couchbase-magmalisted

# Couchbase Magma Storage Engine A skill for *understanding and tuning* the Magma storage engine — Couchbase's LSM-tree-based storage backend optimized for large datasets per node. ## When this skill applies - "Should I use Magma or couchstore for my bucket?" - "What changed with Magma being the default in 8.0?" - "What does 128 vBuckets mean vs 1024?" - "How does Magma handle compaction differently?" - "How much memory does Magma need?" - "My write performance is different after upgrading to 8.0" - "How do I set the storage engine when creating a bucket?" ## Magma vs couchstore at a glance | | Couchstore (classic) | Magma | |---|---|---| | **Architecture** | B-tree per vBucket | LSM-tree per vBucket | | **Default vBuckets** | 1024 | 128 (8.0 default) | | **RAM per node minimum** | 256 MB (per bucket) | 100 MB (128 vBucket Magma) | | **Optimized for** | Smaller datasets, high read ratio | Large datasets (>100M docs/node), high write rate | | **Write performance** | Good at low-moderate write rates | Better at sustained high write rates (LSM absorbs bursts) | | **Read performance** | Excellent (direct B-tree lookup) | Good (may require multi-level lookup on cold data) | | **Compaction** | Explicit compaction cycle | Continuous background compaction (no manual trigger needed) | | **Disk space efficiency** | Good after compaction | Good continuously (LSM merges in background) | | **Available** | CE and EE | EE only | ## When to use Magma Use Magma when: - Dataset exceeds