perf: reduce packet buffer slicing churn (#2381)

* bench: add packet bytes extraction Criterion benchmark

Adds a Criterion benchmark under easytier/benches/ covering
ZCPacket::payload_bytes and tunnel_payload_bytes at 1280/4096-byte payload
sizes, using iter_batched so ZCPacket construction stays in the setup phase
and is excluded from the timed region.

- Register the [[bench]] entry in easytier/Cargo.toml.
- Document the bench and PACKET_BYTES_* env vars in benches/README.md.

* perf: reduce packet buffer slicing churn

Replace BytesMut::split_off with Buf::advance in ZCPacket bytes
extraction paths (payload_bytes, tunnel_payload_bytes, convert_type,
drop_foreign_header) and in TunZCPacketToBytes, and simplify the
copy_from_slice in new_from_payload.

When the buffer is in its unique (VEC) representation, split_off promotes
it to the shared (ARC) representation, allocating a Shared control block
and bumping the refcount on every call, and pins the buffer in shared
mode. advance only mutates the in-place ptr/len/cap fields, avoiding that
allocation/refcount churn on the TX hot path. The byte data itself is not
copied by either path.

easytier/Cargo.toml

@@ -32,6 +32,10 @@ path = "src/lib.rs"
 name = "tx_throughput"
 harness = false
 
+[[bench]]
+name = "packet_bytes_extraction"
+harness = false
+
 [dependencies]
 git-version = "0.3.9"
 

easytier/benches/README.md

@@ -1,4 +1,47 @@
-# TX Throughput Benchmark
+# Benchmarks
+
+Criterion benchmarks for EasyTier hot paths.
+
+| Bench                       | What it measures                                                                 |
+| --------------------------- | -------------------------------------------------------------------------------- |
+| `tx_throughput`             | End-to-end TX injection path through `peer_manager::send_msg_by_ip`              |
+| `packet_bytes_extraction`   | `ZCPacket::payload_bytes` / `tunnel_payload_bytes` extraction (advance hot path)  |
+
+## Packet Bytes Extraction
+
+Criterion benchmark for `ZCPacket` bytes extraction — the methods touched by the
+`advance`-based slicing refactor. Measures `payload_bytes` and
+`tunnel_payload_bytes` at two payload sizes (1280, 4096). Setup
+(`ZCPacket::new_with_payload`) runs in the benchmark harness's preparation
+phase and is excluded from the timed region, so the numbers reflect only the
+extraction call.
+
+### Quick start
+
+```bash
+cargo bench --bench packet_bytes_extraction
+```
+
+Smoke run:
+
+```bash
+PACKET_BYTES_MEASUREMENT_SECS=2 \
+PACKET_BYTES_WARMUP_SECS=1 \
+PACKET_BYTES_SAMPLE_SIZE=10 \
+cargo bench --bench packet_bytes_extraction -- --quiet
+```
+
+### Environment variables
+
+| Variable                        | Default | Notes                        |
+| ------------------------------- | ------- | ---------------------------- |
+| `PACKET_BYTES_MEASUREMENT_SECS` | `10`    | Criterion `measurement_time` |
+| `PACKET_BYTES_WARMUP_SECS`      | `3`     | Criterion `warm_up_time`     |
+| `PACKET_BYTES_SAMPLE_SIZE`      | `10`    | Criterion `sample_size` (min 10) |
+
+---
+
+## TX Throughput Benchmark
 
 Criterion benchmark for EasyTier's TX injection path (`peer_manager::send_msg_by_ip`).
 

easytier/benches/packet_bytes_extraction.rs

@@ -0,0 +1,65 @@
+use std::hint::black_box;
+use std::time::Duration;
+
+use criterion::{BatchSize, Criterion, Throughput, criterion_group, criterion_main};
+
+use easytier::tunnel::packet_def::ZCPacket;
+
+const PAYLOAD_SIZES: &[usize] = &[1280, 4096];
+
+fn env_parse<T: std::str::FromStr>(key: &str, default: T) -> T {
+    std::env::var(key)
+        .ok()
+        .and_then(|v| v.parse().ok())
+        .unwrap_or(default)
+}
+
+fn bench_payload_bytes(c: &mut Criterion) {
+    let mut group = c.benchmark_group("payload_bytes");
+    for &size in PAYLOAD_SIZES {
+        let data = vec![0u8; size];
+        group.throughput(Throughput::Bytes(size as u64));
+        group.bench_with_input(format!("{size}"), &data, |b, data| {
+            b.iter_batched(
+                || ZCPacket::new_with_payload(black_box(data)),
+                |p| black_box(p).payload_bytes(),
+                BatchSize::SmallInput,
+            )
+        });
+    }
+    group.finish();
+}
+
+fn bench_tunnel_payload_bytes(c: &mut Criterion) {
+    let mut group = c.benchmark_group("tunnel_payload_bytes");
+    for &size in PAYLOAD_SIZES {
+        let data = vec![0u8; size];
+        group.throughput(Throughput::Bytes(size as u64));
+        group.bench_with_input(format!("{size}"), &data, |b, data| {
+            b.iter_batched(
+                || ZCPacket::new_with_payload(black_box(data)),
+                |p| black_box(p).tunnel_payload_bytes(),
+                BatchSize::SmallInput,
+            )
+        });
+    }
+    group.finish();
+}
+
+fn criterion_config() -> Criterion {
+    let measurement_secs = env_parse("PACKET_BYTES_MEASUREMENT_SECS", 10u64);
+    let warmup_secs = env_parse("PACKET_BYTES_WARMUP_SECS", 3u64);
+    let sample_size = env_parse("PACKET_BYTES_SAMPLE_SIZE", 10usize).max(10);
+
+    Criterion::default()
+        .measurement_time(Duration::from_secs(measurement_secs))
+        .warm_up_time(Duration::from_secs(warmup_secs))
+        .sample_size(sample_size)
+}
+
+criterion_group! {
+    name = benches;
+    config = criterion_config();
+    targets = bench_payload_bytes, bench_tunnel_payload_bytes
+}
+criterion_main!(benches);

easytier/src/instance/virtual_nic.rs

@@ -24,7 +24,7 @@ use crate::{
 };
 
 use byteorder::WriteBytesExt as _;
-use bytes::{BufMut, BytesMut};
+use bytes::{Buf, BufMut, BytesMut};
 use cidr::{Ipv4Inet, Ipv6Inet};
 use futures::{SinkExt, Stream, StreamExt, lock::BiLock, ready};
 use pin_project_lite::pin_project;
@@ -180,12 +180,13 @@ impl ZCPacketToBytes for TunZCPacketToBytes {
         assert!(payload_offset >= 4);
 
         let ret = if self.has_packet_info {
-            let mut inner = inner.split_off(payload_offset - 4);
+            inner.advance(payload_offset - 4);
             let proto = infer_proto(&inner[4..]);
             self.fill_packet_info(&mut inner[0..4], proto)?;
             inner
         } else {
-            inner.split_off(payload_offset)
+            inner.advance(payload_offset);
+            inner
         };
 
         tracing::debug!(?ret, ?payload_offset, "convert zc packet to tun packet");

easytier/src/tunnel/packet_def.rs

@@ -1,3 +1,4 @@
+use bytes::Buf;
 use bytes::Bytes;
 use bytes::BytesMut;
 use zerocopy::AsBytes;
@@ -486,7 +487,7 @@ impl ZCPacket {
         let total_len = payload_off + payload.len();
         ret.inner.reserve(total_len);
         unsafe { ret.inner.set_len(total_len) };
-        ret.mut_payload()[..payload.len()].copy_from_slice(payload);
+        ret.mut_payload().copy_from_slice(payload);
         ret
     }
 
@@ -587,7 +588,8 @@ impl ZCPacket {
     }
 
     pub fn payload_bytes(mut self) -> BytesMut {
-        self.inner.split_off(self.payload_offset())
+        self.inner.advance(self.payload_offset());
+        self.inner
     }
 
     pub fn peer_manager_header(&self) -> Option<&PeerManagerHeader> {
@@ -652,11 +654,12 @@ impl ZCPacket {
     }
 
     pub fn tunnel_payload_bytes(mut self) -> BytesMut {
-        self.inner.split_off(
+        self.inner.advance(
             self.packet_type
                 .get_packet_offsets()
                 .peer_manager_header_offset,
-        )
+        );
+        self.inner
     }
 
     pub fn convert_type(mut self, target_packet_type: ZCPacketType) -> Self {
@@ -702,7 +705,8 @@ impl ZCPacket {
             return Self::new_from_buf(buf, target_packet_type);
         }
 
-        Self::new_from_buf(self.inner.split_off(new_offset), target_packet_type)
+        self.inner.advance(new_offset);
+        Self::new_from_buf(self.inner, target_packet_type)
     }
 
     pub fn into_bytes(self) -> Bytes {
@@ -748,8 +752,10 @@ impl ZCPacket {
         let foreign_hdr_len = hdr.get_header_len();
 
         Self::new_from_buf(
-            self.inner
+            {
-                .split_off(foreign_hdr_len + self.payload_offset()),
+                self.inner.advance(foreign_hdr_len + self.payload_offset());
+                self.inner
+            },
             ZCPacketType::DummyTunnel,
         )
     }