ge-aerospace/shopdb-flask
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Persist endpoint disk health

Browse Source 
Adds diskhealthjson with its migration in the same change, so the model never references a column the schema has not applied.

Kept separate from disksjson rather than merged into it. That column is per volume and answers how full a drive is; this one is per physical device and answers whether the hardware is dying. They come from different WMI sources with different failure modes, so merging them would make a capacity collection failure indistinguishable from a health collection failure.

Nullable with no backfill: a drive whose health has never been reported is not a healthy drive, and defaulting to an empty list would read as no disks have problems on every endpoint predating the column.
This commit is contained in:
benjamin.baker
2026-09-05 06:25:49 -04:00
parent b297dea822
commit 024910d4f2
3 changed files with 98 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
plugins/endpoints/migrations/versions/0014_endpoint_diskhealth.py Normal file
View File

@@ -0,0 +1,56 @@
"""Add diskhealthjson to endpointstates.
Per-drive health, kept separate from disksjson. That column answers "how full
is this drive"; this one answers "is this drive dying". Merging them would mean
a capacity collection failure and a health collection failure could not be told
apart, and the two come from different WMI sources with different failure modes.
JSON rather than scalar columns because a machine has a variable number of
drives and each carries its own verdict, and because the agent reports the same
drive from two sources - MSFT_PhysicalDisk for NVMe and Win32_DiskDrive for
ATA/SATA - which the server keeps side by side rather than collapsing.
MEDIUMTEXT for consistency with the other snapshot columns on this table.
Nullable with no backfill. A drive whose health has never been reported is not
a healthy drive, and defaulting to an empty list would read as "no disks have
problems" on every endpoint that predates this column.
Idempotent: the column-add checks the live schema first, so a re-run and a
db.create_all() site both stay clean on strict MySQL 8.
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = 'endpoints0014diskhealth'
down_revision = 'endpoints0013inventorycolumns'
branch_labels = None
depends_on = None
TABLE_NAME = 'endpointstates'
COLUMN_NAME = 'diskhealthjson'
def _has_column(table_name, column_name):
from sqlalchemy import inspect
inspector = inspect(op.get_bind())
if not inspector.has_table(table_name):
return False
return any(col['name'] == column_name
for col in inspector.get_columns(table_name))
def upgrade():
if not _has_column(TABLE_NAME, COLUMN_NAME):
op.add_column(
TABLE_NAME,
sa.Column(COLUMN_NAME, sa.Text(length=16777215), nullable=True))
def downgrade():
if _has_column(TABLE_NAME, COLUMN_NAME):
op.drop_column(TABLE_NAME, COLUMN_NAME)

6
plugins/endpoints/models/endpoint.py
View File

@@ -102,6 +102,12 @@ class EndpointState(db.Model):
# is deliberately distinct from a confident False.
pendingreboot = db.Column(db.Boolean, nullable=True)
# Per-drive health from the agent's two disk sources. JSON because a machine
# has a variable number of drives and each carries its own verdict. Kept
# separate from disksjson: that is capacity, this is whether the hardware is
# dying. Null = never reported.
diskhealthjson = db.Column(db.Text(length=16777215), nullable=True)
# Warn-only reconciler output, refreshed on every agent check-in in the same
# commit as servicesjson. Each entry names a policy/shipped-attached monitor
# the endpoint is expected to be running but the latest snapshot does not

37
plugins/endpoints/plugin.py
View File

@@ -53,7 +53,7 @@ KNOWN_PAYLOAD_KEYS = frozenset({
'cpupercent', 'memorypercent', 'services', 'ports', 'interfaces',
'scheduledtasks', 'applications', 'events',
'disks', 'bios', 'memory', 'processor', 'osinfo', 'domain',
'pendingreboot', 'usercontext',
'pendingreboot', 'usercontext', 'diskhealth',
})
@@ -572,6 +572,30 @@ class EndpointsPlugin(BasePlugin):
'position': 17,
'group': 'monitors',
},
{
# Sits directly under Storage because an operator looking at a
# full disk and an operator looking at a dying disk are usually
# the same person in the same minute. Kept a separate panel
# because storage is per volume and this is per physical
# device; the two do not share a key.
'id': 'endpoints-diskhealth',
'title': 'Disk health',
'assettypes': ['computer'],
'endpoint': '/api/endpoints/asset/{assetid}/diskhealth',
'render': 'table',
'collapsible': True,
'columns': [
{'key': 'model', 'label': 'Drive'},
{'key': 'mediatype', 'label': 'Media'},
{'key': 'bustype', 'label': 'Bus'},
{'key': 'healthstatus', 'label': 'Health'},
{'key': 'verdict', 'label': 'Verdict'},
{'key': 'source', 'label': 'Source'},
],
'empty': 'No disk health reported.',
'position': 18,
'group': 'monitors',
},
{
# The listening set is the box's exposed network surface. The
# full connection table is deliberately not here: it is an
@@ -757,6 +781,15 @@ class EndpointsPlugin(BasePlugin):
'reboot. Absent means never reported, '
'which is not the same as false.',
},
'diskhealth': {
'type': 'array',
'description': 'Per-drive health from two sources: '
'physicaldisk (the only one reporting '
'NVMe) and diskdrive (ATA/SATA and '
'fallback). Each entry carries a '
'precomputed predictfailure; null there '
'means the drive did not answer.',
},
'usercontext': {
'type': 'object',
'description': 'Session-scoped data collected by a probe '
@@ -1000,6 +1033,8 @@ class EndpointsPlugin(BasePlugin):
state.domain = payload.get('domain')
if 'pendingreboot' in payload:
state.pendingreboot = payload.get('pendingreboot')
if 'diskhealth' in payload:
state.diskhealthjson = _as_json(payload.get('diskhealth'))
# Session-scoped probe output. The agent repeats its last result between
# probe runs and omits the key entirely when nobody is signed in, so the