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

[Andrea Righi <arighi@develer.com>]

On Mon, Feb 22, 2010 at 10:58:40AM -0500, Vivek Goyal wrote:
> On Sun, Feb 21, 2010 at 04:18:44PM +0100, Andrea Righi wrote:
> > Infrastructure to account dirty pages per cgroup + add memory.dirty_bytes limit
> > in cgroupfs.
> > 
> > Signed-off-by: Andrea Righi <arighi@develer.com>
> > ---
> >  include/linux/memcontrol.h |   31 ++++++
> >  mm/memcontrol.c            |  218 +++++++++++++++++++++++++++++++++++++++++++-
> >  2 files changed, 248 insertions(+), 1 deletions(-)
> > 
> > diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> > index 1f9b119..ba3fe0d 100644
> > --- a/include/linux/memcontrol.h
> > +++ b/include/linux/memcontrol.h
> > @@ -25,6 +25,16 @@ struct page_cgroup;
> >  struct page;
> >  struct mm_struct;
> >  
> > +/* Cgroup memory statistics items exported to the kernel */
> > +enum memcg_page_stat_item {
> > +	MEMCG_NR_FREE_PAGES,
> > +	MEMCG_NR_RECLAIMABLE_PAGES,
> > +	MEMCG_NR_FILE_DIRTY,
> > +	MEMCG_NR_WRITEBACK,
> > +	MEMCG_NR_WRITEBACK_TEMP,
> > +	MEMCG_NR_UNSTABLE_NFS,
> > +};
> > +
> >  #ifdef CONFIG_CGROUP_MEM_RES_CTLR
> >  /*
> >   * All "charge" functions with gfp_mask should use GFP_KERNEL or
> > @@ -48,6 +58,8 @@ extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr);
> >  
> >  extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
> >  					gfp_t gfp_mask);
> > +extern void mem_cgroup_charge_dirty(struct page *page,
> > +			enum zone_stat_item idx, int charge);
> >  extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru);
> >  extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru);
> >  extern void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru);
> > @@ -117,6 +129,10 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
> >  extern int do_swap_account;
> >  #endif
> >  
> > +extern unsigned long mem_cgroup_dirty_bytes(void);
> > +
> > +extern u64 mem_cgroup_page_state(enum memcg_page_stat_item item);
> > +
> >  static inline bool mem_cgroup_disabled(void)
> >  {
> >  	if (mem_cgroup_subsys.disabled)
> > @@ -144,6 +160,11 @@ static inline int mem_cgroup_cache_charge(struct page *page,
> >  	return 0;
> >  }
> >  
> > +static inline void mem_cgroup_charge_dirty(struct page *page,
> > +			enum zone_stat_item idx, int charge)
> > +{
> > +}
> > +
> >  static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
> >  		struct page *page, gfp_t gfp_mask, struct mem_cgroup **ptr)
> >  {
> > @@ -312,6 +333,16 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
> >  	return 0;
> >  }
> >  
> > +static inline unsigned long mem_cgroup_dirty_bytes(void)
> > +{
> > +	return vm_dirty_bytes;
> > +}
> > +
> > +static inline u64 mem_cgroup_page_state(enum memcg_page_stat_item item)
> > +{
> > +	return 0;
> > +}
> > +
> >  #endif /* CONFIG_CGROUP_MEM_CONT */
> >  
> >  #endif /* _LINUX_MEMCONTROL_H */
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index 954032b..288b9a4 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -64,13 +64,18 @@ enum mem_cgroup_stat_index {
> >  	/*
> >  	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
> >  	 */
> > -	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
> > +	MEM_CGROUP_STAT_CACHE,	   /* # of pages charged as cache */
> >  	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as anon rss */
> >  	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
> >  	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
> >  	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
> >  	MEM_CGROUP_STAT_EVENTS,	/* sum of pagein + pageout for internal use */
> >  	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
> > +	MEM_CGROUP_STAT_FILE_DIRTY,   /* # of dirty pages in page cache */
> > +	MEM_CGROUP_STAT_WRITEBACK,   /* # of pages under writeback */
> > +	MEM_CGROUP_STAT_WRITEBACK_TEMP,   /* # of pages under writeback using
> > +						temporary buffers */
> > +	MEM_CGROUP_STAT_UNSTABLE_NFS,   /* # of NFS unstable pages */
> >  
> >  	MEM_CGROUP_STAT_NSTATS,
> >  };
> > @@ -225,6 +230,9 @@ struct mem_cgroup {
> >  	/* set when res.limit == memsw.limit */
> >  	bool		memsw_is_minimum;
> >  
> > +	/* control memory cgroup dirty pages */
> > +	unsigned long dirty_bytes;
> > +
> >  	/*
> >  	 * statistics. This must be placed at the end of memcg.
> >  	 */
> > @@ -519,6 +527,67 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
> >  	put_cpu();
> >  }
> >  
> > +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;
> > +}
> > +
> > +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;
> > +	}
> > +	/* Charge the memory cgroup statistics */
> > +	mem = get_mem_cgroup_from_page(page);
> > +	if (!mem) {
> > +		mem = root_mem_cgroup;
> > +		css_get(&mem->css);
> > +	}
> > +
> > +	local_irq_save(flags);
> > +	cpu = get_cpu();
> > +	cpustat = &mem->stat.cpustat[cpu];
> > +	__mem_cgroup_stat_add_safe(cpustat, idx, charge);
> > +	put_cpu();
> > +	local_irq_restore(flags);
> > +	css_put(&mem->css);
> > +}
> > +
> 
> We seem to be doing same operation as existing "mem_cgroup_update_file_mapped"
> function is doing to udpate some stats. Can we just reuse that? We
> probably can create one core function which take index of stat to update
> and update_file_mapped and other variants for memcg dirty ratio can make
> use of it.
> 
> In fact instead of single function charge_dirty() accounting for
> WRITEBACK, we well as other states like UNSTABLE_NFS is not very intutive.
> May be we can have indivdual functions.
> 
> mem_cgroup_update_dirty()
> mem_cgroup_update_writeback()
> mem_cgroup_update_unstable_nfs() etc.

Right. I like it. We can extend this function or provide separate
functions to account each stat.

Thanks!
-Andrea