Messages in this thread | | | Subject | Re: [PATCH][RFC] dirty balancing for cgroups | Date | Thu, 17 Jul 2008 10:43:35 +0900 (JST) | From | (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
| |