> > What in my mind is (without any throttling)
> >
> > if (PageSwapcache(page)) {
> > if (bdi_write_congested(bdi))
>
> You mentioned following as.
>
> "However !bdi_write_congested(bdi) is now unconditionally true for the
> swapper_space, which means any process can do swap out to a congested
> queue and block there."
>
> But you used bdi_write_congested in here.
> Which is right?
Ah sorry, I was also cheated by the name.. bdi_write_congested()
won't work for swap_backing_dev_info. Anyway you may take it as
"pseudo" code :)
Thanks,
Fengguang
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>