mirror of
https://github.com/jmcorgan/fips.git
synced 2026-08-09 16:24:45 +00:00
Johnathan Corgan
0d93a19e07
Cost-based parent selection: - Replace depth-only parent selection with effective_depth = depth + link_cost - link_cost computed from locally measured MMP metrics: etx * (1.0 + srtt_ms / 100.0) - Prevents bottleneck subtrees in heterogeneous networks where a LoRa link at depth 1 would otherwise always beat fiber at depth 2 - Configurable hysteresis (default 0.2) prevents marginal parent switches - Configurable hold-down timer (default 30s) suppresses re-evaluation after parent switch - Mandatory switches (parent lost, root change) bypass both safeguards - Link costs passed as HashMap parameter to keep TreeState pure Periodic re-evaluation: - evaluate_parent() was only called on TreeAnnounce receipt or parent loss; after tree stabilization, link degradation went undetected - Added timer-based re-evaluation (reeval_interval_secs, default 60s) that calls evaluate_parent() from the tick handler with current MMP link costs - Respects existing hold-down and hysteresis safeguards - Short-circuits when disabled or <2 peers Design documentation: - Update 7 design docs to reflect cost-based parent selection - Replace depth-only algorithm descriptions with effective_depth model - Replace rejected cumulative path cost spec with local-only design rationale - Rewrite Example 2 (heterogeneous links) for local-only cost model - Update config docs: parent_switch_threshold replaced by parent_hysteresis, hold_down_secs, reeval_interval_secs Chaos simulation enhancements: - fips_overrides with deep merge for per-scenario FIPS config customization - Explicit topology algorithm for deterministic test graphs - Control socket querying via fipsctl for tree/MMP snapshot collection - Edge existence validation in netem manager - Per-link netem policy overrides - 9 new chaos scenarios covering cost avoidance, depth-vs-cost tradeoffs, stability, mixed topologies, periodic re-evaluation, and bottleneck parent 12 new unit tests, 667 total passing, clippy clean.
104 lines
3.3 KiB
Python
104 lines
3.3 KiB
Python
"""Control socket querying via docker exec.
|
|
|
|
Queries FIPS nodes' control sockets to observe runtime state (tree
|
|
structure, MMP metrics, peers) without requiring fipsctl in the
|
|
container. Uses a Python one-liner inside docker exec since python3
|
|
is available in the Docker image.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import logging
|
|
|
|
from .docker_exec import docker_exec, docker_exec_quiet
|
|
from .topology import SimTopology
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
# Default control socket path inside containers (XDG_RUNTIME_DIR is
|
|
# typically unset in Docker, so fips falls back to /tmp).
|
|
CONTROL_SOCKET = "/tmp/fips-control.sock"
|
|
|
|
|
|
def query_node(container: str, command: str, timeout: int = 10) -> dict | None:
|
|
"""Send a command to a node's control socket, return the data dict.
|
|
|
|
Returns None if the query fails (node down, socket not ready, etc.).
|
|
"""
|
|
# Python one-liner that connects to the Unix socket, sends the JSON
|
|
# command, and prints the response. Runs inside the container.
|
|
script = (
|
|
"import socket,json,sys; "
|
|
"s=socket.socket(socket.AF_UNIX,socket.SOCK_STREAM); "
|
|
f"s.connect('{CONTROL_SOCKET}'); "
|
|
f"s.sendall(json.dumps({{'command':'{command}'}}).encode()+b'\\n'); "
|
|
"s.shutdown(socket.SHUT_WR); "
|
|
"chunks=[]; "
|
|
"[chunks.append(d) for d in iter(lambda:s.recv(65536),b'')]; "
|
|
"print(b''.join(chunks).decode())"
|
|
)
|
|
stdout = docker_exec_quiet(container, f"python3 -c \"{script}\"", timeout=timeout)
|
|
if stdout is None:
|
|
return None
|
|
|
|
try:
|
|
response = json.loads(stdout.strip())
|
|
except json.JSONDecodeError as e:
|
|
log.warning("Invalid JSON from %s: %s", container, e)
|
|
return None
|
|
|
|
if response.get("status") != "ok":
|
|
msg = response.get("message", "unknown error")
|
|
log.warning("Control query %s on %s failed: %s", command, container, msg)
|
|
return None
|
|
|
|
return response.get("data", {})
|
|
|
|
|
|
def query_tree(container: str) -> dict | None:
|
|
"""Query a node's spanning tree state."""
|
|
return query_node(container, "show_tree")
|
|
|
|
|
|
def query_mmp(container: str) -> dict | None:
|
|
"""Query a node's MMP metrics."""
|
|
return query_node(container, "show_mmp")
|
|
|
|
|
|
def query_peers(container: str) -> dict | None:
|
|
"""Query a node's peer list with MMP metrics."""
|
|
return query_node(container, "show_peers")
|
|
|
|
|
|
def snapshot_all_trees(topology: SimTopology) -> dict[str, dict]:
|
|
"""Query show_tree on all nodes, return {node_id: tree_data}.
|
|
|
|
Nodes that fail to respond are omitted from the result.
|
|
"""
|
|
result = {}
|
|
for node_id in sorted(topology.nodes):
|
|
container = topology.container_name(node_id)
|
|
data = query_tree(container)
|
|
if data is not None:
|
|
result[node_id] = data
|
|
else:
|
|
log.warning("No tree data from %s", node_id)
|
|
return result
|
|
|
|
|
|
def snapshot_all_mmp(topology: SimTopology) -> dict[str, dict]:
|
|
"""Query show_mmp on all nodes, return {node_id: mmp_data}.
|
|
|
|
Nodes that fail to respond are omitted from the result.
|
|
"""
|
|
result = {}
|
|
for node_id in sorted(topology.nodes):
|
|
container = topology.container_name(node_id)
|
|
data = query_mmp(container)
|
|
if data is not None:
|
|
result[node_id] = data
|
|
else:
|
|
log.warning("No MMP data from %s", node_id)
|
|
return result
|