Optimizing Linux Memory Management for Low-latency, High-throughput Databases

Re:Optimizing Linux Memory Management for Low-latency, High-... by erichocean on Tuesday October 08, 2013 @04:25PM (#6517599)

I understood it to mean that it had 1/4 the error rates they were previously seeing.

[ Parent | on HN ]

Re:Optimizing Linux Memory Management for Low-latency, High-... by dllthomas on Tuesday October 08, 2013 @05:16PM (#6517909)

Huh, that's not even one I considered. I guessed 1/5, so the change was 4x the final value. Either way it's wrong - "dropped by X%" should be calculated as (original - final) / original.

[ Parent | on HN ]

Re:Optimizing Linux Memory Management for Low-latency, High-... by apurvamehta on Tuesday October 08, 2013 @04:31PM (#6517630)

This is exactly right :)

[ Parent | on HN ]

Re:Optimizing Linux Memory Management for Low-latency, High-... by caf on Tuesday October 08, 2013 @05:41PM (#6518024)

Then it dropped by 75%.

[ Parent | on HN ]

Re:Optimizing Linux Memory Management for Low-latency, High-... by apurvamehta on Tuesday October 08, 2013 @05:53PM (#6518070)

Yes. It was a blunder. The post has been updated to reflect this.

[ Parent | on HN ]