News for hackers. Stuff that matters.

A comment on A journey to searching Have I Been Pwned database in 49μs. Parent comment

Re:A journey to searching Have I Been Pwned database in 49μs by mstaoru on Sunday March 01, 2020 @10:20PM (#22461371)
Exactly what I thought. Microseconds? On HDD? That would mean the block is in RAM.

HDD latency is composed of seek + rotation latency + processing time, on the best of the best server HDDs random read might be in the ballpark of 10ms (10,000μs), desktop HDD... maybe around 30-40ms (30,000μs). Or ~600x times more than 49μs.

[ Parent | on HN ]
Re:A journey to searching Have I Been Pwned database in 49μs by marcan_42 on Monday March 02, 2020 @02:23AM (#22462384)
Desktop HDDs aren't that bad, but 100 IOPS is a good ballpark for back of the envelope estimates (10ms). The OP wrote their B-Tree to require 3 lookups, so assuming they really are single disk reads that's where I calculated 30ms.
[ Parent | on HN ]
Re:A journey to searching Have I Been Pwned database in 49μs by stryku2393 on Monday March 02, 2020 @03:13PM (#22468406)
Just to confirm, the benchmarks are bad. Almost always the read parts of B-tree file are cached. I'll rewrite the benchmarks and update the results!
[ Parent | on HN ]