Linux / DevOps · Flashcard
What distinguishes a major page fault from a minor one?
- AThe major fault has to read from a backing device; the minor one is satisfied from RAM
- BThe major fault touches an unmapped address; the minor one touches a mapped page
- CThe major fault happens in kernel space; the minor one happens in userspace code
- DThe major fault kills the process; the minor one is retried transparently by the kernel
Why this is the answer
Both faults are ordinary and expected — the difference is cost. A minor fault only needs a mapping fixed up for a page already in memory, taking microseconds. A major fault has to fetch from disk or swap, taking orders of magnitude longer, so a rising major fault rate is a direct latency signal. Touching an unmapped address is a segmentation fault, a different event entirely, and that is also the option describing process death. Both kinds occur in user and kernel context alike.
Official docs