Re: Fix checkpoint skip logic on idle systems by tracking LSN progress

Thank you very much for the testing on the nice machine.

At Fri, 18 Nov 2016 20:35:43 -0800, Michael Paquier <michael(dot)paquier(at)gmail(dot)com> wrote in <CAB7nPqRa=igQMCx+FxbfwJ0TzhLU2tE+YOng7qAvZ+1NPm-FOw(at)mail(dot)gmail(dot)com>
> On Fri, Nov 18, 2016 at 7:00 PM, Amit Kapila <amit(dot)kapila16(at)gmail(dot)com> wrote:
> > Okay, I have done some performance tests with this patch and found that it doesn't have any noticeable impact which is good. Details of performance tests is below:
> > Machine configuration:
> > 2 sockets, 28 cores (56 including Hyper-Threading)
> > RAM = 64GB
> > Data directory is configured on the magnetic disk and WAL on SSD.
>
> Nice spec!

This spec seems enough to see the performance of this patch.

> > The conclusion from my tests is that this patch is okay as far as performance is concerned.
>
> Thank you a lot for doing those additional tests!

So, all my original concern were cleared. The last one is
resetting by a checkpointer restart.. I'd like to remove that if
Andres agrees.

regards,

--
Kyotaro Horiguchi
NTT Open Source Software Center