Re: [PATCH][RFC] dirty balancing for cgroups

[YAMAMOTO Takashi]

hi,

> Now the problem this patch tries to address...
> 
> As you can see you'd need p_{bdi,cgroup,task} for it to work, and the
> obvious approximation p_bdi * p_cgroup * p_task will get even more
> coarse.
> 
> You could possibly attempt to do p_{bdi,cgroup} * p_task since the bdi
> and cgroup set are pretty static, but still that would be painful.

i chose min(p_bdi * p_cgroup, p_bdi * p_task) because i couldn't imagine
a case where p_bdi * p_cgroup * p_task is better.

> So, could you please give some more justification for this work, I'm not
> seeing the value in complicating all this just yet.

a simple example for which my patch can make some sense is:

	while :;do dd if=/dev/zero of=file conv=notrunc bs=4096 count=1;done

YAMAMOTO Takashi
--
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/