Re: [PATCH] remove throttle_vm_writeout()

[Miklos Szeredi]

> Yeah, I'm guestimating O on a per device basis, but I agree that the
> current ratio limiting is quite crude. I'm not at all sorry to see
> throttle_vm_writeback() go, I just wanted to make a point that what it
> does is not quite without merrit - we agree that it can be done better
> differently.

Yes.  So what is it to be?

Is limiting by device queues enough?

Or do we need some global limit?

If so, the cleanest way I see is to separately account and limit
swap-writeback pages, so the global counters don't interfere with the
limiting.

This shouldn't be hard to do, as we have the per-bdi writeback
counting infrastructure already, and also a pseudo bdi for swap in
swapper_space.backing_dev_info.

Miklos
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/