bvandeusenandClaude Opus 5.5
b8f73270e7
The dashboard's host widgets took 18-60 s. Every "latest reading" query (hosts overview, host-agent fleet, host page, vitals, SNMP, MCP get_host) searched plugin_metrics for the newest row per metric. Postgres has no skip scan, so each one read every raw sample in the 7-day window. - plugin_metric_latest: one row per (source, resource, metric). record_metrics upserts it in the same transaction, moving forward only and in sorted key order. Migration 0030 seeds it by stepping the existing index. - Retention drops a latest row once its sample leaves the raw window, so a resource that stopped reporting disappears when its history does, as before. Renames carry it along. - A quiet host keeps its last values, marked stale. A time-bounded query would have shown it as missing. - Vitals sparklines span the 6 h they claim, averaged in SQL to ~120 points, instead of fetching 6 h raw and drawing the last 120 samples. - Dashboard and share-view cells: "Loading…" until the first answer; a 20 s deadline per fetch; "Couldn't load (why)" with Retry now and an automatic retry for cells that don't poll; "as of HH:MM" in the header, and "couldn't refresh · as of" when a refresh fails over shown data. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
56 lines
2.3 KiB
Python
56 lines
2.3 KiB
Python
"""The newest sample of each metric, kept beside plugin_metrics (#5208)
|
|
|
|
Revision ID: 0030_plugin_metric_latest
|
|
Revises: 0029_alert_no_data
|
|
Create Date: 2026-10-07
|
|
"""
|
|
from typing import Sequence, Union
|
|
from alembic import op
|
|
import sqlalchemy as sa
|
|
|
|
revision: str = "0030_plugin_metric_latest"
|
|
down_revision: Union[str, None] = "0029_alert_no_data"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.create_table(
|
|
"plugin_metric_latest",
|
|
sa.Column("source_module", sa.String(64), primary_key=True),
|
|
sa.Column("resource_name", sa.String(255), primary_key=True),
|
|
sa.Column("metric_name", sa.String(128), primary_key=True),
|
|
sa.Column("value", sa.Float, nullable=False),
|
|
sa.Column("recorded_at", sa.DateTime(timezone=True), nullable=False),
|
|
)
|
|
# Seed from history without a full scan: step through the distinct keys of
|
|
# the (source, resource, metric, recorded_at) index one probe at a time,
|
|
# then take each key's newest row with a backward probe of the same index.
|
|
op.execute("""
|
|
WITH RECURSIVE k AS (
|
|
(SELECT source_module, resource_name, metric_name FROM plugin_metrics
|
|
ORDER BY source_module, resource_name, metric_name LIMIT 1)
|
|
UNION ALL
|
|
SELECT n.source_module, n.resource_name, n.metric_name
|
|
FROM k, LATERAL (
|
|
SELECT p.source_module, p.resource_name, p.metric_name FROM plugin_metrics p
|
|
WHERE (p.source_module, p.resource_name, p.metric_name)
|
|
> (k.source_module, k.resource_name, k.metric_name)
|
|
ORDER BY p.source_module, p.resource_name, p.metric_name LIMIT 1
|
|
) n
|
|
)
|
|
INSERT INTO plugin_metric_latest
|
|
(source_module, resource_name, metric_name, value, recorded_at)
|
|
SELECT k.source_module, k.resource_name, k.metric_name, l.value, l.recorded_at
|
|
FROM k, LATERAL (
|
|
SELECT p.value, p.recorded_at FROM plugin_metrics p
|
|
WHERE p.source_module = k.source_module AND p.resource_name = k.resource_name
|
|
AND p.metric_name = k.metric_name
|
|
ORDER BY p.recorded_at DESC LIMIT 1
|
|
) l
|
|
""")
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_table("plugin_metric_latest")
|