feat(traffic): a host's top senders, on its page and as get_host_senders (#6115)
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 1m29s
CI / integration (push) Successful in 1m39s
CI / publish (push) Successful in 1m4s

The host page gains a "Who's sending" panel, and the MCP a tool, that
put the host's outbound (or inbound) traffic down to its containers and
NFS mounts: read in shared time buckets, so the host's busiest bucket
says who was sending in it. A swarm service's tasks add up under its
name; what none of them accounts for is the host itself.

Also fixes CI 9488: per-container net_rx_bps / net_tx_bps join the
docker alert catalog, so a rule can catch a container flooding the
uplink.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-19 14:38:28 -04:00
co-authored by Claude Opus 5.5
parent 613ed4e78b
commit 26bc57ce04
11 changed files with 319 additions and 7 deletions
+3 -1
View File
@@ -19,10 +19,12 @@ def test_plugin_exposes_the_mcp_hooks():
reg = MagicMock()
agent_plugin.register_mcp_tools(reg)
assert [c.args[0].__name__ for c in reg.call_args_list] == [
"list_agents", "list_maintenance_plans", "get_maintenance_job", "run_maintenance"]
"list_agents", "list_maintenance_plans", "get_maintenance_job", "get_host_senders",
"run_maintenance"]
roles = {c.args[0].__name__: c.kwargs["role"] for c in reg.call_args_list}
assert roles["run_maintenance"].value == "admin" # as Update now on the page
assert roles["get_maintenance_job"].value == "viewer"
assert roles["get_host_senders"].value == "viewer"
assert callable(agent_plugin.mcp_overview)
+40
View File
@@ -0,0 +1,40 @@
"""senders.rank: a host's traffic put down to its containers and NFS mounts
(#6115). Pure; no DB."""
from datetime import datetime, timedelta, timezone
from plugins.host_agent.senders import rank, sender_name
T = [datetime(2026, 10, 19, 18, 0, tzinfo=timezone.utc) + timedelta(minutes=i) for i in range(4)]
def test_a_swarm_task_is_its_service_and_anything_else_its_own_name():
assert sender_name("traefik_router.inlbfs5bk5want3q2pw95x9jw.dja1psmx7k2d59o45e1tqyku6") == "traefik_router"
assert sender_name("steward_app.1.ww9m1povzpkx0dcei3p4zh8dm") == "steward_app"
assert sender_name("ak-outpost-fabled_ldap") == "ak-outpost-fabled_ldap"
def test_senders_are_ranked_by_what_they_sent_in_the_host_s_peak():
host = {T[0]: 100.0, T[1]: 1000.0, T[2]: 100.0, T[3]: 200.0}
got = rank(host, {
("container", "web"): {T[0]: 80.0, T[1]: 100.0, T[2]: 80.0, T[3]: 80.0},
("container", "backup"): {T[1]: 700.0},
("nfs", "/nfs/data"): {T[1]: 50.0, T[3]: 100.0},
})
assert got["host"] == {"avg_bps": 350.0, "peak_bps": 1000.0, "peak_at": T[1]}
assert [r["name"] for r in got["senders"]] == ["backup", "web", "/nfs/data"]
backup = got["senders"][0]
assert backup == {"kind": "container", "name": "backup", "avg_bps": 175.0, "peak_bps": 700.0,
"peak_at": T[1], "at_host_peak_bps": 700.0}
assert got["unaccounted_at_peak_bps"] == 150.0 # 1000 - 700 - 100 - 50
assert got["unaccounted_avg_bps"] == 350.0 - 175.0 - 85.0 - 37.5
def test_senders_beyond_the_host_leave_nothing_unaccounted_and_the_list_is_cut():
host = {T[0]: 10.0}
got = rank(host, {("container", f"c{i}"): {T[0]: 20.0} for i in range(3)}, limit=2)
assert len(got["senders"]) == 2 and got["more"] == 1
assert got["unaccounted_at_peak_bps"] == 0.0 and got["unaccounted_avg_bps"] == 0.0
def test_no_host_samples_is_no_answer():
assert rank({}, {("container", "web"): {T[0]: 1.0}})["host"] is None