = HashMap::<SocketAddr, usize>::new();
+        let mut live_writers_by_dc_endpoint = HashMap::<(i16, SocketAddr), usize>::new();
         let mut live_writers_by_dc = HashMap::<i16, usize>::new();
         let mut dc_rtt_agg = HashMap::<i16, (f64, u64)>::new();
         let mut writer_rows = Vec::<MeApiWriterStatusSnapshot>::with_capacity(writers.len());
 
         for writer in writers {
             let endpoint = writer.addr;
-            let dc = endpoint_to_dc.get(&endpoint).and_then(|dcs| {
+            let dc = i16::try_from(writer.writer_dc).ok();
-                if dcs.len() == 1 {
-                    dcs.iter().next().copied()
-                } else {
-                    None
-                }
-            });
             let draining = writer.draining.load(Ordering::Relaxed);
             let degraded = writer.degraded.load(Ordering::Relaxed);
             let bound_clients = activity
@@ -259,8 +263,10 @@ impl MePool {
             };
 
             if !draining {
-                *live_writers_by_endpoint.entry(endpoint).or_insert(0) += 1;
                 if let Some(dc_idx) = dc {
+                    *live_writers_by_dc_endpoint
+                        .entry((dc_idx, endpoint))
+                        .or_insert(0) += 1;
                     *live_writers_by_dc.entry(dc_idx).or_insert(0) += 1;
                     if let Some(ema_ms) = rtt_ema_ms {
                         let entry = dc_rtt_agg.entry(dc_idx).or_insert((0.0, 0));
@@ -298,7 +304,7 @@ impl MePool {
             let endpoint_count = endpoints.len();
             let dc_available_endpoints = endpoints
                 .iter()
-                .filter(|endpoint| live_writers_by_endpoint.contains_key(endpoint))
+                .filter(|endpoint| live_writers_by_dc_endpoint.contains_key(&(dc, **endpoint)))
                 .count();
             let base_required = self.required_writers_for_dc(endpoint_count);
             let dc_required_writers =
@@ -341,6 +347,16 @@ impl MePool {
 
             dcs.push(MeApiDcStatusSnapshot {
                 dc,
+                endpoint_writers: endpoints
+                    .iter()
+                    .map(|endpoint| MeApiDcEndpointWriterSnapshot {
+                        endpoint: *endpoint,
+                        active_writers: live_writers_by_dc_endpoint
+                            .get(&(dc, *endpoint))
+                            .copied()
+                            .unwrap_or(0),
+                    })
+                    .collect(),
                 endpoints: endpoints.into_iter().collect(),
                 available_endpoints: dc_available_endpoints,
                 available_pct: ratio_pct(dc_available_endpoints, endpoint_count),
@@ -443,6 +459,18 @@ impl MePool {
             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_max_active_writers_per_core: self
+                .me_adaptive_floor_max_active_writers_per_core
+                .load(Ordering::Relaxed) as u16,
+            adaptive_floor_max_warm_writers_per_core: self
+                .me_adaptive_floor_max_warm_writers_per_core
+                .load(Ordering::Relaxed) as u16,
+            adaptive_floor_max_active_writers_global: self
+                .me_adaptive_floor_max_active_writers_global
+                .load(Ordering::Relaxed),
+            adaptive_floor_max_warm_writers_global: self
+                .me_adaptive_floor_max_warm_writers_global
+                .load(Ordering::Relaxed),
             adaptive_floor_cpu_cores_detected: self
                 .me_adaptive_floor_cpu_cores_detected
                 .load(Ordering::Relaxed),
@@ -458,6 +486,24 @@ impl MePool {
             adaptive_floor_target_writers_total: self
                 .me_adaptive_floor_target_writers_total
                 .load(Ordering::Relaxed),
+            adaptive_floor_active_cap_configured: self
+                .me_adaptive_floor_active_cap_configured
+                .load(Ordering::Relaxed),
+            adaptive_floor_active_cap_effective: self
+                .me_adaptive_floor_active_cap_effective
+                .load(Ordering::Relaxed),
+            adaptive_floor_warm_cap_configured: self
+                .me_adaptive_floor_warm_cap_configured
+                .load(Ordering::Relaxed),
+            adaptive_floor_warm_cap_effective: self
+                .me_adaptive_floor_warm_cap_effective
+                .load(Ordering::Relaxed),
+            adaptive_floor_active_writers_current: self
+                .me_adaptive_floor_active_writers_current
+                .load(Ordering::Relaxed),
+            adaptive_floor_warm_writers_current: self
+                .me_adaptive_floor_warm_writers_current
+                .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(),
@@ -495,6 +541,8 @@ impl MePool {
             me_deterministic_writer_sort: self
                 .me_deterministic_writer_sort
                 .load(Ordering::Relaxed),
+            me_writer_pick_mode: writer_pick_mode_label(self.writer_pick_mode()),
+            me_writer_pick_sample_size: self.writer_pick_sample_size() as u8,
             me_socks_kdf_policy: socks_kdf_policy_label(self.socks_kdf_policy()),
             quarantined_endpoints,
             network_path,
@@ -543,6 +591,13 @@ fn bind_stale_mode_label(mode: MeBindStaleMode) -> &'static str {
     }
 }
 
+fn writer_pick_mode_label(mode: crate::config::MeWriterPickMode) -> &'static str {
+    match mode {
+        crate::config::MeWriterPickMode::SortedRr => "sorted_rr",
+        crate::config::MeWriterPickMode::P2c => "p2c",
+    }
+}
+
 fn socks_kdf_policy_label(policy: MeSocksKdfPolicy) -> &'static str {
     match policy {
         MeSocksKdfPolicy::Strict => "strict",

src/transport/middle_proxy/pool_writer.rs

@@ -1,9 +1,10 @@
 use std::net::SocketAddr;
 use std::sync::Arc;
-use std::sync::atomic::{AtomicBool, AtomicU8, AtomicU64, Ordering};
+use std::sync::atomic::{AtomicBool, AtomicU8, AtomicU32, AtomicU64, Ordering};
 use std::time::{Duration, Instant};
 use std::io::ErrorKind;
 
+use bytes::Bytes;
 use bytes::BytesMut;
 use rand::Rng;
 use tokio::sync::mpsc;
@@ -49,12 +50,18 @@ impl MePool {
         }
     }
 
-    pub(crate) async fn connect_one(self: &Arc<Self>, addr: SocketAddr, rng: &SecureRandom) -> Result<()> {
+    pub(crate) async fn connect_one_for_dc(
+        self: &Arc<Self>,
+        addr: SocketAddr,
+        writer_dc: i32,
+        rng: &SecureRandom,
+    ) -> Result<()> {
         self.connect_one_with_generation_contour(
             addr,
             rng,
             self.current_generation(),
             WriterContour::Active,
+            writer_dc,
         )
         .await
     }
@@ -65,23 +72,68 @@ impl MePool {
         rng: &SecureRandom,
         generation: u64,
         contour: WriterContour,
+        writer_dc: i32,
     ) -> Result<()> {
+        self.connect_one_with_generation_contour_for_dc(addr, rng, generation, contour, writer_dc)
+            .await
+    }
+
+    pub(super) async fn connect_one_with_generation_contour_for_dc(
+        self: &Arc<Self>,
+        addr: SocketAddr,
+        rng: &SecureRandom,
+        generation: u64,
+        contour: WriterContour,
+        writer_dc: i32,
+    ) -> Result<()> {
+        self.connect_one_with_generation_contour_for_dc_with_cap_policy(
+            addr,
+            rng,
+            generation,
+            contour,
+            writer_dc,
+            false,
+        )
+        .await
+    }
+
+    pub(super) async fn connect_one_with_generation_contour_for_dc_with_cap_policy(
+        self: &Arc<Self>,
+        addr: SocketAddr,
+        rng: &SecureRandom,
+        generation: u64,
+        contour: WriterContour,
+        writer_dc: i32,
+        allow_coverage_override: bool,
+    ) -> Result<()> {
+        if !self
+            .can_open_writer_for_contour(contour, allow_coverage_override)
+            .await
+        {
+            return Err(ProxyError::Proxy(format!(
+                "ME {contour:?} writer cap reached"
+            )));
+        }
+
         let secret_len = self.proxy_secret.read().await.secret.len();
         if secret_len < 32 {
             return Err(ProxyError::Proxy("proxy-secret too short for ME auth".into()));
         }
 
-        let (stream, _connect_ms, upstream_egress) = self.connect_tcp(addr).await?;
+        let dc_idx = i16::try_from(writer_dc).ok();
+        let (stream, _connect_ms, upstream_egress) = self.connect_tcp(addr, dc_idx).await?;
         let hs = self.handshake_only(stream, addr, upstream_egress, rng).await?;
 
         let writer_id = self.next_writer_id.fetch_add(1, Ordering::Relaxed);
         let contour = Arc::new(AtomicU8::new(contour.as_u8()));
         let cancel = CancellationToken::new();
         let degraded = Arc::new(AtomicBool::new(false));
+        let rtt_ema_ms_x10 = Arc::new(AtomicU32::new(0));
         let draining = Arc::new(AtomicBool::new(false));
         let draining_started_at_epoch_secs = Arc::new(AtomicU64::new(0));
+        let drain_deadline_epoch_secs = Arc::new(AtomicU64::new(0));
         let allow_drain_fallback = Arc::new(AtomicBool::new(false));
-        let (tx, mut rx) = mpsc::channel::<WriterCommand>(4096);
+        let (tx, mut rx) = mpsc::channel::<WriterCommand>(self.writer_cmd_channel_capacity);
         let mut rpc_writer = RpcWriter {
             writer: hs.wr,
             key: hs.write_key,
@@ -111,14 +163,17 @@ impl MePool {
         let writer = MeWriter {
             id: writer_id,
             addr,
+            writer_dc,
             generation,
             contour: contour.clone(),
             created_at: Instant::now(),
             tx: tx.clone(),
             cancel: cancel.clone(),
             degraded: degraded.clone(),
+            rtt_ema_ms_x10: rtt_ema_ms_x10.clone(),
             draining: draining.clone(),
             draining_started_at_epoch_secs: draining_started_at_epoch_secs.clone(),
+            drain_deadline_epoch_secs: drain_deadline_epoch_secs.clone(),
             allow_drain_fallback: allow_drain_fallback.clone(),
         };
         self.writers.write().await.push(writer.clone());
@@ -169,6 +224,7 @@ impl MePool {
                 stats_reader,
                 writer_id,
                 degraded.clone(),
+                rtt_ema_ms_x10.clone(),
                 cancel_reader_token.clone(),
             )
             .await;
@@ -254,17 +310,47 @@ impl MePool {
                 p.extend_from_slice(&sent_id.to_le_bytes());
                 {
                     let mut tracker = ping_tracker_ping.lock().await;
-                    let before = tracker.len();
+                    let now_epoch_ms = std::time::SystemTime::now()
-                    tracker.retain(|_, (ts, _)| ts.elapsed() < Duration::from_secs(120));
+                        .duration_since(std::time::UNIX_EPOCH)
-                    let expired = before.saturating_sub(tracker.len());
+                        .unwrap_or_default()
-                    if expired > 0 {
+                        .as_millis() as u64;
-                        stats_ping.increment_me_keepalive_timeout_by(expired as u64);
+                    let mut run_cleanup = false;
+                    if let Some(pool) = pool_ping.upgrade() {
+                        let last_cleanup_ms = pool
+                            .ping_tracker_last_cleanup_epoch_ms
+                            .load(Ordering::Relaxed);
+                        if now_epoch_ms.saturating_sub(last_cleanup_ms) >= 30_000
+                            && pool
+                                .ping_tracker_last_cleanup_epoch_ms
+                                .compare_exchange(
+                                    last_cleanup_ms,
+                                    now_epoch_ms,
+                                    Ordering::AcqRel,
+                                    Ordering::Relaxed,
+                                )
+                                .is_ok()
+                        {
+                            run_cleanup = true;
+                        }
+                    }
+
+                    if run_cleanup {
+                        let before = tracker.len();
+                        tracker.retain(|_, (ts, _)| ts.elapsed() < Duration::from_secs(120));
+                        let expired = before.saturating_sub(tracker.len());
+                        if expired > 0 {
+                            stats_ping.increment_me_keepalive_timeout_by(expired as u64);
+                        }
                     }
                     tracker.insert(sent_id, (std::time::Instant::now(), writer_id));
                 }
                 ping_id = ping_id.wrapping_add(1);
                 stats_ping.increment_me_keepalive_sent();
-                if tx_ping.send(WriterCommand::DataAndFlush(p)).await.is_err() {
+                if tx_ping
+                    .send(WriterCommand::DataAndFlush(Bytes::from(p)))
+                    .await
+                    .is_err()
+                {
                     stats_ping.increment_me_keepalive_failed();
                     debug!("ME ping failed, removing dead writer");
                     cancel_ping.cancel();
@@ -338,7 +424,11 @@ impl MePool {
                     meta.proto_flags,
                 );
 
-                if tx_signal.send(WriterCommand::DataAndFlush(payload)).await.is_err() {
+                if tx_signal
+                    .send(WriterCommand::DataAndFlush(payload))
+                    .await
+                    .is_err()
+                {
                     stats_signal.increment_me_rpc_proxy_req_signal_failed_total();
                     let _ = pool.registry.unregister(conn_id).await;
                     cancel_signal.cancel();
@@ -369,7 +459,7 @@ impl MePool {
                 close_payload.extend_from_slice(&conn_id.to_le_bytes());
 
                 if tx_signal
-                    .send(WriterCommand::DataAndFlush(close_payload))
+                    .send(WriterCommand::DataAndFlush(Bytes::from(close_payload)))
                     .await
                     .is_err()
                 {
@@ -404,6 +494,7 @@ impl MePool {
     async fn remove_writer_only(self: &Arc<Self>, writer_id: u64) -> Vec<BoundConn> {
         let mut close_tx: Option<mpsc::Sender<WriterCommand>> = None;
         let mut removed_addr: Option<SocketAddr> = None;
+        let mut removed_dc: Option<i32> = None;
         let mut removed_uptime: Option<Duration> = None;
         let mut trigger_refill = false;
         {
@@ -417,6 +508,7 @@ impl MePool {
                 self.stats.increment_me_writer_removed_total();
                 w.cancel.cancel();
                 removed_addr = Some(w.addr);
+                removed_dc = Some(w.writer_dc);
                 removed_uptime = Some(w.created_at.elapsed());
                 trigger_refill = !was_draining;
                 if trigger_refill {
@@ -431,11 +523,12 @@ impl MePool {
         }
         if trigger_refill
             && let Some(addr) = removed_addr
+            && let Some(writer_dc) = removed_dc
         {
             if let Some(uptime) = removed_uptime {
                 self.maybe_quarantine_flapping_endpoint(addr, uptime).await;
             }
-            self.trigger_immediate_refill(addr);
+            self.trigger_immediate_refill_for_dc(addr, writer_dc);
         }
         self.rtt_stats.lock().await.remove(&writer_id);
         self.registry.writer_lost(writer_id).await
@@ -454,8 +547,14 @@ impl MePool {
                 let already_draining = w.draining.swap(true, Ordering::Relaxed);
                 w.allow_drain_fallback
                     .store(allow_drain_fallback, Ordering::Relaxed);
+                let now_epoch_secs = Self::now_epoch_secs();
                 w.draining_started_at_epoch_secs
-                    .store(Self::now_epoch_secs(), Ordering::Relaxed);
+                    .store(now_epoch_secs, Ordering::Relaxed);
+                let drain_deadline_epoch_secs = timeout
+                    .map(|duration| now_epoch_secs.saturating_add(duration.as_secs()))
+                    .unwrap_or(0);
+                w.drain_deadline_epoch_secs
+                    .store(drain_deadline_epoch_secs, Ordering::Relaxed);
                 if !already_draining {
                     self.stats.increment_pool_drain_active();
                 }
@@ -479,26 +578,6 @@ impl MePool {
             allow_drain_fallback,
             "ME writer marked draining"
         );
-
-        let pool = Arc::downgrade(self);
-        tokio::spawn(async move {
-            let deadline = timeout.map(|t| Instant::now() + t);
-            while let Some(p) = pool.upgrade() {
-                if let Some(deadline_at) = deadline
-                    && Instant::now() >= deadline_at
-                {
-                    warn!(writer_id, "Drain timeout, force-closing");
-                    p.stats.increment_pool_force_close_total();
-                    let _ = p.remove_writer_and_close_clients(writer_id).await;
-                    break;
-                }
-                if p.registry.is_writer_empty(writer_id).await {
-                    let _ = p.remove_writer_only(writer_id).await;
-                    break;
-                }
-                tokio::time::sleep(Duration::from_secs(1)).await;
-            }
-        });
     }
 
     pub(crate) async fn mark_writer_draining(self: &Arc<Self>, writer_id: u64) {

src/transport/middle_proxy/reader.rs

@@ -1,7 +1,7 @@
 use std::collections::HashMap;
 use std::io::ErrorKind;
 use std::sync::Arc;
-use std::sync::atomic::{AtomicBool, Ordering};
+use std::sync::atomic::{AtomicBool, AtomicU32, Ordering};
 use std::time::Instant;
 
 use bytes::{Bytes, BytesMut};
@@ -34,6 +34,7 @@ pub(crate) async fn reader_loop(
     stats: Arc<Stats>,
     _writer_id: u64,
     degraded: Arc<AtomicBool>,
+    writer_rtt_ema_ms_x10: Arc<AtomicU32>,
     cancel: CancellationToken,
 ) -> Result<()> {
     let mut raw = enc_leftover;
@@ -181,7 +182,11 @@ pub(crate) async fn reader_loop(
                 let mut pong = Vec::with_capacity(12);
                 pong.extend_from_slice(&RPC_PONG_U32.to_le_bytes());
                 pong.extend_from_slice(&ping_id.to_le_bytes());
-                if tx.send(WriterCommand::DataAndFlush(pong)).await.is_err() {
+                if tx
+                    .send(WriterCommand::DataAndFlush(Bytes::from(pong)))
+                    .await
+                    .is_err()
+                {
                     warn!("PONG send failed");
                     break;
                 }
@@ -204,6 +209,8 @@ pub(crate) async fn reader_loop(
                     }
                     let degraded_now = entry.1 > entry.0 * 2.0;
                     degraded.store(degraded_now, Ordering::Relaxed);
+                    writer_rtt_ema_ms_x10
+                        .store((entry.1 * 10.0).clamp(0.0, u32::MAX as f64) as u32, Ordering::Relaxed);
                     trace!(writer_id = wid, rtt_ms = rtt, ema_ms = entry.1, base_ms = entry.0, degraded = degraded_now, "ME RTT sample");
                 }
             } else {
@@ -222,5 +229,5 @@ async fn send_close_conn(tx: &mpsc::Sender<WriterCommand>, conn_id: u64) {
     p.extend_from_slice(&RPC_CLOSE_CONN_U32.to_le_bytes());
     p.extend_from_slice(&conn_id.to_le_bytes());
 
-    let _ = tx.send(WriterCommand::DataAndFlush(p)).await;
+    let _ = tx.send(WriterCommand::DataAndFlush(Bytes::from(p))).await;
 }

src/transport/middle_proxy/registry.rs

@@ -9,7 +9,6 @@ use tokio::sync::mpsc::error::TrySendError;
 use super::codec::WriterCommand;
 use super::MeResponse;
 
-const ROUTE_CHANNEL_CAPACITY: usize = 4096;
 const ROUTE_BACKPRESSURE_BASE_TIMEOUT_MS: u64 = 25;
 const ROUTE_BACKPRESSURE_HIGH_TIMEOUT_MS: u64 = 120;
 const ROUTE_BACKPRESSURE_HIGH_WATERMARK_PCT: u8 = 80;
@@ -78,6 +77,7 @@ impl RegistryInner {
 pub struct ConnRegistry {
     inner: RwLock<RegistryInner>,
     next_id: AtomicU64,
+    route_channel_capacity: usize,
     route_backpressure_base_timeout_ms: AtomicU64,
     route_backpressure_high_timeout_ms: AtomicU64,
     route_backpressure_high_watermark_pct: AtomicU8,
@@ -91,11 +91,12 @@ impl ConnRegistry {
             .as_secs()
     }
 
-    pub fn new() -> Self {
+    pub fn with_route_channel_capacity(route_channel_capacity: usize) -> Self {
         let start = rand::random::<u64>() | 1;
         Self {
             inner: RwLock::new(RegistryInner::new()),
             next_id: AtomicU64::new(start),
+            route_channel_capacity: route_channel_capacity.max(1),
             route_backpressure_base_timeout_ms: AtomicU64::new(
                 ROUTE_BACKPRESSURE_BASE_TIMEOUT_MS,
             ),
@@ -108,6 +109,11 @@ impl ConnRegistry {
         }
     }
 
+    #[cfg(test)]
+    pub fn new() -> Self {
+        Self::with_route_channel_capacity(4096)
+    }
+
     pub fn update_route_backpressure_policy(
         &self,
         base_timeout_ms: u64,
@@ -127,7 +133,7 @@ impl ConnRegistry {
 
     pub async fn register(&self) -> (u64, mpsc::Receiver<MeResponse>) {
         let id = self.next_id.fetch_add(1, Ordering::Relaxed);
-        let (tx, rx) = mpsc::channel(ROUTE_CHANNEL_CAPACITY);
+        let (tx, rx) = mpsc::channel(self.route_channel_capacity);
         self.inner.write().await.map.insert(id, tx);
         (id, rx)
     }
@@ -179,11 +185,11 @@ impl ConnRegistry {
                     .route_backpressure_high_watermark_pct
                     .load(Ordering::Relaxed)
                     .clamp(1, 100);
-                let used = ROUTE_CHANNEL_CAPACITY.saturating_sub(tx.capacity());
+                let used = self.route_channel_capacity.saturating_sub(tx.capacity());
-                let used_pct = if ROUTE_CHANNEL_CAPACITY == 0 {
+                let used_pct = if self.route_channel_capacity == 0 {
                     100
                 } else {
-                    (used.saturating_mul(100) / ROUTE_CHANNEL_CAPACITY) as u8
+                    (used.saturating_mul(100) / self.route_channel_capacity) as u8
                 };
                 let high_profile = used_pct >= high_watermark_pct;
                 let timeout_ms = if high_profile {
@@ -264,6 +270,20 @@ impl ConnRegistry {
         inner.writer_idle_since_epoch_secs.clone()
     }
 
+    pub async fn writer_idle_since_for_writer_ids(
+        &self,
+        writer_ids: &[u64],
+    ) -> HashMap<u64, u64> {
+        let inner = self.inner.read().await;
+        let mut out = HashMap::<u64, u64>::with_capacity(writer_ids.len());
+        for writer_id in writer_ids {
+            if let Some(idle_since) = inner.writer_idle_since_epoch_secs.get(writer_id).copied() {
+                out.insert(*writer_id, idle_since);
+            }
+        }
+        out
+    }
+
     pub(super) async fn writer_activity_snapshot(&self) -> WriterActivitySnapshot {
         let inner = self.inner.read().await;
         let mut bound_clients_by_writer = HashMap::<u64, usize>::new();

src/transport/middle_proxy/send.rs

@@ -5,10 +5,11 @@ use std::sync::Arc;
 use std::sync::atomic::Ordering;
 use std::time::{Duration, Instant};
 
+use bytes::Bytes;
 use tokio::sync::mpsc::error::TrySendError;
 use tracing::{debug, warn};
 
-use crate::config::MeRouteNoWriterMode;
+use crate::config::{MeRouteNoWriterMode, MeWriterPickMode};
 use crate::error::{ProxyError, Result};
 use crate::network::IpFamily;
 use crate::protocol::constants::{RPC_CLOSE_CONN_U32, RPC_CLOSE_EXT_U32};
@@ -23,6 +24,10 @@ use super::registry::ConnMeta;
 const IDLE_WRITER_PENALTY_MID_SECS: u64 = 45;
 const IDLE_WRITER_PENALTY_HIGH_SECS: u64 = 55;
 const HYBRID_GLOBAL_BURST_PERIOD_ROUNDS: u32 = 4;
+const PICK_PENALTY_WARM: u64 = 200;
+const PICK_PENALTY_DRAINING: u64 = 600;
+const PICK_PENALTY_STALE: u64 = 300;
+const PICK_PENALTY_DEGRADED: u64 = 250;
 
 impl MePool {
     /// Send RPC_PROXY_REQ. `tag_override`: per-user ad_tag (from access.user_ad_tags); if None, uses pool default.
@@ -53,12 +58,16 @@ impl MePool {
         };
         let no_writer_mode =
             MeRouteNoWriterMode::from_u8(self.me_route_no_writer_mode.load(Ordering::Relaxed));
+        let (routed_dc, unknown_target_dc) = self
+            .resolve_target_dc_for_routing(target_dc as i32)
+            .await;
         let mut no_writer_deadline: Option<Instant> = None;
         let mut emergency_attempts = 0u32;
         let mut async_recovery_triggered = false;
         let mut hybrid_recovery_round = 0u32;
         let mut hybrid_last_recovery_at: Option<Instant> = None;
         let hybrid_wait_step = self.me_route_no_writer_wait.max(Duration::from_millis(50));
+        let mut hybrid_wait_current = hybrid_wait_step;
 
         loop {
             if let Some(current) = self.registry.get_writer(conn_id).await {
@@ -89,9 +98,9 @@ impl MePool {
                             let deadline = *no_writer_deadline.get_or_insert_with(|| {
                                 Instant::now() + self.me_route_no_writer_wait
                             });
-                            if !async_recovery_triggered {
+                            if !async_recovery_triggered && !unknown_target_dc {
                                 let triggered =
-                                    self.trigger_async_recovery_for_target_dc(target_dc).await;
+                                    self.trigger_async_recovery_for_target_dc(routed_dc).await;
                                 if !triggered {
                                     self.trigger_async_recovery_global().await;
                                 }
@@ -107,31 +116,34 @@ impl MePool {
                         }
                         MeRouteNoWriterMode::InlineRecoveryLegacy => {
                             self.stats.increment_me_inline_recovery_total();
-                            for _ in 0..self.me_route_inline_recovery_attempts.max(1) {
+                            if !unknown_target_dc {
-                                for family in self.family_order() {
+                                for _ in 0..self.me_route_inline_recovery_attempts.max(1) {
-                                    let map = match family {
+                                    for family in self.family_order() {
-                                        IpFamily::V4 => self.proxy_map_v4.read().await.clone(),
+                                        let map = match family {
-                                        IpFamily::V6 => self.proxy_map_v6.read().await.clone(),
+                                            IpFamily::V4 => self.proxy_map_v4.read().await.clone(),
-                                    };
+                                            IpFamily::V6 => self.proxy_map_v6.read().await.clone(),
-                                    for (_dc, addrs) in &map {
+                                        };
-                                        for (ip, port) in addrs {
+                                        for (dc, addrs) in &map {
-                                            let addr = SocketAddr::new(*ip, *port);
+                                            for (ip, port) in addrs {
-                                            let _ = self.connect_one(addr, self.rng.as_ref()).await;
+                                                let addr = SocketAddr::new(*ip, *port);
+                                                let _ = self
+                                                    .connect_one_for_dc(addr, *dc, self.rng.as_ref())
+                                                    .await;
+                                            }
                                         }
                                     }
-                                }
+                                    if !self.writers.read().await.is_empty() {
-                                if !self.writers.read().await.is_empty() {
+                                        break;
-                                    break;
+                                    }
                                 }
                             }
+
                             if !self.writers.read().await.is_empty() {
                                 continue;
                             }
-                            let waiter = self.writer_available.notified();
+                            let deadline = *no_writer_deadline
-                            if tokio::time::timeout(self.me_route_inline_recovery_wait, waiter)
+                                .get_or_insert_with(|| Instant::now() + self.me_route_inline_recovery_wait);
-                                .await
+                            if !self.wait_for_writer_until(deadline).await {
-                                .is_err()
-                            {
                                 if !self.writers.read().await.is_empty() {
                                     continue;
                                 }
@@ -143,15 +155,20 @@ impl MePool {
                             continue;
                         }
                         MeRouteNoWriterMode::HybridAsyncPersistent => {
-                            self.maybe_trigger_hybrid_recovery(
+                            if !unknown_target_dc {
-                                target_dc,
+                                self.maybe_trigger_hybrid_recovery(
-                                &mut hybrid_recovery_round,
+                                    routed_dc,
-                                &mut hybrid_last_recovery_at,
+                                    &mut hybrid_recovery_round,
-                                hybrid_wait_step,
+                                    &mut hybrid_last_recovery_at,
-                            )
+                                    hybrid_wait_current,
-                            .await;
+                                )
-                            let deadline = Instant::now() + hybrid_wait_step;
+                                .await;
+                            }
+                            let deadline = Instant::now() + hybrid_wait_current;
                             let _ = self.wait_for_writer_until(deadline).await;
+                            hybrid_wait_current =
+                                (hybrid_wait_current.saturating_mul(2))
+                                    .min(Duration::from_millis(400));
                             continue;
                         }
                     }
@@ -160,29 +177,31 @@ impl MePool {
             };
 
             let mut candidate_indices = self
-                .candidate_indices_for_dc(&writers_snapshot, target_dc, false)
+                .candidate_indices_for_dc(&writers_snapshot, routed_dc, false)
                 .await;
             if candidate_indices.is_empty() {
                 candidate_indices = self
-                    .candidate_indices_for_dc(&writers_snapshot, target_dc, true)
+                    .candidate_indices_for_dc(&writers_snapshot, routed_dc, true)
                     .await;
             }
             if candidate_indices.is_empty() {
+                let pick_mode = self.writer_pick_mode();
                 match no_writer_mode {
                     MeRouteNoWriterMode::AsyncRecoveryFailfast => {
                         let deadline = *no_writer_deadline.get_or_insert_with(|| {
                             Instant::now() + self.me_route_no_writer_wait
                         });
-                        if !async_recovery_triggered {
+                        if !async_recovery_triggered && !unknown_target_dc {
-                            let triggered = self.trigger_async_recovery_for_target_dc(target_dc).await;
+                            let triggered = self.trigger_async_recovery_for_target_dc(routed_dc).await;
                             if !triggered {
                                 self.trigger_async_recovery_global().await;
                             }
                             async_recovery_triggered = true;
                         }
-                        if self.wait_for_candidate_until(target_dc, deadline).await {
+                        if self.wait_for_candidate_until(routed_dc, deadline).await {
                             continue;
                         }
+                        self.stats.increment_me_writer_pick_no_candidate_total(pick_mode);
                         self.stats.increment_me_no_writer_failfast_total();
                         return Err(ProxyError::Proxy(
                             "No ME writers available for target DC in failfast window".into(),
@@ -190,15 +209,26 @@ impl MePool {
                     }
                     MeRouteNoWriterMode::InlineRecoveryLegacy => {
                         self.stats.increment_me_inline_recovery_total();
+                        if unknown_target_dc {
+                            let deadline = *no_writer_deadline
+                                .get_or_insert_with(|| Instant::now() + self.me_route_inline_recovery_wait);
+                            if self.wait_for_candidate_until(routed_dc, deadline).await {
+                                continue;
+                            }
+                            self.stats.increment_me_writer_pick_no_candidate_total(pick_mode);
+                            self.stats.increment_me_no_writer_failfast_total();
+                            return Err(ProxyError::Proxy("No ME writers available for target DC".into()));
+                        }
                         if emergency_attempts >= self.me_route_inline_recovery_attempts.max(1) {
+                            self.stats.increment_me_writer_pick_no_candidate_total(pick_mode);
                             self.stats.increment_me_no_writer_failfast_total();
                             return Err(ProxyError::Proxy("No ME writers available for target DC".into()));
                         }
                         emergency_attempts += 1;
-                        let mut endpoints = self.endpoint_candidates_for_target_dc(target_dc).await;
+                        let mut endpoints = self.endpoint_candidates_for_target_dc(routed_dc).await;
                         endpoints.shuffle(&mut rand::rng());
                         for addr in endpoints {
-                            if self.connect_one(addr, self.rng.as_ref()).await.is_ok() {
+                            if self.connect_one_for_dc(addr, routed_dc, self.rng.as_ref()).await.is_ok() {
                                 break;
                             }
                         }
@@ -207,96 +237,126 @@ impl MePool {
                         writers_snapshot = ws2.clone();
                         drop(ws2);
                         candidate_indices = self
-                            .candidate_indices_for_dc(&writers_snapshot, target_dc, false)
+                            .candidate_indices_for_dc(&writers_snapshot, routed_dc, false)
                             .await;
                         if candidate_indices.is_empty() {
                             candidate_indices = self
-                                .candidate_indices_for_dc(&writers_snapshot, target_dc, true)
+                                .candidate_indices_for_dc(&writers_snapshot, routed_dc, true)
                                 .await;
                         }
                         if candidate_indices.is_empty() {
+                            self.stats.increment_me_writer_pick_no_candidate_total(pick_mode);
                             return Err(ProxyError::Proxy("No ME writers available for target DC".into()));
                         }
                     }
                     MeRouteNoWriterMode::HybridAsyncPersistent => {
-                        self.maybe_trigger_hybrid_recovery(
+                        if !unknown_target_dc {
-                            target_dc,
+                            self.maybe_trigger_hybrid_recovery(
-                            &mut hybrid_recovery_round,
+                                routed_dc,
-                            &mut hybrid_last_recovery_at,
+                                &mut hybrid_recovery_round,
-                            hybrid_wait_step,
+                                &mut hybrid_last_recovery_at,
-                        )
+                                hybrid_wait_current,
-                        .await;
+                            )
-                        let deadline = Instant::now() + hybrid_wait_step;
+                            .await;
-                        let _ = self.wait_for_candidate_until(target_dc, deadline).await;
+                        }
+                        let deadline = Instant::now() + hybrid_wait_current;
+                        let _ = self.wait_for_candidate_until(routed_dc, deadline).await;
+                        hybrid_wait_current = (hybrid_wait_current.saturating_mul(2))
+                            .min(Duration::from_millis(400));
                         continue;
                     }
                 }
             }
-            let writer_idle_since = self.registry.writer_idle_since_snapshot().await;
+            hybrid_wait_current = hybrid_wait_step;
+            let pick_mode = self.writer_pick_mode();
+            let pick_sample_size = self.writer_pick_sample_size();
+            let writer_ids: Vec<u64> = candidate_indices
+                .iter()
+                .map(|idx| writers_snapshot[*idx].id)
+                .collect();
+            let writer_idle_since = self
+                .registry
+                .writer_idle_since_for_writer_ids(&writer_ids)
+                .await;
             let now_epoch_secs = Self::now_epoch_secs();
-
-            if self.me_deterministic_writer_sort.load(Ordering::Relaxed) {
-                candidate_indices.sort_by(|lhs, rhs| {
-                    let left = &writers_snapshot[*lhs];
-                    let right = &writers_snapshot[*rhs];
-                    let left_key = (
-                        self.writer_contour_rank_for_selection(left),
-                        (left.generation < self.current_generation()) as usize,
-                        left.degraded.load(Ordering::Relaxed) as usize,
-                        self.writer_idle_rank_for_selection(
-                            left,
-                            &writer_idle_since,
-                            now_epoch_secs,
-                        ),
-                        Reverse(left.tx.capacity()),
-                        left.addr,
-                        left.id,
-                    );
-                    let right_key = (
-                        self.writer_contour_rank_for_selection(right),
-                        (right.generation < self.current_generation()) as usize,
-                        right.degraded.load(Ordering::Relaxed) as usize,
-                        self.writer_idle_rank_for_selection(
-                            right,
-                            &writer_idle_since,
-                            now_epoch_secs,
-                        ),
-                        Reverse(right.tx.capacity()),
-                        right.addr,
-                        right.id,
-                    );
-                    left_key.cmp(&right_key)
-                });
-            } else {
-                candidate_indices.sort_by_key(|idx| {
-                    let w = &writers_snapshot[*idx];
-                    let degraded = w.degraded.load(Ordering::Relaxed);
-                    let stale = (w.generation < self.current_generation()) as usize;
-                    (
-                        self.writer_contour_rank_for_selection(w),
-                        stale,
-                        degraded as usize,
-                        self.writer_idle_rank_for_selection(
-                            w,
-                            &writer_idle_since,
-                            now_epoch_secs,
-                        ),
-                        Reverse(w.tx.capacity()),
-                    )
-                });
-            }
-
             let start = self.rr.fetch_add(1, Ordering::Relaxed) as usize % candidate_indices.len();
+            let ordered_candidate_indices = if pick_mode == MeWriterPickMode::P2c {
+                self.p2c_ordered_candidate_indices(
+                    &candidate_indices,
+                    &writers_snapshot,
+                    &writer_idle_since,
+                    now_epoch_secs,
+                    start,
+                    pick_sample_size,
+                )
+            } else {
+                if self.me_deterministic_writer_sort.load(Ordering::Relaxed) {
+                    candidate_indices.sort_by(|lhs, rhs| {
+                        let left = &writers_snapshot[*lhs];
+                        let right = &writers_snapshot[*rhs];
+                        let left_key = (
+                            self.writer_contour_rank_for_selection(left),
+                            (left.generation < self.current_generation()) as usize,
+                            left.degraded.load(Ordering::Relaxed) as usize,
+                            self.writer_idle_rank_for_selection(
+                                left,
+                                &writer_idle_since,
+                                now_epoch_secs,
+                            ),
+                            Reverse(left.tx.capacity()),
+                            left.addr,
+                            left.id,
+                        );
+                        let right_key = (
+                            self.writer_contour_rank_for_selection(right),
+                            (right.generation < self.current_generation()) as usize,
+                            right.degraded.load(Ordering::Relaxed) as usize,
+                            self.writer_idle_rank_for_selection(
+                                right,
+                                &writer_idle_since,
+                                now_epoch_secs,
+                            ),
+                            Reverse(right.tx.capacity()),
+                            right.addr,
+                            right.id,
+                        );
+                        left_key.cmp(&right_key)
+                    });
+                } else {
+                    candidate_indices.sort_by_key(|idx| {
+                        let w = &writers_snapshot[*idx];
+                        let degraded = w.degraded.load(Ordering::Relaxed);
+                        let stale = (w.generation < self.current_generation()) as usize;
+                        (
+                            self.writer_contour_rank_for_selection(w),
+                            stale,
+                            degraded as usize,
+                            self.writer_idle_rank_for_selection(
+                                w,
+                                &writer_idle_since,
+                                now_epoch_secs,
+                            ),
+                            Reverse(w.tx.capacity()),
+                        )
+                    });
+                }
+
+                let mut ordered = Vec::<usize>::with_capacity(candidate_indices.len());
+                for offset in 0..candidate_indices.len() {
+                    ordered.push(candidate_indices[(start + offset) % candidate_indices.len()]);
+                }
+                ordered
+            };
             let mut fallback_blocking_idx: Option<usize> = None;
 
-            for offset in 0..candidate_indices.len() {
+            for idx in ordered_candidate_indices {
-                let idx = candidate_indices[(start + offset) % candidate_indices.len()];
                 let w = &writers_snapshot[idx];
                 if !self.writer_accepts_new_binding(w) {
                     continue;
                 }
                 match w.tx.try_send(WriterCommand::Data(payload.clone())) {
                     Ok(()) => {
+                        self.stats.increment_me_writer_pick_success_try_total(pick_mode);
                         self.registry
                             .bind_writer(conn_id, w.id, w.tx.clone(), meta.clone())
                             .await;
@@ -318,6 +378,7 @@ impl MePool {
                         }
                     }
                     Err(TrySendError::Closed(_)) => {
+                        self.stats.increment_me_writer_pick_closed_total(pick_mode);
                         warn!(writer_id = w.id, "ME writer channel closed");
                         self.remove_writer_and_close_clients(w.id).await;
                         continue;
@@ -326,15 +387,20 @@ impl MePool {
             }
 
             let Some(blocking_idx) = fallback_blocking_idx else {
+                self.stats.increment_me_writer_pick_full_total(pick_mode);
                 continue;
             };
 
             let w = writers_snapshot[blocking_idx].clone();
             if !self.writer_accepts_new_binding(&w) {
+                self.stats.increment_me_writer_pick_full_total(pick_mode);
                 continue;
             }
+            self.stats.increment_me_writer_pick_blocking_fallback_total();
             match w.tx.send(WriterCommand::Data(payload.clone())).await {
                 Ok(()) => {
+                    self.stats
+                        .increment_me_writer_pick_success_fallback_total(pick_mode);
                     self.registry
                         .bind_writer(conn_id, w.id, w.tx.clone(), meta.clone())
                         .await;
@@ -344,6 +410,7 @@ impl MePool {
                     return Ok(());
                 }
                 Err(_) => {
+                    self.stats.increment_me_writer_pick_closed_total(pick_mode);
                     warn!(writer_id = w.id, "ME writer channel closed (blocking)");
                     self.remove_writer_and_close_clients(w.id).await;
                 }
@@ -367,32 +434,32 @@ impl MePool {
         !self.writers.read().await.is_empty()
     }
 
-    async fn wait_for_candidate_until(&self, target_dc: i16, deadline: Instant) -> bool {
+    async fn wait_for_candidate_until(&self, routed_dc: i32, deadline: Instant) -> bool {
         loop {
-            if self.has_candidate_for_target_dc(target_dc).await {
+            if self.has_candidate_for_target_dc(routed_dc).await {
                 return true;
             }
 
             let now = Instant::now();
             if now >= deadline {
-                return self.has_candidate_for_target_dc(target_dc).await;
+                return self.has_candidate_for_target_dc(routed_dc).await;
             }
 
             let waiter = self.writer_available.notified();
-            if self.has_candidate_for_target_dc(target_dc).await {
+            if self.has_candidate_for_target_dc(routed_dc).await {
                 return true;
             }
             let remaining = deadline.saturating_duration_since(Instant::now());
             if remaining.is_zero() {
-                return self.has_candidate_for_target_dc(target_dc).await;
+                return self.has_candidate_for_target_dc(routed_dc).await;
             }
             if tokio::time::timeout(remaining, waiter).await.is_err() {
-                return self.has_candidate_for_target_dc(target_dc).await;
+                return self.has_candidate_for_target_dc(routed_dc).await;
             }
         }
     }
 
-    async fn has_candidate_for_target_dc(&self, target_dc: i16) -> bool {
+    async fn has_candidate_for_target_dc(&self, routed_dc: i32) -> bool {
         let writers_snapshot = {
             let ws = self.writers.read().await;
             if ws.is_empty() {
@@ -401,41 +468,41 @@ impl MePool {
             ws.clone()
         };
         let mut candidate_indices = self
-            .candidate_indices_for_dc(&writers_snapshot, target_dc, false)
+            .candidate_indices_for_dc(&writers_snapshot, routed_dc, false)
             .await;
         if candidate_indices.is_empty() {
             candidate_indices = self
-                .candidate_indices_for_dc(&writers_snapshot, target_dc, true)
+                .candidate_indices_for_dc(&writers_snapshot, routed_dc, true)
                 .await;
         }
         !candidate_indices.is_empty()
     }
 
-    async fn trigger_async_recovery_for_target_dc(self: &Arc<Self>, target_dc: i16) -> bool {
+    async fn trigger_async_recovery_for_target_dc(self: &Arc<Self>, routed_dc: i32) -> bool {
-        let endpoints = self.endpoint_candidates_for_target_dc(target_dc).await;
+        let endpoints = self.endpoint_candidates_for_target_dc(routed_dc).await;
         if endpoints.is_empty() {
             return false;
         }
         self.stats.increment_me_async_recovery_trigger_total();
         for addr in endpoints.into_iter().take(8) {
-            self.trigger_immediate_refill(addr);
+            self.trigger_immediate_refill_for_dc(addr, routed_dc);
         }
         true
     }
 
     async fn trigger_async_recovery_global(self: &Arc<Self>) {
         self.stats.increment_me_async_recovery_trigger_total();
-        let mut seen = HashSet::<SocketAddr>::new();
+        let mut seen = HashSet::<(i32, SocketAddr)>::new();
         for family in self.family_order() {
             let map_guard = match family {
                 IpFamily::V4 => self.proxy_map_v4.read().await,
                 IpFamily::V6 => self.proxy_map_v6.read().await,
             };
-            for addrs in map_guard.values() {
+            for (dc, addrs) in map_guard.iter() {
                 for (ip, port) in addrs {
                     let addr = SocketAddr::new(*ip, *port);
-                    if seen.insert(addr) {
+                    if seen.insert((*dc, addr)) {
-                        self.trigger_immediate_refill(addr);
+                        self.trigger_immediate_refill_for_dc(addr, *dc);
                     }
                     if seen.len() >= 8 {
                         return;
@@ -445,44 +512,13 @@ impl MePool {
         }
     }
 
-    async fn endpoint_candidates_for_target_dc(&self, target_dc: i16) -> Vec<SocketAddr> {
+    async fn endpoint_candidates_for_target_dc(&self, routed_dc: i32) -> Vec<SocketAddr> {
-        let key = target_dc as i32;
+        self.preferred_endpoints_for_dc(routed_dc).await
-        let mut preferred = Vec::<SocketAddr>::new();
-        let mut seen = HashSet::<SocketAddr>::new();
-        let lookup_keys = self.dc_lookup_chain_for_target(key);
-
-        for family in self.family_order() {
-            let map_guard = match family {
-                IpFamily::V4 => self.proxy_map_v4.read().await,
-                IpFamily::V6 => self.proxy_map_v6.read().await,
-            };
-            let mut family_selected = Vec::<SocketAddr>::new();
-            for lookup in lookup_keys.iter().copied() {
-                if let Some(addrs) = map_guard.get(&lookup) {
-                    for (ip, port) in addrs {
-                        family_selected.push(SocketAddr::new(*ip, *port));
-                    }
-                }
-                if !family_selected.is_empty() {
-                    break;
-                }
-            }
-            for addr in family_selected {
-                if seen.insert(addr) {
-                    preferred.push(addr);
-                }
-            }
-            if !preferred.is_empty() && !self.decision.effective_multipath {
-                break;
-            }
-        }
-
-        preferred
     }
 
     async fn maybe_trigger_hybrid_recovery(
         self: &Arc<Self>,
-        target_dc: i16,
+        routed_dc: i32,
         hybrid_recovery_round: &mut u32,
         hybrid_last_recovery_at: &mut Option<Instant>,
         hybrid_wait_step: Duration,
@@ -494,7 +530,7 @@ impl MePool {
         }
 
         let round = *hybrid_recovery_round;
-        let target_triggered = self.trigger_async_recovery_for_target_dc(target_dc).await;
+        let target_triggered = self.trigger_async_recovery_for_target_dc(routed_dc).await;
         if !target_triggered || round % HYBRID_GLOBAL_BURST_PERIOD_ROUNDS == 0 {
             self.trigger_async_recovery_global().await;
         }
@@ -507,7 +543,11 @@ impl MePool {
             let mut p = Vec::with_capacity(12);
             p.extend_from_slice(&RPC_CLOSE_EXT_U32.to_le_bytes());
             p.extend_from_slice(&conn_id.to_le_bytes());
-            if w.tx.send(WriterCommand::DataAndFlush(p)).await.is_err() {
+            if w.tx
+                .send(WriterCommand::DataAndFlush(Bytes::from(p)))
+                .await
+                .is_err()
+            {
                 debug!("ME close write failed");
                 self.remove_writer_and_close_clients(w.writer_id).await;
             }
@@ -524,7 +564,7 @@ impl MePool {
             let mut p = Vec::with_capacity(12);
             p.extend_from_slice(&RPC_CLOSE_CONN_U32.to_le_bytes());
             p.extend_from_slice(&conn_id.to_le_bytes());
-            match w.tx.try_send(WriterCommand::DataAndFlush(p)) {
+            match w.tx.try_send(WriterCommand::DataAndFlush(Bytes::from(p))) {
                 Ok(()) => {}
                 Err(TrySendError::Full(cmd)) => {
                     let _ = tokio::time::timeout(Duration::from_millis(50), w.tx.send(cmd)).await;
@@ -557,38 +597,10 @@ impl MePool {
     pub(super) async fn candidate_indices_for_dc(
         &self,
         writers: &[super::pool::MeWriter],
-        target_dc: i16,
+        routed_dc: i32,
         include_warm: bool,
     ) -> Vec<usize> {
-        let key = target_dc as i32;
+        let preferred = self.preferred_endpoints_for_dc(routed_dc).await;
-        let mut preferred = HashSet::<SocketAddr>::new();
-        let lookup_keys = self.dc_lookup_chain_for_target(key);
-
-        for family in self.family_order() {
-            let map_guard = match family {
-                IpFamily::V4 => self.proxy_map_v4.read().await,
-                IpFamily::V6 => self.proxy_map_v6.read().await,
-            };
-            let mut family_selected = Vec::<SocketAddr>::new();
-            for lookup in lookup_keys.iter().copied() {
-                if let Some(v) = map_guard.get(&lookup) {
-                    family_selected.extend(v.iter().map(|(ip, port)| SocketAddr::new(*ip, *port)));
-                }
-                if !family_selected.is_empty() {
-                    break;
-                }
-            }
-            for endpoint in family_selected {
-                preferred.insert(endpoint);
-            }
-
-            drop(map_guard);
-
-            if !preferred.is_empty() && !self.decision.effective_multipath {
-                break;
-            }
-        }
-
         if preferred.is_empty() {
             return Vec::new();
         }
@@ -598,7 +610,7 @@ impl MePool {
             if !self.writer_eligible_for_selection(w, include_warm) {
                 continue;
             }
-            if preferred.contains(&w.addr) {
+            if w.writer_dc == routed_dc && preferred.iter().any(|endpoint| *endpoint == w.addr) {
                 out.push(idx);
             }
         }
@@ -647,4 +659,87 @@ impl MePool {
             0
         }
     }
+
+    fn writer_pick_score(
+        &self,
+        writer: &super::pool::MeWriter,
+        idle_since_by_writer: &HashMap<u64, u64>,
+        now_epoch_secs: u64,
+    ) -> u64 {
+        let contour_penalty = match WriterContour::from_u8(writer.contour.load(Ordering::Relaxed)) {
+            WriterContour::Active => 0,
+            WriterContour::Warm => PICK_PENALTY_WARM,
+            WriterContour::Draining => PICK_PENALTY_DRAINING,
+        };
+        let stale_penalty = if writer.generation < self.current_generation() {
+            PICK_PENALTY_STALE
+        } else {
+            0
+        };
+        let degraded_penalty = if writer.degraded.load(Ordering::Relaxed) {
+            PICK_PENALTY_DEGRADED
+        } else {
+            0
+        };
+        let idle_penalty =
+            (self.writer_idle_rank_for_selection(writer, idle_since_by_writer, now_epoch_secs) as u64)
+                * 100;
+        let queue_cap = self.writer_cmd_channel_capacity.max(1) as u64;
+        let queue_remaining = writer.tx.capacity() as u64;
+        let queue_used = queue_cap.saturating_sub(queue_remaining.min(queue_cap));
+        let queue_util_pct = queue_used.saturating_mul(100) / queue_cap;
+        let queue_penalty = queue_util_pct.saturating_mul(4);
+        let rtt_penalty = ((writer.rtt_ema_ms_x10.load(Ordering::Relaxed) as u64).saturating_add(5) / 10)
+            .min(400);
+
+        contour_penalty
+            .saturating_add(stale_penalty)
+            .saturating_add(degraded_penalty)
+            .saturating_add(idle_penalty)
+            .saturating_add(queue_penalty)
+            .saturating_add(rtt_penalty)
+    }
+
+    fn p2c_ordered_candidate_indices(
+        &self,
+        candidate_indices: &[usize],
+        writers_snapshot: &[super::pool::MeWriter],
+        idle_since_by_writer: &HashMap<u64, u64>,
+        now_epoch_secs: u64,
+        start: usize,
+        sample_size: usize,
+    ) -> Vec<usize> {
+        let total = candidate_indices.len();
+        if total == 0 {
+            return Vec::new();
+        }
+
+        let mut sampled = Vec::<usize>::with_capacity(sample_size.min(total));
+        let mut seen = HashSet::<usize>::with_capacity(total);
+        for offset in 0..sample_size.min(total) {
+            let idx = candidate_indices[(start + offset) % total];
+            if seen.insert(idx) {
+                sampled.push(idx);
+            }
+        }
+
+        sampled.sort_by_key(|idx| {
+            let writer = &writers_snapshot[*idx];
+            (
+                self.writer_pick_score(writer, idle_since_by_writer, now_epoch_secs),
+                writer.addr,
+                writer.id,
+            )
+        });
+
+        let mut ordered = Vec::<usize>::with_capacity(total);
+        ordered.extend(sampled.iter().copied());
+        for offset in 0..total {
+            let idx = candidate_indices[(start + offset) % total];
+            if seen.insert(idx) {
+                ordered.push(idx);
+            }
+        }
+        ordered
+    }
 }

src/transport/middle_proxy/wire.rs

@@ -1,4 +1,5 @@
 use std::net::{IpAddr, Ipv4Addr, SocketAddr};
+use bytes::Bytes;
 
 use crate::protocol::constants::*;
 
@@ -48,7 +49,7 @@ pub(crate) fn build_proxy_req_payload(
     data: &[u8],
     proxy_tag: Option<&[u8]>,
     proto_flags: u32,
-) -> Vec<u8> {
+) -> Bytes {
     let mut b = Vec::with_capacity(128 + data.len());
 
     b.extend_from_slice(&RPC_PROXY_REQ_U32.to_le_bytes());
@@ -85,7 +86,7 @@ pub(crate) fn build_proxy_req_payload(
     }
 
     b.extend_from_slice(data);
-    b
+    Bytes::from(b)
 }
 
 pub fn proto_flags_for_tag(tag: crate::protocol::constants::ProtoTag, has_proxy_tag: bool) -> u32 {

src/transport/upstream.rs

@@ -7,7 +7,7 @@
 use std::collections::{BTreeSet, HashMap};
 use std::net::{SocketAddr, IpAddr};
 use std::sync::Arc;
-use std::sync::atomic::{AtomicUsize, Ordering};
+use std::sync::atomic::{AtomicU64, AtomicUsize, Ordering};
 use std::time::Duration;
 use tokio::net::TcpStream;
 use tokio::sync::RwLock;
@@ -237,6 +237,8 @@ pub struct UpstreamManager {
     connect_budget: Duration,
     unhealthy_fail_threshold: u32,
     connect_failfast_hard_errors: bool,
+    no_upstreams_warn_epoch_ms: Arc<AtomicU64>,
+    no_healthy_warn_epoch_ms: Arc<AtomicU64>,
     stats: Arc<Stats>,
 }
 
@@ -262,10 +264,35 @@ impl UpstreamManager {
             connect_budget: Duration::from_millis(connect_budget_ms.max(1)),
             unhealthy_fail_threshold: unhealthy_fail_threshold.max(1),
             connect_failfast_hard_errors,
+            no_upstreams_warn_epoch_ms: Arc::new(AtomicU64::new(0)),
+            no_healthy_warn_epoch_ms: Arc::new(AtomicU64::new(0)),
             stats,
         }
     }
 
+    fn now_epoch_ms() -> u64 {
+        std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap_or_default()
+            .as_millis() as u64
+    }
+
+    fn should_emit_warn(last_epoch_ms: &AtomicU64, cooldown_ms: u64) -> bool {
+        let now_epoch_ms = Self::now_epoch_ms();
+        let previous_epoch_ms = last_epoch_ms.load(Ordering::Relaxed);
+        if now_epoch_ms.saturating_sub(previous_epoch_ms) < cooldown_ms {
+            return false;
+        }
+        last_epoch_ms
+            .compare_exchange(
+                previous_epoch_ms,
+                now_epoch_ms,
+                Ordering::AcqRel,
+                Ordering::Relaxed,
+            )
+            .is_ok()
+    }
+
     pub fn try_api_snapshot(&self) -> Option<UpstreamApiSnapshot> {
         let guard = self.upstreams.try_read().ok()?;
         let now = std::time::Instant::now();
@@ -533,12 +560,22 @@ impl UpstreamManager {
             .collect();
 
         if filtered_upstreams.is_empty() {
-            warn!(scope = scope, "No upstreams available! Using first (direct?)");
+            if Self::should_emit_warn(
+                self.no_upstreams_warn_epoch_ms.as_ref(),
+                5_000,
+            ) {
+                warn!(scope = scope, "No upstreams available! Using first (direct?)");
+            }
             return None;
         }
 
         if healthy.is_empty() {
-            warn!(scope = scope, "No healthy upstreams available! Using random.");
+            if Self::should_emit_warn(
+                self.no_healthy_warn_epoch_ms.as_ref(),
+                5_000,
+            ) {
+                warn!(scope = scope, "No healthy upstreams available! Using random.");
+            }
             return Some(filtered_upstreams[rand::rng().gen_range(0..filtered_upstreams.len())]);
         }
 

telemt.service

@@ -1,13 +1,16 @@
 [Unit]
 Description=Telemt
-After=network.target
+After=network-online.target
+Wants=network-online.target
 
 [Service]
 Type=simple
-WorkingDirectory=/bin
+WorkingDirectory=/etc/telemt
 ExecStart=/bin/telemt /etc/telemt.toml
 Restart=on-failure
-LimitNOFILE=65536
+LimitNOFILE=262144
+TasksMax=8192
+MemoryAccounting=yes
 
 [Install]
 WantedBy=multi-user.target