On Fri, Nov 27, 2020 at 1:55 AM Tom Lane <t...@sss.pgh.pa.us> wrote: > > Krunal Bauskar <krunalbaus...@gmail.com> writes: > > On Thu, 26 Nov 2020 at 10:50, Tom Lane <t...@sss.pgh.pa.us> wrote: > >> Also, exactly what hardware/software platform were these curves > >> obtained on? > > > Hardware: ARM Kunpeng 920 BareMetal Server 2.6 GHz. 64 cores (56 cores for > > server and 8 for client) [2 numa nodes] > > Storage: 3.2 TB NVMe SSD > > OS: CentOS Linux release 7.6 > > PGSQL: baseline = Release Tag 13.1 > > Hmm, might not be the sort of hardware ordinary mortals can get their > hands on. What's likely to be far more common ARM64 hardware in the > near future is Apple's new gear. So I thought I'd try this on the new > M1 mini I just got. > > ... and, after retrieving my jaw from the floor, I present the > attached. Apple's chips evidently like this style of spinlock a LOT > better. The difference is so remarkable that I wonder if I made a > mistake somewhere. Can anyone else replicate these results?
Results look very surprising to me. I didn't expect there would be any very busy spin-lock when the number of clients is as low as 4. Especially in read-only pgbench. I don't have an M1 at hand. Could you do some profiling to identify the source of such a huge difference. ------ Regards, Alexander Korotkov