Re: [PATCH] Help Resource Counters Scale better (v4.1)

[Balbir Singh <balbir@linux.vnet.ibm.com>]

* nishimura@mxp.nes.nec.co.jp <nishimura@mxp.nes.nec.co.jp> [2009-08-13 10:03:50]:

> > @@ -1855,9 +1883,14 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
> >  		break;
> >  	}
> >  
> > -	res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess);
> > -	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
> > -		res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
> > +	if (!mem_cgroup_is_root(mem)) {
> > +		res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess);
> > +		if (do_swap_account &&
> > +				(ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
> > +			res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
> > +	}
> > +	if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT && mem_cgroup_is_root(mem))
> > +		mem_cgroup_swap_statistics(mem, true);
> I think mem_cgroup_is_root(mem) would be unnecessary here.
> Otherwise, MEM_CGROUP_STAT_SWAPOUT of groups except root memcgroup wouldn't
> be counted properly.
> 

I think you have a valid point, but it will not impact us currently
since we use SWAPOUT only for root accounting.

> 
> > @@ -2461,10 +2496,26 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
> >  	name = MEMFILE_ATTR(cft->private);
> >  	switch (type) {
> >  	case _MEM:
> > -		val = res_counter_read_u64(&mem->res, name);
> > +		if (name == RES_USAGE && mem_cgroup_is_root(mem)) {
> > +			val = mem_cgroup_read_stat(&mem->stat,
> > +					MEM_CGROUP_STAT_CACHE);
> > +			val += mem_cgroup_read_stat(&mem->stat,
> > +					MEM_CGROUP_STAT_RSS);
> > +			val <<= PAGE_SHIFT;
> > +		} else
> > +			val = res_counter_read_u64(&mem->res, name);
> >  		break;
> >  	case _MEMSWAP:
> > -		val = res_counter_read_u64(&mem->memsw, name);
> > +		if (name == RES_USAGE && mem_cgroup_is_root(mem)) {
> > +			val = mem_cgroup_read_stat(&mem->stat,
> > +					MEM_CGROUP_STAT_CACHE);
> > +			val += mem_cgroup_read_stat(&mem->stat,
> > +					MEM_CGROUP_STAT_RSS);
> > +			val += mem_cgroup_read_stat(&mem->stat,
> > +					MEM_CGROUP_STAT_SWAPOUT);
> > +			val <<= PAGE_SHIFT;
> > +		} else
> > +			val = res_counter_read_u64(&mem->memsw, name);
> >  		break;
> >  	default:
> >  		BUG();
> Considering use_hierarchy==1 case in the root memcgroup, shouldn't we use
> mem_cgroup_walk_tree() here to sum up all the children's usage ?
> *.usage_in_bytes show sum of all the children's usage now if use_hierarchy==1.

If memory.use_hiearchy=1, we should use total_stats..right. Let me
send out a newer version for review.


-- 
	Balbir