fix(host_agent): disks behind a RAID controller each keep their own name (#5806)

smartctl reports every disk behind a PERC/MegaRAID controller as /dev/bus/0
with type megaraid,N; the helper named a drive by its path alone, so all of
VDNT-Docker02's and Docker03's disks read as one drive "0", each overwriting
the last. The slot is now part of the name (bus0-megaraid3), and Steward gives
a repeated name an ordinal so two drives never share a series. Agent 1.20.1.

fix(ansible): Steward stopping mid-run logs no traceback (#5749)

The run's done-callback called exception() on a cancelled task, which raises;
it now logs a run cut short by shutdown at INFO. A finished run's in-memory
state is dropped by a timer rather than a sleeping task, which shutdown found
still pending.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

plugins/host_agent/agent.py

@@ -22,7 +22,7 @@ from collections import deque
 from concurrent.futures import ThreadPoolExecutor, wait as wait_futures
 from datetime import datetime, timezone
 
-AGENT_VERSION = "1.20.0"
+AGENT_VERSION = "1.20.1"
 
 # Default path to the local Docker Engine socket. Overridable via the
 # `docker_socket` config key; collection is silently skipped if it's absent or

plugins/host_agent/drives.py

@@ -69,9 +69,20 @@ def judge(d: dict) -> dict:
 
 
 def drives_of(report) -> list[dict]:
-    """The report's drives, judged, what needs attention first."""
+    """The report's drives, judged, what needs attention first. A name seen
+    twice gets an ordinal, so two drives never share one series: agent
+    1.20.0 named every disk behind a RAID controller "0" (#5806)."""
     drives = report.get("drives") if isinstance(report, dict) else None
-    judged = [judge(d) for d in drives or [] if isinstance(d, dict) and d.get("device")]
+    judged, seen = [], {}
+    for d in drives or []:
+        if not isinstance(d, dict) or not d.get("device"):
+            continue
+        d = judge(d)
+        name = str(d["device"])
+        seen[name] = seen.get(name, 0) + 1
+        if seen[name] > 1:
+            d["device"] = f"{name}#{seen[name]}"
+        judged.append(d)
     return sorted(judged, key=lambda d: (_ORDER[d["state"]], str(d["device"])))
 
 

plugins/host_agent/files/maint.py

@@ -199,9 +199,21 @@ def _int(v):
     return v if isinstance(v, int) and not isinstance(v, bool) else None
 
 
-def drive_summary(name: str, status, data) -> dict:
+def drive_name(name: str, kind) -> str:
+    """A drive's name, unique on its host. Disks behind a RAID controller
+    share one path (/dev/bus/0) and differ only by the slot in their type
+    (megaraid,3; cciss,0), so the slot is part of the name (#5806)."""
+    base = os.path.basename(name)
+    if name.startswith("/dev/bus/"):
+        base = "bus" + base
+    if isinstance(kind, str) and "," in kind:
+        base += "-" + re.sub(r"[^A-Za-z0-9]", "", kind.split("+")[-1])
+    return base
+
+
+def drive_summary(name: str, status, data, kind=None) -> dict:
     """The few figures Steward reads from one drive's `smartctl -a` JSON."""
-    out = {"device": os.path.basename(name)}
+    out = {"device": drive_name(name, kind)}
     if not isinstance(data, dict) or status is None or status & _SMARTCTL_UNREAD:
         messages = ((data.get("smartctl") or {}).get("messages") or []) if isinstance(data, dict) else []
         text = "; ".join(str(m.get("string", "")) for m in messages if isinstance(m, dict))
@@ -267,7 +279,7 @@ def do_drives() -> dict:
             continue
         args = ["-a", name] if not isinstance(kind, str) else ["-a", "-d", kind, name]
         status, data = smartctl_json(args)
-        drives.append(drive_summary(name, status, data))
+        drives.append(drive_summary(name, status, data, kind))
     return {**base, "drives": drives}