astelm/telemt
1
0
Fork 0
mirror of https://github.com/telemt/telemt.git synced 2026-04-17 02:24:10 +03:00
Code Issues Packages Projects Releases Wiki Activity

ME Writer Pick

Browse Source
This commit is contained in:
Alexey
2026-03-08 03:05:47 +03:00
parent 6b3697ee87
commit 9401c46727
9 changed files with 300 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/transport/middle_proxy/config_updater.rs
View File

@@ -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,
@@ -530,6 +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,

31
src/transport/middle_proxy/pool.rs
View File

@@ -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;
@@ -39,6 +41,7 @@ pub struct MeWriter {
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>,
@@ -177,6 +180,8 @@ 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,
@@ -274,6 +279,8 @@ 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,
@@ -450,6 +457,8 @@ 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),
@@ -489,6 +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,
@@ -535,6 +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
@@ -692,6 +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;

28
src/transport/middle_proxy/pool_status.rs
View File

@@ -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,
@@ -118,6 +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>,
@@ -338,6 +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),
@@ -522,6 +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,
@@ -570,6 +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",

226
src/transport/middle_proxy/send.rs
View File

@@ -9,7 +9,7 @@ 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};
@@ -24,6 +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.
@@ -181,6 +185,7 @@ impl MePool {
.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(|| {
@@ -196,6 +201,7 @@ impl MePool {
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(),
@@ -209,10 +215,12 @@ impl MePool {
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()));
}
@@ -237,6 +245,7 @@ impl MePool {
.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()));
}
}
@@ -259,6 +268,8 @@ impl MePool {
}
}
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)
@@ -268,69 +279,84 @@ impl MePool {
.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() {
let idx = candidate_indices[(start + offset) % candidate_indices.len()];
for idx in ordered_candidate_indices {
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;
@@ -352,6 +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;
@@ -360,15 +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;
@@ -378,6 +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;
}
@@ -626,4 +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
}
}