Re: [PATCH] tests/qtest/migration-test: Run some basic tests on s390x and ppc64 with TCG, too

[Fabiano Rosas <farosas@suse.de>]

Thomas Huth <thuth@redhat.com> writes:

> On 24/05/2024 02.05, Nicholas Piggin wrote:
>> On Wed May 22, 2024 at 7:12 PM AEST, Thomas Huth wrote:
>>> On s390x, we recently had a regression that broke migration / savevm
>>> (see commit bebe9603fc ("hw/intc/s390_flic: Fix crash that occurs when
>>> saving the machine state"). The problem was merged without being noticed
>>> since we currently do not run any migration / savevm related tests on
>>> x86 hosts.
>>> While we currently cannot run all migration tests for the s390x target
>>> on x86 hosts yet (due to some unresolved issues with TCG), we can at
>>> least run some of the non-live tests to avoid such problems in the future.
>>> Thus enable the "analyze-script" and the "bad_dest" tests before checking
>>> for KVM on s390x or ppc64 (this also fixes the problem that the
>>> "analyze-script" test was not run on s390x at all anymore since it got
>>> disabled again by accident in a previous refactoring of the code).
>> 
>> ppc64 is working for me, can it be enabled fully, or is it still
>> breaking somewhere? FWIW I have a patch to change it from using
>> open-firmware commands to a boot file which speeds it up.
>
> IIRC last time that I tried it was working fine for me, too, but getting a 
> speedup here first would be very welcome since using the Forth code slows 
> down the whole testing quite a bit.

Yeah, we're all gonna get kicked from the project if we add 10m to make
check in CI. =)

@Nick, send us that patch and I'd be glad to reenable the tests.