bvandeusenandClaude Opus 5.5
b6c4ce510d
#5760 "One stalled NFS mount freezes the whole agent: statvfs has no deadline, so the host goes silent while it still answers ping". The agent read every mount inline in its only loop; a hard-mounted share whose server stops blocks statvfs in the kernel with no timeout. Each mount is now read in a daemon thread under one 5 s deadline. One that misses it is sent as stalled, and isn't probed again while its last probe is still blocked. A mount that errors (a stale handle) is left out instead of emptying the list. Steward counts them as mounts_stalled (alertable: "an NFS share stopped"), and skips the fullest-disk figure when every mount stalled. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
75 lines
3.2 KiB
Python
75 lines
3.2 KiB
Python
# plugins/host_agent/__init__.py
|
|
from __future__ import annotations
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from quart import Quart
|
|
|
|
_app: "Quart | None" = None
|
|
|
|
|
|
def setup(app: "Quart") -> None:
|
|
global _app
|
|
_app = app
|
|
# A host's CPU, memory and load per core learn their normal (#5742), each
|
|
# with its floor from Settings → Thresholds. Parts don't: a host's CPU has
|
|
# a normal, each of its cores doesn't. Disks stay on their fixed cutoffs:
|
|
# a nearly full disk is a failure whatever its history (System 182).
|
|
from steward.core.norms import floor_setting, learn_normal
|
|
learn_normal("host_agent", "cpu_pct", floor_setting(app, "host_cpu_pct"), parts=False)
|
|
learn_normal("host_agent", "mem_used_pct", floor_setting(app, "host_mem_pct"), parts=False)
|
|
learn_normal("host_agent", "load_pct", floor_setting(app, "host_load_pct"), parts=False)
|
|
# "Agent offline" speaks for everything the agent carries: while it is
|
|
# firing, the host's other rules going silent isn't emailed (#5721).
|
|
from steward.core.alerts import agent_fed, agent_heartbeat
|
|
from steward.hosts.service import agent_stale_after_seconds
|
|
agent_heartbeat("host_agent", "seconds_since_seen", lambda: agent_stale_after_seconds(app.config))
|
|
agent_fed("host_agent", lambda resource: resource.split(":", 1)[0])
|
|
# A reboot the agent announced is silence with a reason, for a while (#5756).
|
|
from datetime import datetime, timezone
|
|
from steward.core.alerts import agents_away
|
|
from .downtime import hosts_away, restart_grace_seconds
|
|
agents_away(lambda session: hosts_away(session, datetime.now(timezone.utc),
|
|
restart_grace_seconds(app.config)))
|
|
from steward.core.cleanup import prune_by_age
|
|
from .models import HostDowntime
|
|
prune_by_age(HostDowntime.started_at)
|
|
|
|
|
|
def get_scheduled_tasks() -> list:
|
|
from .scheduler import make_task
|
|
return [make_task(_app)]
|
|
|
|
|
|
def get_blueprint():
|
|
from .routes import host_agent_bp
|
|
return host_agent_bp
|
|
|
|
|
|
def register_mcp_tools(register) -> None:
|
|
from .mcp_tools import register_tools
|
|
register_tools(register)
|
|
|
|
|
|
async def mcp_overview(db) -> list[dict]:
|
|
from .mcp_tools import mcp_overview as findings
|
|
return await findings(db)
|
|
|
|
|
|
def get_alert_metrics() -> dict[str, list[str]]:
|
|
"""Host metrics ingest records for alert rules (resource = the host name;
|
|
disk_used_pct per mount, resource "<host>:<mount>"). seconds_since_seen
|
|
comes from the scheduler, not the agent: "agent offline" is > 180.
|
|
clock_off_secs is how far the host's clock is from Steward's, either way
|
|
(agent ≥ 1.12.0): "clock drifting" is > 30. load_pct is load_1m as a %
|
|
of the host's cores. inodes_used_pct is per mount (agent ≥ 1.13.0), and
|
|
disk_used_pct_worst is the fullest mount by space or inodes.
|
|
mounts_stalled counts the mounts that didn't answer the agent in time
|
|
(agent ≥ 1.14.0): "an NFS share stopped" is > 0."""
|
|
return {"host_agent": [
|
|
"cpu_pct", "mem_used_pct", "mem_available_bytes", "swap_used_bytes",
|
|
"disk_used_pct_worst", "disk_used_pct", "inodes_used_pct", "load_1m", "load_5m", "load_15m",
|
|
"load_pct",
|
|
"uptime_secs", "seconds_since_seen", "clock_off_secs", "mounts_stalled",
|
|
]}
|