Re: The case for removing replacement selection sort

On Fri, Sep 29, 2017 at 7:19 AM, Robert Haas <robertmhaas(at)gmail(dot)com> wrote:
> That supports your theory that there's some confounding factor in the
> CREATE INDEX case, such as I/O scheduling. Since this machine has an
> SSD, I guess I don't have a mental model for how that works. We're
> not waiting for the platter to rotate...

Random I/O is still significantly more expensive with SSDs, especially
random writes, where all the wear leveling stuff comes into play.
There is a tiny universe of very complicated firmware within every SSD
[1]. (I am generally concerned about the trend towards increasingly
complicated, unauditable firmware like this, but that's another
story.)

> ...but I guess that's all irrelevant as far as this patch goes. The
> point of this patch is to simplify things from removing a technique
> that is no longer effective, and the evidence we have supports the
> contention that it is no longer effective. I'll go commit this.

Thanks.

[1] https://lwn.net/Articles/353411/
--
Peter Geoghegan