Benedict mentioned it briefly above, but the earliest / most detailed conversation on this can be found in CASSANDRA-1470.
You may also find some stuff from the dev list and other issues around the same time from specifically from Chris G. and Peter S. (names on that ticket) as, IIRC, they were both doing a lot of experimentation at the time tuning Cassandra IO for their hardware platforms. Both those guys were knowledgeable/approachable - pretty sure they wouldn't mind getting pinged directly for something interesting like this via the twitters or some such. -N On Wed, Oct 19, 2016 at 6:28 AM, Michael Kjellman <mkjell...@internalcircle.com> wrote: > Sorry, No. Always document your assumptions. I shouldn't need to git blame a > thousand commits and read thru a billion tickets to maybe understand why > something was done. Clearly thru the conversations on this topic I've had on > IRC and the responses so far on this email thread it's not/still not obvious. > > best, > kjellman > > On Oct 18, 2016, at 10:07 AM, Benedict Elliott Smith > <bened...@apache.org<mailto:bened...@apache.org>> wrote: > > This is what JIRA is for. >