On 02 Apr 1999 20:16:16 -0800, Russell Senior <seniorr@teleport.com>
said:
> The oom messages are more reliable than the put_dirty_page messages,
> but the latter occur without too much difficulty.
> Apr 2 19:57:27 dalles kernel: put_dirty_page: pte 00070040 already exists
> Apr 2 19:57:27 dalles kernel: put_dirty_page: pte 00078040 already exists
Ahh, new information: these are both SysV shared memory swap ptes. What
on _earth_ are they doing there, in the fresh address space of a
newly-exec()ed process? Good question.
What sort of things are you doing with shared memory? As root, what
does ipcs -a show? Are you aware of any shared memory activity going on
when the problems start?
And while we're on the subject, is anybody else having VM problems able
to relate them to shared memory usage?
Thanks for tracing this, at least it gives me somewhere to start looking
for the problem.
--Stephen
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/