Re: Linux 6.5 speed regression, boot VERY slow with anything systemd related

[Sean Christopherson]

On Tue, Aug 29, 2023, Marc Haber wrote:
> On Tue, Aug 29, 2023 at 07:53:45AM -0700, Sean Christopherson wrote:
> > What is different between the bad host(s) and the good host(s)?  E.g. kernel, QEMU,
> 
> The bad host is an APU ("AMD GX-412TC SOC") with 4 GB of RAM, one of the
> good hosts is a "Xeon(R) CPU E3-1246 v3" with 32 GB of RAM.

I don't expect it to help, but can you try booting the bad host with
"spec_rstack_overflow=off"?

> system configuration is from the same ansible playbook, but of course there
> are differences.

Can you capture the QEMU command lines for the good and bad hosts?  KVM doesn't
get directly involved in serial port emulation; if the blamed commit in 6.5 is
triggering unexpected behavior then QEMU is a better starting point than KVM.