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

[Peter Xu]

On Wed, May 22, 2024 at 11:12:55AM +0200, 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).
> 
> Signed-off-by: Thomas Huth <thuth@redhat.com>

Reviewed-by: Peter Xu <peterx@redhat.com>

Irrelevant of this patch, when I was looking at cleaning of bootfile it
looks to me that we're leaking bootpath in the test loops.. maybe we need a
bootfile_delete() at the entry of bootfile_create()?

Or even better, prepare bootfile once only and use it in all tests.  The
only trick arch is x86 who needs to support suspend_me=true, but maybe we
can provide two bootfiles.

-- 
Peter Xu