← ClaudeAtlas

couchbase-performance-tuninglisted

Diagnose and tune cluster-level performance problems in Couchbase. Use whenever the user asks about slow KV operations, high latency, low throughput, DCP backpressure, connection limits, thread pool tuning, compaction impact on performance, autocompaction settings, KV engine tuning, vBucket distribution, rebalance performance, disk I/O bottlenecks, CPU saturation on Couchbase nodes, network throughput limits, or 'my cluster is healthy but slow.' Distinct from couchbase-sqlpp-tuning (SQL++ query tuning — index design and EXPLAIN plans), couchbase-observability (what metrics to watch), and couchbase-sizing (how much capacity to provision). This skill covers the operational tuning layer: what to change when the cluster is right-sized but still not performing.
celticht32/Couchbase-Skills-for-Claude.ai · ★ 1 · AI & Automation · score 75
Install: claude install-skill celticht32/Couchbase-Skills-for-Claude.ai
# Couchbase Performance Tuning A skill for diagnosing and fixing performance problems at the cluster level — KV latency, throughput limits, disk I/O, compaction, connection saturation, and thread pool configuration. Distinct from: - `couchbase-sqlpp-tuning` — SQL++ query tuning (index design, EXPLAIN plans, anti-patterns) - `couchbase-observability` — what metrics to monitor and alert thresholds - `couchbase-sizing` — how much capacity to provision in the first place If the question is "my queries are slow," go to `couchbase-sqlpp-tuning`. If the question is "my cluster is right-sized but everything is slow," this is the right skill. ## When this skill applies - "KV get/set latency is higher than expected" - "Throughput isn't reaching the hardware's capability" - "Compaction is killing performance" - "We're hitting connection limits" - "Rebalance is taking too long" - "High CPU on Couchbase nodes but no obvious cause" - "Disk I/O is spiking unpredictably" - "DCP consumers are falling behind" ## Pick the right reference | Question | Read | |---|---| | "KV latency / throughput — diagnosis and tuning" | `references/kv-tuning.md` | | "Compaction — autocompaction settings, impact, tuning" | `references/compaction.md` | | "Connection limits, thread pools, OS-level tuning" | `references/system-tuning.md` | ## The diagnosis sequence Before tuning anything, locate the actual bottleneck: 1. **Is it memory?** Check `ep_mem_used / ep_mem_high_wat`. If > 85%, ejections are happe