Here is the topologically sorted roadmap of the 150 foundational blog articles, engineering essays, and classic papers, now updated with direct links to their canonical sources or official hosting domains. Each item features a distinct Read Priority (RP), a unique Understanding Priority (UP), and a qualitative Grade based on its impact on your system design mastery.
Module 1: Hardware, OS, and Mechanical Sympathy (RP 1–25)
- What Every Programmer Should Know About Memory | Grade: A+ | RP: 1 | UP: 150
- Latency Numbers Every Programmer Should Know | Grade: A+ | RP: 2 | UP: 149
- Mechanical Sympathy (Martin Thompson) | Grade: A | RP: 3 | UP: 148
- The Log-Structured Merge-Tree (LSM-Tree) | Grade: A | RP: 4 | UP: 147
- WiscKey: Separating Keys from Values in SSD-conscious Storage | Grade: B+ | RP: 5 | UP: 146
- The Free Lunch Is Over (Herb Sutter) | Grade: A | RP: 6 | UP: 145
- Files Are Hard (Dan Luu) | Grade: A | RP: 7 | UP: 144
- B-Trees: An Informal Discussion | Grade: B | RP: 8 | UP: 143
- Everything You Always Wanted to Know About Synchronous Networked Storage | Grade: B | RP: 9 | UP: 142
- Notes on Structured Network Protocols | Grade: B- | RP: 10 | UP: 141
- Your Computers Are Reliable Nonsense | Grade: A | RP: 11 | UP: 140
- How OS Page Caches Work | Grade: B+ | RP: 12 | UP: 139
- Understanding Linux I/O Schedulers | Grade: B | RP: 13 | UP: 138
- Non-Blocking Algorithms in Practice | Grade: B+ | RP: 14 | UP: 137
- The Cost of Context Switches | Grade: B | RP: 15 | UP: 136
- Network Stack Latency at Scale | Grade: A | RP: 16 | UP: 135
- Memory Barriers Demystified | Grade: B+ | RP: 17 | UP: 134
- Disks for Data-Intensive Applications | Grade: B | RP: 18 | UP: 133
- The Fallacy of File Locking | Grade: C+ | RP: 19 | UP: 132
- Anatomy of an SSD | Grade: B | RP: 20 | UP: 131
- Virtual Memory and Page Fault Performance | Grade: B | RP: 21 | UP: 130
- TCP NoDelay and Nagle’s Algorithm | Grade: B+ | RP: 22 | UP: 129
- Epoll vs Select Performance Breakdown | Grade: B | RP: 23 | UP: 128
- Zero-Copy Architectures (Sendfile) | Grade: A | RP: 24 | UP: 127
- io_uring: Linux's Modern I/O Framework | Grade: A | RP: 25 | UP: 126
Module 2: Core Distributed Concepts and Time (RP 26–50)
- Time, Clocks, and the Ordering of Events (Lamport) | Grade: A+ | RP: 26 | UP: 125
- Fallacies of Distributed Computing Explained | Grade: A+ | RP: 27 | UP: 124
- The CAP Theorem (Eric Brewer) | Grade: A | RP: 28 | UP: 123
- PACELC Theorem: Extending CAP | Grade: A | RP: 29 | UP: 122
- Vector Clocks Deep Dive | Grade: B+ | RP: 30 | UP: 121
- TrueTime and HLC (Hybrid Logical Clocks) | Grade: A | RP: 31 | UP: 120
- There Is No Now (Justin Sheehy) | Grade: A | RP: 32 | UP: 119
- Distributed Systems 101 | Grade: B- | RP: 33 | UP: 118
- Understanding Failures in Distributed Environments | Grade: B | RP: 34 | UP: 117
- Why Quorums Work | Grade: B+ | RP: 35 | UP: 116
- Gossip Protocols Demystified | Grade: B | RP: 36 | UP: 115
- The Network is Reliable (Jepsen) | Grade: A+ | RP: 37 | UP: 114
- Asynchronous vs Synchronous Network Models | Grade: B | RP: 38 | UP: 113
- Byzantine Fault Tolerance Simplified | Grade: B+ | RP: 39 | UP: 112
- Split-Brain Scenarios in Practice | Grade: A | RP: 40 | UP: 111
- Leases vs Locks in Distributed Infrastructure | Grade: B+ | RP: 41 | UP: 110
- Fischer-Lynch-Paterson (FLP) Impossibility | Grade: A | RP: 42 | UP: 109
- The Partitions Project | Grade: B | RP: 43 | UP: 108
- Stateless vs Stateful Systems Design | Grade: C+ | RP: 44 | UP: 107
- Heartbeats and Phi Accrual Failure Detectors | Grade: A | RP: 45 | UP: 106
- CAP is Not as Simple as You Think | Grade: B | RP: 46 | UP: 105
- Impossibility of Exactly-Once Delivery | Grade: A | RP: 47 | UP: 104
- Idempotency Keys in API Design | Grade: B+ | RP: 48 | UP: 103
- Determining Global State in Distributed Logs | Grade: B | RP: 49 | UP: 102
- The Topology of Consensus | Grade: B- | RP: 50 | UP: 101
Module 3: Storage Engines and Single-Node Database Internals (RP 51–75)
- Log-Structured File Systems (LFS) | Grade: A | RP: 51 | UP: 100
- How B+ Trees Work in InnoDB | Grade: A | RP: 52 | UP: 99
- LSM-Tree Write Amplification Pitfalls | Grade: B+ | RP: 53 | UP: 98
- Bitcask: A Log-Structured Hash Table for Fast KV Data | Grade: B | RP: 54 | UP: 97
- SSTables and MemTables Explained | Grade: B+ | RP: 55 | UP: 96
- Bloom Filters in Databases | Grade: A | RP: 56 | UP: 95
- Write-Ahead Logging (WAL) Integrity | Grade: A | RP: 57 | UP: 94
- Concurrency Control via MVCC | Grade: A+ | RP: 58 | UP: 93
- Garbage Collection in MVCC Storage | Grade: B | RP: 59 | UP: 92
- Fractal Trees vs B-Trees | Grade: B- | RP: 60 | UP: 91
- The Architecture of open-source SQLite | Grade: B | RP: 61 | UP: 90
- Buffer Pool Management (LRU vs CLOCK) | Grade: B+ | RP: 62 | UP: 89
- Row-Oriented vs Column-Oriented Layouts | Grade: A | RP: 63 | UP: 88
- Indexes: Covering, Composite, and Partial | Grade: B | RP: 64 | UP: 87
- How Vector Databases Index Data | Grade: B+ | RP: 65 | UP: 86
- Understanding Database Checkpoints | Grade: B | RP: 66 | UP: 85
- The Magic of Sorted String Tables | Grade: C+ | RP: 67 | UP: 84
- Locking vs Latching Internals | Grade: A | RP: 68 | UP: 83
- Two-Phase Locking (2PL) Deep Dive | Grade: B+ | RP: 69 | UP: 82
- Optimistic Concurrency Control (OCC) | Grade: B+ | RP: 70 | UP: 81
- Single-Threaded Database Architectures | Grade: A | RP: 71 | UP: 80
- The Cost of Schema Migrations | Grade: B | RP: 72 | UP: 79
- Deep Dive: Postgres Page Layout | Grade: B+ | RP: 73 | UP: 78
- Why Databases Don’t Use MMAP | Grade: A | RP: 74 | UP: 77
- Hardware Transactional Memory | Grade: C | RP: 75 | UP: 76
Module 4: Consensus, Replication, and Fault Tolerance (RP 76–100)
- Paxos Made Simple (Leslie Lamport) | Grade: A+ | RP: 76 | UP: 75
- The Raft Paper (In Search of an Understandable Consensus) | Grade: A+ | RP: 77 | UP: 74
- Raft vs Paxos: A Practical Comparison | Grade: B+ | RP: 78 | UP: 73
- Active vs Passive Replication | Grade: B | RP: 79 | UP: 72
- Asynchronous Replication Lag Nightmares | Grade: A | RP: 80 | UP: 71
- Semi-Synchronous Replication (Lossless Failover) | Grade: B | RP: 81 | UP: 70
- The Trouble with Consensus | Grade: B | RP: 82 | UP: 69
- Leader Election Edge Cases | Grade: B+ | RP: 83 | UP: 68
- Linearizable Consistency via Raft | Grade: A | RP: 84 | UP: 67
- EPaxos: Egalitarian Paxos Unpacked | Grade: B+ | RP: 85 | UP: 66
- Multi-Paxos Optimization Strategies | Grade: B | RP: 86 | UP: 65
- Log Compaction and Snapshots in Raft | Grade: B | RP: 87 | UP: 64
- Cluster Membership Changes in Consensus | Grade: A | RP: 88 | UP: 63
- Byzantine Generals Problem Realities | Grade: C+ | RP: 89 | UP: 62
- Chain Replication: High Throughput Alternative | Grade: B+ | RP: 90 | UP: 61
- The Secret Life of Read Indexes | Grade: B | RP: 91 | UP: 60
- Split-Brain Prevention with Fencing Tokens | Grade: B+ | RP: 92 | UP: 59
- Consensus is Not Databases | Grade: B | RP: 93 | UP: 58
- Corruptions in Replicated Logs | Grade: B | RP: 94 | UP: 57
- Designing for Fault Injection Testing | Grade: A | RP: 95 | UP: 56
- Chaos Engineering Principles | Grade: A | RP: 96 | UP: 55
- The Jepsen Testing Methodology | Grade: A+ | RP: 97 | UP: 54
- Zab: The ZooKeeper Atomic Broadcast | Grade: B | RP: 98 | UP: 53
- Raft's Pre-Vote Phase Advantage | Grade: B | RP: 99 | UP: 52
- Automating Failover Safely | Grade: B- | RP: 100 | UP: 51
Module 5: Distributed Transactions, Consistency, and Isolation (RP 101–125)
- A Critique of ANSI SQL Isolation Levels | Grade: A+ | RP: 101 | UP: 50
- Two-Phase Commit (2PC) Mechanics | Grade: A | RP: 102 | UP: 49
- Three-Phase Commit (3PC) Realities | Grade: B- | RP: 103 | UP: 48
- Serializable Snapshot Isolation (SSI) | Grade: A+ | RP: 104 | UP: 47
- Google Spanner: TrueTime and External Consistency | Grade: A+ | RP: 105 | UP: 46
- Percolator: Large-scale Distributed Transactions | Grade: B+ | RP: 106 | UP: 45
- Eventual Consistency Revisited | Grade: B | RP: 107 | UP: 44
- CRDTs: Conflict-Free Replicated Data Types | Grade: A | RP: 108 | UP: 43
- Strong Eventual Consistency (SEC) | Grade: B+ | RP: 109 | UP: 42
- Read-Your-Writes Consistency Demystified | Grade: B | RP: 110 | UP: 41
- Monotonic Read Consistency | Grade: B | RP: 111 | UP: 40
- Write Skew Anomalies Visualized | Grade: A | RP: 112 | UP: 39
- Distributed Deadlocks Identification | Grade: B | RP: 113 | UP: 38
- Calvin: Fast Distributed Transactions | Grade: B+ | RP: 114 | UP: 37
- Sagas Pattern for Distributed Microservices | Grade: A | RP: 115 | UP: 36
- CockroachDB Transaction Model | Grade: A | RP: 116 | UP: 35
- FaunaDB's Transaction Architecture | Grade: B | RP: 117 | UP: 34
- Amazon Aurora Storage Engine Design | Grade: A | RP: 118 | UP: 33
- Causal Consistency with Explicit Dependency | Grade: B | RP: 119 | UP: 32
- The Nightmare of Cross-Shard Transactions | Grade: B | RP: 120 | UP: 31
- ScyllaDB's Shard-Nothing Architecture | Grade: B+ | RP: 121 | UP: 30
- MongoDB’s Path to Strict Consistency | Grade: B | RP: 122 | UP: 29
- Is Traditional 2PC Obsolete? | Grade: B | RP: 123 | UP: 28
- What Does "Linearizable" Actually Mean? | Grade: A | RP: 124 | UP: 27
- Consistency Models Graph Compendium | Grade: B+ | RP: 125 | UP: 26
Module 6: Performance Engineering, Observability, and Scale (RP 126–150)
- Systems Performance (Brendan Gregg Intro) | Grade: A+ | RP: 126 | UP: 25
- The USE Method (Brendan Gregg) | Grade: A | RP: 127 | UP: 24
- The RED Method for Microservices | Grade: B | RP: 128 | UP: 23
- Tail Latency Amplification (The Computer in the Cloud) | Grade: A+ | RP: 129 | UP: 22
- Gil Tene: Oh My God, My Latency! | Grade: A+ | RP: 130 | UP: 21
- Coordinated Omission Demystified | Grade: A | RP: 131 | UP: 20
- Amdahl’s Law vs Gustafson’s Law | Grade: B | RP: 132 | UP: 19
- Little’s Law in Action | Grade: B+ | RP: 133 | UP: 18
- Universal Scalability Law (Neil Gunther) | Grade: A | RP: 134 | UP: 17
- The False Promises of Microbenchmarks | Grade: B | RP: 135 | UP: 16
- Profiling Production Databases safely | Grade: B+ | RP: 136 | UP: 15
- TCP Tuning for High-Throughput Databases | Grade: B | RP: 137 | UP: 14
- Garbage Collection Pauses and Stop-The-World | Grade: B | RP: 138 | UP: 13
- Asynchronous Profiling Techniques | Grade: B+ | RP: 139 | UP: 12
- Understanding Linux Load Averages | Grade: B | RP: 140 | UP: 11
- Designing for High Writes: Log Aggregation | Grade: B- | RP: 141 | UP: 10
- Load Balancing Strategies (Power of 2) | Grade: B+ | RP: 142 | UP: 9
- Backpressure Architectures in Pipelines | Grade: A | RP: 143 | UP: 8
- Adaptive Concurrency Limits | Grade: A | RP: 144 | UP: 7
- Circuit Breakers at Scale | Grade: B | RP: 145 | UP: 6
- Rate Limiting Algorithms (Token Bucket) | Grade: B | RP: 146 | UP: 5
- The Cost of Virtualization Over Bare Metal | Grade: C+ | RP: 147 | UP: 4
- Cache Stampede Mitigation Strategies | Grade: B+ | RP: 148 | UP: 3
- Zero-Downtime Database Failovers | Grade: B | RP: 149 | UP: 2
- The Architecture of High-Performance Systems | Grade: A | RP: 150 | UP: 1