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>
77 lines
3.8 KiB
Python
77 lines
3.8 KiB
Python
from __future__ import annotations
|
||
from datetime import datetime, timezone
|
||
from sqlalchemy import DateTime, Float, Index, Integer, String, UniqueConstraint
|
||
from sqlalchemy.orm import Mapped, mapped_column
|
||
from .base import Base
|
||
from steward.core.ids import time_ordered_id
|
||
|
||
|
||
class PluginMetric(Base):
|
||
__tablename__ = "plugin_metrics"
|
||
|
||
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=time_ordered_id)
|
||
source_module: Mapped[str] = mapped_column(String(64), nullable=False)
|
||
resource_name: Mapped[str] = mapped_column(String(255), nullable=False)
|
||
metric_name: Mapped[str] = mapped_column(String(128), nullable=False)
|
||
value: Mapped[float] = mapped_column(Float, nullable=False)
|
||
recorded_at: Mapped[datetime] = mapped_column(
|
||
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
|
||
)
|
||
|
||
# This time-series table grows by (sources × resources × sample cadence); every
|
||
# host-detail / full-metrics / dashboard-widget read filters by
|
||
# (source_module, resource_name) over a recorded_at range. Without these it's a
|
||
# full sequential scan on every load.
|
||
__table_args__ = (
|
||
Index("ix_plugin_metrics_module_resource_recorded",
|
||
"source_module", "resource_name", "recorded_at"),
|
||
Index("ix_plugin_metrics_module_resource_metric_recorded",
|
||
"source_module", "resource_name", "metric_name", "recorded_at"),
|
||
)
|
||
|
||
|
||
class PluginMetricLatest(Base):
|
||
"""The newest sample of each (source, resource, metric), kept beside
|
||
plugin_metrics by record_metrics so "what is it now" never scans history.
|
||
|
||
Postgres has no skip scan, so a newest-per-key query over plugin_metrics
|
||
reads every raw sample in the window: on a seven-day window that took a
|
||
dashboard widget a minute (#5208). This table is one row per key. Retention
|
||
drops a row once its sample has aged out of the raw window, so a resource
|
||
that stopped reporting disappears when its raw history does.
|
||
"""
|
||
__tablename__ = "plugin_metric_latest"
|
||
|
||
source_module: Mapped[str] = mapped_column(String(64), primary_key=True)
|
||
resource_name: Mapped[str] = mapped_column(String(255), primary_key=True)
|
||
metric_name: Mapped[str] = mapped_column(String(128), primary_key=True)
|
||
value: Mapped[float] = mapped_column(Float, nullable=False)
|
||
recorded_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
|
||
|
||
|
||
class PluginMetricHourly(Base):
|
||
"""Hourly rollup of plugin_metrics — the coarse series that retention rolls
|
||
raw samples into before pruning them, so multi-day/week history stays cheap.
|
||
|
||
One row per (source_module, resource_name, metric_name, hour bucket); the
|
||
unique constraint is the conflict target for the idempotent rollup upsert.
|
||
Charts read this for the part of a range older than the raw-retention window.
|
||
"""
|
||
__tablename__ = "plugin_metrics_hourly"
|
||
|
||
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=time_ordered_id)
|
||
source_module: Mapped[str] = mapped_column(String(64), nullable=False)
|
||
resource_name: Mapped[str] = mapped_column(String(255), nullable=False)
|
||
metric_name: Mapped[str] = mapped_column(String(128), nullable=False)
|
||
bucket: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
|
||
value_avg: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
|
||
value_max: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
|
||
sample_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
||
|
||
__table_args__ = (
|
||
UniqueConstraint("source_module", "resource_name", "metric_name", "bucket",
|
||
name="uq_plugin_metrics_hourly_bucket"),
|
||
Index("ix_plugin_metrics_hourly_lookup",
|
||
"source_module", "resource_name", "metric_name", "bucket"),
|
||
)
|