Re: [PATCH 1/2] memcg: dirty pages accounting and limiting infrastructure

[Andrea Righi <arighi@develer.com>]

On Sun, Feb 21, 2010 at 01:28:35PM -0800, David Rientjes wrote:

[snip]

> > +static struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
> > +{
> > +	struct page_cgroup *pc;
> > +	struct mem_cgroup *mem = NULL;
> > +
> > +	pc = lookup_page_cgroup(page);
> > +	if (unlikely(!pc))
> > +		return NULL;
> > +	lock_page_cgroup(pc);
> > +	if (PageCgroupUsed(pc)) {
> > +		mem = pc->mem_cgroup;
> > +		if (mem)
> > +			css_get(&mem->css);
> > +	}
> > +	unlock_page_cgroup(pc);
> > +	return mem;
> > +}
> 
> Is it possible to merge this with try_get_mem_cgroup_from_page()?

Agreed.

> 
> > +
> > +void mem_cgroup_charge_dirty(struct page *page,
> > +			enum zone_stat_item idx, int charge)
> > +{
> > +	struct mem_cgroup *mem;
> > +	struct mem_cgroup_stat_cpu *cpustat;
> > +	unsigned long flags;
> > +	int cpu;
> > +
> > +	if (mem_cgroup_disabled())
> > +		return;
> > +	/* Translate the zone_stat_item into a mem_cgroup_stat_index */
> > +	switch (idx) {
> > +	case NR_FILE_DIRTY:
> > +		idx = MEM_CGROUP_STAT_FILE_DIRTY;
> > +		break;
> > +	case NR_WRITEBACK:
> > +		idx = MEM_CGROUP_STAT_WRITEBACK;
> > +		break;
> > +	case NR_WRITEBACK_TEMP:
> > +		idx = MEM_CGROUP_STAT_WRITEBACK_TEMP;
> > +		break;
> > +	case NR_UNSTABLE_NFS:
> > +		idx = MEM_CGROUP_STAT_UNSTABLE_NFS;
> > +		break;
> > +	default:
> > +		return;
> 
> WARN()?  We don't want to silently leak counters.

Agreed.

> 
> > +	}
> > +	/* Charge the memory cgroup statistics */
> > +	mem = get_mem_cgroup_from_page(page);
> > +	if (!mem) {
> > +		mem = root_mem_cgroup;
> > +		css_get(&mem->css);
> > +	}
> 
> get_mem_cgroup_from_page() should probably handle the root_mem_cgroup case 
> and return a reference from it.

Right. But I'd prefer to use try_get_mem_cgroup_from_page() without
changing the behaviour of this function.

> 
> > +
> > +	local_irq_save(flags);
> > +	cpu = get_cpu();
> > +	cpustat = &mem->stat.cpustat[cpu];
> > +	__mem_cgroup_stat_add_safe(cpustat, idx, charge);
> 
> get_cpu()?  Preemption is already disabled, just use smp_processor_id().

mmmh... actually, we can just copy the code from
mem_cgroup_charge_statistics(), so local_irq_save/restore are not
necessarily needed and we can just use get_cpu()/put_cpu().

> > +	put_cpu();
> > +	local_irq_restore(flags);
> > +	css_put(&mem->css);
> > +}
> > +
> >  static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
> >  					enum lru_list idx)
> >  {
> > @@ -992,6 +1061,97 @@ static unsigned int get_swappiness(struct mem_cgroup *memcg)
> >  	return swappiness;
> >  }
> >  
> > +static unsigned long get_dirty_bytes(struct mem_cgroup *memcg)
> > +{
> > +	struct cgroup *cgrp = memcg->css.cgroup;
> > +	unsigned long dirty_bytes;
> > +
> > +	/* root ? */
> > +	if (cgrp->parent == NULL)
> > +		return vm_dirty_bytes;
> > +
> > +	spin_lock(&memcg->reclaim_param_lock);
> > +	dirty_bytes = memcg->dirty_bytes;
> > +	spin_unlock(&memcg->reclaim_param_lock);
> > +
> > +	return dirty_bytes;
> > +}
> > +
> > +unsigned long mem_cgroup_dirty_bytes(void)
> > +{
> > +	struct mem_cgroup *memcg;
> > +	unsigned long dirty_bytes;
> > +
> > +	if (mem_cgroup_disabled())
> > +		return vm_dirty_bytes;
> > +
> > +	rcu_read_lock();
> > +	memcg = mem_cgroup_from_task(current);
> > +	if (memcg == NULL)
> > +		dirty_bytes = vm_dirty_bytes;
> > +	else
> > +		dirty_bytes = get_dirty_bytes(memcg);
> > +	rcu_read_unlock();
> 
> The rcu_read_lock() isn't protecting anything here.

Right!

> 
> > +
> > +	return dirty_bytes;
> > +}
> > +
> > +u64 mem_cgroup_page_state(enum memcg_page_stat_item item)
> > +{
> > +	struct mem_cgroup *memcg;
> > +	struct cgroup *cgrp;
> > +	u64 ret = 0;
> > +
> > +	if (mem_cgroup_disabled())
> > +		return 0;
> > +
> > +	rcu_read_lock();
> 
> Again, this isn't necessary.

OK. I'll apply your changes to the next version of this patch.

Thanks for reviewing!

-Andrea