On Wed, 7 Nov 2007, Nicolas Joly wrote:
> On Tue, Nov 06, 2007 at 06:22:51PM +0000, David Laight wrote:
>> On Tue, Nov 06, 2007 at 12:32:05PM +0200, Arto Huusko wrote:
>>> I've been trying to analyse the problem I'm seeing with 32 bit linux
>>> java on NetBSD/amd64 (4.99.34, with the recent linux32 changes), but
>>> I'm not getting very far.
>>
>> There are some problems (still) with linux32 emulation.
>> Specifically some system calls are directly to the linux_xxx() wrapper
>> which definitely does not DTRT for calls with more than one argument.
>
> I just commited a fix for them, please update. And let us know if it
> changes anything ...

No change. Same symptoms as I described earlier: two java
processes eating system time, ktrace shows the other process
in a loop calling sched_yield (top shows state CPU for that
process) and the other process is not doing anything according
to ktrace (top shows state RUN).

Last line before SIGKILL for the latter process in ktrace is return
from system call, which changes more or less for every trace,
i.e. the process just "stops" at a random point.