openhcl_servicing_keepalive test fails with sidecar enabled

Open jstarks opened this issue 7 months ago • 1 comments

Probably this is due to some kind of memory corruption caused by sidecar memory conflicting with keepalive memory, or something like that. We'll disable sidecar for this test until this can be fixed, since keepalive is not production ready anyway.

May 12 '25 22:05 jstarks

I suspect the issue is that the dma gpa range is being stomped on by the servicing load & nvme device. I'll see if i can take a look later this week.

May 12 '25 22:05 chris-oo

This actually looks like some kind of race between an interrupt arriving and us onlining a sidecar VP. See #2070, but we fail on every test with this assertion: openhcl/underhill_core/src/vp.rs:300:13:

Oct 03 '25 20:10 chris-oo