> I'm observing *excessive high* number of pagefaults
> after a process has forked.
...
> Now I would expect that we can finally write to the stack in the
> child process. But instead we now get *lots* of F_INVAL / S_WRITE
> stack page faults at address [2]. That doesn't seem to be
> correct.
I (google) just found this:
Joe Bonasera's blog might contain an explanation what is
happening, in the section "Spurious Page Faults":
http://blogs.sun.com/JoeBonasera/entry/i_ve_got_spur_ious
The only thing that does not match is that my 32bit PV domUs
run with vcpus = 1; and my Tecra S1 is an UP machine, so
dom0 = domU = 1 vcpu.
This message posted from opensolaris.org
_______________________________________________
xen-discuss mailing list
[email protected]
