merge: distributed performance baseline benchmark

packages/node/meshnet_node/route_session_benchmark.py

@@ -44,6 +44,7 @@ class SeamSample:
     cache_mode: CacheMode
     model_ms: float
     encode_ms: float
+    activation_decode_ms: float
     framing_ms: float
     metadata_ms: float
     copy_allocation_ms: float
@@ -52,6 +53,7 @@ class SeamSample:
     decompression_ms: float
     connection_setup_ms: float
     queue_wait_ms: float
+    local_http_forwarding_ms: float
     transport_ms: float
     seam_latency_ms: float
     payload_bytes: int
@@ -120,6 +122,10 @@ def _summary(samples: list[SeamSample]) -> dict[str, float | int]:
         "compression_cpu_ms": round(
             sum(sample.compression_ms + sample.decompression_ms for sample in samples), 4
         ),
+        "model_execution_ms": round(sum(sample.model_ms for sample in samples), 4),
+        "activation_encoding_ms": round(sum(sample.encode_ms for sample in samples), 4),
+        "activation_decoding_ms": round(sum(sample.activation_decode_ms for sample in samples), 4),
+        "local_http_forwarding_ms": round(sum(sample.local_http_forwarding_ms for sample in samples), 4),
         "peak_buffered_bytes": max((sample.copy_allocation_bytes for sample in samples), default=0),
     }
 
@@ -159,6 +165,7 @@ class _StubTransport:
         queue_wait_ms = 0.0 if self.mode == "direct" else 0.18 + (0.05 if token_index is not None and token_index % 2 else 0.0)
         model_ms = 1.6 if phase == "prefill" else 0.45
         encode_ms = 0.16 if phase == "prefill" else 0.06
+        activation_decode_ms = 0.055 if phase == "prefill" else 0.02
         # Keep framing/metadata/copy costs explicit rather than hiding them in
         # serialization or transport time.  The stub owns one binary frame and
         # one response body per hop; no base64 body is modeled.
@@ -168,20 +175,26 @@ class _StubTransport:
         copy_allocation_bytes = wire_bytes + payload_bytes
         compression_ms = 0.09 if self.scenario.compression else 0.0
         decompression_ms = 0.07 if self.scenario.compression else 0.0
+        # Both routes finish by forwarding the decoded activation to the local
+        # tail-node HTTP handler; relay adds its own queue before that hop.
+        local_http_forwarding_ms = 0.11 if self.mode == "direct" else 0.16
         transport_ms = (0.32 if self.mode == "direct" else 0.61) + wire_bytes / 100_000
         seam_latency_ms = round(
-            model_ms + encode_ms + framing_ms + metadata_ms + copy_allocation_ms
-            + compression_ms + decompression_ms + connection_setup_ms + queue_wait_ms + transport_ms,
+            model_ms + encode_ms + activation_decode_ms + framing_ms + metadata_ms + copy_allocation_ms
+            + compression_ms + decompression_ms + connection_setup_ms + queue_wait_ms + transport_ms
+            + local_http_forwarding_ms,
             4,
         )
         return SeamSample(
             phase=phase, token_index=token_index, session_id=self.session_id,
             activation_id=f"benchmark-activation-{self._activation_count}", seam="head->tail", mode=self.mode,
             cache_mode=self.cache_mode, model_ms=model_ms, encode_ms=encode_ms,
+            activation_decode_ms=activation_decode_ms,
             framing_ms=framing_ms, metadata_ms=metadata_ms,
             copy_allocation_ms=copy_allocation_ms, copy_allocation_bytes=copy_allocation_bytes,
             compression_ms=compression_ms, decompression_ms=decompression_ms,
             connection_setup_ms=connection_setup_ms, queue_wait_ms=queue_wait_ms,
+            local_http_forwarding_ms=local_http_forwarding_ms,
             transport_ms=round(transport_ms, 4), seam_latency_ms=seam_latency_ms,
             payload_bytes=payload_bytes, wire_bytes=wire_bytes,
             compression_ratio=round(payload_bytes / wire_bytes, 4), connection_attempted=connection_attempted,
@@ -329,9 +342,10 @@ def run_real_model_lan_benchmark(url: str, *, model: str, timeout: float = 120.0
     sample = SeamSample(
         phase="decode", token_index=0, session_id=session_id, activation_id="lan-activation-1",
         seam="head->tail", mode="direct", cache_mode="cached", model_ms=0.0, encode_ms=0.0,
+        activation_decode_ms=0.0,
         framing_ms=0.0, metadata_ms=0.0, copy_allocation_ms=0.0, copy_allocation_bytes=0,
         compression_ms=0.0, decompression_ms=0.0, connection_setup_ms=elapsed_ms,
-        queue_wait_ms=0.0, transport_ms=elapsed_ms, seam_latency_ms=elapsed_ms,
+        queue_wait_ms=0.0, local_http_forwarding_ms=0.0, transport_ms=elapsed_ms, seam_latency_ms=elapsed_ms,
         payload_bytes=len(body), wire_bytes=len(body) + len(response_body), compression_ratio=1.0,
         connection_attempted=True,
     )
@@ -354,6 +368,10 @@ def format_summary(report: dict) -> str:
             f"{decode['tokens_per_sec']:.1f} tok/s; {decode['bytes_per_token']:.0f} B/tok; "
             f"seam {seam['payload_bytes']}/{seam['wire_bytes']} B "
             f"({seam['compression_ratio']:.2f}x); connections {run['connections']['attempts']}; "
+            f"model/encode/decode {decode['model_execution_ms']:.2f}/"
+            f"{decode['activation_encoding_ms']:.2f}/{decode['activation_decoding_ms']:.2f} ms; "
+            f"compression {decode['compression_cpu_ms']:.2f} ms; "
+            f"HTTP {decode['local_http_forwarding_ms']:.2f} ms; "
             f"queue p95 {decode['p95_queue_wait_ms']:.2f} ms"
         )
     return "\n".join(lines)