------- Comment From [email protected] 2018-05-09 08:47 EDT-------
(In reply to comment #26)
> Is it essential to have two NUMA nodes for the guest memory to see this bug?
> Can we reproduce it without the NUMA node stuff in the xml?

I haven't attempted it on my end. Can give it a try. But we suspect
https://bugzilla.linux.ibm.com/show_bug.cgi?id=167036https://bugzilla.linux.ibm.com/show_bug.cgi?id=167036
may be the same issue (but with Pegas) since see they're doing IO tests
and various IO related failures after migration. In that particular
config there were no additional NUMA nodes in the guest.

I am hoping to get the dump-bitmap-on-demand test you suggested going
today and hopefully that can reproduce at a high enough frequency that I
can try the kernel patches, disabling THP, and NUMA configurations
within a reasonable timeframe. The test I kicked off yesterday to
capture first 128MB of dirty bitmap ran all night without triggering...

-- 
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1768115

Title:
  ISST-LTE:KVM:Ubuntu1804:BostonLC:boslcp3g1: Migration guest running
  with IO stress crashed@security_file_permission+0xf4/0x160.

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu-power-systems/+bug/1768115/+subscriptions

-- 
ubuntu-bugs mailing list
[email protected]
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs

Reply via email to