#storage
Wiki 7
- IndexedDB Browser-native key-value store with indexes, transactions, and cursors for client-side data
- LSM Tree Write-optimized storage: append-only MemTable/SSTable design behind Cassandra, RocksDB, LevelDB
- LSM Trees and NoSQL Storage LSM tree architecture; MemTable, WAL, SSTables, Bloom filters, compaction strategies, and failure modes
- ScyllaDB's trie-based SSTable index Replacing Summary.db + Index.db with a page-packed prefix tree: up to 3x read throughput
- Ursa: Iceberg-First Storage Engine for Kafka StreamNative's diskless Kafka storage engine — writes directly to S3 as Iceberg/Delta tables, 10x cheaper
- Your harddrive is probably full Marginalia's author on why storage stays full at every scale, and budgeting artificial constraints as the fix
- ZeroFS vs. Amazon S3 Files Two POSIX filesystems on object storage — one keeps files as S3 objects, the other treats the bucket as private substrate
Toolbox 1
- zerofs Log-structured POSIX filesystem over NFS, 9P or NBD backed entirely by an S3-compatible bucket
Books 3
- Database Internals: A Deep Dive into How Distributed Data Systems Work Petrov's two-part survey of storage engines and the distributed side of database systems
- Designing Data-Intensive Applications (2nd ed.) Kleppmann on the tradeoffs behind storage engines, replication, and stream processing
- Memory Systems: Cache, DRAM, Disk Hardware-level walk through SRAM cache organization, DDR DRAM timing and disk scheduling