Hacker News Reader

I’m a bit confused with the analysis here. How do you confirm a downward trend in the data that is not visible on the graph. It looks like the median drops a little in the first few versions, but then rises in the last few. The R2 is really low, so I’m not sold on the correlation here. Basically, it looks like tail latency has improved and YMMV for everything else.

View on HN

I'm the author of the blog post.

"Tail latency has improved by YMMV for everything else" => yes, I think that's a valid (but conservative) read. Of course, in many (most?) applications, tail latency is very important. Tail latency also tends to be the thing that optimizer engineers target (i.e., reduce the runtime of the longest running query).

Reply on news.ycombinator.com