Phase 3: dashboards and alerting
Saved, shareable multi-panel dashboards (table/line/bar/single-stat panels via gridstack + uPlot, global + per-panel time range, JSON export/import) and threshold/absence alert rules with an ok/pending/firing evaluator and webhook/Slack/PagerDuty delivery. - New /metadata component: Postgres control-plane store for dashboards, panels, notification targets, alert rules/state, and delivery log -- see docs/phase-3-dashboard-design.md for why ClickHouse's MergeTree family isn't a fit for this access pattern (needs real row-level locking and read-your-writes consistency). - api/internal/dashboards: dashboard/panel CRUD, pure -- panel query execution stays client-side, reusing the existing /query endpoint. - New /alerting service: rule/target CRUD, a ticker-driven evaluator (claim-then-evaluate concurrency control, transactional-outbox delivery, query errors and threshold zero-rows never coerced into a false transition) and webhook/Slack/PagerDuty delivery with retry/backoff. See docs/phase-3-alerting-design.md for the full state-machine design and the four correctness properties it implements. - web: /dashboards and /alerts UIs; cli: sentryctl dashboards/alerts list/get/apply, seeding a future Terraform provider's JSON contract. - hack/alert-load-test: 500 rules against real ClickHouse data, real measured results in docs/phase-3-runbook.md. Five real bugs found by actually running this against a live stack (documented in the runbook, not just fixed silently): a latent Phase 2 bug where ClickHouse rejected the timestamp format used for earliest=/latest= queries; a "now" literal token injected into query text; a GridStack/uPlot layout-timing race; JS's Date.parse being too lenient to use as a timestamp-detection heuristic; a rule's "enabled" field silently defaulting to false when omitted; and the evaluator's claim-batch-size and worker-pool-concurrency defaulting to the same value, causing 500 concurrently-due rules to take 125s to cycle through instead of the configured 60s.
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
CREATE TABLE IF NOT EXISTS dashboards
|
||||
(
|
||||
id UUID PRIMARY KEY,
|
||||
tenant_id TEXT NOT NULL DEFAULT 'default',
|
||||
name TEXT NOT NULL,
|
||||
description TEXT NOT NULL DEFAULT '',
|
||||
default_earliest TEXT NOT NULL DEFAULT '-1h',
|
||||
default_latest TEXT NOT NULL DEFAULT 'now',
|
||||
created_by TEXT NOT NULL DEFAULT 'anonymous',
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||||
)
|
||||
@@ -0,0 +1,19 @@
|
||||
CREATE TABLE IF NOT EXISTS dashboard_panels
|
||||
(
|
||||
id UUID PRIMARY KEY,
|
||||
dashboard_id UUID NOT NULL REFERENCES dashboards(id) ON DELETE CASCADE,
|
||||
title TEXT NOT NULL DEFAULT '',
|
||||
query TEXT NOT NULL,
|
||||
query_language TEXT NOT NULL DEFAULT '',
|
||||
viz_type TEXT NOT NULL CHECK (viz_type IN ('table', 'line', 'bar', 'single_stat', 'top_n')),
|
||||
viz_config JSONB NOT NULL DEFAULT '{}',
|
||||
position_x INT NOT NULL,
|
||||
position_y INT NOT NULL,
|
||||
width INT NOT NULL,
|
||||
height INT NOT NULL,
|
||||
earliest_override TEXT,
|
||||
latest_override TEXT,
|
||||
sort_order INT NOT NULL DEFAULT 0,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||||
)
|
||||
@@ -0,0 +1,14 @@
|
||||
CREATE TABLE IF NOT EXISTS notification_targets
|
||||
(
|
||||
id UUID PRIMARY KEY,
|
||||
tenant_id TEXT NOT NULL DEFAULT 'default',
|
||||
name TEXT NOT NULL,
|
||||
kind TEXT NOT NULL CHECK (kind IN ('webhook', 'slack', 'pagerduty')),
|
||||
webhook_url TEXT NOT NULL,
|
||||
payload_template TEXT,
|
||||
headers JSONB NOT NULL DEFAULT '{}',
|
||||
secret TEXT,
|
||||
created_by TEXT NOT NULL DEFAULT 'anonymous',
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||||
)
|
||||
@@ -0,0 +1,20 @@
|
||||
CREATE TABLE IF NOT EXISTS alert_rules
|
||||
(
|
||||
id UUID PRIMARY KEY,
|
||||
tenant_id TEXT NOT NULL DEFAULT 'default',
|
||||
name TEXT NOT NULL,
|
||||
description TEXT NOT NULL DEFAULT '',
|
||||
query TEXT NOT NULL,
|
||||
query_language TEXT NOT NULL DEFAULT '',
|
||||
condition_type TEXT NOT NULL CHECK (condition_type IN ('threshold', 'absence')),
|
||||
comparator TEXT CHECK (comparator IN ('gt', 'gte', 'lt', 'lte', 'eq', 'ne')),
|
||||
threshold_value DOUBLE PRECISION,
|
||||
eval_interval_seconds INT NOT NULL CHECK (eval_interval_seconds >= 30),
|
||||
for_minutes INT NOT NULL DEFAULT 0,
|
||||
renotify_interval_minutes INT,
|
||||
notification_target_id UUID NOT NULL REFERENCES notification_targets(id),
|
||||
enabled BOOLEAN NOT NULL DEFAULT true,
|
||||
created_by TEXT NOT NULL DEFAULT 'anonymous',
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||||
)
|
||||
@@ -0,0 +1,15 @@
|
||||
CREATE TABLE IF NOT EXISTS alert_state
|
||||
(
|
||||
rule_id UUID PRIMARY KEY REFERENCES alert_rules(id) ON DELETE CASCADE,
|
||||
state TEXT NOT NULL DEFAULT 'ok' CHECK (state IN ('ok', 'pending', 'firing')),
|
||||
condition_true_since TIMESTAMPTZ,
|
||||
fired_at TIMESTAMPTZ,
|
||||
last_notified_at TIMESTAMPTZ,
|
||||
last_evaluated_at TIMESTAMPTZ,
|
||||
last_eval_status TEXT NOT NULL DEFAULT 'ok' CHECK (last_eval_status IN ('ok', 'error')),
|
||||
last_error TEXT,
|
||||
last_value DOUBLE PRECISION,
|
||||
consecutive_errors INT NOT NULL DEFAULT 0,
|
||||
next_eval_at TIMESTAMPTZ NOT NULL,
|
||||
claimed_at TIMESTAMPTZ
|
||||
)
|
||||
@@ -0,0 +1 @@
|
||||
CREATE INDEX IF NOT EXISTS alert_state_next_eval_at_idx ON alert_state (next_eval_at)
|
||||
@@ -0,0 +1,16 @@
|
||||
CREATE TABLE IF NOT EXISTS delivery_log
|
||||
(
|
||||
id BIGSERIAL PRIMARY KEY,
|
||||
rule_id UUID NOT NULL REFERENCES alert_rules(id) ON DELETE CASCADE,
|
||||
notification_target_id UUID NOT NULL REFERENCES notification_targets(id),
|
||||
event_type TEXT NOT NULL CHECK (event_type IN ('firing', 'resolved')),
|
||||
status TEXT NOT NULL DEFAULT 'pending' CHECK (status IN ('pending', 'sent', 'failed', 'retrying')),
|
||||
attempt_count INT NOT NULL DEFAULT 0,
|
||||
max_attempts INT NOT NULL DEFAULT 5,
|
||||
next_attempt_at TIMESTAMPTZ,
|
||||
last_attempt_at TIMESTAMPTZ,
|
||||
last_error TEXT,
|
||||
response_status INT,
|
||||
payload JSONB NOT NULL,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||||
)
|
||||
@@ -0,0 +1 @@
|
||||
CREATE INDEX IF NOT EXISTS delivery_log_rule_id_created_at_idx ON delivery_log (rule_id, created_at DESC)
|
||||
@@ -0,0 +1,2 @@
|
||||
CREATE INDEX IF NOT EXISTS delivery_log_claim_idx ON delivery_log (status, next_attempt_at)
|
||||
WHERE status IN ('pending', 'retrying')
|
||||
Reference in New Issue
Block a user