This section goes beyond the foundational storage topics in ../overview.md into the internals of distributed filesystems, advanced erasure coding math, deep storage engine theory, content-addressable deduplication, next-generation memory/storage tiers, and low-level storage reliability mechanisms. These topics appear in senior SRE, storage-engineer, and database-internals interviews at companies running petabyte-scale infrastructure.
graph TD
D[Section D: Advanced Distributed Storage] --> DFS[distributed-fs.md]
D --> EC[erasure-coding-deep.md]
D --> SE[storage-engines.md]
D --> DC[dedup-cas.md]
D --> TP[tiered-persistent.md]
D --> SI[storage-internals.md]
DFS --> DFS1[Ceph RADOS + BlueStore + Reef]
DFS --> DFS2[HDFS NameNode + EC]
DFS --> DFS3[GFS / Colossus / MinIO / S3]
DFS --> DFS4[JuiceFS / GlusterFS / Lustre / BeeGFS]
EC --> EC1[Reed-Solomon + LRC + Regenerating]
EC --> EC2[Fountain Codes]
EC --> EC3[Replication vs EC Trade-offs]
SE --> SE1[LSM Amplifications + Compaction]
SE --> SE2[Bloom/Cuckoo/Quotient Filters]
SE --> SE3[Learned Indexes + Bε Trees]
SE --> SE4[WAL / Journaling / CoW / Snapshots]
DC --> DC1[Chunking + Fingerprinting]
DC --> DC2[CAS + Immutable Storage]
TP --> TP1[SCM / PMem / CXL]
TP --> TP2[NVMe-oF / RDMA / Disaggregated Storage]
TP --> TP3[Computational Storage / SmartNIC]
SI --> SI1[QoS / Noisy Neighbor / GC]
SI --> SI2[Crash Consistency / Torn Writes]
SI --> SI3[Atomic Writes / Checksums]
Order File Focus Prerequisites
1 distributed-fs.md Production distributed storage systems ../distributed.md , ../ceph.md 2 erasure-coding-deep.md Math-heavy EC theory ../erasure-coding.md 3 storage-engines.md LSM/B-Tree internals, filters, learned structures ../sstable.md , ../lsm-compaction.md , ../wal.md 4 dedup-cas.md Dedup and content-addressable storage ../blobdb.md 5 tiered-persistent.md PMem, NVMe-oF, disaggregated/computational storage ../tiered-storage.md , ../nvme.md , ../nvmeof.md 6 storage-internals.md QoS, crash consistency, checksums Any of the above
Dimension Foundations (../) Advanced (./)
Ceph Architecture overview, CRUSH basics BlueStore internals, Reef release, OSD recovery pipeline Erasure Coding What, why, basic RS Galois-field arithmetic, LRC, regenerating codes, fountain codes LSM Compaction types, amplification Learned bloom filters, Bε trees, fractal tree merge cost Tiering Hot/warm/cold, policies SCM/PMem, CXL, disaggregated architectures, computational storage Object Storage S3 API, metadata, consistency models S3 internal partitioning, MinIO erasure sets, strong consistency mechanics