How it works
Why does it behave this way?
- 1
The frame: what "durable" means
Why is durability not a yes/no property, and which two numbers measure it?
- 2
Logs and undo
How does a write-ahead log turn many random durable writes into one sequential write, and why does redo exist?
3 pages - 3
Group commit and fsync
Why does one flush per commit cap throughput, and how does sharing a flush lift the ceiling with no tuning?
2 pages - 4
Bounding the log
Which two liabilities does every commit build up, and what does recovery time really depend on?
3 pages - 5
Surviving your own mistakes
Why is a snapshot a garbage-collection policy rather than a copy, and what does keeping one cost?
2 pages - 6
When the storage lies
Why does a write larger than the device's atomic unit break recovery, and which three ways close the hole?
3 pages - 7
Durability across machines
How do copies on several machines raise durability, and what do they cost?
2 pages - 8
Durability across a pipeline
When data passes through several systems, whose "yes" is the reader's promise, and for how long does it hold?