98 lines
2.7 KiB
YAML
98 lines
2.7 KiB
YAML
# Set language: fr for French headings (English by default).
|
|
# Add languages in plugins/report/locales.json.
|
|
id: INC-2026-001
|
|
title: Service Interruption Investigation
|
|
subtitle: Incident analysis and shift handoff
|
|
report_type: technical
|
|
status: open
|
|
severity: high
|
|
metadata:
|
|
Date: '2026-09-05'
|
|
Author: Your Name
|
|
Service: Example API
|
|
Environment: Production
|
|
Owner: Operations
|
|
summary: 'The API is available but intermittently slow. Database connection exhaustion
|
|
is the strongest current lead. No permanent data loss has been observed.
|
|
|
|
'
|
|
timeline:
|
|
- time: 09:15
|
|
event: Alert received
|
|
notes: Latency exceeded the five-second threshold.
|
|
- time: 09:22
|
|
event: Initial mitigation
|
|
notes: One unhealthy application instance was removed from rotation.
|
|
findings:
|
|
- title: Connection pool saturation
|
|
severity: high
|
|
status: confirmed
|
|
evidence: 'Pool utilization remained at 100 percent during each latency spike.
|
|
|
|
'
|
|
assessment: 'Requests are waiting for database connections. Query duration and pool
|
|
sizing both need review.
|
|
|
|
'
|
|
id: pool-saturation
|
|
evidence_refs:
|
|
- artifact: observations.json
|
|
pointer: /metrics/pool_utilization
|
|
label: Synthetic metric
|
|
- title: No evidence of data loss
|
|
severity: info
|
|
status: confirmed
|
|
evidence: 'Record counts and replication checks are consistent across nodes.
|
|
|
|
'
|
|
assessment: 'Continue monitoring, but recovery work can prioritize availability.
|
|
|
|
'
|
|
sections:
|
|
- title: Operational precautions
|
|
content:
|
|
- type: bullets
|
|
items:
|
|
- Avoid schema changes during diagnosis.
|
|
- Record exact timestamps for new latency spikes.
|
|
- type: callout
|
|
title: Escalation condition
|
|
kind: critical
|
|
text: Escalate immediately if replication lag exceeds five minutes.
|
|
- title: Diagnostic procedure
|
|
content:
|
|
- type: steps
|
|
items:
|
|
- Capture application and database metrics.
|
|
- Correlate slow requests with query duration.
|
|
- Test a pool-size adjustment in staging.
|
|
- type: subsection
|
|
title: Useful command
|
|
content:
|
|
- type: code
|
|
text: systemctl status example-api
|
|
actions_title: Next-shift plan
|
|
actions:
|
|
- title: Capture a diagnostic bundle
|
|
status: pending
|
|
text: Collect logs and metrics covering the next occurrence.
|
|
commands:
|
|
- journalctl -u example-api --since '1 hour ago'
|
|
- title: Validate mitigation in staging
|
|
status: pending
|
|
text: Load-test the proposed connection-pool configuration.
|
|
closing: 'Service is operational with intermittent degradation. The next priority
|
|
is to capture a complete occurrence and validate the pool adjustment in staging.
|
|
|
|
'
|
|
schema_version: 1
|
|
branding:
|
|
organization: Example Organization
|
|
theme:
|
|
accent: '#086f83'
|
|
appendices:
|
|
- title: Example provenance
|
|
content:
|
|
- type: text
|
|
text: All content is synthetic.
|