adamksmith/jbod-monitor
1
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Add per-enclosure temperature metrics + Home Assistant MQTT publisher

Browse Source 
- enclosure: fetch SES element descriptor page (0x07) and label temp/fan/
  psu/voltage elements with human-readable names
- temps service + /api/temps: per-enclosure hotspot (max across SES sensors
  and housed drive temps) plus named SES sensor list
- mqtt_publisher: paho-mqtt with HA discovery (device per enclosure, hotspot
  + per-sensor entities), LWT availability, opt-in via MQTT_HOST
- secrets: OpenBao KV v2 reader; MQTT creds sourced from secret/home_assistant
  with env fallback
- compose/requirements/README updated
This commit is contained in:
adam
2026-06-16 04:45:32 +00:00
parent 50dd2a631e
commit d41e3838d5
11 changed files with 591 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
services/enclosure.py
View File

@@ -152,29 +152,88 @@ def _parse_slot_number(entry: Path) -> int | None:
return None
async def get_enclosure_status(sg_device: str) -> dict | None:
"""Run sg_ses --page=0x02 and parse enclosure health data."""
async def _run_sg_ses(sg_device: str, page: str) -> str | None:
"""Run sg_ses for a given page, returning decoded stdout or None."""
try:
proc = await asyncio.create_subprocess_exec(
"sg_ses", "--page=0x02", sg_device,
"sg_ses", f"--page={page}", sg_device,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
)
stdout, stderr = await proc.communicate()
if proc.returncode != 0:
logger.warning("sg_ses failed for %s: %s", sg_device, stderr.decode().strip())
logger.warning(
"sg_ses page %s failed for %s: %s",
page, sg_device, stderr.decode().strip(),
)
return None
return _parse_ses_page02(stdout.decode(errors="replace"))
return stdout.decode(errors="replace")
except FileNotFoundError:
logger.warning("sg_ses not found")
return None
except Exception as e:
logger.warning("sg_ses error for %s: %s", sg_device, e)
logger.warning("sg_ses page %s error for %s: %s", page, sg_device, e)
return None
def _parse_ses_page02(text: str) -> dict:
"""Parse sg_ses --page=0x02 text output into structured health data."""
async def get_enclosure_status(sg_device: str) -> dict | None:
"""Run sg_ses status (0x02) + element descriptor (0x07) pages and parse.
The element descriptor page provides human-readable names for each
element (e.g. "Temp Inlet", "Fan 1"); these are merged into the status
elements so callers get labelled sensors. Descriptor lookup is
best-effort — if page 0x07 is unsupported, elements fall back to bare
indices.
"""
status_text, desc_text = await asyncio.gather(
_run_sg_ses(sg_device, "0x02"),
_run_sg_ses(sg_device, "0x07"),
)
if status_text is None:
return None
names = _parse_element_descriptors(desc_text) if desc_text else {}
return _parse_ses_page02(status_text, names)
def _norm_type(element_type: str) -> str:
"""Normalize an SES element type line to a stable key.
sg_ses appends qualifiers like ", subenclosure id: 0 [ti=2]" to the
type line; strip those so the same element type matches across the
status (0x02) and element descriptor (0x07) pages.
"""
return element_type.split(",")[0].strip().lower()
def _parse_element_descriptors(text: str) -> dict[tuple[str, int], str]:
"""Parse sg_ses --page=0x07 into {(element_type, index): name}."""
names: dict[tuple[str, int], str] = {}
sections = re.split(r"(?=\s*Element type:)", text)
for section in sections:
type_match = re.match(r"\s*Element type:\s*(.+)", section)
if not type_match:
continue
etype = _norm_type(type_match.group(1).strip().rstrip(","))
for line in section.splitlines():
m = re.match(r"\s*Element (\d+) descriptor:\s*(.*)", line)
if not m:
continue
idx = int(m.group(1))
name = m.group(2).strip()
if name:
names[(etype, idx)] = name
return names
def _parse_ses_page02(
text: str, names: dict[tuple[str, int], str] | None = None
) -> dict:
"""Parse sg_ses --page=0x02 text output into structured health data.
``names`` maps (normalized element type, index) -> descriptor name from
the element descriptor page (0x07); when present it labels each element.
"""
names = names or {}
result = {
"overall_status": "OK",
"psus": [],
@@ -192,6 +251,7 @@ def _parse_ses_page02(text: str) -> dict:
if not type_match:
continue
element_type = type_match.group(1).strip().rstrip(",").lower()
etype_key = _norm_type(element_type)
# Find individual element blocks (skip "Overall descriptor")
elements = re.split(r"(?=\s*Element \d+ descriptor:)", section)
@@ -209,12 +269,15 @@ def _parse_ses_page02(text: str) -> dict:
if status.lower() == "not installed":
continue
name = names.get((etype_key, idx))
if "power supply" in element_type:
fail = "Fail=1" in elem_text
ac_fail = "AC fail=1" in elem_text
dc_fail = "DC fail=1" in elem_text
result["psus"].append({
"index": idx,
"name": name,
"status": status,
"fail": fail,
"ac_fail": ac_fail,
@@ -227,6 +290,7 @@ def _parse_ses_page02(text: str) -> dict:
rpm = int(rpm_match.group(1)) if rpm_match else None
result["fans"].append({
"index": idx,
"name": name,
"status": status,
"rpm": rpm,
"fail": fail,
@@ -243,6 +307,7 @@ def _parse_ses_page02(text: str) -> dict:
continue
result["temps"].append({
"index": idx,
"name": name,
"status": status,
"temperature_c": temp,
})
@@ -254,6 +319,7 @@ def _parse_ses_page02(text: str) -> dict:
voltage = float(volt_match.group(1)) if volt_match else None
result["voltages"].append({
"index": idx,
"name": name,
"status": status,
"voltage": voltage,
})