> I just had the following message in my syslog (with the extra
> arguments to the try_to_free_page printk :-)
>
> mvmap66 kernel: try_to_free_page: state(0) stop(3) i(2) sleep instead of fail
>
> Hope this makes sense to somebody.
stop=3, so we did not want to wait.
we probably called in this order:
- swap_out(6, dma, 0)
- shrink_mmap(5, dma)
- shm_swap(4, dma)
- swap_out(3, dma, 0)
seems the way kswapd does background pageout.
Nothing bad, except the message that should only be
printed if wait!=0, in my opinion (and perhaps something else).
I will download 2.0.31 and look into this #@!$% change.
Gerard.