switch from synchronous threaded pinging to an async implementation (#1170)

still seeing churn in our networking - lets properly rate limit it

## changes

added an httpx client with max connections with a persistent AsyncClient

## testing

deployed on cluster, discovery VASTLY more stable (the only deleted
edges were those discovered by mdns)

pyproject.toml

@@ -23,6 +23,7 @@ dependencies = [
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",
     "openai-harmony>=0.0.8",
+    "httpx>=0.28.1",
 ]
 
 [project.scripts]

src/exo/shared/logging.py

@@ -31,6 +31,8 @@ def logger_setup(log_file: Path | None, verbosity: int = 0):
     """Set up logging for this process - formatting, file handles, verbosity and output"""
 
     logging.getLogger("exo_pyo3_bindings").setLevel(logging.WARNING)
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    logging.getLogger("httpcore").setLevel(logging.WARNING)
 
     logger.remove()
 

src/exo/worker/utils/net_profile.py

@@ -1,60 +1,63 @@
-import http.client
-import time
-
-from anyio import create_task_group, to_thread
+import anyio
+import httpx
+from anyio import create_task_group
 from loguru import logger
 
 from exo.shared.topology import Topology
 from exo.shared.types.common import NodeId
 
-BAD_STATUSLINE_ATTEMPTS = 3
+REACHABILITY_ATTEMPTS = 3
 
 
 async def check_reachability(
     target_ip: str,
     expected_node_id: NodeId,
-    self_node_id: NodeId,
     out: dict[NodeId, set[str]],
+    client: httpx.AsyncClient,
 ) -> None:
     """Check if a node is reachable at the given IP and verify its identity."""
+    if ":" in target_ip:
+        # TODO: use real IpAddress types
+        target_ip = f"[{target_ip}]"
+    url = f"http://{target_ip}:52415/node_id"
 
-    # TODO: use an async http client
-    def _fetch_remote_node_id(*, attempt: int = 1) -> NodeId | None:
-        connection = http.client.HTTPConnection(target_ip, 52415, timeout=3)
+    remote_node_id = None
+
+    last_error = None
+
+    for _ in range(REACHABILITY_ATTEMPTS):
         try:
-            connection.request("GET", "/node_id")
-            response = connection.getresponse()
-            if response.status != 200:
-                return None
+            r = await client.get(url)
+            if r.status_code != 200:
+                await anyio.sleep(1)
+                continue
 
-            body = response.read().decode("utf-8").strip()
+            body = r.text.strip().strip('"')
+            if not body:
+                await anyio.sleep(1)
+                continue
 
-            # Strip quotes if present (JSON string response)
-            if body.startswith('"') and body.endswith('"') and len(body) >= 2:
-                body = body[1:-1]
+            remote_node_id = NodeId(body)
+            break
 
-            return NodeId(body) or None
-        except OSError:
-            return None
-        except http.client.BadStatusLine:
-            if attempt >= BAD_STATUSLINE_ATTEMPTS:
-                logger.warning(
-                    f"BadStatusLine from {target_ip}, after {attempt} attempts, assuming connection to {expected_node_id} has dropped"
-                )
-                return None
-            time.sleep(1)
-            return _fetch_remote_node_id(attempt=attempt + 1)
-        except http.client.HTTPException as e:
-            logger.warning(f"HTTPException from {target_ip}: {type(e).__name__}: {e}")
-            return None
-        finally:
-            connection.close()
+        except (
+            httpx.ConnectError,
+            httpx.ConnectTimeout,
+            httpx.ReadTimeout,
+            httpx.RemoteProtocolError,
+        ) as e:
+            last_error = e
+            await anyio.sleep(1)
 
-    remote_node_id = await to_thread.run_sync(_fetch_remote_node_id)
-    if remote_node_id is None:
-        return
-
-    if remote_node_id == self_node_id:
+    else:
+        if last_error is not None:
+            logger.warning(
+                f"connect error {type(last_error).__name__} from {target_ip} after {REACHABILITY_ATTEMPTS} attempts; treating as down"
+            )
+        else:
+            logger.warning(
+                f"malformed response from {target_ip} after {REACHABILITY_ATTEMPTS} attempts; treating as down"
+            )
         return
 
     if remote_node_id != expected_node_id:
@@ -74,18 +77,33 @@ async def check_reachable(
     topology: Topology, self_node_id: NodeId
 ) -> dict[NodeId, set[str]]:
     """Check which nodes are reachable and return their IPs."""
+
     reachable: dict[NodeId, set[str]] = {}
-    async with create_task_group() as tg:
+
+    # these are intentionally httpx's defaults so we can tune them later
+    timeout = httpx.Timeout(timeout=5.0)
+    limits = httpx.Limits(
+        max_connections=100,
+        max_keepalive_connections=20,
+        keepalive_expiry=5,
+    )
+
+    async with (
+        httpx.AsyncClient(timeout=timeout, limits=limits) as client,
+        create_task_group() as tg,
+    ):
         for node in topology.list_nodes():
             if not node.node_profile:
                 continue
+            if node.node_id == self_node_id:
+                continue
             for iface in node.node_profile.network_interfaces:
                 tg.start_soon(
                     check_reachability,
                     iface.ip_address,
                     node.node_id,
-                    self_node_id,
                     reachable,
+                    client,
                 )
 
     return reachable