tezvyn:

Maximizing object-store throughput for small files

Source: interviewadvanced

WHAT IT TESTS: object-store scaling internals. OUTLINE: spread keys across prefixes for partition parallelism, batch small files, parallelize and use multipart uploads.

WHAT IT TESTS: whether you understand how object stores partition by key and how per-object overhead caps small-file throughput. ANSWER OUTLINE: per-object request overhead dominates with millions of tiny files, and sequential or monotonic key prefixes can hotspot a single partition. Re-architect by spreading keys across many prefixes, batching small files into larger aggregates, and parallelizing uploads with many concurrent clients.

Read the original → interview

Get five bites like this every day.

Tezvyn delivers a daily feed of 60-second tech bites with quizzes to lock in what you learn.

Maximizing object-store throughput for small files · Tezvyn