CentOS Stream 9 – Common Problem 236 – Diagnosis and Fix

📖 ~1 min read

Table of contents

1. Symptom & Impact
2. Environment & Reproduction
3. Root Cause Analysis
4. Quick Triage
5. Step-by-Step Diagnosis
6. Solution – Primary Fix
7. Solution – Alternative Approaches
8. Verification & Acceptance Criteria
9. Rollback Plan
10. Prevention & Hardening
11. Related Errors & Cross-Refs
12. References & Further Reading

Symptom & Impact

Postgres latency spikes on CS9

Environment & Reproduction

THP defragmentation pauses Postgres workers.

Root Cause Analysis

khugepaged compaction contends with database memory mapping.

Quick Triage

cat /sys/kernel/mm/transparent_hugepage/enabled and check perf top.

Step-by-Step Diagnosis

Run: grep -H . /sys/kernel/mm/transparent_hugepage/{enabled,defrag}.

Solution – Primary Fix

echo never > /sys/kernel/mm/transparent_hugepage/enabled and persist via tuned profile.

Solution – Alternative Approaches

Switch to madvise instead of never for mixed workloads.

Verification & Acceptance Criteria

p99 query latency returns to baseline and khugepaged CPU usage drops.

Rollback Plan

Re-enable THP via tuned-adm profile switch if regression occurs.

Prevention & Hardening

Apply throughput-performance tuned profile with custom THP override.

Related Errors & Cross-Refs

Pairs with stalled task warnings and high sys CPU.

Related tutorial: View the step-by-step tutorial for centos-stream-9.

View all centos-stream-9 tutorials on the Tutorials Hub →

Browse all common problems & solutions on the Tutorials Hub.

References & Further Reading

tuned(8) and PostgreSQL THP guidance.