Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

It's the default setting that didn't cope well. The final setting seemed to get pretty decent performance. And if you only have one knob then the rabbit hole is pretty shallow.

The question not answered (as it wasn't asked) is how many workload profiles can be catered for? But as a sample of one, this appears successful.



The question though is does the setting that worked for this particular micro-benchmark actually work well for more generic workloads that have similar performance issues.


Does it matter? If they code up their target workload and get near linear scaling with collection on 5000% or 12000% it's still a win.

The important question is whether or not they can get the scaling with some setting.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: