mirror of
https://github.com/telemt/telemt.git
synced 2026-04-25 14:34:10 +03:00
ME Writer Pick
This commit is contained in:
@@ -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
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user