On 3 September 2015 at 07:24, Peter Geoghegan <pg@heroku.com> wrote:
On Wed, Sep 2, 2015 at 7:12 AM, Andres Freund <andres@anarazel.de> wrote: > What worries me about adding explicit prefetching is that it's *highly* > platform and even micro-architecture dependent. Why is looking three > elements ahead the right value?
Because that was the fastest value following testing on my laptop. You are absolutely right to point out that this isn't a good reason to go with the patch -- I share your concern. All I can say in defense of that is that other major system software does the same, without any regard for the underlying microarchitecture AFAICT. So, yes, certainly, more testing is required across a reasonable cross-section of platforms to justify the patch.
FWIW someone else found 3 to be good on the platform they tested on: